diff --git "a/checkpoint-2823824/trainer_state.json" "b/checkpoint-2823824/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2823824/trainer_state.json" @@ -0,0 +1,33411 @@ +{ + "best_metric": 4.022037506103516, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj/lstm/2/checkpoints/checkpoint-2823824", + "epoch": 2.025000606015738, + "eval_steps": 10, + "global_step": 2823824, + "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": 10.8189, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 7.5766, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 7.0513, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.9791, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 6.9499, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 6.8293, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 6.6937, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 6.5841, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 6.5062, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 6.4294, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 6.3809, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 6.3188, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 6.2573, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 6.1866, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 6.1218, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 6.075, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986582483983168e-05, + "loss": 6.0276, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985743889232116e-05, + "loss": 5.9778, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984905294481064e-05, + "loss": 5.9435, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984066699730012e-05, + "loss": 5.9012, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.8726, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 5.8347, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.981552553357229e-05, + "loss": 5.7997, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.980713958606178e-05, + "loss": 5.7776, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 5.7449, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 5.7183, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9781998122333946e-05, + "loss": 5.6939, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773612174823426e-05, + "loss": 5.6724, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 5.6387, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 5.6235, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 5.5966, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.974008476358507e-05, + "loss": 5.5782, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.973169881607455e-05, + "loss": 5.5656, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.972331286856403e-05, + "loss": 5.5474, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 5.5259, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.9706557352346724e-05, + "loss": 5.5167, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 5.5017, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 5.482, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 5.4636, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 5.4535, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 5.4274, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965625804608733e-05, + "loss": 5.427, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964787209857681e-05, + "loss": 5.397, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963948615106629e-05, + "loss": 5.3968, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963110020355577e-05, + "loss": 5.3891, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962271425604525e-05, + "loss": 5.3783, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.961432830853473e-05, + "loss": 5.3527, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960594236102421e-05, + "loss": 5.3507, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 5.347, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 5.3236, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 5.3095, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.95724313285896e-05, + "loss": 5.3072, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 5.3124, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 5.2793, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954728986486177e-05, + "loss": 5.3005, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953890391735125e-05, + "loss": 5.2593, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530517969840727e-05, + "loss": 5.271, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522132022330207e-05, + "loss": 5.2487, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.9513746074819686e-05, + "loss": 5.2442, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 5.2368, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 5.2306, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 5.2106, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948021866358134e-05, + "loss": 5.2175, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947183271607082e-05, + "loss": 5.1997, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.94634467685603e-05, + "loss": 5.207, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945506082104978e-05, + "loss": 5.1876, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944669125234299e-05, + "loss": 5.1789, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943830530483247e-05, + "loss": 5.163, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942991935732195e-05, + "loss": 5.1704, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942153340981143e-05, + "loss": 5.1645, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413147462300904e-05, + "loss": 5.1443, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404761514790384e-05, + "loss": 5.1472, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.939637556727987e-05, + "loss": 5.1392, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.938798961976935e-05, + "loss": 5.1349, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 5.1317, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 5.1258, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362864534845256e-05, + "loss": 5.1141, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935447858733473e-05, + "loss": 5.0967, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.934609263982421e-05, + "loss": 5.1035, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 5.0945, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 5.0964, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 5.0893, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 5.077, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 5.0572, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295793333564825e-05, + "loss": 5.0639, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 5.0656, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 5.0612, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 5.0507, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.9262265922326474e-05, + "loss": 5.0429, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.9253879974815954e-05, + "loss": 5.0312, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.9245494027305433e-05, + "loss": 5.026, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.9237108079794913e-05, + "loss": 5.0214, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922872213228439e-05, + "loss": 5.0314, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 5.0199, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.9966, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920361342616403e-05, + "loss": 4.9978, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919522747865351e-05, + "loss": 5.0043, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 5.0006, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.9896, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.9891, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916168368861143e-05, + "loss": 4.975, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915329774110091e-05, + "loss": 4.9736, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.9806, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.9754, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.9499, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119770329862556e-05, + "loss": 4.9608, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.9397, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.9444, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.9426, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.9309, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.9304, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.9191, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.9176, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.915, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.9269, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.9017, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.887, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901918809614751e-05, + "loss": 4.8958, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901080214863699e-05, + "loss": 4.9079, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900241620112647e-05, + "loss": 4.8892, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899403025361595e-05, + "loss": 4.8975, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.886, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.8858, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.8717, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.8754, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.8691, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.8736, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.8521, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.8618, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.8586, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.842, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.8528, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.845, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.8487, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.8461, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.8282, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.8239, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.8227, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.8276, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.8349, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882637681862047e-05, + "loss": 4.8233, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881799087110995e-05, + "loss": 4.8141, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880960492359943e-05, + "loss": 4.8091, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.807, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.8068, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.801, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.8136, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.7994, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.7912, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.7854, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.802785396575928, + "eval_runtime": 550.4578, + "eval_samples_per_second": 693.225, + "eval_steps_per_second": 21.664, + "step": 76319 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.8012, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.7914, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.777, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.7791, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.7677, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.7651, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.7614, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.7634, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.7597, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.7602, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.7597, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.7637, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.7515, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.7417, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.7411, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.7232, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.7367, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.7329, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.73, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.7404, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.7285, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.7269, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.7296, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.7236, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.7151, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.7136, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.7194, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.7053, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.707, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.6927, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.6949, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.7082, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.6972, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.6968, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.6934, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.6974, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.6919, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.6885, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.6887, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.6757, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.6813, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.6665, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.6726, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838210176740395e-05, + "loss": 4.6812, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.6797, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.6638, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.668, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834855797736188e-05, + "loss": 4.6723, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834017202985136e-05, + "loss": 4.6518, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.6516, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.6527, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315046944927255e-05, + "loss": 4.665, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306660997416735e-05, + "loss": 4.642, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.6677, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.6356, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.6499, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.643, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.6451, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.637, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824797574364683e-05, + "loss": 4.64, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.6291, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823120384862579e-05, + "loss": 4.637, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.6292, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.6349, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820606238489796e-05, + "loss": 4.6269, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819767643738744e-05, + "loss": 4.6261, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818929048987692e-05, + "loss": 4.6066, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.81809045423664e-05, + "loss": 4.633, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817251859485588e-05, + "loss": 4.6213, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816413264734535e-05, + "loss": 4.6099, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815574669983483e-05, + "loss": 4.6187, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.613, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8138991183617535e-05, + "loss": 4.6147, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813060523610701e-05, + "loss": 4.6222, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812221928859649e-05, + "loss": 4.6186, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.6067, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.5984, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.6051, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.6053, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.6125, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.6048, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063550413630307e-05, + "loss": 4.5983, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805518084492352e-05, + "loss": 4.5809, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046794897413e-05, + "loss": 4.5895, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.596, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803002300239196e-05, + "loss": 4.5945, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.5962, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801326748617466e-05, + "loss": 4.5893, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.5819, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799649559115361e-05, + "loss": 4.5842, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798812602244683e-05, + "loss": 4.5763, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.79797400749363e-05, + "loss": 4.5844, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797135412742578e-05, + "loss": 4.5858, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.5637, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954598611208476e-05, + "loss": 4.5665, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.5763, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937826716187436e-05, + "loss": 4.5837, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.7929440768676916e-05, + "loss": 4.568, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.7921054821166396e-05, + "loss": 4.5738, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912668873655876e-05, + "loss": 4.5667, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904282926145356e-05, + "loss": 4.5639, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.7895913357438565e-05, + "loss": 4.5752, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.5693, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.5528, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.5681, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862385946200214e-05, + "loss": 4.5467, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7853999998689694e-05, + "loss": 4.5518, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784561405117918e-05, + "loss": 4.5601, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.5475, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.5484, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782047258745135e-05, + "loss": 4.5441, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781208663994083e-05, + "loss": 4.5431, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780370069243031e-05, + "loss": 4.5425, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779531474491979e-05, + "loss": 4.5577, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778692879740927e-05, + "loss": 4.5377, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777854284989875e-05, + "loss": 4.5303, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777015690238823e-05, + "loss": 4.5368, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776177095487771e-05, + "loss": 4.5445, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775338500736719e-05, + "loss": 4.5379, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.77450154386604e-05, + "loss": 4.5427, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773662949114988e-05, + "loss": 4.5391, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772824354363936e-05, + "loss": 4.5395, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.7719857596128845e-05, + "loss": 4.5314, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.7711488027422054e-05, + "loss": 4.527, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703102079911534e-05, + "loss": 4.5312, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694716132401014e-05, + "loss": 4.5352, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686330184890494e-05, + "loss": 4.5209, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76779606161837e-05, + "loss": 4.5246, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766957466867318e-05, + "loss": 4.5385, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766118872116266e-05, + "loss": 4.5115, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.7652802773652136e-05, + "loss": 4.5258, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.7644416826141616e-05, + "loss": 4.5212, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636030878631096e-05, + "loss": 4.5318, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762764493112058e-05, + "loss": 4.5242, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761925898361006e-05, + "loss": 4.5118, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761088941490327e-05, + "loss": 4.5102, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760251984619649e-05, + "loss": 4.5115, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759413389868596e-05, + "loss": 4.5185, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758574795117544e-05, + "loss": 4.5266, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757736200366492e-05, + "loss": 4.5214, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.75689760561544e-05, + "loss": 4.5069, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756059010864388e-05, + "loss": 4.5098, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755220416113336e-05, + "loss": 4.5113, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754381821362284e-05, + "loss": 4.5089, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753544864491605e-05, + "loss": 4.5068, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527062697405536e-05, + "loss": 4.5223, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518676749895016e-05, + "loss": 4.5033, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510290802384496e-05, + "loss": 4.5023, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7501921233677705e-05, + "loss": 4.4977, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.522295951843262, + "eval_runtime": 547.7152, + "eval_samples_per_second": 696.696, + "eval_steps_per_second": 21.772, + "step": 152638 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493535286167185e-05, + "loss": 4.5143, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.7485149338656665e-05, + "loss": 4.5101, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.7476763391146145e-05, + "loss": 4.4949, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468377443635625e-05, + "loss": 4.4972, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7459991496125105e-05, + "loss": 4.4873, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451605548614585e-05, + "loss": 4.4913, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443219601104065e-05, + "loss": 4.4891, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434833653593545e-05, + "loss": 4.4901, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426447706083025e-05, + "loss": 4.4893, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418061758572505e-05, + "loss": 4.4903, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409675811061985e-05, + "loss": 4.495, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401289863551465e-05, + "loss": 4.4973, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.7392903916040945e-05, + "loss": 4.4858, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.7384517968530425e-05, + "loss": 4.4765, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.7376132021019905e-05, + "loss": 4.4825, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.7367746073509385e-05, + "loss": 4.4608, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.7359360125998865e-05, + "loss": 4.4801, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7350974178488345e-05, + "loss": 4.475, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.7342588230977825e-05, + "loss": 4.4732, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.7334218662271034e-05, + "loss": 4.49, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325832714760514e-05, + "loss": 4.4767, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317446767249994e-05, + "loss": 4.478, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309060819739474e-05, + "loss": 4.4815, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730069125103269e-05, + "loss": 4.474, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729230530352217e-05, + "loss": 4.4703, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728391935601165e-05, + "loss": 4.4667, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727553340850113e-05, + "loss": 4.4738, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726716383979434e-05, + "loss": 4.4629, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725877789228382e-05, + "loss": 4.4671, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.72503919447733e-05, + "loss": 4.4514, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724200599726278e-05, + "loss": 4.4581, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723363642855599e-05, + "loss": 4.4717, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.722525048104547e-05, + "loss": 4.4578, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721686453353495e-05, + "loss": 4.4653, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720847858602443e-05, + "loss": 4.4588, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720010901731764e-05, + "loss": 4.4626, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719172306980712e-05, + "loss": 4.4658, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833371222966e-05, + "loss": 4.4611, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.717495117478608e-05, + "loss": 4.4602, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716656522727556e-05, + "loss": 4.449, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.715817927976504e-05, + "loss": 4.4563, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149793332254516e-05, + "loss": 4.4437, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141407384743996e-05, + "loss": 4.4568, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.713303781603721e-05, + "loss": 4.4552, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124651868526685e-05, + "loss": 4.4577, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.71162822998199e-05, + "loss": 4.4444, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710789635230938e-05, + "loss": 4.4459, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709951040479886e-05, + "loss": 4.4545, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709114083609208e-05, + "loss": 4.434, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708275488858156e-05, + "loss": 4.4405, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.7074368941071037e-05, + "loss": 4.4358, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.7065982993560517e-05, + "loss": 4.4542, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705759704604999e-05, + "loss": 4.4314, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704921109853947e-05, + "loss": 4.456, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704082515102895e-05, + "loss": 4.4268, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703243920351843e-05, + "loss": 4.4349, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702405325600791e-05, + "loss": 4.4374, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701566730849739e-05, + "loss": 4.4359, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700728136098687e-05, + "loss": 4.4329, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699889541347635e-05, + "loss": 4.443, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699052584476956e-05, + "loss": 4.4176, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982139897259045e-05, + "loss": 4.4335, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973753949748525e-05, + "loss": 4.4279, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965368002238005e-05, + "loss": 4.4358, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.6956998433531214e-05, + "loss": 4.4252, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.6948612486020694e-05, + "loss": 4.4266, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.6940226538510174e-05, + "loss": 4.4095, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.6931840590999654e-05, + "loss": 4.4355, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.6923454643489134e-05, + "loss": 4.4252, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915068695978614e-05, + "loss": 4.4183, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.6906682748468094e-05, + "loss": 4.4242, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898296800957574e-05, + "loss": 4.421, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.688992723225078e-05, + "loss": 4.4202, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688154128474026e-05, + "loss": 4.4327, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687317171603348e-05, + "loss": 4.4292, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686478576852296e-05, + "loss": 4.4191, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685639982101244e-05, + "loss": 4.4104, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684801387350192e-05, + "loss": 4.4149, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.68396279259914e-05, + "loss": 4.4208, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683125835728461e-05, + "loss": 4.4246, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682287240977409e-05, + "loss": 4.4173, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681448646226357e-05, + "loss": 4.4193, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680610051475305e-05, + "loss": 4.3971, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679771456724252e-05, + "loss": 4.4091, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789328619732e-05, + "loss": 4.4057, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678095905102522e-05, + "loss": 4.4133, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772573103514697e-05, + "loss": 4.4188, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764187156004177e-05, + "loss": 4.4099, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755801208493657e-05, + "loss": 4.4003, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674743163978687e-05, + "loss": 4.4081, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739045692276346e-05, + "loss": 4.3995, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730659744765826e-05, + "loss": 4.407, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722273797255305e-05, + "loss": 4.4073, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713887849744785e-05, + "loss": 4.3908, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705501902234265e-05, + "loss": 4.3941, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697132333527474e-05, + "loss": 4.4008, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688746386016954e-05, + "loss": 4.4074, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668037681731017e-05, + "loss": 4.3968, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667199086979965e-05, + "loss": 4.4046, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666360492228913e-05, + "loss": 4.3954, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665521897477861e-05, + "loss": 4.3962, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664683302726809e-05, + "loss": 4.4031, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663844707975757e-05, + "loss": 4.3996, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663006113224705e-05, + "loss": 4.3861, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662167518473653e-05, + "loss": 4.4039, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661328923722601e-05, + "loss": 4.3782, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660491966851922e-05, + "loss": 4.3829, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.65965337210087e-05, + "loss": 4.3968, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658814777349818e-05, + "loss": 4.3806, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657976182598766e-05, + "loss": 4.3922, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657137587847714e-05, + "loss": 4.3801, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656298993096662e-05, + "loss": 4.3781, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.65546039834561e-05, + "loss": 4.3784, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546218035945586e-05, + "loss": 4.3995, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537848467238795e-05, + "loss": 4.3784, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529462519728275e-05, + "loss": 4.375, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521076572217755e-05, + "loss": 4.3735, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.6512690624707234e-05, + "loss": 4.3822, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.6504321056000444e-05, + "loss": 4.3866, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649595148729365e-05, + "loss": 4.3839, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648756553978313e-05, + "loss": 4.3803, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647917959227261e-05, + "loss": 4.3817, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647079364476209e-05, + "loss": 4.377, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646240769725157e-05, + "loss": 4.3787, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645402174974105e-05, + "loss": 4.3775, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644563580223053e-05, + "loss": 4.38, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643724985472001e-05, + "loss": 4.3707, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642889666481696e-05, + "loss": 4.3711, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642051071730644e-05, + "loss": 4.3867, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641212476979592e-05, + "loss": 4.3615, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.64037388222854e-05, + "loss": 4.3712, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639535287477488e-05, + "loss": 4.372, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6386983306068086e-05, + "loss": 4.3826, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378597358557566e-05, + "loss": 4.3736, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370211411047046e-05, + "loss": 4.3683, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361825463536526e-05, + "loss": 4.3603, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353439516026006e-05, + "loss": 4.3622, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345053568515486e-05, + "loss": 4.372, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336667621004966e-05, + "loss": 4.3804, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328281673494446e-05, + "loss": 4.3761, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319912104787655e-05, + "loss": 4.3628, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631154253608087e-05, + "loss": 4.3614, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630315658857035e-05, + "loss": 4.3717, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629477064105983e-05, + "loss": 4.3632, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286384693549304e-05, + "loss": 4.3629, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627801512484252e-05, + "loss": 4.3765, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.6269629177332e-05, + "loss": 4.3602, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626124322982148e-05, + "loss": 4.3616, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.6252873661114696e-05, + "loss": 4.3587, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 4.388879776000977, + "eval_runtime": 535.2125, + "eval_samples_per_second": 712.971, + "eval_steps_per_second": 22.281, + "step": 228957 + }, + { + "epoch": 1.0, + "learning_rate": 4.6244487713604176e-05, + "loss": 4.3695, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.6236101766093656e-05, + "loss": 4.3717, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622771581858313e-05, + "loss": 4.3561, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621932987107261e-05, + "loss": 4.3555, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621094392356209e-05, + "loss": 4.3531, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620255797605157e-05, + "loss": 4.3488, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619417202854105e-05, + "loss": 4.3541, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618578608103053e-05, + "loss": 4.3502, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617740013352001e-05, + "loss": 4.3534, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616903056481322e-05, + "loss": 4.3586, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.61606446173027e-05, + "loss": 4.355, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152258669792184e-05, + "loss": 4.3584, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6143872722281664e-05, + "loss": 4.3533, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613550315357487e-05, + "loss": 4.3454, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612711720606435e-05, + "loss": 4.3462, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611873125855383e-05, + "loss": 4.3296, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611034531104331e-05, + "loss": 4.3448, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610195936353279e-05, + "loss": 4.3443, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609357341602227e-05, + "loss": 4.3428, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608518746851175e-05, + "loss": 4.3567, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607680152100123e-05, + "loss": 4.3482, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606843195229444e-05, + "loss": 4.3507, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606004600478392e-05, + "loss": 4.3461, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.60516600572734e-05, + "loss": 4.341, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604327410976288e-05, + "loss": 4.3422, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.60349045410561e-05, + "loss": 4.3426, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602651859354558e-05, + "loss": 4.3416, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601813264603506e-05, + "loss": 4.3368, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600974669852454e-05, + "loss": 4.3372, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.600136075101402e-05, + "loss": 4.3249, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599299118230723e-05, + "loss": 4.3327, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984621613600436e-05, + "loss": 4.3436, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976235666089916e-05, + "loss": 4.3358, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967849718579396e-05, + "loss": 4.3388, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959463771068876e-05, + "loss": 4.3348, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595109420236209e-05, + "loss": 4.3379, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594270825485157e-05, + "loss": 4.339, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593432230734105e-05, + "loss": 4.3432, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592593635983053e-05, + "loss": 4.3345, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591755041232001e-05, + "loss": 4.3269, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590916446480949e-05, + "loss": 4.3344, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.5900778517298965e-05, + "loss": 4.3178, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.5892392569788445e-05, + "loss": 4.3388, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884006622277925e-05, + "loss": 4.3354, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.5875620674767404e-05, + "loss": 4.3347, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867234727256884e-05, + "loss": 4.3233, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858848779746364e-05, + "loss": 4.3256, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.5850479211039573e-05, + "loss": 4.3364, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.5842093263529053e-05, + "loss": 4.3145, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583370731601854e-05, + "loss": 4.3222, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582532136850802e-05, + "loss": 4.3211, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.58169354209975e-05, + "loss": 4.3352, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580856585229071e-05, + "loss": 4.3093, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580017990478019e-05, + "loss": 4.3387, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.57918103360734e-05, + "loss": 4.3106, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578342438856288e-05, + "loss": 4.313, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577503844105236e-05, + "loss": 4.3245, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576665249354184e-05, + "loss": 4.313, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575826654603132e-05, + "loss": 4.3241, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.57498805985208e-05, + "loss": 4.3272, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574149465101028e-05, + "loss": 4.3063, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573310870349976e-05, + "loss": 4.3144, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572472275598924e-05, + "loss": 4.3181, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716353187282454e-05, + "loss": 4.3201, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5707967239771934e-05, + "loss": 4.311, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.5699581292261414e-05, + "loss": 4.315, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691195344750894e-05, + "loss": 4.295, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682809397240374e-05, + "loss": 4.3257, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567443982853358e-05, + "loss": 4.3098, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566605388102306e-05, + "loss": 4.3046, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565766793351254e-05, + "loss": 4.3126, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564928198600202e-05, + "loss": 4.3108, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564091241729523e-05, + "loss": 4.3102, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563252646978471e-05, + "loss": 4.3186, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562414052227419e-05, + "loss": 4.3213, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561575457476368e-05, + "loss": 4.3097, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560736862725315e-05, + "loss": 4.3038, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559899905854637e-05, + "loss": 4.3064, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590629489839576e-05, + "loss": 4.3073, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582243542329056e-05, + "loss": 4.3206, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5573857594818536e-05, + "loss": 4.3113, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.5565471647308016e-05, + "loss": 4.3049, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557085699797496e-05, + "loss": 4.2938, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554869975228697e-05, + "loss": 4.3014, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554031380477645e-05, + "loss": 4.3005, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.5531944236069665e-05, + "loss": 4.3052, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523558288559145e-05, + "loss": 4.3057, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.5515172341048625e-05, + "loss": 4.3037, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.5506786393538105e-05, + "loss": 4.2966, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.5498400446027585e-05, + "loss": 4.3054, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490014498517065e-05, + "loss": 4.2968, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481628551006545e-05, + "loss": 4.2989, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473242603496025e-05, + "loss": 4.3016, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5464856655985505e-05, + "loss": 4.2875, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.5456470708474985e-05, + "loss": 4.2881, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.5448084760964465e-05, + "loss": 4.3026, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.5439698813453945e-05, + "loss": 4.2966, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431329244747154e-05, + "loss": 4.3016, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542295967604037e-05, + "loss": 4.2977, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541457372852985e-05, + "loss": 4.2928, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540618778101933e-05, + "loss": 4.2921, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539780183350881e-05, + "loss": 4.3009, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538941588599829e-05, + "loss": 4.2996, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.53810463172915e-05, + "loss": 4.2831, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537266036978098e-05, + "loss": 4.3035, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536427442227046e-05, + "loss": 4.2744, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535588847475994e-05, + "loss": 4.2848, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534750252724942e-05, + "loss": 4.2963, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.53391165797389e-05, + "loss": 4.2799, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533073063222838e-05, + "loss": 4.2919, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532234468471786e-05, + "loss": 4.2797, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.53139914948148e-05, + "loss": 4.2767, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530560554730428e-05, + "loss": 4.2791, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529721959979376e-05, + "loss": 4.3003, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528883365228324e-05, + "loss": 4.2841, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528046408357645e-05, + "loss": 4.2757, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527207813606593e-05, + "loss": 4.2755, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526369218855541e-05, + "loss": 4.2834, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525530624104489e-05, + "loss": 4.289, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.52469366723381e-05, + "loss": 4.2883, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523855072482758e-05, + "loss": 4.2779, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523016477731706e-05, + "loss": 4.2897, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522177882980654e-05, + "loss": 4.2817, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521339288229602e-05, + "loss": 4.2819, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.52050069347855e-05, + "loss": 4.2814, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519662098727499e-05, + "loss": 4.2842, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518823503976446e-05, + "loss": 4.2751, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.517984909225394e-05, + "loss": 4.2763, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517147952354716e-05, + "loss": 4.2891, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516309357603663e-05, + "loss": 4.268, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515470762852611e-05, + "loss": 4.2766, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514632168101559e-05, + "loss": 4.2796, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513793573350507e-05, + "loss": 4.2872, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512954978599455e-05, + "loss": 4.2793, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512118021728776e-05, + "loss": 4.2777, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511279426977724e-05, + "loss": 4.2673, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104408322266726e-05, + "loss": 4.2704, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096022374756206e-05, + "loss": 4.2784, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087652806049415e-05, + "loss": 4.2863, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.5079266858538895e-05, + "loss": 4.2839, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.5070880911028375e-05, + "loss": 4.2713, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.5062494963517855e-05, + "loss": 4.267, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054109016007334e-05, + "loss": 4.2788, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.5045723068496814e-05, + "loss": 4.2719, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037337120986294e-05, + "loss": 4.2734, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5028951173475774e-05, + "loss": 4.2824, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020565225965254e-05, + "loss": 4.2733, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501219565725846e-05, + "loss": 4.2698, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500380970974794e-05, + "loss": 4.2696, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 4.306464672088623, + "eval_runtime": 533.2267, + "eval_samples_per_second": 715.626, + "eval_steps_per_second": 22.364, + "step": 305276 + }, + { + "epoch": 0.0, + "learning_rate": 4.499542376223742e-05, + "loss": 4.2842, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498703781472691e-05, + "loss": 4.2806, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497865186721639e-05, + "loss": 4.2659, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497026591970587e-05, + "loss": 4.2649, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496187997219535e-05, + "loss": 4.2671, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495349402468482e-05, + "loss": 4.2624, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.49451080771743e-05, + "loss": 4.2647, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.493672212966378e-05, + "loss": 4.2592, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492833618215326e-05, + "loss": 4.2675, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.491995023464274e-05, + "loss": 4.2748, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491156428713222e-05, + "loss": 4.2647, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.49031783396217e-05, + "loss": 4.2652, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489479239211118e-05, + "loss": 4.2681, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488640644460066e-05, + "loss": 4.2603, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487802049709014e-05, + "loss": 4.2599, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486963454957962e-05, + "loss": 4.2421, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486126498087284e-05, + "loss": 4.2558, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485287903336232e-05, + "loss": 4.2573, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48444930858518e-05, + "loss": 4.2551, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483612351714501e-05, + "loss": 4.2761, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482773756963449e-05, + "loss": 4.2597, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481935162212397e-05, + "loss": 4.2658, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481096567461345e-05, + "loss": 4.2579, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480257972710293e-05, + "loss": 4.2609, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479419377959241e-05, + "loss": 4.2527, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478580783208188e-05, + "loss": 4.2588, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477742188457136e-05, + "loss": 4.2572, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476903593706084e-05, + "loss": 4.255, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476064998955033e-05, + "loss": 4.2512, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475226404203981e-05, + "loss": 4.2428, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474387809452929e-05, + "loss": 4.2451, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.4735508525822496e-05, + "loss": 4.2599, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.4727122578311976e-05, + "loss": 4.2549, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.4718753009605185e-05, + "loss": 4.2569, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.4710367062094665e-05, + "loss": 4.2534, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.4701981114584145e-05, + "loss": 4.2548, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693595167073625e-05, + "loss": 4.256, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685209219563105e-05, + "loss": 4.2626, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4676839650856314e-05, + "loss": 4.2542, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668453703345794e-05, + "loss": 4.2439, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466006775583528e-05, + "loss": 4.2565, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465168180832476e-05, + "loss": 4.2347, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464329586081424e-05, + "loss": 4.2531, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463490991330372e-05, + "loss": 4.2508, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46265239657932e-05, + "loss": 4.2597, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461815439708641e-05, + "loss": 4.2454, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460976844957589e-05, + "loss": 4.2412, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460138250206537e-05, + "loss": 4.255, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459299655455485e-05, + "loss": 4.2387, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458461060704433e-05, + "loss": 4.2401, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457622465953381e-05, + "loss": 4.2444, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456783871202329e-05, + "loss": 4.251, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455945276451277e-05, + "loss": 4.2353, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455108319580598e-05, + "loss": 4.2541, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542697248295465e-05, + "loss": 4.2324, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534311300784945e-05, + "loss": 4.2369, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4525925353274425e-05, + "loss": 4.2456, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517555784567634e-05, + "loss": 4.2314, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509169837057114e-05, + "loss": 4.2498, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4500783889546594e-05, + "loss": 4.2526, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449239794203607e-05, + "loss": 4.2263, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448402837332928e-05, + "loss": 4.2355, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447564242581876e-05, + "loss": 4.2404, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446725647830824e-05, + "loss": 4.2475, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4458870530797716e-05, + "loss": 4.2322, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445050096209093e-05, + "loss": 4.2352, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444211501458041e-05, + "loss": 4.2229, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443374544587363e-05, + "loss": 4.2443, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442535949836311e-05, + "loss": 4.2364, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441697355085259e-05, + "loss": 4.2275, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440858760334207e-05, + "loss": 4.2386, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440020165583154e-05, + "loss": 4.2352, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439181570832102e-05, + "loss": 4.2329, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.43834297608105e-05, + "loss": 4.243, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437504381329998e-05, + "loss": 4.2428, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436667424459319e-05, + "loss": 4.2344, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435828829708267e-05, + "loss": 4.231, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.434990234957216e-05, + "loss": 4.2339, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341532780865366e-05, + "loss": 4.2293, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.4333146833354846e-05, + "loss": 4.2488, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4324760885844326e-05, + "loss": 4.2342, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316374938333806e-05, + "loss": 4.2335, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4307988990823286e-05, + "loss": 4.2166, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299603043312766e-05, + "loss": 4.2314, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291217095802245e-05, + "loss": 4.2228, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4282831148291725e-05, + "loss": 4.2362, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274445200781205e-05, + "loss": 4.2291, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266059253270685e-05, + "loss": 4.2308, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257673305760165e-05, + "loss": 4.2229, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249303737053374e-05, + "loss": 4.2356, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4240917789542854e-05, + "loss": 4.2215, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232531842032334e-05, + "loss": 4.2235, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422414589452182e-05, + "loss": 4.234, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.42157599470113e-05, + "loss": 4.2113, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420737399950078e-05, + "loss": 4.2163, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419898805199026e-05, + "loss": 4.2309, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190602104479734e-05, + "loss": 4.2203, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418223253577295e-05, + "loss": 4.2351, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417384658826243e-05, + "loss": 4.2253, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.41654606407519e-05, + "loss": 4.217, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415707469324138e-05, + "loss": 4.2217, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414868874573086e-05, + "loss": 4.2295, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414031917702408e-05, + "loss": 4.2278, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413194960831729e-05, + "loss": 4.215, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123563660806775e-05, + "loss": 4.2321, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115177713296255e-05, + "loss": 4.204, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4106791765785735e-05, + "loss": 4.2161, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409840581827521e-05, + "loss": 4.2272, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409005262837215e-05, + "loss": 4.2077, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408166668086163e-05, + "loss": 4.223, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407328073335111e-05, + "loss": 4.216, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406489478584059e-05, + "loss": 4.2014, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405650883833007e-05, + "loss": 4.2091, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404812289081955e-05, + "loss": 4.2301, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.4039736943309026e-05, + "loss": 4.2128, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403135099579851e-05, + "loss": 4.2098, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402296504828799e-05, + "loss": 4.2063, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401457910077747e-05, + "loss": 4.2135, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400619315326695e-05, + "loss": 4.2224, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399782358456016e-05, + "loss": 4.2186, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398943763704964e-05, + "loss": 4.2119, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398105168953912e-05, + "loss": 4.2175, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39726657420286e-05, + "loss": 4.2154, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396427979451808e-05, + "loss": 4.2145, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395589384700756e-05, + "loss": 4.215, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394750789949704e-05, + "loss": 4.2143, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393912195198652e-05, + "loss": 4.205, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393075238327973e-05, + "loss": 4.214, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922382814572946e-05, + "loss": 4.2172, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3913996867062426e-05, + "loss": 4.2039, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905610919551906e-05, + "loss": 4.2098, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897224972041386e-05, + "loss": 4.2149, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3888839024530866e-05, + "loss": 4.2166, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880453077020346e-05, + "loss": 4.2174, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872067129509826e-05, + "loss": 4.2112, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3863681181999306e-05, + "loss": 4.1999, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855311613292515e-05, + "loss": 4.2037, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3846925665781995e-05, + "loss": 4.2112, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838539718271475e-05, + "loss": 4.2199, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830153770760955e-05, + "loss": 4.2202, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3821784202054164e-05, + "loss": 4.2078, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813398254543644e-05, + "loss": 4.1976, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380501230703313e-05, + "loss": 4.213, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379662635952261e-05, + "loss": 4.2039, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378825679081582e-05, + "loss": 4.2068, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.37798708433053e-05, + "loss": 4.2197, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377148489579478e-05, + "loss": 4.2121, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376311532708799e-05, + "loss": 4.2007, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375472937957747e-05, + "loss": 4.207, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 4.250527858734131, + "eval_runtime": 529.3053, + "eval_samples_per_second": 720.928, + "eval_steps_per_second": 22.53, + "step": 381595 + }, + { + "epoch": 1.0, + "learning_rate": 4.374634343206695e-05, + "loss": 4.2133, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373795748455643e-05, + "loss": 4.2178, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372957153704591e-05, + "loss": 4.2003, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372118558953539e-05, + "loss": 4.1993, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.37128160208286e-05, + "loss": 4.2055, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.3704446452121813e-05, + "loss": 4.197, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369606050461129e-05, + "loss": 4.2016, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368767455710077e-05, + "loss": 4.1902, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367928860959025e-05, + "loss": 4.2054, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367091904088346e-05, + "loss": 4.2152, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366253309337294e-05, + "loss": 4.1985, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365414714586242e-05, + "loss": 4.2007, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.36457611983519e-05, + "loss": 4.2095, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363737525084138e-05, + "loss": 4.1957, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362898930333086e-05, + "loss": 4.1988, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620603355820335e-05, + "loss": 4.1803, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361221740830982e-05, + "loss": 4.1918, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.36038314607993e-05, + "loss": 4.1926, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359544551328878e-05, + "loss": 4.1934, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358705956577826e-05, + "loss": 4.2152, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357867361826774e-05, + "loss": 4.1962, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357030404956095e-05, + "loss": 4.206, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356191810205043e-05, + "loss": 4.198, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355353215453991e-05, + "loss": 4.1976, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354516258583312e-05, + "loss": 4.1882, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.35367766383226e-05, + "loss": 4.1963, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352839069081208e-05, + "loss": 4.1967, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352000474330156e-05, + "loss": 4.194, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351161879579104e-05, + "loss": 4.1913, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350323284828052e-05, + "loss": 4.184, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3494863279573736e-05, + "loss": 4.1792, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486477332063216e-05, + "loss": 4.2035, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478091384552696e-05, + "loss": 4.1957, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3469705437042175e-05, + "loss": 4.1933, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461335868335385e-05, + "loss": 4.1935, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3452949920824865e-05, + "loss": 4.1939, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444563973314344e-05, + "loss": 4.1992, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436178025803824e-05, + "loss": 4.1987, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3427792078293304e-05, + "loss": 4.1942, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419406130782784e-05, + "loss": 4.1858, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411020183272264e-05, + "loss": 4.193, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402634235761744e-05, + "loss": 4.1782, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339426466705496e-05, + "loss": 4.1937, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338587871954444e-05, + "loss": 4.1906, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337749277203392e-05, + "loss": 4.2007, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.33691068245234e-05, + "loss": 4.1893, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336073725581661e-05, + "loss": 4.1822, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335236768710982e-05, + "loss": 4.2001, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.33439817395993e-05, + "loss": 4.1753, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333559579208878e-05, + "loss": 4.1832, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332720984457826e-05, + "loss": 4.1859, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331884027587147e-05, + "loss": 4.191, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331045432836095e-05, + "loss": 4.1768, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330206838085043e-05, + "loss": 4.1938, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3293682433339914e-05, + "loss": 4.1792, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285296485829394e-05, + "loss": 4.1779, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3276910538318874e-05, + "loss": 4.1898, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326852459080835e-05, + "loss": 4.1766, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326015502210156e-05, + "loss": 4.1902, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325176907459104e-05, + "loss": 4.1935, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324338312708052e-05, + "loss": 4.1754, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.3234997179569996e-05, + "loss": 4.1768, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.3226611232059476e-05, + "loss": 4.1801, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218225284548956e-05, + "loss": 4.1945, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3209839337038436e-05, + "loss": 4.177, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201453389527916e-05, + "loss": 4.1817, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193067442017396e-05, + "loss": 4.1645, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3184681494506876e-05, + "loss": 4.1883, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317631192580009e-05, + "loss": 4.1782, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316792597828957e-05, + "loss": 4.1711, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315954003077905e-05, + "loss": 4.1797, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315115408326853e-05, + "loss": 4.182, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.314276813575801e-05, + "loss": 4.1773, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313438218824749e-05, + "loss": 4.1847, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312599624073697e-05, + "loss": 4.1881, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311762667203018e-05, + "loss": 4.1798, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310924072451966e-05, + "loss": 4.1729, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310085477700914e-05, + "loss": 4.1815, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309246882949862e-05, + "loss": 4.1743, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.30840828819881e-05, + "loss": 4.1887, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307569693447758e-05, + "loss": 4.1776, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306731098696706e-05, + "loss": 4.182, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305892503945654e-05, + "loss": 4.1634, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050571849553485e-05, + "loss": 4.1762, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042185902042965e-05, + "loss": 4.1651, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3033799954532445e-05, + "loss": 4.1838, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025414007021925e-05, + "loss": 4.1757, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.3017028059511405e-05, + "loss": 4.1748, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008658490804614e-05, + "loss": 4.1721, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000272543294094e-05, + "loss": 4.1842, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.2991886595783574e-05, + "loss": 4.1603, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983500648273054e-05, + "loss": 4.1707, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975114700762534e-05, + "loss": 4.1812, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296676151085948e-05, + "loss": 4.1582, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295837556334896e-05, + "loss": 4.1646, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.294998961583844e-05, + "loss": 4.1785, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294160366832792e-05, + "loss": 4.1649, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.29332177208174e-05, + "loss": 4.1852, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292483177330688e-05, + "loss": 4.171, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291644582579636e-05, + "loss": 4.1623, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290805987828583e-05, + "loss": 4.1655, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.289967393077531e-05, + "loss": 4.179, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289128798326479e-05, + "loss": 4.1772, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288291841455801e-05, + "loss": 4.1611, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287453246704749e-05, + "loss": 4.1764, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286614651953697e-05, + "loss": 4.1501, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285776057202645e-05, + "loss": 4.1636, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284937462451593e-05, + "loss": 4.1749, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284098867700541e-05, + "loss": 4.1567, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283260272949489e-05, + "loss": 4.1686, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824233160788096e-05, + "loss": 4.169, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2815847213277576e-05, + "loss": 4.1448, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807461265767056e-05, + "loss": 4.1599, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799075318256536e-05, + "loss": 4.175, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2790689370746016e-05, + "loss": 4.1673, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782303423235496e-05, + "loss": 4.1546, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2773917475724976e-05, + "loss": 4.1543, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765531528214456e-05, + "loss": 4.163, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.275716195950767e-05, + "loss": 4.1694, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.274879239080088e-05, + "loss": 4.17, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274040644329036e-05, + "loss": 4.158, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273202049577984e-05, + "loss": 4.1633, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272363454826932e-05, + "loss": 4.1635, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.27152486007588e-05, + "loss": 4.1657, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270686265324828e-05, + "loss": 4.1607, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269849308454149e-05, + "loss": 4.1634, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269010713703097e-05, + "loss": 4.1559, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268172118952045e-05, + "loss": 4.1646, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267333524200993e-05, + "loss": 4.1671, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266494929449941e-05, + "loss": 4.1503, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265656334698889e-05, + "loss": 4.1585, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.2648210157085835e-05, + "loss": 4.1684, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2639824209575315e-05, + "loss": 4.1656, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631438262064795e-05, + "loss": 4.1659, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623052314554274e-05, + "loss": 4.1611, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2614666367043754e-05, + "loss": 4.1461, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606280419533234e-05, + "loss": 4.1525, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2597894472022714e-05, + "loss": 4.1586, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258950852451219e-05, + "loss": 4.1748, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581138955805403e-05, + "loss": 4.1699, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257275300829488e-05, + "loss": 4.1544, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256436706078436e-05, + "loss": 4.1568, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255598111327384e-05, + "loss": 4.1598, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254759516576332e-05, + "loss": 4.1585, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.25392092182528e-05, + "loss": 4.1562, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253082327074228e-05, + "loss": 4.1716, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252247008083923e-05, + "loss": 4.1617, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251408413332871e-05, + "loss": 4.151, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250569818581819e-05, + "loss": 4.1571, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 4.209777355194092, + "eval_runtime": 527.1364, + "eval_samples_per_second": 723.894, + "eval_steps_per_second": 22.622, + "step": 457914 + }, + { + "epoch": 0.0, + "learning_rate": 4.249731223830766e-05, + "loss": 4.1703, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248892629079714e-05, + "loss": 4.17, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248054034328662e-05, + "loss": 4.1553, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.24721543957761e-05, + "loss": 4.1534, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246376844826558e-05, + "loss": 4.1548, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245538250075506e-05, + "loss": 4.1494, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244699655324455e-05, + "loss": 4.1526, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243861060573403e-05, + "loss": 4.1432, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243022465822351e-05, + "loss": 4.1547, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242183871071299e-05, + "loss": 4.169, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.241345276320247e-05, + "loss": 4.1508, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240506681569195e-05, + "loss": 4.1521, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239668086818143e-05, + "loss": 4.1623, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238829492067091e-05, + "loss": 4.1467, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.237990897316038e-05, + "loss": 4.1553, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237152302564986e-05, + "loss": 4.1335, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236313707813934e-05, + "loss": 4.1401, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235475113062882e-05, + "loss": 4.1465, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.23463651831183e-05, + "loss": 4.1468, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233797923560778e-05, + "loss": 4.1709, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.232959328809726e-05, + "loss": 4.1513, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321223719390476e-05, + "loss": 4.1603, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2312837771879956e-05, + "loss": 4.1474, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304451824369436e-05, + "loss": 4.1511, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.2296065876858916e-05, + "loss": 4.1423, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2287696308152125e-05, + "loss": 4.1505, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.2279310360641605e-05, + "loss": 4.15, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.2270924413131085e-05, + "loss": 4.1435, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2262538465620565e-05, + "loss": 4.1506, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254168896913774e-05, + "loss": 4.135, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2245782949403254e-05, + "loss": 4.1332, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237397001892734e-05, + "loss": 4.1557, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229011054382214e-05, + "loss": 4.1498, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.22206251068717e-05, + "loss": 4.1518, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221223915936118e-05, + "loss": 4.144, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220386959065439e-05, + "loss": 4.1507, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.21955000219476e-05, + "loss": 4.1496, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218711407443708e-05, + "loss": 4.1549, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217872812692656e-05, + "loss": 4.1473, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217034217941604e-05, + "loss": 4.1409, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216195623190552e-05, + "loss": 4.1501, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2153570284395e-05, + "loss": 4.1305, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214518433688448e-05, + "loss": 4.1488, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213679838937396e-05, + "loss": 4.1476, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212841244186344e-05, + "loss": 4.1531, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212002649435292e-05, + "loss": 4.1454, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2111656925646134e-05, + "loss": 4.1357, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103270978135614e-05, + "loss": 4.1546, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2094885030625094e-05, + "loss": 4.1343, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208649908311457e-05, + "loss": 4.1366, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207811313560405e-05, + "loss": 4.1405, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.206972718809353e-05, + "loss": 4.1451, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206134124058301e-05, + "loss": 4.1362, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205295529307249e-05, + "loss": 4.1437, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204456934556197e-05, + "loss": 4.1328, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036199776855176e-05, + "loss": 4.1367, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2027813829344656e-05, + "loss": 4.1419, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201944426063787e-05, + "loss": 4.135, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201105831312735e-05, + "loss": 4.1444, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200267236561683e-05, + "loss": 4.1487, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199430279691004e-05, + "loss": 4.1314, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198591684939952e-05, + "loss": 4.1337, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977530901889e-05, + "loss": 4.1326, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196914495437848e-05, + "loss": 4.1539, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196075900686796e-05, + "loss": 4.1352, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195237305935744e-05, + "loss": 4.1354, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194398711184692e-05, + "loss": 4.1232, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.19356011643364e-05, + "loss": 4.1413, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192721521682588e-05, + "loss": 4.135, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191884564811909e-05, + "loss": 4.1299, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191045970060857e-05, + "loss": 4.1383, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.1902073753098057e-05, + "loss": 4.1378, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1893687805587537e-05, + "loss": 4.1354, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885301858077017e-05, + "loss": 4.1387, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1876915910566496e-05, + "loss": 4.1477, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1868529963055976e-05, + "loss": 4.1362, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860160394349186e-05, + "loss": 4.1318, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.1851790825642395e-05, + "loss": 4.1356, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843404878131875e-05, + "loss": 4.1328, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835018930621355e-05, + "loss": 4.1471, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1826632983110834e-05, + "loss": 4.1344, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818247035600314e-05, + "loss": 4.1402, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.1809861088089794e-05, + "loss": 4.1197, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.1801475140579274e-05, + "loss": 4.1355, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793089193068754e-05, + "loss": 4.1194, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1784703245558234e-05, + "loss": 4.1407, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776317298047714e-05, + "loss": 4.133, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1767931350537194e-05, + "loss": 4.1341, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1759545403026674e-05, + "loss": 4.1281, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175117583431988e-05, + "loss": 4.1375, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.17428062656131e-05, + "loss": 4.1237, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173442031810257e-05, + "loss": 4.127, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172603437059205e-05, + "loss": 4.1383, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171764842308153e-05, + "loss": 4.1179, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170926247557101e-05, + "loss": 4.122, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170087652806049e-05, + "loss": 4.1316, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169250695935371e-05, + "loss": 4.1237, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168412101184319e-05, + "loss": 4.1449, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167573506433267e-05, + "loss": 4.1267, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166734911682215e-05, + "loss": 4.1258, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165896316931163e-05, + "loss": 4.1229, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165057722180111e-05, + "loss": 4.136, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164220765309432e-05, + "loss": 4.1363, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16338217055838e-05, + "loss": 4.1215, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162543575807328e-05, + "loss": 4.1299, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161704981056276e-05, + "loss": 4.1144, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160866386305224e-05, + "loss": 4.118, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160027791554172e-05, + "loss": 4.1322, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1591891968031197e-05, + "loss": 4.1198, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1583506020520677e-05, + "loss": 4.1259, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157515283061762e-05, + "loss": 4.1261, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15667668831071e-05, + "loss": 4.1056, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155838093559658e-05, + "loss": 4.1195, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155001136688979e-05, + "loss": 4.1379, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154162541937927e-05, + "loss": 4.1289, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153323947186875e-05, + "loss": 4.108, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152485352435823e-05, + "loss": 4.1161, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151646757684771e-05, + "loss": 4.1214, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150809800814092e-05, + "loss": 4.127, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.14997120606304e-05, + "loss": 4.1305, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149132611311988e-05, + "loss": 4.119, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1482940165609366e-05, + "loss": 4.1239, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1474554218098846e-05, + "loss": 4.1236, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466168270588326e-05, + "loss": 4.1244, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1457782323077806e-05, + "loss": 4.1227, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1449396375567286e-05, + "loss": 4.1231, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144101042805676e-05, + "loss": 4.1182, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143262448054624e-05, + "loss": 4.1234, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142423853303572e-05, + "loss": 4.1237, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.14158525855252e-05, + "loss": 4.1099, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140748301681841e-05, + "loss": 4.1206, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.1399113448111624e-05, + "loss": 4.1256, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1390727500601104e-05, + "loss": 4.1272, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138235793189432e-05, + "loss": 4.1282, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.13739719843838e-05, + "loss": 4.1236, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136558603687328e-05, + "loss": 4.1085, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135720008936276e-05, + "loss": 4.1098, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134881414185223e-05, + "loss": 4.1203, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134042819434171e-05, + "loss": 4.1366, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133204224683119e-05, + "loss": 4.1306, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132365629932067e-05, + "loss": 4.1159, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131527035181015e-05, + "loss": 4.1121, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130690078310336e-05, + "loss": 4.1231, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129851483559284e-05, + "loss": 4.1185, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129012888808232e-05, + "loss": 4.1164, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128175931937554e-05, + "loss": 4.1317, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127337337186502e-05, + "loss": 4.1236, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.12649874243545e-05, + "loss": 4.1106, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125660147684398e-05, + "loss": 4.121, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 4.179218769073486, + "eval_runtime": 538.4308, + "eval_samples_per_second": 708.709, + "eval_steps_per_second": 22.148, + "step": 534233 + }, + { + "epoch": 1.0, + "learning_rate": 4.124821552933346e-05, + "loss": 4.1211, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.123982958182294e-05, + "loss": 4.1308, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123144363431242e-05, + "loss": 4.1181, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12230576868019e-05, + "loss": 4.1147, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121467173929138e-05, + "loss": 4.1124, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120628579178086e-05, + "loss": 4.1163, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119789984427034e-05, + "loss": 4.1119, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.118951389675982e-05, + "loss": 4.1065, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.1181144328053026e-05, + "loss": 4.1145, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.1172758380542506e-05, + "loss": 4.1281, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116438881183572e-05, + "loss": 4.1117, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.11560028643252e-05, + "loss": 4.1138, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114761691681468e-05, + "loss": 4.127, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113924734810789e-05, + "loss": 4.107, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113086140059737e-05, + "loss": 4.1182, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112247545308685e-05, + "loss": 4.0956, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111408950557633e-05, + "loss": 4.0997, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110570355806581e-05, + "loss": 4.1122, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109731761055529e-05, + "loss": 4.1073, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108893166304477e-05, + "loss": 4.1319, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1080545715534244e-05, + "loss": 4.1147, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072159768023724e-05, + "loss": 4.1194, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106377382051321e-05, + "loss": 4.1101, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105538787300269e-05, + "loss": 4.1166, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104700192549217e-05, + "loss": 4.1036, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103863235678538e-05, + "loss": 4.1133, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103024640927486e-05, + "loss": 4.115, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102186046176434e-05, + "loss": 4.1089, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101347451425382e-05, + "loss": 4.1084, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100510494554703e-05, + "loss": 4.1002, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099671899803651e-05, + "loss": 4.0953, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098833305052599e-05, + "loss": 4.1167, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.097994710301547e-05, + "loss": 4.1125, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097156115550495e-05, + "loss": 4.1118, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096319158679816e-05, + "loss": 4.1098, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0954805639287644e-05, + "loss": 4.1151, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0946419691777124e-05, + "loss": 4.1126, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938033744266604e-05, + "loss": 4.1113, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0929647796756084e-05, + "loss": 4.1093, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921261849245564e-05, + "loss": 4.1112, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0912875901735044e-05, + "loss": 4.106, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0904489954224524e-05, + "loss": 4.0977, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896104006714004e-05, + "loss": 4.1144, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088773443800721e-05, + "loss": 4.11, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087934849049669e-05, + "loss": 4.1176, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087096254298617e-05, + "loss": 4.1132, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086257659547565e-05, + "loss": 4.0967, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085419064796513e-05, + "loss": 4.1185, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084582107925834e-05, + "loss": 4.0975, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083743513174783e-05, + "loss": 4.1044, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082904918423731e-05, + "loss": 4.0994, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082066323672678e-05, + "loss": 4.1106, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081229366802e-05, + "loss": 4.0996, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080390772050948e-05, + "loss": 4.1048, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079552177299896e-05, + "loss": 4.1002, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078713582548843e-05, + "loss": 4.0964, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.0778766256781647e-05, + "loss": 4.1062, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0770380309271127e-05, + "loss": 4.1005, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0761994361760607e-05, + "loss": 4.1118, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075364117185755e-05, + "loss": 4.1083, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074525522434703e-05, + "loss": 4.1008, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073686927683651e-05, + "loss": 4.0925, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072848332932599e-05, + "loss": 4.1001, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072009738181547e-05, + "loss": 4.1142, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071171143430495e-05, + "loss": 4.1009, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070332548679443e-05, + "loss": 4.0967, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0694939539283904e-05, + "loss": 4.0919, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0686553591773384e-05, + "loss": 4.105, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678167644262864e-05, + "loss": 4.0963, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0669781696752344e-05, + "loss": 4.0998, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0661412128045553e-05, + "loss": 4.1022, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065302618053503e-05, + "loss": 4.0994, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064464023302452e-05, + "loss": 4.1026, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636254285514e-05, + "loss": 4.1064, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.062786833800348e-05, + "loss": 4.1107, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.061948239049296e-05, + "loss": 4.1007, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.061111282178617e-05, + "loss": 4.0966, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060272687427565e-05, + "loss": 4.1018, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059435730556886e-05, + "loss": 4.0977, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058597135805834e-05, + "loss": 4.1104, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057758541054782e-05, + "loss": 4.1039, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.05691994630373e-05, + "loss": 4.1054, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056081351552678e-05, + "loss": 4.0852, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055242756801626e-05, + "loss": 4.0984, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054404162050574e-05, + "loss": 4.0863, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.0535672051798954e-05, + "loss": 4.1053, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.0527286104288434e-05, + "loss": 4.1011, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.0518900156777914e-05, + "loss": 4.0991, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.0510514209267394e-05, + "loss": 4.1001, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.05021446405606e-05, + "loss": 4.101, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049375869305008e-05, + "loss": 4.0906, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048537274553956e-05, + "loss": 4.0938, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047698679802904e-05, + "loss": 4.1023, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046860085051852e-05, + "loss": 4.0867, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.0460214903008e-05, + "loss": 4.0884, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045182895549748e-05, + "loss": 4.0908, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044344300798696e-05, + "loss": 4.0945, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043505706047644e-05, + "loss": 4.1096, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042667111296592e-05, + "loss": 4.0931, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.04182851654554e-05, + "loss": 4.0935, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.040989921794488e-05, + "loss": 4.0873, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040151327043436e-05, + "loss": 4.1044, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039314370172757e-05, + "loss": 4.0981, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038477413302079e-05, + "loss": 4.0897, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037638818551027e-05, + "loss": 4.0992, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036800223799974e-05, + "loss": 4.0802, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.035961629048922e-05, + "loss": 4.0795, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.03512303429787e-05, + "loss": 4.1002, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034284439546818e-05, + "loss": 4.0878, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033445844795766e-05, + "loss": 4.0943, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326088879250876e-05, + "loss": 4.0927, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0317702931740356e-05, + "loss": 4.0685, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309316984229836e-05, + "loss": 4.0881, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0300931036719316e-05, + "loss": 4.1017, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0292545089208796e-05, + "loss": 4.0941, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284159141698276e-05, + "loss": 4.0796, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0275773194187756e-05, + "loss": 4.0818, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0267403625480965e-05, + "loss": 4.0841, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259017677970445e-05, + "loss": 4.0953, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0250631730459925e-05, + "loss": 4.0971, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242245782949405e-05, + "loss": 4.0872, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0233859835438885e-05, + "loss": 4.086, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0225473887928365e-05, + "loss": 4.0947, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217087940417845e-05, + "loss": 4.0901, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020871837171106e-05, + "loss": 4.0863, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020033242420054e-05, + "loss": 4.093, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019194647669002e-05, + "loss": 4.086, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.01835605291795e-05, + "loss": 4.0886, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017517458166898e-05, + "loss": 4.0996, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016678863415845e-05, + "loss": 4.0726, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015840268664793e-05, + "loss": 4.0887, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015003311794115e-05, + "loss": 4.0942, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014164717043063e-05, + "loss": 4.0923, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.01332612229201e-05, + "loss": 4.0925, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012487527540958e-05, + "loss": 4.0929, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011648932789906e-05, + "loss": 4.0783, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010811975919228e-05, + "loss": 4.0776, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.009973381168176e-05, + "loss": 4.0898, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009134786417124e-05, + "loss": 4.0991, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008296191666072e-05, + "loss": 4.101, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.00745759691502e-05, + "loss": 4.0824, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006619002163968e-05, + "loss": 4.0798, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005780407412916e-05, + "loss": 4.0925, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.004941812661864e-05, + "loss": 4.0824, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004104855791185e-05, + "loss": 4.0878, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003266261040133e-05, + "loss": 4.0965, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024293041694536e-05, + "loss": 4.0946, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0015907094184016e-05, + "loss": 4.0797, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0007521146673496e-05, + "loss": 4.0895, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 4.154397964477539, + "eval_runtime": 534.4827, + "eval_samples_per_second": 713.945, + "eval_steps_per_second": 22.311, + "step": 610552 + }, + { + "epoch": 0.0, + "learning_rate": 3.999913519916298e-05, + "loss": 4.0919, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999074925165246e-05, + "loss": 4.1014, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998236330414194e-05, + "loss": 4.0854, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997397735663142e-05, + "loss": 4.0874, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.99655914091209e-05, + "loss": 4.0793, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995720546161038e-05, + "loss": 4.0853, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994881951409986e-05, + "loss": 4.0851, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994043356658934e-05, + "loss": 4.0699, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932047619078815e-05, + "loss": 4.0814, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9923661671568295e-05, + "loss": 4.098, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9915275724057775e-05, + "loss": 4.0829, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9906889776547255e-05, + "loss": 4.0798, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9898503829036735e-05, + "loss": 4.0952, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890134260329944e-05, + "loss": 4.0759, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988174831281943e-05, + "loss": 4.086, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987336236530891e-05, + "loss": 4.0669, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986497641779839e-05, + "loss": 4.0668, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985659047028787e-05, + "loss": 4.0827, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984820452277735e-05, + "loss": 4.0742, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.983981857526683e-05, + "loss": 4.0986, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983143262775631e-05, + "loss": 4.0865, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982304668024579e-05, + "loss": 4.0881, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981466073273527e-05, + "loss": 4.0788, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980627478522475e-05, + "loss": 4.0877, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979788883771423e-05, + "loss": 4.0739, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9789502890203704e-05, + "loss": 4.0795, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978114970030065e-05, + "loss": 4.0764, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977276375279013e-05, + "loss": 4.0809, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9764377805279616e-05, + "loss": 4.0821, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9755991857769096e-05, + "loss": 4.0684, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9747605910258575e-05, + "loss": 4.0678, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739219962748055e-05, + "loss": 4.0824, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973083401523753e-05, + "loss": 4.0837, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.9722464446530744e-05, + "loss": 4.0802, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714078499020224e-05, + "loss": 4.0785, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9705692551509704e-05, + "loss": 4.082, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969730660399918e-05, + "loss": 4.0801, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968892065648866e-05, + "loss": 4.0839, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968053470897814e-05, + "loss": 4.0795, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967214876146762e-05, + "loss": 4.0785, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.96637628139571e-05, + "loss": 4.0773, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9655376866446584e-05, + "loss": 4.0672, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964702367654353e-05, + "loss": 4.0792, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9638637729033e-05, + "loss": 4.085, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963025178152248e-05, + "loss": 4.0828, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962186583401196e-05, + "loss": 4.0856, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961347988650144e-05, + "loss": 4.0628, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960509393899092e-05, + "loss": 4.0915, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.95967079914804e-05, + "loss": 4.0692, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958832204396988e-05, + "loss": 4.0752, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.957993609645936e-05, + "loss": 4.072, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957156652775257e-05, + "loss": 4.0743, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956319695904579e-05, + "loss": 4.078, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9554827390339e-05, + "loss": 4.07, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9546441442828476e-05, + "loss": 4.0757, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538055495317956e-05, + "loss": 4.0654, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9529669547807436e-05, + "loss": 4.0798, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9521283600296916e-05, + "loss": 4.0688, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9512897652786396e-05, + "loss": 4.0834, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9504511705275876e-05, + "loss": 4.0756, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496125757765356e-05, + "loss": 4.073, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9487739810254836e-05, + "loss": 4.0682, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9479353862744316e-05, + "loss": 4.0692, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9470967915233796e-05, + "loss": 4.079, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.9462581967723276e-05, + "loss": 4.0728, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454212399016485e-05, + "loss": 4.0714, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944582645150597e-05, + "loss": 4.0653, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943744050399545e-05, + "loss": 4.0713, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942905455648493e-05, + "loss": 4.0694, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942066860897441e-05, + "loss": 4.0694, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941229904026762e-05, + "loss": 4.0697, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.94039130927571e-05, + "loss": 4.0715, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939552714524658e-05, + "loss": 4.0744, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938714119773606e-05, + "loss": 4.0796, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9378755250225533e-05, + "loss": 4.076, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937036930271501e-05, + "loss": 4.0695, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936198335520449e-05, + "loss": 4.0708, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935359740769397e-05, + "loss": 4.0735, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934522783898719e-05, + "loss": 4.0663, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933684189147667e-05, + "loss": 4.079, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932845594396615e-05, + "loss": 4.077, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932006999645563e-05, + "loss": 4.0774, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931170042774884e-05, + "loss": 4.0583, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930331448023832e-05, + "loss": 4.0689, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.92949285327278e-05, + "loss": 4.0567, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.928654258521728e-05, + "loss": 4.0788, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927815663770676e-05, + "loss": 4.0756, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.926977069019624e-05, + "loss": 4.0657, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926138474268572e-05, + "loss": 4.0696, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.92529987951752e-05, + "loss": 4.0755, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924464560527214e-05, + "loss": 4.0618, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923627603656536e-05, + "loss": 4.0652, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922789008905484e-05, + "loss": 4.0738, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.921950414154431e-05, + "loss": 4.0589, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921111819403379e-05, + "loss": 4.0624, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920273224652327e-05, + "loss": 4.06, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919434629901275e-05, + "loss": 4.0682, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918596035150223e-05, + "loss": 4.0812, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917757440399171e-05, + "loss": 4.0659, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.916918845648119e-05, + "loss": 4.0674, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916080250897067e-05, + "loss": 4.0635, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915241656146015e-05, + "loss": 4.0737, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914403061394963e-05, + "loss": 4.0713, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9135677424046576e-05, + "loss": 4.0624, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9127291476536056e-05, + "loss": 4.0722, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9118905529025536e-05, + "loss": 4.0517, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9110519581515016e-05, + "loss": 4.055, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102150012808225e-05, + "loss": 4.0718, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9093764065297705e-05, + "loss": 4.0647, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9085378117787185e-05, + "loss": 4.0591, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9076992170276665e-05, + "loss": 4.0667, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.9068606222766145e-05, + "loss": 4.0429, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.9060220275255625e-05, + "loss": 4.0634, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9051834327745105e-05, + "loss": 4.0695, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9043448380234585e-05, + "loss": 4.0688, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035062432724065e-05, + "loss": 4.052, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9026676485213545e-05, + "loss": 4.0574, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9018290537703025e-05, + "loss": 4.0527, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9009904590192505e-05, + "loss": 4.0671, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900153502148572e-05, + "loss": 4.0684, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.89931490739752e-05, + "loss": 4.0615, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8984763126464674e-05, + "loss": 4.0598, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8976377178954154e-05, + "loss": 4.0692, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896800761024737e-05, + "loss": 4.063, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.895962166273684e-05, + "loss": 4.0612, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895123571522632e-05, + "loss": 4.0605, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894286614651954e-05, + "loss": 4.06, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893448019900902e-05, + "loss": 4.0641, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.89260942514985e-05, + "loss": 4.067, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891770830398798e-05, + "loss": 4.0509, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.890932235647746e-05, + "loss": 4.0593, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890093640896694e-05, + "loss": 4.0678, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889255046145642e-05, + "loss": 4.063, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.88841645139459e-05, + "loss": 4.0678, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887579494523911e-05, + "loss": 4.0644, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886740899772859e-05, + "loss": 4.0547, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859039429021797e-05, + "loss": 4.0519, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8850653481511277e-05, + "loss": 4.0605, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8842267534000757e-05, + "loss": 4.0738, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8833881586490236e-05, + "loss": 4.0736, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8825495638979716e-05, + "loss": 4.0544, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.88171096914692e-05, + "loss": 4.0581, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880872374395868e-05, + "loss": 4.0607, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880033779644816e-05, + "loss": 4.0596, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879196822774137e-05, + "loss": 4.0615, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878361503783832e-05, + "loss": 4.069, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877522909032779e-05, + "loss": 4.0694, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876684314281727e-05, + "loss": 4.0521, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875845719530675e-05, + "loss": 4.0629, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 4.134845733642578, + "eval_runtime": 543.0015, + "eval_samples_per_second": 702.744, + "eval_steps_per_second": 21.961, + "step": 686871 + }, + { + "epoch": 1.0, + "learning_rate": 3.875007124779623e-05, + "loss": 4.0585, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874168530028571e-05, + "loss": 4.0739, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873329935277519e-05, + "loss": 4.0635, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872491340526467e-05, + "loss": 4.0578, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871652745775416e-05, + "loss": 4.0538, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870814151024364e-05, + "loss": 4.0575, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.869975556273312e-05, + "loss": 4.0602, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.86913696152226e-05, + "loss": 4.045, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868298366771208e-05, + "loss": 4.0561, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.8674614099005286e-05, + "loss": 4.0715, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.8666244530298495e-05, + "loss": 4.0551, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.8657858582787975e-05, + "loss": 4.0528, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8649472635277455e-05, + "loss": 4.0714, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641086687766935e-05, + "loss": 4.0492, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8632700740256415e-05, + "loss": 4.0594, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8624314792745895e-05, + "loss": 4.0408, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8615928845235375e-05, + "loss": 4.0396, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8607542897724855e-05, + "loss": 4.057, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859917332901807e-05, + "loss": 4.0481, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859078738150755e-05, + "loss": 4.0716, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858240143399703e-05, + "loss": 4.0561, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.8574015486486503e-05, + "loss": 4.0705, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856564591777972e-05, + "loss": 4.0521, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.85572599702692e-05, + "loss": 4.0571, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854889040156241e-05, + "loss": 4.0471, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854050445405189e-05, + "loss": 4.0571, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853211850654137e-05, + "loss": 4.0539, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852373255903085e-05, + "loss": 4.0563, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851534661152033e-05, + "loss": 4.0541, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.8506977042813544e-05, + "loss": 4.0419, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8498591095303024e-05, + "loss": 4.0408, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490205147792504e-05, + "loss": 4.0591, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848185195788944e-05, + "loss": 4.0529, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847346601037892e-05, + "loss": 4.0553, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.84650800628684e-05, + "loss": 4.0543, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845669411535788e-05, + "loss": 4.0567, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844830816784736e-05, + "loss": 4.0515, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.843992222033684e-05, + "loss": 4.0563, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843153627282632e-05, + "loss": 4.0578, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.84231503253158e-05, + "loss": 4.0515, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841476437780528e-05, + "loss": 4.0521, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840637843029476e-05, + "loss": 4.0469, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839799248278424e-05, + "loss": 4.05, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.838960653527372e-05, + "loss": 4.0607, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.83812205877632e-05, + "loss": 4.0585, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837285101905641e-05, + "loss": 4.0583, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836446507154589e-05, + "loss": 4.0399, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835607912403537e-05, + "loss": 4.0622, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834769317652485e-05, + "loss": 4.0455, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.833930722901433e-05, + "loss": 4.0467, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833093766030754e-05, + "loss": 4.0471, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832255171279702e-05, + "loss": 4.046, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.83141657652865e-05, + "loss": 4.0555, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.8305779817775986e-05, + "loss": 4.0439, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8297410249069195e-05, + "loss": 4.0516, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289024301558675e-05, + "loss": 4.0357, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8280638354048155e-05, + "loss": 4.0551, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8272252406537635e-05, + "loss": 4.0428, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8263866459027115e-05, + "loss": 4.058, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8255480511516595e-05, + "loss": 4.0551, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8247094564006075e-05, + "loss": 4.0462, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8238708616495555e-05, + "loss": 4.0445, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8230339047788764e-05, + "loss": 4.0456, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.8221953100278244e-05, + "loss": 4.0498, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8213567152767724e-05, + "loss": 4.051, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205181205257204e-05, + "loss": 4.0477, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8196795257746684e-05, + "loss": 4.0397, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8188409310236164e-05, + "loss": 4.0481, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818003974152938e-05, + "loss": 4.0426, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817165379401886e-05, + "loss": 4.0464, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816326784650834e-05, + "loss": 4.044, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815488189899781e-05, + "loss": 4.042, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814649595148729e-05, + "loss": 4.0521, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813812638278051e-05, + "loss": 4.0541, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.812974043526999e-05, + "loss": 4.0507, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812135448775946e-05, + "loss": 4.0495, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811296854024894e-05, + "loss": 4.041, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810459897154216e-05, + "loss": 4.0524, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809621302403164e-05, + "loss": 4.0442, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808782707652112e-05, + "loss": 4.0517, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.80794411290106e-05, + "loss": 4.0552, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807105518150008e-05, + "loss": 4.0543, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806268561279329e-05, + "loss": 4.0368, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805429966528277e-05, + "loss": 4.0402, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804591371777225e-05, + "loss": 4.029, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8037527770261727e-05, + "loss": 4.0556, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029141822751207e-05, + "loss": 4.0494, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8020755875240687e-05, + "loss": 4.0449, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8012369927730166e-05, + "loss": 4.0441, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004000359023376e-05, + "loss": 4.0483, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7995614411512856e-05, + "loss": 4.0382, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798724484280607e-05, + "loss": 4.0405, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797885889529555e-05, + "loss": 4.0526, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797047294778503e-05, + "loss": 4.0314, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796208700027451e-05, + "loss": 4.0386, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795370105276399e-05, + "loss": 4.0361, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.79453314840572e-05, + "loss": 4.0443, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793694553654668e-05, + "loss": 4.0526, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792857596783989e-05, + "loss": 4.0409, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792019002032937e-05, + "loss": 4.0444, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791180407281885e-05, + "loss": 4.0382, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790341812530833e-05, + "loss": 4.0503, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789503217779781e-05, + "loss": 4.0459, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7886646230287296e-05, + "loss": 4.0393, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7878260282776776e-05, + "loss": 4.0439, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7869874335266256e-05, + "loss": 4.0292, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7861504766559465e-05, + "loss": 4.0306, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853118819048945e-05, + "loss": 4.0466, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7844732871538425e-05, + "loss": 4.0421, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.7836346924027905e-05, + "loss": 4.0337, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.7827960976517385e-05, + "loss": 4.0436, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.7819575029006865e-05, + "loss": 4.0233, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.7811189081496345e-05, + "loss": 4.0374, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.7802819512789554e-05, + "loss": 4.0455, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7794433565279034e-05, + "loss": 4.0461, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786047617768514e-05, + "loss": 4.0321, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7777661670257994e-05, + "loss": 4.0311, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7769275722747474e-05, + "loss": 4.0287, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7760889775236954e-05, + "loss": 4.0395, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775252020653017e-05, + "loss": 4.0454, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774413425901965e-05, + "loss": 4.0429, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773574831150912e-05, + "loss": 4.0299, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.77273623639986e-05, + "loss": 4.0477, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771897641648808e-05, + "loss": 4.0363, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771059046897756e-05, + "loss": 4.0387, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770220452146704e-05, + "loss": 4.0333, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769381857395652e-05, + "loss": 4.0429, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768544900524973e-05, + "loss": 4.0369, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767706305773921e-05, + "loss": 4.0441, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.76686771102287e-05, + "loss": 4.0308, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766029116271818e-05, + "loss": 4.0352, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765190521520766e-05, + "loss": 4.0463, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764351926769714e-05, + "loss": 4.0377, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763513332018662e-05, + "loss": 4.0417, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.76267473726761e-05, + "loss": 4.0458, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761837780396931e-05, + "loss": 4.0303, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.760999185645879e-05, + "loss": 4.0316, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760160590894827e-05, + "loss": 4.0357, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759321996143775e-05, + "loss": 4.0431, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7584850392730956e-05, + "loss": 4.055, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.7576480824024165e-05, + "loss": 4.0327, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756809487651365e-05, + "loss": 4.038, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.755970892900313e-05, + "loss": 4.0365, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755132298149261e-05, + "loss": 4.0359, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754293703398209e-05, + "loss": 4.0392, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753455108647157e-05, + "loss": 4.0431, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752616513896105e-05, + "loss": 4.0454, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751777919145053e-05, + "loss": 4.0313, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.750939324394001e-05, + "loss": 4.0412, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 4.119292736053467, + "eval_runtime": 542.6643, + "eval_samples_per_second": 703.181, + "eval_steps_per_second": 21.975, + "step": 763190 + }, + { + "epoch": 0.0, + "learning_rate": 3.750102367523322e-05, + "loss": 4.0553, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.74926377277227e-05, + "loss": 4.0476, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748425178021218e-05, + "loss": 4.0428, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7475865832701654e-05, + "loss": 4.032, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7467479885191134e-05, + "loss": 4.034, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745909393768062e-05, + "loss": 4.0324, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.74507079901701e-05, + "loss": 4.0388, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744232204265958e-05, + "loss": 4.0196, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743393609514906e-05, + "loss": 4.0329, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742555014763854e-05, + "loss": 4.0485, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741716420012802e-05, + "loss": 4.0353, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74087782526175e-05, + "loss": 4.0334, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740039230510698e-05, + "loss": 4.0454, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739200635759646e-05, + "loss": 4.0253, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738362041008594e-05, + "loss": 4.0376, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737523446257542e-05, + "loss": 4.0179, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.73668485150649e-05, + "loss": 4.0154, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735847894635811e-05, + "loss": 4.0396, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735009299884759e-05, + "loss": 4.0279, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734170705133707e-05, + "loss": 4.05, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7333337482630285e-05, + "loss": 4.0303, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7324951535119765e-05, + "loss": 4.0452, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7316565587609245e-05, + "loss": 4.0344, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308179640098725e-05, + "loss": 4.033, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.72997936925882e-05, + "loss": 4.0248, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729140774507768e-05, + "loss": 4.038, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728302179756716e-05, + "loss": 4.0299, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727463585005664e-05, + "loss": 4.0335, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726624990254612e-05, + "loss": 4.0296, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.72578639550356e-05, + "loss": 4.0257, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.724947800752508e-05, + "loss": 4.015, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724109206001456e-05, + "loss": 4.038, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723270611250404e-05, + "loss": 4.0324, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722433654379725e-05, + "loss": 4.0328, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721595059628673e-05, + "loss": 4.0321, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720756464877621e-05, + "loss": 4.0342, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.719917870126569e-05, + "loss": 4.0322, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.71908091325589e-05, + "loss": 4.0347, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718242318504838e-05, + "loss": 4.0337, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717403723753786e-05, + "loss": 4.0311, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716565129002734e-05, + "loss": 4.0292, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715728172132055e-05, + "loss": 4.0293, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714889577381003e-05, + "loss": 4.0266, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714050982629951e-05, + "loss": 4.0367, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713212387878899e-05, + "loss": 4.0346, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712373793127847e-05, + "loss": 4.0365, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711536836257169e-05, + "loss": 4.0181, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710698241506117e-05, + "loss": 4.0417, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7098612846354376e-05, + "loss": 4.0263, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7090226898843856e-05, + "loss": 4.022, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7081840951333336e-05, + "loss": 4.0281, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7073455003822816e-05, + "loss": 4.0276, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065069056312296e-05, + "loss": 4.0331, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7056683108801776e-05, + "loss": 4.0242, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7048297161291256e-05, + "loss": 4.0301, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7039927592584465e-05, + "loss": 4.0135, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7031541645073945e-05, + "loss": 4.036, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7023155697563425e-05, + "loss": 4.0218, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7014769750052905e-05, + "loss": 4.035, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700640018134612e-05, + "loss": 4.0335, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.69980142338356e-05, + "loss": 4.0273, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.698962828632508e-05, + "loss": 4.0244, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698124233881456e-05, + "loss": 4.0191, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6972856391304034e-05, + "loss": 4.0255, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696448682259725e-05, + "loss": 4.0329, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695610087508673e-05, + "loss": 4.0297, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.69477149275762e-05, + "loss": 4.0171, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.693932898006568e-05, + "loss": 4.0246, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693094303255516e-05, + "loss": 4.0233, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692255708504464e-05, + "loss": 4.0238, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691417113753413e-05, + "loss": 4.0238, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690578519002361e-05, + "loss": 4.0265, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6897432000120554e-05, + "loss": 4.027, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889046052610034e-05, + "loss": 4.0354, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688066010509951e-05, + "loss": 4.0301, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687227415758899e-05, + "loss": 4.0253, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686388821007847e-05, + "loss": 4.0235, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6855518641371676e-05, + "loss": 4.029, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684714907266489e-05, + "loss": 4.0271, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683876312515437e-05, + "loss": 4.0265, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683037717764385e-05, + "loss": 4.0347, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682199123013333e-05, + "loss": 4.0343, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681360528262281e-05, + "loss": 4.0173, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680521933511229e-05, + "loss": 4.0146, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679683338760177e-05, + "loss": 4.0107, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678844744009125e-05, + "loss": 4.0351, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678007787138446e-05, + "loss": 4.0252, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677169192387394e-05, + "loss": 4.0281, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676330597636342e-05, + "loss": 4.0233, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.67549200288529e-05, + "loss": 4.029, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674653408134238e-05, + "loss": 4.0163, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673816451263559e-05, + "loss": 4.019, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.672977856512507e-05, + "loss": 4.0325, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672139261761455e-05, + "loss": 4.0099, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713006670104037e-05, + "loss": 4.0164, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.6704620722593516e-05, + "loss": 4.016, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.6696234775082996e-05, + "loss": 4.0276, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.6687848827572476e-05, + "loss": 4.0283, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6679479258865685e-05, + "loss": 4.0265, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6671093311355165e-05, + "loss": 4.0224, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6662707363844645e-05, + "loss": 4.0176, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6654321416334125e-05, + "loss": 4.0283, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6645935468823605e-05, + "loss": 4.0248, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6637549521313085e-05, + "loss": 4.023, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629179952606294e-05, + "loss": 4.023, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6620794005095774e-05, + "loss": 4.0072, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6612408057585254e-05, + "loss": 4.0116, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604022110074734e-05, + "loss": 4.027, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6595636162564214e-05, + "loss": 4.0232, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6587250215053694e-05, + "loss": 4.0123, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6578864267543174e-05, + "loss": 4.0257, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6570478320032654e-05, + "loss": 4.0033, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.65621251301296e-05, + "loss": 4.0135, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655373918261908e-05, + "loss": 4.0255, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654535323510856e-05, + "loss": 4.0268, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653696728759804e-05, + "loss": 4.0124, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652859771889125e-05, + "loss": 4.0122, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652021177138073e-05, + "loss": 4.0056, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651182582387021e-05, + "loss": 4.0192, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650343987635969e-05, + "loss": 4.0282, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.6495070307652904e-05, + "loss": 4.0207, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.6486684360142384e-05, + "loss": 4.0116, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6478298412631864e-05, + "loss": 4.0289, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6469912465121344e-05, + "loss": 4.0196, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646152651761082e-05, + "loss": 4.018, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.64531405701003e-05, + "loss": 4.011, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644475462258978e-05, + "loss": 4.0237, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643636867507926e-05, + "loss": 4.0149, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.642798272756874e-05, + "loss": 4.0233, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6419596780058217e-05, + "loss": 4.0118, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6411210832547697e-05, + "loss": 4.014, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6402841263840906e-05, + "loss": 4.0234, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639445531633039e-05, + "loss": 4.0206, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638606936881987e-05, + "loss": 4.0207, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637768342130935e-05, + "loss": 4.0264, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.636931385260256e-05, + "loss": 4.0108, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636092790509204e-05, + "loss": 4.0076, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635254195758152e-05, + "loss": 4.0167, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.6344156010071e-05, + "loss": 4.0246, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633577006256048e-05, + "loss": 4.0357, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632740049385369e-05, + "loss": 4.0124, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631901454634317e-05, + "loss": 4.018, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631062859883265e-05, + "loss": 4.0143, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630224265132213e-05, + "loss": 4.0169, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629385670381161e-05, + "loss": 4.0184, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6285487135104826e-05, + "loss": 4.0228, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6277101187594306e-05, + "loss": 4.03, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6268715240083786e-05, + "loss": 4.0091, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6260329292573266e-05, + "loss": 4.0214, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 4.107080459594727, + "eval_runtime": 538.215, + "eval_samples_per_second": 708.994, + "eval_steps_per_second": 22.157, + "step": 839509 + }, + { + "epoch": 1.0, + "learning_rate": 3.6251943345062746e-05, + "loss": 4.0188, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6243557397552226e-05, + "loss": 4.0294, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.62351714500417e-05, + "loss": 4.0218, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622678550253118e-05, + "loss": 4.014, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6218415933824395e-05, + "loss": 4.0175, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210046365117604e-05, + "loss": 4.0142, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6201660417607084e-05, + "loss": 4.0199, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6193274470096564e-05, + "loss": 3.9988, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6184888522586044e-05, + "loss": 4.0153, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617650257507553e-05, + "loss": 4.0267, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616813300636874e-05, + "loss": 4.0105, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.615974705885822e-05, + "loss": 4.015, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.61513611113477e-05, + "loss": 4.0284, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614297516383717e-05, + "loss": 4.0085, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613458921632665e-05, + "loss": 4.0137, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612621964761987e-05, + "loss": 4.002, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611783370010935e-05, + "loss": 3.9921, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.610944775259882e-05, + "loss": 4.0214, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.61010618050883e-05, + "loss": 4.004, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609267585757778e-05, + "loss": 4.0288, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608428991006727e-05, + "loss": 4.0148, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607590396255675e-05, + "loss": 4.0232, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606751801504623e-05, + "loss": 4.0113, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605913206753571e-05, + "loss": 4.0212, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6050778877632646e-05, + "loss": 3.9987, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6042392930122126e-05, + "loss": 4.0192, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034006982611606e-05, + "loss": 4.011, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6025621035101086e-05, + "loss": 4.014, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6017235087590566e-05, + "loss": 4.0089, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6008865518883775e-05, + "loss": 4.0073, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6000479571373255e-05, + "loss": 3.9965, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992093623862735e-05, + "loss": 4.0137, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.5983707676352215e-05, + "loss": 4.0148, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.59753217288417e-05, + "loss": 4.0123, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596693578133118e-05, + "loss": 4.014, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595856621262439e-05, + "loss": 4.0205, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595018026511387e-05, + "loss": 4.0089, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594179431760335e-05, + "loss": 4.0161, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593340837009283e-05, + "loss": 4.0148, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592502242258231e-05, + "loss": 4.0158, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591663647507179e-05, + "loss": 4.0096, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590825052756127e-05, + "loss": 4.0033, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.589986458005075e-05, + "loss": 4.0082, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589149501134396e-05, + "loss": 4.0181, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588310906383344e-05, + "loss": 4.0141, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587472311632292e-05, + "loss": 4.0165, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.58663371688124e-05, + "loss": 4.0028, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5857967600105615e-05, + "loss": 4.0255, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5849581652595095e-05, + "loss": 4.0089, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5841195705084575e-05, + "loss": 4.0028, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5832826136377784e-05, + "loss": 4.0023, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5824440188867264e-05, + "loss": 4.0116, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816054241356744e-05, + "loss": 4.0135, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5807668293846224e-05, + "loss": 4.0022, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5799282346335704e-05, + "loss": 4.0136, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5790896398825184e-05, + "loss": 3.9943, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578251045131466e-05, + "loss": 4.017, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577412450380414e-05, + "loss": 4.005, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5765738556293624e-05, + "loss": 4.0151, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575736898758683e-05, + "loss": 4.011, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574898304007631e-05, + "loss": 4.008, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574059709256579e-05, + "loss": 4.0082, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.573221114505527e-05, + "loss": 4.0016, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572382519754475e-05, + "loss": 4.0066, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571543925003423e-05, + "loss": 4.0147, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570705330252371e-05, + "loss": 4.0119, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569866735501319e-05, + "loss": 3.9938, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569031416511013e-05, + "loss": 4.0081, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568192821759961e-05, + "loss": 4.0044, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567354227008909e-05, + "loss": 4.0076, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566515632257858e-05, + "loss": 3.9997, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565677037506806e-05, + "loss": 4.0113, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564838442755754e-05, + "loss": 4.0056, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.563999848004702e-05, + "loss": 4.0136, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.56316125325365e-05, + "loss": 4.0137, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562324296382971e-05, + "loss": 4.0109, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.5614873395122916e-05, + "loss": 4.002, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5606487447612396e-05, + "loss": 4.0081, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5598101500101876e-05, + "loss": 4.0053, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5589715552591356e-05, + "loss": 4.0145, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5581345983884565e-05, + "loss": 4.0132, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5572960036374045e-05, + "loss": 4.0192, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556457408886353e-05, + "loss": 4.0, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555618814135301e-05, + "loss": 3.9969, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554780219384249e-05, + "loss": 3.9927, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.553941624633197e-05, + "loss": 4.0166, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553103029882145e-05, + "loss": 4.0059, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552264435131093e-05, + "loss": 4.0081, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551425840380041e-05, + "loss": 4.0075, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550588883509362e-05, + "loss": 4.0092, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.54975028875831e-05, + "loss": 3.9956, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.548911694007258e-05, + "loss": 4.005, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548073099256206e-05, + "loss": 4.0122, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547234504505154e-05, + "loss": 3.9928, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546397547634475e-05, + "loss": 3.9934, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545558952883423e-05, + "loss": 3.9995, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544720358132371e-05, + "loss": 4.01, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5438817633813196e-05, + "loss": 4.0078, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5430448065106405e-05, + "loss": 4.0096, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422062117595885e-05, + "loss": 4.0078, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5413676170085365e-05, + "loss": 3.9945, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5405290222574845e-05, + "loss": 4.0102, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5396920653868054e-05, + "loss": 4.0087, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538855108516126e-05, + "loss": 4.0017, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538016513765074e-05, + "loss": 4.0005, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537177919014022e-05, + "loss": 3.994, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.53633932426297e-05, + "loss": 3.9952, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535500729511918e-05, + "loss": 4.0035, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534662134760866e-05, + "loss": 4.0048, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533823540009814e-05, + "loss": 3.9981, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.532984945258762e-05, + "loss": 4.0037, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.53214635050771e-05, + "loss": 3.9868, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531307755756658e-05, + "loss": 3.9938, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530469161005606e-05, + "loss": 4.0052, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529632204134927e-05, + "loss": 4.0099, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528793609383875e-05, + "loss": 3.9931, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.527955014632823e-05, + "loss": 3.996, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527116419881771e-05, + "loss": 3.9898, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526279463011092e-05, + "loss": 3.9976, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52544086826004e-05, + "loss": 4.0055, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524602273508989e-05, + "loss": 4.0019, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523763678757937e-05, + "loss": 3.9938, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.522925084006885e-05, + "loss": 4.0075, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522086489255833e-05, + "loss": 3.9975, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521247894504781e-05, + "loss": 4.0053, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520409299753729e-05, + "loss": 3.9914, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5195723428830496e-05, + "loss": 4.0077, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.5187337481319976e-05, + "loss": 3.9959, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.5178967912613185e-05, + "loss": 4.0047, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.5170581965102665e-05, + "loss": 3.9956, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5162196017592145e-05, + "loss": 3.9959, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.5153810070081625e-05, + "loss": 4.0024, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5145424122571105e-05, + "loss": 4.0067, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137038175060585e-05, + "loss": 4.0001, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512865222755007e-05, + "loss": 4.0076, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512026628003955e-05, + "loss": 3.9931, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511188033252903e-05, + "loss": 3.9923, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5103494385018505e-05, + "loss": 3.9989, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5095108437507985e-05, + "loss": 4.0052, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5086722489997465e-05, + "loss": 4.018, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507835292129068e-05, + "loss": 3.9975, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5069966973780154e-05, + "loss": 4.0, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5061581026269634e-05, + "loss": 3.9958, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.5053195078759114e-05, + "loss": 3.9961, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504482551005232e-05, + "loss": 4.0027, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503643956254181e-05, + "loss": 4.0072, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502805361503129e-05, + "loss": 4.0086, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.501966766752077e-05, + "loss": 3.9918, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501128172001025e-05, + "loss": 4.0024, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 4.0951337814331055, + "eval_runtime": 554.2963, + "eval_samples_per_second": 688.424, + "eval_steps_per_second": 21.514, + "step": 915828 + }, + { + "epoch": 0.0, + "learning_rate": 3.500289577249973e-05, + "loss": 4.0099, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499450982498921e-05, + "loss": 4.0103, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498612387747869e-05, + "loss": 4.0057, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497773792996817e-05, + "loss": 3.9949, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.496935198245765e-05, + "loss": 4.0021, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496096603494713e-05, + "loss": 3.9947, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495258008743661e-05, + "loss": 4.0027, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494419413992609e-05, + "loss": 3.9822, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493580819241557e-05, + "loss": 4.0042, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492742224490504e-05, + "loss": 4.0036, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.491905267619826e-05, + "loss": 3.9938, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491066672868774e-05, + "loss": 3.9973, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490228078117722e-05, + "loss": 4.007, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.48938948336667e-05, + "loss": 3.9996, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488550888615618e-05, + "loss": 3.9937, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487712293864566e-05, + "loss": 3.985, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486873699113514e-05, + "loss": 3.9753, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486035104362462e-05, + "loss": 4.001, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.48519650961141e-05, + "loss": 3.99, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484357914860358e-05, + "loss": 4.0059, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483519320109306e-05, + "loss": 3.9998, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482680725358254e-05, + "loss": 4.009, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481842130607202e-05, + "loss": 3.993, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.48100353585615e-05, + "loss": 4.0032, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480164941105098e-05, + "loss": 3.9866, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4793279842344187e-05, + "loss": 4.0004, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478489389483367e-05, + "loss": 3.995, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477650794732315e-05, + "loss": 3.997, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476812199981263e-05, + "loss": 3.9897, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.475975243110584e-05, + "loss": 3.9927, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475136648359532e-05, + "loss": 3.982, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.47429805360848e-05, + "loss": 3.9927, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473459458857428e-05, + "loss": 3.9998, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4726208641063755e-05, + "loss": 3.9972, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4717822693553235e-05, + "loss": 3.9924, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.470945312484645e-05, + "loss": 4.0034, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470106717733593e-05, + "loss": 3.9954, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469268122982541e-05, + "loss": 3.9939, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468429528231489e-05, + "loss": 3.9995, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467590933480437e-05, + "loss": 4.0002, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466753976609758e-05, + "loss": 3.9935, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.465915381858706e-05, + "loss": 3.9867, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465076787107654e-05, + "loss": 3.9896, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464238192356602e-05, + "loss": 3.9992, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.46339959760555e-05, + "loss": 4.0007, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462562640734871e-05, + "loss": 3.9992, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461724045983819e-05, + "loss": 3.9885, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460885451232767e-05, + "loss": 4.0085, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460046856481715e-05, + "loss": 3.9899, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.459208261730663e-05, + "loss": 3.9832, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458369666979611e-05, + "loss": 3.9842, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4575327101089325e-05, + "loss": 3.9932, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4566941153578805e-05, + "loss": 3.9996, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4558555206068285e-05, + "loss": 3.9841, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4550169258557764e-05, + "loss": 3.9982, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4541799689850974e-05, + "loss": 3.9777, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4533413742340454e-05, + "loss": 3.9965, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4525027794829933e-05, + "loss": 3.9917, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4516641847319413e-05, + "loss": 3.9991, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4508255899808893e-05, + "loss": 3.9891, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.449986995229837e-05, + "loss": 3.9943, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449150038359158e-05, + "loss": 3.9911, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448311443608106e-05, + "loss": 3.9853, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447472848857054e-05, + "loss": 3.9901, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446634254106003e-05, + "loss": 4.0005, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445797297235324e-05, + "loss": 3.9985, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.444958702484272e-05, + "loss": 3.9742, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444121745613593e-05, + "loss": 3.9913, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443283150862541e-05, + "loss": 3.9897, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442444556111489e-05, + "loss": 3.9878, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441605961360437e-05, + "loss": 3.9842, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440767366609385e-05, + "loss": 3.9953, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.439928771858333e-05, + "loss": 3.9887, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439090177107281e-05, + "loss": 3.9956, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438251582356229e-05, + "loss": 3.9976, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437412987605177e-05, + "loss": 3.9953, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436574392854125e-05, + "loss": 3.9896, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435737435983446e-05, + "loss": 3.9899, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.434898841232394e-05, + "loss": 3.9892, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4340602464813416e-05, + "loss": 3.9966, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4332216517302896e-05, + "loss": 4.0007, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4323830569792376e-05, + "loss": 3.9988, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4315444622281856e-05, + "loss": 3.983, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4307058674771336e-05, + "loss": 3.9843, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.4298672727260816e-05, + "loss": 3.9769, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4290286779750296e-05, + "loss": 3.9981, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4281933589847234e-05, + "loss": 3.9873, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427354764233672e-05, + "loss": 3.9968, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.42651616948262e-05, + "loss": 3.9881, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425677574731568e-05, + "loss": 3.9905, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424838979980516e-05, + "loss": 3.9809, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424002023109837e-05, + "loss": 3.9922, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423163428358785e-05, + "loss": 3.9967, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422324833607733e-05, + "loss": 3.9793, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421486238856681e-05, + "loss": 3.9803, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420647644105629e-05, + "loss": 3.9803, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419809049354577e-05, + "loss": 3.9928, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.418970454603525e-05, + "loss": 3.9918, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418135135613219e-05, + "loss": 3.9951, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4172965408621674e-05, + "loss": 3.9929, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4164579461111154e-05, + "loss": 3.9805, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4156193513600634e-05, + "loss": 3.9913, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4147807566090114e-05, + "loss": 3.9898, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4139421618579594e-05, + "loss": 3.9934, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4131035671069074e-05, + "loss": 3.9788, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4122649723558554e-05, + "loss": 3.9852, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4114263776048034e-05, + "loss": 3.9751, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410589420734124e-05, + "loss": 3.9862, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409750825983072e-05, + "loss": 3.9903, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.40891223123202e-05, + "loss": 3.9842, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408073636480968e-05, + "loss": 3.9877, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407235041729916e-05, + "loss": 3.9749, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406396446978864e-05, + "loss": 3.9752, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405557852227812e-05, + "loss": 3.9902, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404720895357134e-05, + "loss": 3.9968, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403882300606082e-05, + "loss": 3.9746, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.40304370585503e-05, + "loss": 3.9809, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402205111103978e-05, + "loss": 3.977, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401368154233299e-05, + "loss": 3.9834, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400529559482247e-05, + "loss": 3.9922, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399690964731195e-05, + "loss": 3.9845, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398852369980142e-05, + "loss": 3.9801, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.39801377522909e-05, + "loss": 3.9944, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3971768183584117e-05, + "loss": 3.9814, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3963382236073596e-05, + "loss": 3.9922, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3954996288563076e-05, + "loss": 3.9758, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3946610341052556e-05, + "loss": 3.9894, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3938224393542036e-05, + "loss": 3.9835, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3929838446031516e-05, + "loss": 3.9896, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3921468877324725e-05, + "loss": 3.9797, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3913082929814205e-05, + "loss": 3.9789, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3904696982303685e-05, + "loss": 3.9879, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3896311034793165e-05, + "loss": 3.9934, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3887941466086374e-05, + "loss": 3.9844, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3879555518575854e-05, + "loss": 3.9932, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3871169571065334e-05, + "loss": 3.9799, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3862783623554814e-05, + "loss": 3.9727, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3854397676044294e-05, + "loss": 3.9855, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3846011728533774e-05, + "loss": 3.989, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383762578102326e-05, + "loss": 4.0058, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.382925621231647e-05, + "loss": 3.9788, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382087026480595e-05, + "loss": 3.9881, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381248431729543e-05, + "loss": 3.9771, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380409836978491e-05, + "loss": 3.9835, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379571242227439e-05, + "loss": 3.9897, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.37873428535676e-05, + "loss": 3.991, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.377895690605708e-05, + "loss": 3.9978, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377057095854656e-05, + "loss": 3.9759, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376218501103604e-05, + "loss": 3.9814, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 4.086766719818115, + "eval_runtime": 539.9627, + "eval_samples_per_second": 706.699, + "eval_steps_per_second": 22.085, + "step": 992147 + }, + { + "epoch": 1.0, + "learning_rate": 3.375381544232925e-05, + "loss": 3.989, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374542949481873e-05, + "loss": 3.9944, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3737043547308215e-05, + "loss": 3.9929, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3728657599797694e-05, + "loss": 3.9788, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3720271652287174e-05, + "loss": 3.9882, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3711885704776654e-05, + "loss": 3.9853, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3703516136069863e-05, + "loss": 3.9848, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3695130188559343e-05, + "loss": 3.9698, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3686744241048823e-05, + "loss": 3.985, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.36783582935383e-05, + "loss": 3.9873, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.366998872483151e-05, + "loss": 3.9807, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366160277732099e-05, + "loss": 3.9852, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365321682981047e-05, + "loss": 3.9927, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364483088229995e-05, + "loss": 3.9819, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363644493478943e-05, + "loss": 3.9794, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362805898727891e-05, + "loss": 3.9706, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.361967303976839e-05, + "loss": 3.962, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361130347106161e-05, + "loss": 3.9826, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360291752355109e-05, + "loss": 3.9782, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359453157604056e-05, + "loss": 3.9931, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358614562853004e-05, + "loss": 3.9869, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357775968101952e-05, + "loss": 3.9908, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.356939011231273e-05, + "loss": 3.9797, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356100416480221e-05, + "loss": 3.9896, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355261821729169e-05, + "loss": 3.9721, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354423226978117e-05, + "loss": 3.9822, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353584632227065e-05, + "loss": 3.9859, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352746037476014e-05, + "loss": 3.9817, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.351907442724962e-05, + "loss": 3.9747, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3510704858542826e-05, + "loss": 3.9809, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3502318911032306e-05, + "loss": 3.9644, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3493932963521786e-05, + "loss": 3.9769, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3485547016011266e-05, + "loss": 3.9859, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3477161068500746e-05, + "loss": 3.9832, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3468775120990226e-05, + "loss": 3.9819, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3460405552283435e-05, + "loss": 3.983, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3452019604772915e-05, + "loss": 3.9823, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3443633657262395e-05, + "loss": 3.983, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3435264088555604e-05, + "loss": 3.9798, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342687814104509e-05, + "loss": 3.9887, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341849219353457e-05, + "loss": 3.9777, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341010624602405e-05, + "loss": 3.967, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340172029851353e-05, + "loss": 3.9825, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339333435100301e-05, + "loss": 3.9814, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338494840349249e-05, + "loss": 3.9854, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337656245598197e-05, + "loss": 3.9834, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336817650847144e-05, + "loss": 3.9765, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.335979056096092e-05, + "loss": 3.9924, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.33514046134504e-05, + "loss": 3.9781, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334301866593988e-05, + "loss": 3.9706, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333463271842936e-05, + "loss": 3.9746, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332626314972257e-05, + "loss": 3.977, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331787720221205e-05, + "loss": 3.977, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.330949125470154e-05, + "loss": 3.9723, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330110530719102e-05, + "loss": 3.9895, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329273573848423e-05, + "loss": 3.9563, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328434979097371e-05, + "loss": 3.9846, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327596384346319e-05, + "loss": 3.9814, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326757789595267e-05, + "loss": 3.9817, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.325920832724588e-05, + "loss": 3.9829, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325082237973536e-05, + "loss": 3.9737, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324243643222484e-05, + "loss": 3.9777, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323405048471432e-05, + "loss": 3.9702, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322569729481126e-05, + "loss": 3.9757, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321731134730074e-05, + "loss": 3.985, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320892539979022e-05, + "loss": 3.9842, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.32005394522797e-05, + "loss": 3.9626, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319215350476918e-05, + "loss": 3.9759, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318376755725866e-05, + "loss": 3.9786, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317538160974814e-05, + "loss": 3.9728, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316701204104135e-05, + "loss": 3.9703, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315862609353083e-05, + "loss": 3.9779, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315024014602031e-05, + "loss": 3.9764, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314185419850979e-05, + "loss": 3.9811, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313346825099927e-05, + "loss": 3.9852, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312509868229248e-05, + "loss": 3.9784, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311671273478196e-05, + "loss": 3.9773, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3108326787271446e-05, + "loss": 3.9735, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3099940839760926e-05, + "loss": 3.9745, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3091554892250406e-05, + "loss": 3.9813, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3083185323543615e-05, + "loss": 3.9871, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3074799376033095e-05, + "loss": 3.9827, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3066413428522575e-05, + "loss": 3.9671, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.3058027481012055e-05, + "loss": 3.9725, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3049641533501535e-05, + "loss": 3.9626, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3041255585991015e-05, + "loss": 3.9783, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3032869638480495e-05, + "loss": 3.9772, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3024483690969975e-05, + "loss": 3.9824, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3016114122263184e-05, + "loss": 3.9747, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3007728174752664e-05, + "loss": 3.9754, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.2999342227242144e-05, + "loss": 3.9693, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299095627973163e-05, + "loss": 3.9758, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298258671102484e-05, + "loss": 3.9794, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297420076351432e-05, + "loss": 3.9695, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.29658148160038e-05, + "loss": 3.9609, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295744524729701e-05, + "loss": 3.9672, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.294905929978649e-05, + "loss": 3.9785, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294067335227597e-05, + "loss": 3.9755, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293228740476545e-05, + "loss": 3.9845, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292390145725493e-05, + "loss": 3.9757, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.29155155097444e-05, + "loss": 3.9685, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290712956223388e-05, + "loss": 3.9693, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.28987599935271e-05, + "loss": 3.9801, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2890374046016584e-05, + "loss": 3.9842, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288198809850606e-05, + "loss": 3.9641, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287360215099554e-05, + "loss": 3.97, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286521620348502e-05, + "loss": 3.9601, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.28568302559745e-05, + "loss": 3.973, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284844430846398e-05, + "loss": 3.9757, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284005836095346e-05, + "loss": 3.9714, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283167241344294e-05, + "loss": 3.9746, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282328646593242e-05, + "loss": 3.9596, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2814916897225626e-05, + "loss": 3.9608, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2806530949715106e-05, + "loss": 3.9712, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2798145002204586e-05, + "loss": 3.9825, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2789759054694066e-05, + "loss": 3.9653, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278138948598728e-05, + "loss": 3.9602, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277301991728049e-05, + "loss": 3.9672, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276463396976997e-05, + "loss": 3.9663, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275624802225945e-05, + "loss": 3.9764, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274786207474893e-05, + "loss": 3.9739, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.273947612723841e-05, + "loss": 3.9675, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273109017972789e-05, + "loss": 3.9792, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.27227206110211e-05, + "loss": 3.9683, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271433466351058e-05, + "loss": 3.9737, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270594871600006e-05, + "loss": 3.9646, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269756276848954e-05, + "loss": 3.9788, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.268917682097902e-05, + "loss": 3.9657, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.26807908734685e-05, + "loss": 3.9758, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2672421304761716e-05, + "loss": 3.968, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2664035357251196e-05, + "loss": 3.9627, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2655649409740676e-05, + "loss": 3.9763, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2647263462230156e-05, + "loss": 3.9797, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2638877514719636e-05, + "loss": 3.9669, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2630491567209115e-05, + "loss": 3.9812, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262210561969859e-05, + "loss": 3.9644, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261371967218807e-05, + "loss": 3.9608, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2605350103481284e-05, + "loss": 3.973, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2596964155970764e-05, + "loss": 3.9725, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258857820846024e-05, + "loss": 3.991, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2580192260949724e-05, + "loss": 3.9683, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257182269224294e-05, + "loss": 3.9696, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.2563436744732413e-05, + "loss": 3.964, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255505079722189e-05, + "loss": 3.9693, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254666484971137e-05, + "loss": 3.9719, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253827890220085e-05, + "loss": 3.9789, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.252990933349406e-05, + "loss": 3.9808, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252152338598354e-05, + "loss": 3.9662, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251315381727676e-05, + "loss": 3.9685, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 4.0789875984191895, + "eval_runtime": 540.1202, + "eval_samples_per_second": 706.493, + "eval_steps_per_second": 22.078, + "step": 1068466 + }, + { + "epoch": 0.0, + "learning_rate": 3.250476786976624e-05, + "loss": 3.9696, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249638192225571e-05, + "loss": 3.9851, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248799597474519e-05, + "loss": 3.9744, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.247961002723468e-05, + "loss": 3.9689, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247122407972416e-05, + "loss": 3.9763, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246283813221364e-05, + "loss": 3.969, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245445218470312e-05, + "loss": 3.9694, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.24460662371926e-05, + "loss": 3.9583, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243768028968208e-05, + "loss": 3.971, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.242929434217156e-05, + "loss": 3.9682, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242092477346477e-05, + "loss": 3.9677, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241253882595425e-05, + "loss": 3.975, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240415287844373e-05, + "loss": 3.9708, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239576693093321e-05, + "loss": 3.9758, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238738098342269e-05, + "loss": 3.9636, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237899503591217e-05, + "loss": 3.9609, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2370609088401647e-05, + "loss": 3.9445, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2362223140891127e-05, + "loss": 3.9709, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2353837193380606e-05, + "loss": 3.965, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2345451245870086e-05, + "loss": 3.9761, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2337065298359566e-05, + "loss": 3.9801, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2328679350849046e-05, + "loss": 3.973, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2320293403338526e-05, + "loss": 3.9654, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.2311907455828006e-05, + "loss": 3.9748, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.2303521508317486e-05, + "loss": 3.9632, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.2295151939610695e-05, + "loss": 3.966, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.2286765992100175e-05, + "loss": 3.9716, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.2278380044589655e-05, + "loss": 3.968, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2269994097079135e-05, + "loss": 3.9609, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2261608149568615e-05, + "loss": 3.9649, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2253222202058095e-05, + "loss": 3.9565, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2244836254547575e-05, + "loss": 3.9597, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223646668584079e-05, + "loss": 3.9768, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222808073833027e-05, + "loss": 3.9683, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.221969479081975e-05, + "loss": 3.9669, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221130884330923e-05, + "loss": 3.9713, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220292289579871e-05, + "loss": 3.9736, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219453694828819e-05, + "loss": 3.9704, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2186151000777664e-05, + "loss": 3.9688, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2177765053267144e-05, + "loss": 3.9704, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2169379105756624e-05, + "loss": 3.9644, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216100953704984e-05, + "loss": 3.9565, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215262358953931e-05, + "loss": 3.9661, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214423764202879e-05, + "loss": 3.9669, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213586807332201e-05, + "loss": 3.9749, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212748212581149e-05, + "loss": 3.9695, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.211909617830097e-05, + "loss": 3.9632, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211071023079045e-05, + "loss": 3.9792, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210232428327993e-05, + "loss": 3.9657, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209393833576941e-05, + "loss": 3.9534, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208555238825889e-05, + "loss": 3.9648, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207716644074837e-05, + "loss": 3.9606, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206878049323785e-05, + "loss": 3.9699, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206041092453106e-05, + "loss": 3.9584, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205202497702054e-05, + "loss": 3.9744, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2043655408313746e-05, + "loss": 3.9463, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203526946080323e-05, + "loss": 3.967, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202688351329271e-05, + "loss": 3.9683, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201849756578219e-05, + "loss": 3.967, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201011161827167e-05, + "loss": 3.9694, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200172567076115e-05, + "loss": 3.9623, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199335610205436e-05, + "loss": 3.9608, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198497015454384e-05, + "loss": 3.9644, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197660058583705e-05, + "loss": 3.9587, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196821463832653e-05, + "loss": 3.976, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.195982869081601e-05, + "loss": 3.9656, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195144274330549e-05, + "loss": 3.9555, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194305679579497e-05, + "loss": 3.9572, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193467084828445e-05, + "loss": 3.968, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192628490077393e-05, + "loss": 3.9573, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191789895326342e-05, + "loss": 3.9572, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.19095130057529e-05, + "loss": 3.9691, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190112705824238e-05, + "loss": 3.9594, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189274111073185e-05, + "loss": 3.9741, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1884371542025067e-05, + "loss": 3.9689, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1875985594514547e-05, + "loss": 3.9694, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1867599647004027e-05, + "loss": 3.9628, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.18592136994935e-05, + "loss": 3.9582, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185082775198298e-05, + "loss": 3.9681, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1842458183276196e-05, + "loss": 3.9638, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834088614569405e-05, + "loss": 3.9761, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1825702667058885e-05, + "loss": 3.9715, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1817316719548365e-05, + "loss": 3.9575, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180893077203785e-05, + "loss": 3.9558, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1800544824527324e-05, + "loss": 3.9497, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1792158877016804e-05, + "loss": 3.9645, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.1783772929506284e-05, + "loss": 3.9698, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1775386981995764e-05, + "loss": 3.9639, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1767001034485244e-05, + "loss": 3.9626, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1758615086974724e-05, + "loss": 3.96, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1750229139464204e-05, + "loss": 3.955, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174187594956115e-05, + "loss": 3.9599, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173349000205062e-05, + "loss": 3.9715, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.17251040545401e-05, + "loss": 3.9576, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171671810702959e-05, + "loss": 3.9487, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170833215951907e-05, + "loss": 3.9522, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.169994621200855e-05, + "loss": 3.9647, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169156026449803e-05, + "loss": 3.9623, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168317431698751e-05, + "loss": 3.969, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.167480474828072e-05, + "loss": 3.9678, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166643517957393e-05, + "loss": 3.957, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165804923206341e-05, + "loss": 3.9606, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.164966328455289e-05, + "loss": 3.9649, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164127733704237e-05, + "loss": 3.9717, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163289138953185e-05, + "loss": 3.949, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162450544202133e-05, + "loss": 3.961, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161611949451081e-05, + "loss": 3.9482, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160773354700029e-05, + "loss": 3.9563, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.1599347599489773e-05, + "loss": 3.9655, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.1590961651979253e-05, + "loss": 3.9562, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.1582575704468733e-05, + "loss": 3.9607, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157418975695821e-05, + "loss": 3.9473, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156582018825142e-05, + "loss": 3.9537, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.15574342407409e-05, + "loss": 3.9591, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154906467203411e-05, + "loss": 3.9681, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154067872452359e-05, + "loss": 3.9511, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153229277701307e-05, + "loss": 3.9488, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152390682950255e-05, + "loss": 3.9518, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151552088199203e-05, + "loss": 3.9572, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150713493448151e-05, + "loss": 3.9634, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149876536577473e-05, + "loss": 3.9616, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149037941826421e-05, + "loss": 3.9509, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1482009849557416e-05, + "loss": 3.9673, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1473623902046896e-05, + "loss": 3.9558, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1465237954536376e-05, + "loss": 3.9636, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1456852007025856e-05, + "loss": 3.9515, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1448466059515336e-05, + "loss": 3.9658, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144008011200481e-05, + "loss": 3.9522, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143169416449429e-05, + "loss": 3.9645, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1423324595787505e-05, + "loss": 3.9568, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141493864827698e-05, + "loss": 3.9527, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1406552700766465e-05, + "loss": 3.9639, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1398166753255945e-05, + "loss": 3.9639, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1389780805745425e-05, + "loss": 3.9567, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1381394858234905e-05, + "loss": 3.9729, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1373008910724385e-05, + "loss": 3.9512, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1364622963213865e-05, + "loss": 3.948, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1356253394507074e-05, + "loss": 3.9609, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1347867446996554e-05, + "loss": 3.9608, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1339481499486034e-05, + "loss": 3.9791, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1331095551975514e-05, + "loss": 3.9555, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1322709604464994e-05, + "loss": 3.9568, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1314323656954474e-05, + "loss": 3.9532, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1305937709443954e-05, + "loss": 3.9591, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129756814073716e-05, + "loss": 3.9597, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.128918219322665e-05, + "loss": 3.9652, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128079624571613e-05, + "loss": 3.9689, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127241029820561e-05, + "loss": 3.9552, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126402435069509e-05, + "loss": 3.9564, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 4.072175979614258, + "eval_runtime": 304.8841, + "eval_samples_per_second": 1251.594, + "eval_steps_per_second": 39.113, + "step": 1144785 + }, + { + "epoch": 1.0, + "learning_rate": 3.125563840318457e-05, + "loss": 3.9544, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124725245567405e-05, + "loss": 3.9763, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123886650816352e-05, + "loss": 3.9649, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1230480560653e-05, + "loss": 3.958, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122211099194622e-05, + "loss": 3.9617, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.12137250444357e-05, + "loss": 3.9524, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120533909692517e-05, + "loss": 3.9585, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119695314941465e-05, + "loss": 3.9489, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118858358070787e-05, + "loss": 3.959, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118019763319735e-05, + "loss": 3.957, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117184444329429e-05, + "loss": 3.9568, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116345849578377e-05, + "loss": 3.9635, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115507254827325e-05, + "loss": 3.9583, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114668660076273e-05, + "loss": 3.9598, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113830065325221e-05, + "loss": 3.953, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.112991470574169e-05, + "loss": 3.95, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1121528758231165e-05, + "loss": 3.9329, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1113142810720645e-05, + "loss": 3.9563, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1104756863210125e-05, + "loss": 3.9525, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109638729450334e-05, + "loss": 3.9616, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108800134699282e-05, + "loss": 3.9699, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.10796153994823e-05, + "loss": 3.9626, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107122945197178e-05, + "loss": 3.9484, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106284350446126e-05, + "loss": 3.9631, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105445755695074e-05, + "loss": 3.9533, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104608798824395e-05, + "loss": 3.9534, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103770204073343e-05, + "loss": 3.956, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.102931609322291e-05, + "loss": 3.96, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102093014571239e-05, + "loss": 3.9486, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101254419820187e-05, + "loss": 3.9568, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100415825069135e-05, + "loss": 3.9445, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099577230318083e-05, + "loss": 3.9448, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098738635567031e-05, + "loss": 3.965, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.097900040815979e-05, + "loss": 3.9545, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0970630839453005e-05, + "loss": 3.9517, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0962261270746214e-05, + "loss": 3.9593, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0953875323235694e-05, + "loss": 3.9574, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0945489375725174e-05, + "loss": 3.9572, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0937103428214654e-05, + "loss": 3.9541, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0928717480704134e-05, + "loss": 3.9616, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0920331533193614e-05, + "loss": 3.9502, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0911945585683094e-05, + "loss": 3.9478, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.0903559638172574e-05, + "loss": 3.9472, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089519006946578e-05, + "loss": 3.9609, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088682050075899e-05, + "loss": 3.9612, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087843455324847e-05, + "loss": 3.9561, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087004860573796e-05, + "loss": 3.9515, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086166265822744e-05, + "loss": 3.9623, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085327671071692e-05, + "loss": 3.9582, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.08448907632064e-05, + "loss": 3.9443, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083652119449961e-05, + "loss": 3.9484, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082815162579282e-05, + "loss": 3.951, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.08197656782823e-05, + "loss": 3.9577, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081137973077178e-05, + "loss": 3.947, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080299378326126e-05, + "loss": 3.9644, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079460783575074e-05, + "loss": 3.935, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078622188824022e-05, + "loss": 3.953, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.07778359407297e-05, + "loss": 3.953, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.076944999321918e-05, + "loss": 3.961, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0761064045708657e-05, + "loss": 3.9539, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0752678098198137e-05, + "loss": 3.9505, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.0744292150687617e-05, + "loss": 3.9467, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0735906203177096e-05, + "loss": 3.9557, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0727536634470306e-05, + "loss": 3.9464, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0719150686959786e-05, + "loss": 3.957, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0710764739449265e-05, + "loss": 3.9576, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0702395170742475e-05, + "loss": 3.9442, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0694009223231955e-05, + "loss": 3.9428, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0685623275721434e-05, + "loss": 3.9582, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0677237328210914e-05, + "loss": 3.9442, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0668851380700394e-05, + "loss": 3.9428, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066046543318988e-05, + "loss": 3.9569, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065207948567936e-05, + "loss": 3.9462, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064369353816884e-05, + "loss": 3.9588, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063534034826578e-05, + "loss": 3.9583, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062695440075526e-05, + "loss": 3.9593, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061856845324474e-05, + "loss": 3.95, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061018250573422e-05, + "loss": 3.9482, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.06017965582237e-05, + "loss": 3.9554, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059341061071318e-05, + "loss": 3.9521, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0585057420810124e-05, + "loss": 3.9655, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0576671473299604e-05, + "loss": 3.9598, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0568285525789084e-05, + "loss": 3.9458, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0559899578278564e-05, + "loss": 3.9437, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0551513630768044e-05, + "loss": 3.9389, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0543127683257524e-05, + "loss": 3.9533, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0534741735747004e-05, + "loss": 3.9572, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0526355788236484e-05, + "loss": 3.9545, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0517969840725964e-05, + "loss": 3.9514, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0509600272019173e-05, + "loss": 3.9495, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0501230703312382e-05, + "loss": 3.9477, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0492844755801865e-05, + "loss": 3.9498, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0484458808291345e-05, + "loss": 3.9559, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0476072860780825e-05, + "loss": 3.9437, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0467686913270305e-05, + "loss": 3.9408, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0459300965759785e-05, + "loss": 3.9432, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0450915018249265e-05, + "loss": 3.954, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0442529070738745e-05, + "loss": 3.9495, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0434143123228225e-05, + "loss": 3.9577, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0425773554521437e-05, + "loss": 3.9528, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0417387607010917e-05, + "loss": 3.9478, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0409001659500397e-05, + "loss": 3.9517, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0400632090793606e-05, + "loss": 3.9509, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0392246143283086e-05, + "loss": 3.9585, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0383860195772566e-05, + "loss": 3.9398, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037547424826205e-05, + "loss": 3.9491, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036708830075153e-05, + "loss": 3.9398, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.035870235324101e-05, + "loss": 3.9419, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035031640573049e-05, + "loss": 3.9542, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0341930458219963e-05, + "loss": 3.9411, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0333544510709443e-05, + "loss": 3.9516, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0325158563198926e-05, + "loss": 3.9391, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0316788994492135e-05, + "loss": 3.9407, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0308403046981615e-05, + "loss": 3.9444, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0300017099471095e-05, + "loss": 3.9564, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0291631151960575e-05, + "loss": 3.9431, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0283245204450055e-05, + "loss": 3.9326, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0274859256939535e-05, + "loss": 3.9414, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0266473309429015e-05, + "loss": 3.9496, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0258087361918498e-05, + "loss": 3.9515, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0249734172015436e-05, + "loss": 3.9544, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0241364603308652e-05, + "loss": 3.9391, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0232978655798132e-05, + "loss": 3.9569, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022459270828761e-05, + "loss": 3.9428, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021620676077709e-05, + "loss": 3.9526, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020782081326657e-05, + "loss": 3.9401, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.019943486575605e-05, + "loss": 3.9543, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019104891824553e-05, + "loss": 3.9368, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018266297073501e-05, + "loss": 3.953, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017429340202822e-05, + "loss": 3.9427, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.01659074545177e-05, + "loss": 3.9433, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015752150700718e-05, + "loss": 3.9522, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.014913555949666e-05, + "loss": 3.9508, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014074961198614e-05, + "loss": 3.947, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013236366447562e-05, + "loss": 3.9587, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.01239777169651e-05, + "loss": 3.9397, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0115608148258313e-05, + "loss": 3.9375, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0107238579551522e-05, + "loss": 3.9477, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0098852632041002e-05, + "loss": 3.9522, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0090466684530482e-05, + "loss": 3.962, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0082080737019962e-05, + "loss": 3.949, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0073694789509442e-05, + "loss": 3.9446, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0065308841998922e-05, + "loss": 3.9452, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0056922894488406e-05, + "loss": 3.9469, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0048536946977885e-05, + "loss": 3.9489, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0040150999467365e-05, + "loss": 3.9524, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0031781430760575e-05, + "loss": 3.957, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0023395483250055e-05, + "loss": 3.9439, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0015009535739534e-05, + "loss": 3.9452, + "step": 1220608 + }, + { + "epoch": 1.03, + "eval_loss": 4.066517353057861, + "eval_runtime": 306.0501, + "eval_samples_per_second": 1246.825, + "eval_steps_per_second": 38.964, + "step": 1221104 + }, + { + "epoch": 0.0, + "learning_rate": 3.0006623588229014e-05, + "loss": 3.9625, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9998237640718498e-05, + "loss": 3.9438, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.998985169320797e-05, + "loss": 3.945, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.998146574569745e-05, + "loss": 3.9595, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997307979818693e-05, + "loss": 3.9551, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996469385067641e-05, + "loss": 3.9496, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995630790316589e-05, + "loss": 3.944, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9947921955655374e-05, + "loss": 3.9439, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9939536008144854e-05, + "loss": 3.9422, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9931150060634334e-05, + "loss": 3.9566, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9922764113123814e-05, + "loss": 3.9446, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9914394544417023e-05, + "loss": 3.9518, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9906008596906503e-05, + "loss": 3.956, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9897622649395983e-05, + "loss": 3.9379, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9889236701885466e-05, + "loss": 3.9448, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9880850754374946e-05, + "loss": 3.932, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9872464806864426e-05, + "loss": 3.9366, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9864078859353906e-05, + "loss": 3.9475, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9855692911843386e-05, + "loss": 3.9403, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984730696433286e-05, + "loss": 3.9411, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9838921016822343e-05, + "loss": 3.9641, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9830535069311823e-05, + "loss": 3.9439, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9822149121801303e-05, + "loss": 3.9518, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981377955309451e-05, + "loss": 3.9498, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980539360558399e-05, + "loss": 3.9441, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979700765807347e-05, + "loss": 3.9454, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.978862171056295e-05, + "loss": 3.9353, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978023576305243e-05, + "loss": 3.9469, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9771866194345644e-05, + "loss": 3.9433, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9763480246835124e-05, + "loss": 3.9355, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9755094299324604e-05, + "loss": 3.9456, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9746708351814084e-05, + "loss": 3.9361, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9738322404303564e-05, + "loss": 3.9512, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9729936456793044e-05, + "loss": 3.9516, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9721566888086256e-05, + "loss": 3.9391, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9713180940575736e-05, + "loss": 3.9412, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9704794993065216e-05, + "loss": 3.9596, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9696409045554696e-05, + "loss": 3.9363, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9688023098044176e-05, + "loss": 3.9433, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9679637150533656e-05, + "loss": 3.944, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9671251203023136e-05, + "loss": 3.9351, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9662865255512616e-05, + "loss": 3.9422, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.96544793080021e-05, + "loss": 3.9575, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964610973929531e-05, + "loss": 3.9477, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963772379178479e-05, + "loss": 3.9407, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9629354223077997e-05, + "loss": 3.9513, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9620968275567477e-05, + "loss": 3.9366, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961258232805696e-05, + "loss": 3.9532, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960419638054644e-05, + "loss": 3.9241, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959581043303592e-05, + "loss": 3.9413, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958744086432913e-05, + "loss": 3.9528, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.957905491681861e-05, + "loss": 3.9474, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957066896930809e-05, + "loss": 3.9452, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956228302179757e-05, + "loss": 3.9302, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9553897074287046e-05, + "loss": 3.9445, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9545511126776526e-05, + "loss": 3.9285, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9537125179266006e-05, + "loss": 3.9617, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9528739231755486e-05, + "loss": 3.939, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.95203696630487e-05, + "loss": 3.9573, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951198371553818e-05, + "loss": 3.9405, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9503614146831394e-05, + "loss": 3.9368, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9495228199320874e-05, + "loss": 3.9482, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9486842251810347e-05, + "loss": 3.9372, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9478456304299827e-05, + "loss": 3.9391, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9470070356789307e-05, + "loss": 3.9389, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946168440927879e-05, + "loss": 3.9486, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945329846176827e-05, + "loss": 3.9351, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944491251425775e-05, + "loss": 3.9391, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943652656674723e-05, + "loss": 3.9264, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942814061923671e-05, + "loss": 3.9315, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.941975467172619e-05, + "loss": 3.9503, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941136872421567e-05, + "loss": 3.9513, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9402999155508883e-05, + "loss": 3.9375, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9394613207998363e-05, + "loss": 3.941, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9386227260487843e-05, + "loss": 3.9493, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9377841312977323e-05, + "loss": 3.9459, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9369471744270532e-05, + "loss": 3.9415, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9361085796760012e-05, + "loss": 3.9427, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9352699849249492e-05, + "loss": 3.9426, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9344313901738972e-05, + "loss": 3.9454, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9335927954228455e-05, + "loss": 3.9433, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9327558385521664e-05, + "loss": 3.9415, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9319172438011144e-05, + "loss": 3.953, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9310786490500624e-05, + "loss": 3.9447, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9302400542990104e-05, + "loss": 3.9259, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9294014595479584e-05, + "loss": 3.9459, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.928562864796906e-05, + "loss": 3.9443, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927724270045854e-05, + "loss": 3.94, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.926885675294802e-05, + "loss": 3.9425, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.926048718424123e-05, + "loss": 3.9327, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925210123673071e-05, + "loss": 3.947, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9243715289220193e-05, + "loss": 3.9349, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9235329341709673e-05, + "loss": 3.9401, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9226943394199153e-05, + "loss": 3.9426, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9218557446688633e-05, + "loss": 3.9363, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9210171499178113e-05, + "loss": 3.9529, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9201785551667593e-05, + "loss": 3.9295, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9193399604157073e-05, + "loss": 3.9291, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9185030035450285e-05, + "loss": 3.9398, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9176660466743494e-05, + "loss": 3.9418, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9168274519232974e-05, + "loss": 3.9484, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9159888571722454e-05, + "loss": 3.9426, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9151502624211934e-05, + "loss": 3.9332, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9143116676701414e-05, + "loss": 3.9372, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9134763486798356e-05, + "loss": 3.9407, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9126377539287836e-05, + "loss": 3.9274, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9117991591777316e-05, + "loss": 3.9324, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9109605644266796e-05, + "loss": 3.9416, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9101219696756276e-05, + "loss": 3.9413, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9092833749245755e-05, + "loss": 3.928, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9084480559342704e-05, + "loss": 3.929, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9076094611832177e-05, + "loss": 3.9304, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9067708664321657e-05, + "loss": 3.943, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9059322716811137e-05, + "loss": 3.9318, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9050936769300617e-05, + "loss": 3.9346, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.90425508217901e-05, + "loss": 3.9384, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903416487427958e-05, + "loss": 3.9436, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902577892676906e-05, + "loss": 3.9339, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901739297925854e-05, + "loss": 3.9375, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.900900703174802e-05, + "loss": 3.9389, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.90006210842375e-05, + "loss": 3.9397, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899223513672698e-05, + "loss": 3.9227, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898384918921646e-05, + "loss": 3.9435, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.897546324170594e-05, + "loss": 3.9369, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8967077294195423e-05, + "loss": 3.946, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8958691346684896e-05, + "loss": 3.9311, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8950321777978112e-05, + "loss": 3.9391, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8941935830467592e-05, + "loss": 3.9328, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.89335662617608e-05, + "loss": 3.9325, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8925180314250285e-05, + "loss": 3.9249, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8916794366739765e-05, + "loss": 3.9472, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8908424798032974e-05, + "loss": 3.9486, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8900038850522454e-05, + "loss": 3.9378, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8891652903011934e-05, + "loss": 3.9299, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8883266955501414e-05, + "loss": 3.9445, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8874881007990894e-05, + "loss": 3.9406, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886649506048037e-05, + "loss": 3.9358, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885810911296985e-05, + "loss": 3.9354, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.884972316545933e-05, + "loss": 3.9484, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884133721794881e-05, + "loss": 3.94, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8832967649242022e-05, + "loss": 3.9387, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8824581701731502e-05, + "loss": 3.9301, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8816195754220982e-05, + "loss": 3.94, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8807809806710462e-05, + "loss": 3.9415, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.879944023800367e-05, + "loss": 3.9286, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.879105429049315e-05, + "loss": 3.9526, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878266834298263e-05, + "loss": 3.9338, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8774282395472115e-05, + "loss": 3.9407, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8765896447961595e-05, + "loss": 3.9428, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8757510500451075e-05, + "loss": 3.9355, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 4.060186862945557, + "eval_runtime": 394.0942, + "eval_samples_per_second": 968.274, + "eval_steps_per_second": 30.259, + "step": 1297424 + }, + { + "epoch": 1.0, + "learning_rate": 2.8749124552940555e-05, + "loss": 3.9346, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8740738605430035e-05, + "loss": 3.9363, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8732352657919514e-05, + "loss": 3.9493, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8723983089212724e-05, + "loss": 3.9386, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8715597141702204e-05, + "loss": 3.9429, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8707211194191687e-05, + "loss": 3.9327, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8698825246681167e-05, + "loss": 3.9334, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8690455677974376e-05, + "loss": 3.9288, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8682069730463856e-05, + "loss": 3.9488, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8673700161757065e-05, + "loss": 3.9303, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866531421424655e-05, + "loss": 3.9418, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8656944645539757e-05, + "loss": 3.9421, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8648558698029237e-05, + "loss": 3.9311, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8640172750518717e-05, + "loss": 3.9307, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8631786803008197e-05, + "loss": 3.922, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8623400855497677e-05, + "loss": 3.9298, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8615014907987157e-05, + "loss": 3.9337, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860662896047664e-05, + "loss": 3.9303, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859824301296612e-05, + "loss": 3.9311, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.85898570654556e-05, + "loss": 3.956, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858147111794508e-05, + "loss": 3.9317, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8573085170434554e-05, + "loss": 3.9384, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8564699222924034e-05, + "loss": 3.9423, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8556313275413517e-05, + "loss": 3.9327, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8547943706706726e-05, + "loss": 3.9339, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8539557759196206e-05, + "loss": 3.9238, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8531171811685686e-05, + "loss": 3.9337, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8522785864175166e-05, + "loss": 3.9367, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8514399916664646e-05, + "loss": 3.9218, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8506013969154126e-05, + "loss": 3.9358, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849762802164361e-05, + "loss": 3.9254, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.848924207413309e-05, + "loss": 3.9426, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8480872505426298e-05, + "loss": 3.9414, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8472486557915778e-05, + "loss": 3.9268, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8464116989208987e-05, + "loss": 3.9358, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845573104169847e-05, + "loss": 3.9504, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844734509418795e-05, + "loss": 3.9224, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.843895914667743e-05, + "loss": 3.9353, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843057319916691e-05, + "loss": 3.9319, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842218725165639e-05, + "loss": 3.9242, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841380130414587e-05, + "loss": 3.9333, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840541535663535e-05, + "loss": 3.9445, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.839702940912483e-05, + "loss": 3.938, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.838864346161431e-05, + "loss": 3.9321, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8380257514103794e-05, + "loss": 3.9412, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8371871566593267e-05, + "loss": 3.9296, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8363485619082747e-05, + "loss": 3.9366, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835513242917969e-05, + "loss": 3.9187, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.834674648166917e-05, + "loss": 3.9297, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8338360534158655e-05, + "loss": 3.9412, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8329990965451864e-05, + "loss": 3.9391, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8321605017941344e-05, + "loss": 3.9318, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8313219070430824e-05, + "loss": 3.9254, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8304833122920304e-05, + "loss": 3.9361, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8296447175409784e-05, + "loss": 3.9208, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8288061227899264e-05, + "loss": 3.9471, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.827967528038874e-05, + "loss": 3.9288, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.827128933287822e-05, + "loss": 3.9477, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8262919764171436e-05, + "loss": 3.9306, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8254533816660916e-05, + "loss": 3.9283, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8246147869150393e-05, + "loss": 3.9324, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8237761921639873e-05, + "loss": 3.9329, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8229375974129353e-05, + "loss": 3.9276, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8220990026618833e-05, + "loss": 3.9235, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8212604079108313e-05, + "loss": 3.9415, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8204218131597793e-05, + "loss": 3.9264, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8195848562891e-05, + "loss": 3.9207, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818746261538048e-05, + "loss": 3.9219, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8179076667869965e-05, + "loss": 3.9202, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8170707099163174e-05, + "loss": 3.9441, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8162321151652654e-05, + "loss": 3.9399, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8153935204142134e-05, + "loss": 3.9283, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8145549256631614e-05, + "loss": 3.9324, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8137163309121094e-05, + "loss": 3.9371, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8128777361610574e-05, + "loss": 3.9326, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8120391414100057e-05, + "loss": 3.93, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8112005466589537e-05, + "loss": 3.9348, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8103619519079017e-05, + "loss": 3.9335, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8095249950372226e-05, + "loss": 3.9379, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8086864002861706e-05, + "loss": 3.9283, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.807849443415492e-05, + "loss": 3.9351, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.80701084866444e-05, + "loss": 3.9383, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.806172253913388e-05, + "loss": 3.9346, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805333659162336e-05, + "loss": 3.9172, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804495064411284e-05, + "loss": 3.9382, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8036581075406048e-05, + "loss": 3.9322, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8028195127895527e-05, + "loss": 3.9348, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.801980918038501e-05, + "loss": 3.9341, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801142323287449e-05, + "loss": 3.9241, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800303728536397e-05, + "loss": 3.9334, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.799465133785345e-05, + "loss": 3.9248, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7986265390342924e-05, + "loss": 3.9347, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797789582163614e-05, + "loss": 3.9268, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.796950987412562e-05, + "loss": 3.9292, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7961123926615103e-05, + "loss": 3.9418, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7952737979104576e-05, + "loss": 3.9244, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7944352031594056e-05, + "loss": 3.9149, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7935982462887272e-05, + "loss": 3.9324, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792759651537675e-05, + "loss": 3.9324, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.791921056786623e-05, + "loss": 3.9401, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791082462035571e-05, + "loss": 3.928, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790243867284519e-05, + "loss": 3.9252, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7894069104138398e-05, + "loss": 3.925, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7885683156627878e-05, + "loss": 3.9332, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7877297209117358e-05, + "loss": 3.9161, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7868927640410573e-05, + "loss": 3.9192, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.786054169290005e-05, + "loss": 3.9318, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785215574538953e-05, + "loss": 3.935, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784376979787901e-05, + "loss": 3.9158, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783538385036849e-05, + "loss": 3.9201, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782699790285797e-05, + "loss": 3.9199, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.781861195534745e-05, + "loss": 3.9307, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7810226007836933e-05, + "loss": 3.924, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7801840060326413e-05, + "loss": 3.9214, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7793454112815893e-05, + "loss": 3.9342, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7785068165305373e-05, + "loss": 3.9316, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7776698596598582e-05, + "loss": 3.9237, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7768312649088062e-05, + "loss": 3.9287, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7759926701577542e-05, + "loss": 3.9282, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7751540754067022e-05, + "loss": 3.9284, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7743154806556505e-05, + "loss": 3.9152, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7734768859045985e-05, + "loss": 3.9334, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7726382911535465e-05, + "loss": 3.9277, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7718013342828674e-05, + "loss": 3.9315, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7709627395318154e-05, + "loss": 3.9231, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7701241447807634e-05, + "loss": 3.9294, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.769285550029711e-05, + "loss": 3.922, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7684485931590327e-05, + "loss": 3.9229, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7676099984079807e-05, + "loss": 3.9093, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7667714036569287e-05, + "loss": 3.941, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.765932808905876e-05, + "loss": 3.938, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7650942141548243e-05, + "loss": 3.9302, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7642556194037723e-05, + "loss": 3.9166, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7634170246527203e-05, + "loss": 3.9405, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7625800677820412e-05, + "loss": 3.9318, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7617414730309892e-05, + "loss": 3.9269, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7609028782799372e-05, + "loss": 3.9241, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7600642835288852e-05, + "loss": 3.9356, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7592256887778335e-05, + "loss": 3.9287, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7583870940267815e-05, + "loss": 3.9338, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7575484992757295e-05, + "loss": 3.9174, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7567099045246775e-05, + "loss": 3.9286, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7558729476539984e-05, + "loss": 3.9335, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7550343529029464e-05, + "loss": 3.922, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7541957581518944e-05, + "loss": 3.9412, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7533571634008427e-05, + "loss": 3.9235, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7525202065301637e-05, + "loss": 3.93, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7516816117791117e-05, + "loss": 3.9294, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7508430170280596e-05, + "loss": 3.9281, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 4.056643486022949, + "eval_runtime": 357.6026, + "eval_samples_per_second": 1067.081, + "eval_steps_per_second": 33.347, + "step": 1373744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7500044222770076e-05, + "loss": 3.924, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7491658275259556e-05, + "loss": 3.9301, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7483272327749036e-05, + "loss": 3.9352, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747488638023852e-05, + "loss": 3.9327, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7466500432728e-05, + "loss": 3.9337, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7458114485217473e-05, + "loss": 3.9191, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7449728537706953e-05, + "loss": 3.9246, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7441342590196433e-05, + "loss": 3.9223, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7432956642685913e-05, + "loss": 3.9353, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7424570695175396e-05, + "loss": 3.9265, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7416201126468605e-05, + "loss": 3.9298, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7407815178958085e-05, + "loss": 3.9357, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7399429231447565e-05, + "loss": 3.9176, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7391043283937045e-05, + "loss": 3.9238, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7382657336426525e-05, + "loss": 3.9122, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7374271388916005e-05, + "loss": 3.9223, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7365885441405488e-05, + "loss": 3.9228, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7357499493894968e-05, + "loss": 3.9203, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7349113546384448e-05, + "loss": 3.9225, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7340727598873928e-05, + "loss": 3.9453, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7332341651363408e-05, + "loss": 3.9259, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7323955703852888e-05, + "loss": 3.9258, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7315569756342365e-05, + "loss": 3.9334, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7307183808831845e-05, + "loss": 3.9254, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7298797861321325e-05, + "loss": 3.9249, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7290411913810804e-05, + "loss": 3.9152, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7282042345104014e-05, + "loss": 3.9241, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7273656397593494e-05, + "loss": 3.9247, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726528682888671e-05, + "loss": 3.9114, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7256900881376186e-05, + "loss": 3.929, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7248514933865666e-05, + "loss": 3.9151, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7240128986355146e-05, + "loss": 3.9335, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7231759417648362e-05, + "loss": 3.9301, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7223373470137835e-05, + "loss": 3.9154, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7214987522627315e-05, + "loss": 3.9268, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7206601575116798e-05, + "loss": 3.9408, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7198215627606278e-05, + "loss": 3.9145, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7189829680095758e-05, + "loss": 3.9262, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7181443732585238e-05, + "loss": 3.9165, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7173057785074718e-05, + "loss": 3.918, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7164688216367927e-05, + "loss": 3.9209, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7156302268857407e-05, + "loss": 3.9361, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714791632134689e-05, + "loss": 3.9284, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.713953037383637e-05, + "loss": 3.9218, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713114442632585e-05, + "loss": 3.9329, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712277485761906e-05, + "loss": 3.9194, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711440528891227e-05, + "loss": 3.9308, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7106019341401752e-05, + "loss": 3.9115, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7097633393891232e-05, + "loss": 3.9166, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7089247446380712e-05, + "loss": 3.9328, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7080861498870192e-05, + "loss": 3.9303, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7072475551359672e-05, + "loss": 3.9192, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706410598265288e-05, + "loss": 3.917, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705572003514236e-05, + "loss": 3.9276, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7047334087631844e-05, + "loss": 3.9086, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7038948140121324e-05, + "loss": 3.9351, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7030578571414533e-05, + "loss": 3.9232, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7022192623904013e-05, + "loss": 3.9365, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7013806676393493e-05, + "loss": 3.9244, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7005420728882973e-05, + "loss": 3.9167, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6997034781372453e-05, + "loss": 3.9221, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6988648833861936e-05, + "loss": 3.9252, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6980262886351416e-05, + "loss": 3.9159, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6971876938840896e-05, + "loss": 3.915, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6963507370134105e-05, + "loss": 3.9286, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6955121422623585e-05, + "loss": 3.9215, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6946735475113065e-05, + "loss": 3.9087, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6938349527602545e-05, + "loss": 3.9137, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6929963580092022e-05, + "loss": 3.9091, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6921577632581502e-05, + "loss": 3.9322, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691319168507098e-05, + "loss": 3.9313, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6904822116364198e-05, + "loss": 3.9193, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6896436168853674e-05, + "loss": 3.9252, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6888050221343154e-05, + "loss": 3.9221, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6879664273832634e-05, + "loss": 3.9245, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6871278326322114e-05, + "loss": 3.9203, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6862892378811594e-05, + "loss": 3.9265, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6854506431301074e-05, + "loss": 3.9234, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6846120483790554e-05, + "loss": 3.929, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6837734536280034e-05, + "loss": 3.9187, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6829381346376975e-05, + "loss": 3.9235, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6820995398866455e-05, + "loss": 3.926, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6812609451355935e-05, + "loss": 3.9279, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6804223503845415e-05, + "loss": 3.9121, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6795837556334895e-05, + "loss": 3.9234, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6787451608824375e-05, + "loss": 3.9204, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6779065661313855e-05, + "loss": 3.9257, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677067971380334e-05, + "loss": 3.9259, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6762310145096548e-05, + "loss": 3.9097, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6753924197586028e-05, + "loss": 3.9237, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6745538250075508e-05, + "loss": 3.9177, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6737152302564987e-05, + "loss": 3.9247, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6728766355054467e-05, + "loss": 3.9092, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6720380407543947e-05, + "loss": 3.9214, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671199446003343e-05, + "loss": 3.9351, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670360851252291e-05, + "loss": 3.9187, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669523894381612e-05, + "loss": 3.9038, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668686937510933e-05, + "loss": 3.9213, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.667848342759881e-05, + "loss": 3.9257, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6670097480088292e-05, + "loss": 3.9269, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6661711532577772e-05, + "loss": 3.9208, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6653325585067252e-05, + "loss": 3.9159, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664495601636046e-05, + "loss": 3.914, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663657006884994e-05, + "loss": 3.9261, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.662818412133942e-05, + "loss": 3.9072, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.66197981738289e-05, + "loss": 3.913, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6611412226318384e-05, + "loss": 3.9235, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6603026278807858e-05, + "loss": 3.9266, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6594640331297338e-05, + "loss": 3.9038, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6586254383786817e-05, + "loss": 3.9179, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6577868436276297e-05, + "loss": 3.9077, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.656949886756951e-05, + "loss": 3.9221, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.656111292005899e-05, + "loss": 3.9153, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.655272697254847e-05, + "loss": 3.9107, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.654434102503795e-05, + "loss": 3.9262, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653597145633116e-05, + "loss": 3.9241, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6527601887624375e-05, + "loss": 3.914, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6519215940113855e-05, + "loss": 3.922, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6510846371407067e-05, + "loss": 3.916, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6502460423896547e-05, + "loss": 3.9215, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6494074476386027e-05, + "loss": 3.9046, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6485688528875507e-05, + "loss": 3.9271, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6477302581364984e-05, + "loss": 3.9172, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6468916633854464e-05, + "loss": 3.9219, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6460530686343944e-05, + "loss": 3.9151, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6452144738833424e-05, + "loss": 3.9226, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6443758791322903e-05, + "loss": 3.9093, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6435389222616113e-05, + "loss": 3.9164, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6427003275105593e-05, + "loss": 3.9029, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6418617327595076e-05, + "loss": 3.9323, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6410231380084556e-05, + "loss": 3.9251, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6401845432574036e-05, + "loss": 3.9226, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.6393459485063516e-05, + "loss": 3.9084, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6385089916356725e-05, + "loss": 3.9277, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6376703968846205e-05, + "loss": 3.9249, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6368318021335685e-05, + "loss": 3.9165, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6359932073825168e-05, + "loss": 3.9178, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6351562505118377e-05, + "loss": 3.9242, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6343176557607857e-05, + "loss": 3.9213, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6334790610097337e-05, + "loss": 3.9251, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6326404662586817e-05, + "loss": 3.9079, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6318018715076297e-05, + "loss": 3.9224, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.630964914636951e-05, + "loss": 3.9194, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.630126319885899e-05, + "loss": 3.9136, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.62928936301522e-05, + "loss": 3.9341, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628450768264168e-05, + "loss": 3.9136, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627612173513116e-05, + "loss": 3.9217, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626773578762064e-05, + "loss": 3.9191, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6259349840110122e-05, + "loss": 3.917, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 4.05181360244751, + "eval_runtime": 398.3524, + "eval_samples_per_second": 957.923, + "eval_steps_per_second": 29.936, + "step": 1450064 + }, + { + "epoch": 1.0, + "learning_rate": 2.6250963892599602e-05, + "loss": 3.9175, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.624257794508908e-05, + "loss": 3.9208, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623419199757856e-05, + "loss": 3.9252, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622582242887177e-05, + "loss": 3.9243, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621743648136125e-05, + "loss": 3.9294, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.620905053385073e-05, + "loss": 3.9113, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620066458634021e-05, + "loss": 3.9159, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6192278638829694e-05, + "loss": 3.9107, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6183892691319167e-05, + "loss": 3.9279, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6175506743808647e-05, + "loss": 3.9176, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6167120796298127e-05, + "loss": 3.923, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.615875122759134e-05, + "loss": 3.9255, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615036528008082e-05, + "loss": 3.9087, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.61419793325703e-05, + "loss": 3.9117, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613359338505978e-05, + "loss": 3.9071, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.612520743754926e-05, + "loss": 3.9085, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.611682149003874e-05, + "loss": 3.9171, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.610843554252822e-05, + "loss": 3.9101, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.61000495950177e-05, + "loss": 3.9138, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.609168002631091e-05, + "loss": 3.9349, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.608329407880039e-05, + "loss": 3.9183, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607490813128987e-05, + "loss": 3.9175, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606652218377935e-05, + "loss": 3.9231, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.605813623626883e-05, + "loss": 3.9216, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.604976666756204e-05, + "loss": 3.9116, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6041380720051524e-05, + "loss": 3.906, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6032994772541004e-05, + "loss": 3.9225, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6024608825030484e-05, + "loss": 3.907, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6016222877519964e-05, + "loss": 3.906, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6007836930009444e-05, + "loss": 3.9187, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.5999450982498924e-05, + "loss": 3.9091, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5991081413792133e-05, + "loss": 3.9201, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5982695466281616e-05, + "loss": 3.9209, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5974309518771096e-05, + "loss": 3.9087, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5965923571260576e-05, + "loss": 3.9205, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5957537623750056e-05, + "loss": 3.9305, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.5949168055043265e-05, + "loss": 3.9063, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5940782107532745e-05, + "loss": 3.9223, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5932396160022225e-05, + "loss": 3.9059, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.59240102125117e-05, + "loss": 3.9135, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5915640643804917e-05, + "loss": 3.9103, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5907254696294397e-05, + "loss": 3.9261, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5898868748783877e-05, + "loss": 3.9164, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5890482801273354e-05, + "loss": 3.9162, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588211323256657e-05, + "loss": 3.9208, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587372728505605e-05, + "loss": 3.9123, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5865341337545523e-05, + "loss": 3.9261, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.585697176883874e-05, + "loss": 3.9016, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.584858582132822e-05, + "loss": 3.9066, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.58401998738177e-05, + "loss": 3.923, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5831813926307175e-05, + "loss": 3.9189, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5823427978796655e-05, + "loss": 3.9165, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5815042031286135e-05, + "loss": 3.9076, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5806656083775615e-05, + "loss": 3.9164, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5798270136265095e-05, + "loss": 3.9006, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5789900567558308e-05, + "loss": 3.9211, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5781514620047788e-05, + "loss": 3.9172, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5773128672537268e-05, + "loss": 3.9252, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5764742725026747e-05, + "loss": 3.9178, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5756356777516227e-05, + "loss": 3.9118, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5747970830005707e-05, + "loss": 3.9079, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5739584882495187e-05, + "loss": 3.9217, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5731198934984667e-05, + "loss": 3.904, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572282936627788e-05, + "loss": 3.9087, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571444341876736e-05, + "loss": 3.9171, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570605747125684e-05, + "loss": 3.9158, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569767152374632e-05, + "loss": 3.9015, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.568930195503953e-05, + "loss": 3.9027, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568091600752901e-05, + "loss": 3.9016, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5672530060018492e-05, + "loss": 3.9227, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5664144112507972e-05, + "loss": 3.9217, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5655758164997452e-05, + "loss": 3.9113, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5647372217486932e-05, + "loss": 3.9172, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5638986269976412e-05, + "loss": 3.9102, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5630600322465885e-05, + "loss": 3.9242, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5622247132562833e-05, + "loss": 3.9038, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5613861185052313e-05, + "loss": 3.925, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5605475237541793e-05, + "loss": 3.9159, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5597089290031273e-05, + "loss": 3.9184, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5588719721324482e-05, + "loss": 3.9114, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5580333773813962e-05, + "loss": 3.9154, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5571947826303442e-05, + "loss": 3.9207, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5563561878792926e-05, + "loss": 3.9193, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5555175931282406e-05, + "loss": 3.904, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5546822741379344e-05, + "loss": 3.9162, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5538436793868824e-05, + "loss": 3.9142, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5530050846358307e-05, + "loss": 3.9168, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5521664898847787e-05, + "loss": 3.9167, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5513278951337267e-05, + "loss": 3.9038, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5504893003826747e-05, + "loss": 3.9162, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5496507056316227e-05, + "loss": 3.9085, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5488121108805707e-05, + "loss": 3.9167, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5479735161295187e-05, + "loss": 3.9012, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5471349213784663e-05, + "loss": 3.9172, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5462963266274143e-05, + "loss": 3.9242, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5454577318763623e-05, + "loss": 3.9109, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5446207750056832e-05, + "loss": 3.8972, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5437821802546312e-05, + "loss": 3.9119, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5429435855035792e-05, + "loss": 3.9132, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5421049907525272e-05, + "loss": 3.9222, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5412663960014756e-05, + "loss": 3.9144, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5404294391307965e-05, + "loss": 3.9046, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5395908443797445e-05, + "loss": 3.9089, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5387522496286925e-05, + "loss": 3.9182, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5379152927580134e-05, + "loss": 3.8988, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5370766980069617e-05, + "loss": 3.9073, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5362397411362833e-05, + "loss": 3.9115, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5354011463852306e-05, + "loss": 3.9186, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5345625516341786e-05, + "loss": 3.8936, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5337239568831266e-05, + "loss": 3.9114, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5328853621320746e-05, + "loss": 3.9033, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5320467673810226e-05, + "loss": 3.9071, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531208172629971e-05, + "loss": 3.9079, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530369577878919e-05, + "loss": 3.903, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529530983127867e-05, + "loss": 3.9226, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528694026257188e-05, + "loss": 3.9113, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5278570693865087e-05, + "loss": 3.9044, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527018474635457e-05, + "loss": 3.9114, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526179879884405e-05, + "loss": 3.9099, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525341285133353e-05, + "loss": 3.9115, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524502690382301e-05, + "loss": 3.8949, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.523664095631249e-05, + "loss": 3.9185, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.522825500880197e-05, + "loss": 3.9083, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.521986906129145e-05, + "loss": 3.9135, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5211499492584663e-05, + "loss": 3.9082, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5203113545074143e-05, + "loss": 3.913, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5194727597563623e-05, + "loss": 3.9038, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5186341650053103e-05, + "loss": 3.9036, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5177955702542583e-05, + "loss": 3.8979, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5169569755032063e-05, + "loss": 3.9192, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5161183807521543e-05, + "loss": 3.9174, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5152814238814755e-05, + "loss": 3.9149, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5144428291304235e-05, + "loss": 3.9025, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5136058722597444e-05, + "loss": 3.9166, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5127672775086924e-05, + "loss": 3.9171, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5119286827576404e-05, + "loss": 3.9078, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5110900880065884e-05, + "loss": 3.9115, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5102514932555364e-05, + "loss": 3.9125, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5094128985044847e-05, + "loss": 3.9153, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508574303753432e-05, + "loss": 3.9185, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.50773570900238e-05, + "loss": 3.9031, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.506897114251328e-05, + "loss": 3.911, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506058519500276e-05, + "loss": 3.9111, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505219924749224e-05, + "loss": 3.9053, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5043813299981724e-05, + "loss": 3.9243, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5035443731274933e-05, + "loss": 3.905, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5027057783764413e-05, + "loss": 3.9138, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5018688215057622e-05, + "loss": 3.9094, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5010302267547102e-05, + "loss": 3.9124, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 4.048308372497559, + "eval_runtime": 393.9482, + "eval_samples_per_second": 968.632, + "eval_steps_per_second": 30.27, + "step": 1526384 + }, + { + "epoch": 0.0, + "learning_rate": 2.5001916320036585e-05, + "loss": 3.9046, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4993530372526065e-05, + "loss": 3.9125, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4985144425015545e-05, + "loss": 3.9182, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4976758477505025e-05, + "loss": 3.9151, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4968372529994505e-05, + "loss": 3.9232, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4959986582483985e-05, + "loss": 3.9011, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4951600634973465e-05, + "loss": 3.911, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494321468746294e-05, + "loss": 3.8978, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4934828739952425e-05, + "loss": 3.9228, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4926442792441905e-05, + "loss": 3.9112, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4918056844931385e-05, + "loss": 3.913, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4909670897420865e-05, + "loss": 3.9143, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4901317707517806e-05, + "loss": 3.9088, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4892931760007286e-05, + "loss": 3.8975, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4884545812496766e-05, + "loss": 3.9018, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4876159864986246e-05, + "loss": 3.8986, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4867773917475726e-05, + "loss": 3.9077, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4859387969965206e-05, + "loss": 3.9055, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4851002022454686e-05, + "loss": 3.9013, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4842616074944166e-05, + "loss": 3.9294, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4834230127433646e-05, + "loss": 3.9072, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4825844179923126e-05, + "loss": 3.9116, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4817458232412606e-05, + "loss": 3.9193, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4809072284902086e-05, + "loss": 3.9107, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4800686337391566e-05, + "loss": 3.9059, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4792316768684775e-05, + "loss": 3.8991, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4783930821174255e-05, + "loss": 3.9157, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4775544873663735e-05, + "loss": 3.8938, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4767158926153218e-05, + "loss": 3.9029, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4758789357446427e-05, + "loss": 3.903, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4750403409935907e-05, + "loss": 3.9022, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474203384122912e-05, + "loss": 3.9137, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4733647893718596e-05, + "loss": 3.9128, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472526194620808e-05, + "loss": 3.9015, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.471687599869756e-05, + "loss": 3.9101, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.470849005118704e-05, + "loss": 3.9201, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470010410367652e-05, + "loss": 3.9008, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4691718156166e-05, + "loss": 3.9122, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4683332208655476e-05, + "loss": 3.8966, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4674946261144956e-05, + "loss": 3.9104, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4666560313634436e-05, + "loss": 3.8979, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.465817436612392e-05, + "loss": 3.9198, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.46497884186134e-05, + "loss": 3.9112, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464141884990661e-05, + "loss": 3.9063, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4633032902396088e-05, + "loss": 3.913, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4624646954885568e-05, + "loss": 3.9028, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4616261007375048e-05, + "loss": 3.9134, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.460789143866826e-05, + "loss": 3.898, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4599521869961473e-05, + "loss": 3.8964, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.459113592245095e-05, + "loss": 3.9169, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458274997494043e-05, + "loss": 3.9078, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457436402742991e-05, + "loss": 3.9072, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456597807991939e-05, + "loss": 3.8996, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4557608511212602e-05, + "loss": 3.9083, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4549222563702082e-05, + "loss": 3.8946, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4540836616191562e-05, + "loss": 3.913, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4532450668681042e-05, + "loss": 3.9081, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4524064721170522e-05, + "loss": 3.9178, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4515695152463734e-05, + "loss": 3.9123, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4507325583756947e-05, + "loss": 3.9035, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4498939636246423e-05, + "loss": 3.9003, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4490553688735903e-05, + "loss": 3.9101, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4482167741225383e-05, + "loss": 3.8944, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4473781793714863e-05, + "loss": 3.9045, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4465395846204343e-05, + "loss": 3.909, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4457009898693827e-05, + "loss": 3.909, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4448623951183307e-05, + "loss": 3.8908, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4440254382476516e-05, + "loss": 3.8953, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4431868434965996e-05, + "loss": 3.8933, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4423482487455476e-05, + "loss": 3.917, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4415096539944956e-05, + "loss": 3.9067, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4406726971238168e-05, + "loss": 3.9064, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4398341023727648e-05, + "loss": 3.9103, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4389955076217128e-05, + "loss": 3.903, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4381569128706605e-05, + "loss": 3.918, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4373183181196084e-05, + "loss": 3.8926, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4364813612489297e-05, + "loss": 3.9141, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435642766497878e-05, + "loss": 3.9112, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4348041717468257e-05, + "loss": 3.9058, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4339655769957737e-05, + "loss": 3.9096, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4331269822447217e-05, + "loss": 3.9057, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4322883874936697e-05, + "loss": 3.9121, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4314497927426177e-05, + "loss": 3.9081, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4306111979915657e-05, + "loss": 3.8959, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.42977587900126e-05, + "loss": 3.9101, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4289372842502078e-05, + "loss": 3.8985, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4280986894991558e-05, + "loss": 3.9133, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4272600947481038e-05, + "loss": 3.9061, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4264214999970518e-05, + "loss": 3.8936, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4255829052459998e-05, + "loss": 3.9098, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424744310494948e-05, + "loss": 3.9011, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.423905715743896e-05, + "loss": 3.9053, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423068758873217e-05, + "loss": 3.8948, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422231802002538e-05, + "loss": 3.9103, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421393207251486e-05, + "loss": 3.915, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4205546125004343e-05, + "loss": 3.9006, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4197160177493823e-05, + "loss": 3.89, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4188790608787032e-05, + "loss": 3.9045, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4180404661276512e-05, + "loss": 3.9016, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4172018713765992e-05, + "loss": 3.9149, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4163632766255472e-05, + "loss": 3.9063, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4155246818744952e-05, + "loss": 3.9004, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4146860871234435e-05, + "loss": 3.8964, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4138491302527644e-05, + "loss": 3.9124, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4130105355017124e-05, + "loss": 3.888, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4121719407506604e-05, + "loss": 3.8975, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4113349838799813e-05, + "loss": 3.902, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4104963891289296e-05, + "loss": 3.9098, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4096577943778776e-05, + "loss": 3.8847, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4088191996268256e-05, + "loss": 3.9048, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4079806048757733e-05, + "loss": 3.8966, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4071420101247213e-05, + "loss": 3.9001, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4063034153736693e-05, + "loss": 3.8983, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4054648206226173e-05, + "loss": 3.893, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4046262258715653e-05, + "loss": 3.9115, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4037892690008865e-05, + "loss": 3.9048, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4029506742498345e-05, + "loss": 3.8984, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4021120794987825e-05, + "loss": 3.9001, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4012734847477305e-05, + "loss": 3.9017, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4004348899966785e-05, + "loss": 3.9058, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3995979331259998e-05, + "loss": 3.8859, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3987593383749478e-05, + "loss": 3.909, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3979207436238957e-05, + "loss": 3.8978, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3970821488728437e-05, + "loss": 3.9051, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3962435541217914e-05, + "loss": 3.8973, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3954049593707394e-05, + "loss": 3.91, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3945663646196874e-05, + "loss": 3.8998, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3937277698686357e-05, + "loss": 3.8961, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3928908129979566e-05, + "loss": 3.8882, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3920522182469046e-05, + "loss": 3.9129, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3912136234958526e-05, + "loss": 3.9044, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3903750287448006e-05, + "loss": 3.9063, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3895364339937486e-05, + "loss": 3.896, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.38869947712307e-05, + "loss": 3.9082, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.387860882372018e-05, + "loss": 3.909, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387022287620966e-05, + "loss": 3.8989, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386183692869914e-05, + "loss": 3.9013, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385345098118862e-05, + "loss": 3.9034, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3845081412481828e-05, + "loss": 3.908, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3836695464971308e-05, + "loss": 3.9093, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.382832589626452e-05, + "loss": 3.895, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3819939948754e-05, + "loss": 3.9044, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381155400124348e-05, + "loss": 3.9001, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380318443253669e-05, + "loss": 3.9024, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3794798485026172e-05, + "loss": 3.9094, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3786412537515652e-05, + "loss": 3.8966, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3778026590005132e-05, + "loss": 3.9082, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3769640642494612e-05, + "loss": 3.8961, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3761254694984092e-05, + "loss": 3.908, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 4.044469833374023, + "eval_runtime": 291.1078, + "eval_samples_per_second": 1310.824, + "eval_steps_per_second": 40.964, + "step": 1602704 + }, + { + "epoch": 0.0, + "learning_rate": 2.375286874747357e-05, + "loss": 3.8979, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374448279996305e-05, + "loss": 3.9041, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373609685245253e-05, + "loss": 3.9108, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3727710904942012e-05, + "loss": 3.9049, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3719324957431492e-05, + "loss": 3.9138, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3710939009920972e-05, + "loss": 3.8945, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3702553062410452e-05, + "loss": 3.8978, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369416711489993e-05, + "loss": 3.8922, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368578116738941e-05, + "loss": 3.91, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.367739521987889e-05, + "loss": 3.9063, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.36690256511721e-05, + "loss": 3.9056, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.366063970366158e-05, + "loss": 3.9024, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.365225375615106e-05, + "loss": 3.897, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.364386780864054e-05, + "loss": 3.8946, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.363548186113002e-05, + "loss": 3.8979, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.36270959136195e-05, + "loss": 3.8867, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.361870996610898e-05, + "loss": 3.8997, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.361032401859846e-05, + "loss": 3.8939, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.360193807108794e-05, + "loss": 3.8932, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.359355212357742e-05, + "loss": 3.9265, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.35851661760669e-05, + "loss": 3.8976, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357678022855638e-05, + "loss": 3.9049, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.356839428104586e-05, + "loss": 3.905, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.356002471233907e-05, + "loss": 3.9044, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3551638764828553e-05, + "loss": 3.8969, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3543269196121762e-05, + "loss": 3.8951, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3534883248611242e-05, + "loss": 3.9053, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3526497301100722e-05, + "loss": 3.8887, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3518111353590202e-05, + "loss": 3.8956, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.350972540607968e-05, + "loss": 3.8905, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350133945856916e-05, + "loss": 3.8958, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.349295351105864e-05, + "loss": 3.902, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.348456756354812e-05, + "loss": 3.9058, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.34761816160376e-05, + "loss": 3.8969, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3467828426134543e-05, + "loss": 3.8999, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3459442478624023e-05, + "loss": 3.9088, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.3451056531113506e-05, + "loss": 3.8954, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.3442670583602986e-05, + "loss": 3.9039, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3434284636092463e-05, + "loss": 3.8907, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3425898688581943e-05, + "loss": 3.9043, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3417512741071423e-05, + "loss": 3.8883, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3409126793560903e-05, + "loss": 3.9154, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3400740846050383e-05, + "loss": 3.902, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3392354898539863e-05, + "loss": 3.899, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3383968951029346e-05, + "loss": 3.9059, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3375583003518823e-05, + "loss": 3.8998, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3367213434812035e-05, + "loss": 3.9045, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3358827487301515e-05, + "loss": 3.8886, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.335044153979099e-05, + "loss": 3.8852, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3342055592280475e-05, + "loss": 3.9108, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3333686023573687e-05, + "loss": 3.901, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3325300076063167e-05, + "loss": 3.9025, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3316914128552644e-05, + "loss": 3.8925, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3308528181042124e-05, + "loss": 3.8949, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3300142233531604e-05, + "loss": 3.89, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3291772664824816e-05, + "loss": 3.9021, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3283386717314296e-05, + "loss": 3.9003, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.327501714860751e-05, + "loss": 3.9116, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.326663120109699e-05, + "loss": 3.9033, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3258245253586465e-05, + "loss": 3.8947, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3249859306075945e-05, + "loss": 3.8942, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.324147335856543e-05, + "loss": 3.9043, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.323308741105491e-05, + "loss": 3.8883, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3224717842348118e-05, + "loss": 3.8971, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321634827364133e-05, + "loss": 3.898, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.320796232613081e-05, + "loss": 3.9028, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.319957637862029e-05, + "loss": 3.8852, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.319119043110977e-05, + "loss": 3.8919, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.318280448359925e-05, + "loss": 3.8853, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317441853608873e-05, + "loss": 3.9072, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316603258857821e-05, + "loss": 3.9003, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.315764664106769e-05, + "loss": 3.8998, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.314926069355717e-05, + "loss": 3.8997, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3140874746046646e-05, + "loss": 3.8955, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3132505177339862e-05, + "loss": 3.9118, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3124119229829342e-05, + "loss": 3.8863, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3115733282318822e-05, + "loss": 3.9074, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.31073473348083e-05, + "loss": 3.8994, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.309896138729778e-05, + "loss": 3.8981, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309057543978726e-05, + "loss": 3.9053, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.308220587108047e-05, + "loss": 3.9, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.307381992356995e-05, + "loss": 3.9008, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.306543397605943e-05, + "loss": 3.9035, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.305704802854891e-05, + "loss": 3.8879, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.304866208103839e-05, + "loss": 3.9043, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304027613352787e-05, + "loss": 3.8936, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303189018601735e-05, + "loss": 3.9026, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302350423850683e-05, + "loss": 3.8991, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3015134669800043e-05, + "loss": 3.8886, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3006748722289523e-05, + "loss": 3.9005, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.2998362774779003e-05, + "loss": 3.8971, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.298997682726848e-05, + "loss": 3.8996, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.298159087975796e-05, + "loss": 3.8838, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297320493224744e-05, + "loss": 3.903, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2964818984736923e-05, + "loss": 3.9134, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2956449416030132e-05, + "loss": 3.8934, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2948063468519612e-05, + "loss": 3.8809, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2939677521009092e-05, + "loss": 3.8985, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2931291573498572e-05, + "loss": 3.8956, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2922905625988052e-05, + "loss": 3.9072, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2914519678477532e-05, + "loss": 3.9019, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2906150109770744e-05, + "loss": 3.8933, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2897764162260224e-05, + "loss": 3.8928, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2889378214749704e-05, + "loss": 3.9006, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2880992267239184e-05, + "loss": 3.8813, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287260631972866e-05, + "loss": 3.8926, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2864236751021877e-05, + "loss": 3.8924, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2855867182315086e-05, + "loss": 3.9016, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2847481234804566e-05, + "loss": 3.8793, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2839095287294046e-05, + "loss": 3.8947, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2830709339783526e-05, + "loss": 3.8901, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2822323392273006e-05, + "loss": 3.8932, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2813937444762486e-05, + "loss": 3.8955, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2805551497251966e-05, + "loss": 3.8869, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2797165549741446e-05, + "loss": 3.9019, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2788779602230925e-05, + "loss": 3.9019, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2780426412327867e-05, + "loss": 3.889, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2772040464817347e-05, + "loss": 3.8976, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276365451730683e-05, + "loss": 3.8862, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2755268569796307e-05, + "loss": 3.905, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2746882622285787e-05, + "loss": 3.8852, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2738496674775267e-05, + "loss": 3.9007, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2730110727264747e-05, + "loss": 3.8876, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2721724779754227e-05, + "loss": 3.8977, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2713338832243707e-05, + "loss": 3.8917, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2704952884733187e-05, + "loss": 3.9021, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2696566937222667e-05, + "loss": 3.893, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.268819736851588e-05, + "loss": 3.8955, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.267981142100536e-05, + "loss": 3.878, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267142547349484e-05, + "loss": 3.9119, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2663039525984316e-05, + "loss": 3.8932, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.26546535784738e-05, + "loss": 3.9035, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.264626763096328e-05, + "loss": 3.8871, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.263788168345276e-05, + "loss": 3.9039, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.262949573594224e-05, + "loss": 3.9023, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262110978843172e-05, + "loss": 3.8935, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2612740219724928e-05, + "loss": 3.8939, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.260437065101814e-05, + "loss": 3.8997, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.259598470350762e-05, + "loss": 3.9002, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.25875987559971e-05, + "loss": 3.9077, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.257921280848658e-05, + "loss": 3.8818, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257082686097606e-05, + "loss": 3.9003, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256244091346554e-05, + "loss": 3.891, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255405496595502e-05, + "loss": 3.8991, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.25456690184445e-05, + "loss": 3.901, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.253728307093398e-05, + "loss": 3.8873, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.252889712342346e-05, + "loss": 3.9044, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.25205439335204e-05, + "loss": 3.8916, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251215798600988e-05, + "loss": 3.9004, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 4.0419111251831055, + "eval_runtime": 301.7752, + "eval_samples_per_second": 1264.488, + "eval_steps_per_second": 39.516, + "step": 1679024 + }, + { + "epoch": 1.0, + "learning_rate": 2.250377203849936e-05, + "loss": 3.8919, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.249538609098884e-05, + "loss": 3.8975, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.248700014347832e-05, + "loss": 3.9035, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2478630574771534e-05, + "loss": 3.8973, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2470261006064743e-05, + "loss": 3.9052, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2461875058554223e-05, + "loss": 3.8956, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2453489111043703e-05, + "loss": 3.8872, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.2445103163533186e-05, + "loss": 3.8867, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.2436717216022666e-05, + "loss": 3.903, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2428331268512143e-05, + "loss": 3.9029, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2419945321001623e-05, + "loss": 3.8961, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2411575752294835e-05, + "loss": 3.8984, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2403206183588048e-05, + "loss": 3.8873, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2394820236077528e-05, + "loss": 3.8891, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2386434288567008e-05, + "loss": 3.8933, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2378048341056488e-05, + "loss": 3.8816, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2369662393545968e-05, + "loss": 3.8945, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2361276446035444e-05, + "loss": 3.8836, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2352890498524924e-05, + "loss": 3.8888, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2344504551014407e-05, + "loss": 3.9231, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2336118603503887e-05, + "loss": 3.8897, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2327732655993367e-05, + "loss": 3.8968, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2319346708482847e-05, + "loss": 3.899, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2310960760972324e-05, + "loss": 3.9009, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2302591192265536e-05, + "loss": 3.8825, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2294205244755016e-05, + "loss": 3.8926, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2285819297244496e-05, + "loss": 3.8963, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2277433349733976e-05, + "loss": 3.8827, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2269047402223456e-05, + "loss": 3.8898, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226067783351667e-05, + "loss": 3.8836, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.2252291886006145e-05, + "loss": 3.8912, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.2243905938495625e-05, + "loss": 3.8995, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.223551999098511e-05, + "loss": 3.8945, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.222715042227832e-05, + "loss": 3.8923, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.2218764474767798e-05, + "loss": 3.8917, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.2210378527257277e-05, + "loss": 3.9037, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.2201992579746757e-05, + "loss": 3.8879, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.2193606632236237e-05, + "loss": 3.8995, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.2185220684725717e-05, + "loss": 3.8783, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.21768347372152e-05, + "loss": 3.9018, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.216844878970468e-05, + "loss": 3.8755, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.216007922099789e-05, + "loss": 3.9088, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.215169327348737e-05, + "loss": 3.8955, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214330732597685e-05, + "loss": 3.8966, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.2134921378466326e-05, + "loss": 3.8972, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.2126551809759542e-05, + "loss": 3.8934, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2118165862249022e-05, + "loss": 3.8957, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2109779914738502e-05, + "loss": 3.8871, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210139396722798e-05, + "loss": 3.8755, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209302439852119e-05, + "loss": 3.9062, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208463845101067e-05, + "loss": 3.8933, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.2076252503500154e-05, + "loss": 3.9006, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.206786655598963e-05, + "loss": 3.8846, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.205948060847911e-05, + "loss": 3.8911, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2051111039772323e-05, + "loss": 3.8811, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2042741471065532e-05, + "loss": 3.8968, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2034355523555016e-05, + "loss": 3.8929, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.2025969576044496e-05, + "loss": 3.9056, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.2017583628533976e-05, + "loss": 3.8984, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2009197681023452e-05, + "loss": 3.8869, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2000811733512932e-05, + "loss": 3.8897, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1992425786002412e-05, + "loss": 3.8989, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1984039838491892e-05, + "loss": 3.8817, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1975670269785105e-05, + "loss": 3.8899, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1967300701078317e-05, + "loss": 3.8921, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1958914753567797e-05, + "loss": 3.9015, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1950528806057274e-05, + "loss": 3.8732, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1942142858546754e-05, + "loss": 3.8853, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1933756911036234e-05, + "loss": 3.8803, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1925370963525717e-05, + "loss": 3.8936, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1916985016015197e-05, + "loss": 3.8951, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1908599068504677e-05, + "loss": 3.8927, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1900213120994157e-05, + "loss": 3.8921, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1891827173483633e-05, + "loss": 3.8874, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1883441225973113e-05, + "loss": 3.9093, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1875071657266326e-05, + "loss": 3.8802, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.186668570975581e-05, + "loss": 3.8978, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1858299762245286e-05, + "loss": 3.8908, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1849913814734766e-05, + "loss": 3.8925, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1841527867224246e-05, + "loss": 3.8991, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1833174677321187e-05, + "loss": 3.8908, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.182478872981067e-05, + "loss": 3.8945, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.181640278230015e-05, + "loss": 3.8993, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.180801683478963e-05, + "loss": 3.8806, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.1799630887279107e-05, + "loss": 3.8959, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.1791244939768587e-05, + "loss": 3.8908, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1782858992258067e-05, + "loss": 3.8982, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1774473044747547e-05, + "loss": 3.8899, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1766087097237027e-05, + "loss": 3.884, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.175770114972651e-05, + "loss": 3.8919, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1749315202215987e-05, + "loss": 3.8943, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.1740929254705467e-05, + "loss": 3.8912, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.173255968599868e-05, + "loss": 3.8784, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172417373848816e-05, + "loss": 3.8953, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171580416978137e-05, + "loss": 3.9034, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.170741822227085e-05, + "loss": 3.8886, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.169903227476033e-05, + "loss": 3.8711, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.169066270605354e-05, + "loss": 3.8903, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168227675854302e-05, + "loss": 3.891, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.16738908110325e-05, + "loss": 3.8977, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166550486352198e-05, + "loss": 3.8973, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.165711891601146e-05, + "loss": 3.8873, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.164873296850094e-05, + "loss": 3.8837, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164034702099042e-05, + "loss": 3.8963, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.16319610734799e-05, + "loss": 3.8742, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162357512596938e-05, + "loss": 3.8884, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161520555726259e-05, + "loss": 3.882, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.1606819609752073e-05, + "loss": 3.8988, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.1598433662241553e-05, + "loss": 3.8734, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1590047714731033e-05, + "loss": 3.8873, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1581661767220513e-05, + "loss": 3.8833, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1573275819709993e-05, + "loss": 3.8868, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.15649062510032e-05, + "loss": 3.8866, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.155652030349268e-05, + "loss": 3.8814, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1548134355982165e-05, + "loss": 3.8933, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.153974840847164e-05, + "loss": 3.8938, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1531378839764854e-05, + "loss": 3.8803, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1522992892254334e-05, + "loss": 3.8978, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1514606944743814e-05, + "loss": 3.8832, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1506220997233294e-05, + "loss": 3.8933, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1497851428526506e-05, + "loss": 3.8814, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1489465481015986e-05, + "loss": 3.8898, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1481079533505466e-05, + "loss": 3.8807, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1472693585994943e-05, + "loss": 3.8909, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1464307638484423e-05, + "loss": 3.8893, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1455921690973903e-05, + "loss": 3.8899, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1447535743463386e-05, + "loss": 3.8848, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1439149795952866e-05, + "loss": 3.8883, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1430763848442346e-05, + "loss": 3.8721, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1422377900931823e-05, + "loss": 3.9008, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1413991953421303e-05, + "loss": 3.8884, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1405622384714515e-05, + "loss": 3.8924, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1397252816007728e-05, + "loss": 3.8819, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1388866868497207e-05, + "loss": 3.8982, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1380480920986687e-05, + "loss": 3.893, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1372094973476167e-05, + "loss": 3.8865, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1363709025965647e-05, + "loss": 3.8883, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1355323078455124e-05, + "loss": 3.89, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1346937130944604e-05, + "loss": 3.8921, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.133856756223782e-05, + "loss": 3.9061, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1330181614727296e-05, + "loss": 3.8735, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.1321795667216776e-05, + "loss": 3.8934, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.1313409719706256e-05, + "loss": 3.8832, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.1305023772195736e-05, + "loss": 3.8961, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.1296637824685216e-05, + "loss": 3.8898, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.1288251877174696e-05, + "loss": 3.8821, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.127986592966418e-05, + "loss": 3.9019, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127149636095739e-05, + "loss": 3.887, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.126311041344687e-05, + "loss": 3.893, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 4.039084434509277, + "eval_runtime": 307.7668, + "eval_samples_per_second": 1239.871, + "eval_steps_per_second": 38.747, + "step": 1755344 + }, + { + "epoch": 0.0, + "learning_rate": 2.125472446593635e-05, + "loss": 3.8879, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.124633851842583e-05, + "loss": 3.8881, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1237952570915305e-05, + "loss": 3.8955, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1229566623404788e-05, + "loss": 3.8942, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1221180675894268e-05, + "loss": 3.897, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1212794728383748e-05, + "loss": 3.8893, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1204408780873228e-05, + "loss": 3.8813, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1196022833362708e-05, + "loss": 3.8811, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1187636885852185e-05, + "loss": 3.8955, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1179250938341665e-05, + "loss": 3.8963, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1170864990831145e-05, + "loss": 3.8862, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1162479043320628e-05, + "loss": 3.8932, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1154109474613837e-05, + "loss": 3.8811, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1145723527103317e-05, + "loss": 3.8849, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1137337579592797e-05, + "loss": 3.8864, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1128951632082277e-05, + "loss": 3.8759, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1120565684571757e-05, + "loss": 3.8883, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1112179737061237e-05, + "loss": 3.8764, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1103793789550717e-05, + "loss": 3.8813, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1095407842040197e-05, + "loss": 3.9141, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1087021894529677e-05, + "loss": 3.8855, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1078635947019157e-05, + "loss": 3.8885, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1070266378312366e-05, + "loss": 3.8911, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106188043080185e-05, + "loss": 3.8963, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105349448329133e-05, + "loss": 3.8737, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.104510853578081e-05, + "loss": 3.8875, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.103672258827029e-05, + "loss": 3.8904, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.102833664075977e-05, + "loss": 3.8802, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1019967072052978e-05, + "loss": 3.8817, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1011581124542458e-05, + "loss": 3.8772, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100319517703194e-05, + "loss": 3.8876, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.099480922952142e-05, + "loss": 3.8911, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0986423282010898e-05, + "loss": 3.8902, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0978037334500378e-05, + "loss": 3.8839, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.096966776579359e-05, + "loss": 3.8884, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096128181828307e-05, + "loss": 3.8947, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095289587077255e-05, + "loss": 3.8801, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094450992326203e-05, + "loss": 3.8941, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093612397575151e-05, + "loss": 3.8739, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.092773802824099e-05, + "loss": 3.893, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.09193684595342e-05, + "loss": 3.8732, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.091098251202368e-05, + "loss": 3.9021, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090259656451316e-05, + "loss": 3.8878, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0894210617002642e-05, + "loss": 3.8891, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0885824669492122e-05, + "loss": 3.8887, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0877438721981602e-05, + "loss": 3.8861, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.086906915327481e-05, + "loss": 3.8911, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086068320576429e-05, + "loss": 3.882, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085229725825377e-05, + "loss": 3.862, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084391131074325e-05, + "loss": 3.9037, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083552536323273e-05, + "loss": 3.8829, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.082713941572221e-05, + "loss": 3.8979, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0818769847015424e-05, + "loss": 3.8772, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0810383899504904e-05, + "loss": 3.8836, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080199795199438e-05, + "loss": 3.8736, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079361200448386e-05, + "loss": 3.8926, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0785226056973343e-05, + "loss": 3.8891, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0776840109462823e-05, + "loss": 3.8937, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0768454161952303e-05, + "loss": 3.8961, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0760068214441783e-05, + "loss": 3.8788, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.075168226693126e-05, + "loss": 3.8808, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0743312698224472e-05, + "loss": 3.8964, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0734926750713952e-05, + "loss": 3.8735, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0726540803203436e-05, + "loss": 3.8819, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0718154855692912e-05, + "loss": 3.8845, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0709801665789854e-05, + "loss": 3.8967, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0701415718279334e-05, + "loss": 3.8727, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0693029770768814e-05, + "loss": 3.8752, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0684643823258297e-05, + "loss": 3.8744, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0676257875747777e-05, + "loss": 3.8858, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0667871928237257e-05, + "loss": 3.8875, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0659485980726734e-05, + "loss": 3.8902, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0651100033216214e-05, + "loss": 3.8872, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0642730464509426e-05, + "loss": 3.8799, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0634344516998906e-05, + "loss": 3.9024, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0625958569488386e-05, + "loss": 3.8741, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0617572621977866e-05, + "loss": 3.8928, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.060920305327108e-05, + "loss": 3.8888, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060081710576056e-05, + "loss": 3.881, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0592431158250035e-05, + "loss": 3.8916, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0584045210739515e-05, + "loss": 3.886, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0575659263228998e-05, + "loss": 3.8858, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0567273315718478e-05, + "loss": 3.8936, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0558887368207958e-05, + "loss": 3.8776, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0550517799501167e-05, + "loss": 3.8883, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0542131851990647e-05, + "loss": 3.8839, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0533745904480127e-05, + "loss": 3.8935, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0525359956969607e-05, + "loss": 3.8809, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.051699038826282e-05, + "loss": 3.8784, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.05086044407523e-05, + "loss": 3.8825, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050021849324178e-05, + "loss": 3.8919, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049183254573126e-05, + "loss": 3.8828, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0483446598220736e-05, + "loss": 3.8721, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.047506065071022e-05, + "loss": 3.8923, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.04666747031997e-05, + "loss": 3.8935, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.045828875568918e-05, + "loss": 3.8857, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.044990280817866e-05, + "loss": 3.867, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044151686066814e-05, + "loss": 3.8826, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043313091315762e-05, + "loss": 3.8804, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0424744965647096e-05, + "loss": 3.8945, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0416375396940308e-05, + "loss": 3.8903, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.040798944942979e-05, + "loss": 3.8789, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.039960350191927e-05, + "loss": 3.8824, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0391217554408748e-05, + "loss": 3.8852, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038284798570196e-05, + "loss": 3.8705, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.037446203819144e-05, + "loss": 3.8795, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036607609068092e-05, + "loss": 3.8741, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0357722900777862e-05, + "loss": 3.8945, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0349336953267342e-05, + "loss": 3.867, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0340951005756822e-05, + "loss": 3.8774, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0332565058246302e-05, + "loss": 3.8769, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0324179110735782e-05, + "loss": 3.8879, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0315793163225262e-05, + "loss": 3.8728, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0307407215714745e-05, + "loss": 3.8754, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0299037647007954e-05, + "loss": 3.8866, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0290651699497434e-05, + "loss": 3.8878, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0282282130790643e-05, + "loss": 3.8742, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0273896183280123e-05, + "loss": 3.8923, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0265510235769607e-05, + "loss": 3.8755, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0257124288259087e-05, + "loss": 3.8838, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0248738340748567e-05, + "loss": 3.8806, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0240352393238043e-05, + "loss": 3.881, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0231966445727523e-05, + "loss": 3.8805, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0223580498217003e-05, + "loss": 3.8863, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0215210929510216e-05, + "loss": 3.8851, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0206824981999696e-05, + "loss": 3.8845, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0198439034489175e-05, + "loss": 3.878, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0190053086978655e-05, + "loss": 3.8791, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0181667139468135e-05, + "loss": 3.8682, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0173281191957615e-05, + "loss": 3.8959, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0164895244447095e-05, + "loss": 3.8798, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0156509296936575e-05, + "loss": 3.8858, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0148123349426055e-05, + "loss": 3.8776, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0139737401915535e-05, + "loss": 3.8946, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0131351454405015e-05, + "loss": 3.8873, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0122965506894495e-05, + "loss": 3.8804, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0114579559383975e-05, + "loss": 3.8823, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0106209990677184e-05, + "loss": 3.8845, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.009787317957786e-05, + "loss": 3.8857, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0089487232067338e-05, + "loss": 3.8996, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0081101284556818e-05, + "loss": 3.8663, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.0072715337046298e-05, + "loss": 3.8912, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.006432938953578e-05, + "loss": 3.8799, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.005594344202526e-05, + "loss": 3.888, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.004755749451474e-05, + "loss": 3.8815, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.003917154700422e-05, + "loss": 3.8801, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0030785599493698e-05, + "loss": 3.8882, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0022399651983178e-05, + "loss": 3.8843, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0014013704472658e-05, + "loss": 3.8861, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 4.037192344665527, + "eval_runtime": 357.7768, + "eval_samples_per_second": 1066.562, + "eval_steps_per_second": 33.331, + "step": 1831664 + }, + { + "epoch": 1.0, + "learning_rate": 2.0005627756962138e-05, + "loss": 3.8856, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.999724180945162e-05, + "loss": 3.8816, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.99888558619411e-05, + "loss": 3.8893, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9980469914430578e-05, + "loss": 3.889, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9972083966920058e-05, + "loss": 3.8929, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9963698019409538e-05, + "loss": 3.8774, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995532845070275e-05, + "loss": 3.8768, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994694250319223e-05, + "loss": 3.8783, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.993855655568171e-05, + "loss": 3.8879, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993017060817119e-05, + "loss": 3.8928, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9921801039464402e-05, + "loss": 3.8762, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991341509195388e-05, + "loss": 3.8874, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9905061902050824e-05, + "loss": 3.8792, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9896675954540304e-05, + "loss": 3.876, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9888290007029784e-05, + "loss": 3.8808, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9879904059519264e-05, + "loss": 3.8677, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9871518112008744e-05, + "loss": 3.8829, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9863132164498224e-05, + "loss": 3.8715, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.98547462169877e-05, + "loss": 3.8741, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9846360269477184e-05, + "loss": 3.9076, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.9837974321966664e-05, + "loss": 3.8851, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9829588374456144e-05, + "loss": 3.8795, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9821202426945624e-05, + "loss": 3.8871, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9812832858238833e-05, + "loss": 3.8895, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9804446910728313e-05, + "loss": 3.8668, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9796060963217793e-05, + "loss": 3.8823, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9787691394511005e-05, + "loss": 3.8837, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9779305447000485e-05, + "loss": 3.8747, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9770919499489965e-05, + "loss": 3.8724, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9762533551979445e-05, + "loss": 3.8772, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9754147604468925e-05, + "loss": 3.875, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9745761656958405e-05, + "loss": 3.8867, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9737375709447885e-05, + "loss": 3.884, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9728989761937365e-05, + "loss": 3.8804, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9720620193230577e-05, + "loss": 3.8828, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9712234245720057e-05, + "loss": 3.8864, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9703848298209534e-05, + "loss": 3.8817, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9695478729502746e-05, + "loss": 3.8846, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.968709278199223e-05, + "loss": 3.8679, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9678706834481706e-05, + "loss": 3.8848, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9670320886971186e-05, + "loss": 3.8706, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9661934939460666e-05, + "loss": 3.8956, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9653548991950146e-05, + "loss": 3.8844, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9645163044439626e-05, + "loss": 3.8796, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9636777096929106e-05, + "loss": 3.8872, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.962840752822232e-05, + "loss": 3.8794, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.96200215807118e-05, + "loss": 3.8865, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9611635633201278e-05, + "loss": 3.8779, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9603249685690758e-05, + "loss": 3.8547, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.9594863738180238e-05, + "loss": 3.8947, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9586477790669715e-05, + "loss": 3.8774, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9578091843159198e-05, + "loss": 3.8935, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9569705895648678e-05, + "loss": 3.8742, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9561336326941887e-05, + "loss": 3.8772, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9552950379431367e-05, + "loss": 3.8685, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954458081072458e-05, + "loss": 3.8849, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953619486321406e-05, + "loss": 3.8849, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.952780891570354e-05, + "loss": 3.8864, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.951942296819302e-05, + "loss": 3.8942, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9511053399486232e-05, + "loss": 3.8757, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9502667451975712e-05, + "loss": 3.8708, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949428150446519e-05, + "loss": 3.893, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948589555695467e-05, + "loss": 3.8715, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.947750960944415e-05, + "loss": 3.8751, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9469123661933632e-05, + "loss": 3.8786, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946073771442311e-05, + "loss": 3.8859, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.945235176691259e-05, + "loss": 3.8689, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9443965819402068e-05, + "loss": 3.8708, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943559625069528e-05, + "loss": 3.8677, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.942721030318476e-05, + "loss": 3.878, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.941882435567424e-05, + "loss": 3.887, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.941043840816372e-05, + "loss": 3.881, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.94020524606532e-05, + "loss": 3.8803, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9393682891946413e-05, + "loss": 3.8788, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.938529694443589e-05, + "loss": 3.8961, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9376927375729102e-05, + "loss": 3.8706, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9368541428218585e-05, + "loss": 3.886, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9360155480708065e-05, + "loss": 3.8838, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9351769533197542e-05, + "loss": 3.8719, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9343383585687022e-05, + "loss": 3.8881, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9334997638176502e-05, + "loss": 3.884, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9326611690665982e-05, + "loss": 3.8802, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9318225743155462e-05, + "loss": 3.8856, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9309839795644942e-05, + "loss": 3.8732, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9301470226938154e-05, + "loss": 3.8778, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9293084279427634e-05, + "loss": 3.8809, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9284698331917114e-05, + "loss": 3.8878, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9276312384406594e-05, + "loss": 3.8742, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9267942815699807e-05, + "loss": 3.8762, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9259556868189286e-05, + "loss": 3.874, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9251170920678766e-05, + "loss": 3.8868, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9242784973168246e-05, + "loss": 3.8808, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9234399025657723e-05, + "loss": 3.8683, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9226029456950935e-05, + "loss": 3.8849, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9217643509440415e-05, + "loss": 3.8875, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9209257561929895e-05, + "loss": 3.8809, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9200871614419375e-05, + "loss": 3.861, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9192485666908855e-05, + "loss": 3.8769, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9184099719398335e-05, + "loss": 3.8733, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9175713771887815e-05, + "loss": 3.89, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9167344203181024e-05, + "loss": 3.8841, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9158958255670508e-05, + "loss": 3.88, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9150572308159988e-05, + "loss": 3.8755, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9142186360649468e-05, + "loss": 3.876, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9133800413138947e-05, + "loss": 3.8703, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9125414465628427e-05, + "loss": 3.8736, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9117044896921637e-05, + "loss": 3.8693, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9108658949411117e-05, + "loss": 3.8882, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.91002730019006e-05, + "loss": 3.8638, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.909188705439008e-05, + "loss": 3.8705, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.908351748568329e-05, + "loss": 3.8715, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.907513153817277e-05, + "loss": 3.8796, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.906674559066225e-05, + "loss": 3.8726, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9058359643151725e-05, + "loss": 3.8689, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.904997369564121e-05, + "loss": 3.8823, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.904160412693442e-05, + "loss": 3.8869, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.90332181794239e-05, + "loss": 3.8684, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9024832231913378e-05, + "loss": 3.8846, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9016446284402858e-05, + "loss": 3.8726, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9008060336892338e-05, + "loss": 3.8789, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.8999674389381818e-05, + "loss": 3.8753, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.89912884418713e-05, + "loss": 3.8733, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.898290249436078e-05, + "loss": 3.8722, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.897453292565399e-05, + "loss": 3.8822, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896614697814347e-05, + "loss": 3.8839, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.895776103063295e-05, + "loss": 3.8771, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.894937508312243e-05, + "loss": 3.8733, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8941005514415642e-05, + "loss": 3.8777, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893263594570885e-05, + "loss": 3.8611, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892424999819833e-05, + "loss": 3.8917, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.891586405068781e-05, + "loss": 3.8714, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.890747810317729e-05, + "loss": 3.8839, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.889909215566677e-05, + "loss": 3.8733, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.8890706208156255e-05, + "loss": 3.8872, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.8882320260645735e-05, + "loss": 3.8789, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.8873950691938944e-05, + "loss": 3.8783, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8865564744428424e-05, + "loss": 3.8797, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8857178796917904e-05, + "loss": 3.8773, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.884879284940738e-05, + "loss": 3.882, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8840406901896863e-05, + "loss": 3.8939, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8832020954386343e-05, + "loss": 3.8616, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8823635006875823e-05, + "loss": 3.8883, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8815249059365303e-05, + "loss": 3.8708, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8806879490658512e-05, + "loss": 3.8831, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8798509921951725e-05, + "loss": 3.8764, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8790123974441205e-05, + "loss": 3.8746, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8781738026930685e-05, + "loss": 3.8816, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8773352079420165e-05, + "loss": 3.8814, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8764982510713377e-05, + "loss": 3.8812, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 4.034798622131348, + "eval_runtime": 355.5342, + "eval_samples_per_second": 1073.289, + "eval_steps_per_second": 33.541, + "step": 1907984 + }, + { + "epoch": 0.0, + "learning_rate": 1.8756596563202854e-05, + "loss": 3.8791, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8748210615692334e-05, + "loss": 3.8766, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8739824668181817e-05, + "loss": 3.8872, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8731438720671297e-05, + "loss": 3.8808, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8723052773160777e-05, + "loss": 3.8867, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8714666825650257e-05, + "loss": 3.8766, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8706280878139737e-05, + "loss": 3.8709, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8697894930629214e-05, + "loss": 3.8735, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8689508983118693e-05, + "loss": 3.8833, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8681123035608173e-05, + "loss": 3.8878, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8672737088097657e-05, + "loss": 3.8733, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8664351140587137e-05, + "loss": 3.8797, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8655981571880346e-05, + "loss": 3.8759, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8647595624369826e-05, + "loss": 3.8714, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8639209676859306e-05, + "loss": 3.8751, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8630823729348786e-05, + "loss": 3.8652, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8622437781838266e-05, + "loss": 3.8742, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8614051834327746e-05, + "loss": 3.8665, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8605665886817226e-05, + "loss": 3.872, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8597279939306706e-05, + "loss": 3.8957, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8588893991796185e-05, + "loss": 3.8818, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.8580508044285665e-05, + "loss": 3.8781, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8572122096775145e-05, + "loss": 3.88, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8563752528068358e-05, + "loss": 3.8863, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8555366580557838e-05, + "loss": 3.8611, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8546980633047318e-05, + "loss": 3.8758, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8538594685536798e-05, + "loss": 3.8789, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.8530225116830007e-05, + "loss": 3.8688, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8521839169319487e-05, + "loss": 3.8685, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.851345322180897e-05, + "loss": 3.8727, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.850506727429845e-05, + "loss": 3.871, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8496681326787927e-05, + "loss": 3.8828, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8488295379277407e-05, + "loss": 3.8778, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.847992581057062e-05, + "loss": 3.8802, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847155624186383e-05, + "loss": 3.8722, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846317029435331e-05, + "loss": 3.88, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.845478434684279e-05, + "loss": 3.8802, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.844639839933227e-05, + "loss": 3.8757, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8438012451821748e-05, + "loss": 3.8627, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8429626504311228e-05, + "loss": 3.8796, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8421240556800708e-05, + "loss": 3.8693, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8412854609290188e-05, + "loss": 3.8869, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.84044850405834e-05, + "loss": 3.881, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.839609909307288e-05, + "loss": 3.8737, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.838771314556236e-05, + "loss": 3.8835, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.837932719805184e-05, + "loss": 3.8739, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837094125054132e-05, + "loss": 3.8833, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.83625553030308e-05, + "loss": 3.8734, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835416935552028e-05, + "loss": 3.8476, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834578340800976e-05, + "loss": 3.8894, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.833739746049924e-05, + "loss": 3.8761, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8329027891792453e-05, + "loss": 3.884, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.832064194428193e-05, + "loss": 3.871, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.831225599677141e-05, + "loss": 3.873, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8303886428064625e-05, + "loss": 3.8628, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8295500480554105e-05, + "loss": 3.8779, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.828711453304358e-05, + "loss": 3.8813, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.827872858553306e-05, + "loss": 3.8781, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827034263802254e-05, + "loss": 3.8899, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8261973069315754e-05, + "loss": 3.8721, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8253587121805234e-05, + "loss": 3.869, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8245201174294714e-05, + "loss": 3.8867, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8236815226784194e-05, + "loss": 3.8658, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8228429279273674e-05, + "loss": 3.8656, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8220043331763154e-05, + "loss": 3.8775, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8211657384252634e-05, + "loss": 3.8794, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.820327143674211e-05, + "loss": 3.8672, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.819488548923159e-05, + "loss": 3.8657, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8186499541721073e-05, + "loss": 3.8628, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8178113594210553e-05, + "loss": 3.8709, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8169727646700033e-05, + "loss": 3.8808, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8161358077993242e-05, + "loss": 3.8729, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8152972130482722e-05, + "loss": 3.8774, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8144586182972202e-05, + "loss": 3.871, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8136200235461682e-05, + "loss": 3.8968, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8127830666754895e-05, + "loss": 3.8645, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8119444719244375e-05, + "loss": 3.8832, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8111058771733855e-05, + "loss": 3.877, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8102672824223335e-05, + "loss": 3.8705, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8094286876712815e-05, + "loss": 3.882, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8085917308006027e-05, + "loss": 3.8801, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8077547739299236e-05, + "loss": 3.8766, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8069161791788716e-05, + "loss": 3.8792, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8060775844278196e-05, + "loss": 3.8713, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8052389896767676e-05, + "loss": 3.8728, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8044003949257156e-05, + "loss": 3.8781, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8035618001746636e-05, + "loss": 3.8781, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8027232054236116e-05, + "loss": 3.8699, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8018846106725596e-05, + "loss": 3.8726, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8010460159215076e-05, + "loss": 3.8709, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8002074211704556e-05, + "loss": 3.8803, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7993704642997765e-05, + "loss": 3.8761, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7985318695487248e-05, + "loss": 3.8651, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7976932747976728e-05, + "loss": 3.8803, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7968546800466208e-05, + "loss": 3.8799, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7960160852955688e-05, + "loss": 3.8784, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.7951791284248897e-05, + "loss": 3.8574, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794342171554211e-05, + "loss": 3.8699, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793503576803159e-05, + "loss": 3.8706, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792664982052107e-05, + "loss": 3.8839, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.791826387301055e-05, + "loss": 3.8814, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.790987792550003e-05, + "loss": 3.8755, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.790149197798951e-05, + "loss": 3.8732, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.789310603047899e-05, + "loss": 3.8707, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788472008296847e-05, + "loss": 3.8675, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787633413545795e-05, + "loss": 3.8705, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.786794818794743e-05, + "loss": 3.8647, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.785956224043691e-05, + "loss": 3.8788, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.785117629292639e-05, + "loss": 3.8676, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7842806724219598e-05, + "loss": 3.8609, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783443715551281e-05, + "loss": 3.869, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.782605120800229e-05, + "loss": 3.8703, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.781766526049177e-05, + "loss": 3.8696, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.780927931298125e-05, + "loss": 3.863, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780089336547073e-05, + "loss": 3.88, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.779250741796021e-05, + "loss": 3.8791, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.778412147044969e-05, + "loss": 3.8665, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7775751901742903e-05, + "loss": 3.8781, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7767365954232383e-05, + "loss": 3.8687, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7758980006721863e-05, + "loss": 3.8748, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7750594059211343e-05, + "loss": 3.8733, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7742208111700823e-05, + "loss": 3.8661, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7733838542994032e-05, + "loss": 3.8707, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7725452595483512e-05, + "loss": 3.873, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7717066647972995e-05, + "loss": 3.8801, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7708680700462475e-05, + "loss": 3.8695, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7700311131755684e-05, + "loss": 3.868, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7691941563048893e-05, + "loss": 3.8738, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7683555615538373e-05, + "loss": 3.8575, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7675169668027857e-05, + "loss": 3.8872, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7666783720517337e-05, + "loss": 3.8643, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7658397773006817e-05, + "loss": 3.883, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7650011825496297e-05, + "loss": 3.8653, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7641625877985773e-05, + "loss": 3.884, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7633239930475253e-05, + "loss": 3.878, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7624853982964733e-05, + "loss": 3.8705, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7616468035454213e-05, + "loss": 3.8753, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7608098466747425e-05, + "loss": 3.8701, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7599712519236905e-05, + "loss": 3.8801, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.7591326571726385e-05, + "loss": 3.8915, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.7582940624215865e-05, + "loss": 3.8561, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.7574554676705345e-05, + "loss": 3.8795, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7566168729194825e-05, + "loss": 3.8704, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7557782781684305e-05, + "loss": 3.8803, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7549396834173785e-05, + "loss": 3.8714, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7541043644270727e-05, + "loss": 3.8737, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7532657696760207e-05, + "loss": 3.8718, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7524271749249687e-05, + "loss": 3.8767, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7515885801739167e-05, + "loss": 3.8753, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 4.033708572387695, + "eval_runtime": 303.7272, + "eval_samples_per_second": 1256.361, + "eval_steps_per_second": 39.262, + "step": 1984304 + }, + { + "epoch": 0.0, + "learning_rate": 1.750749985422865e-05, + "loss": 3.8735, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.749911390671813e-05, + "loss": 3.8721, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7490727959207606e-05, + "loss": 3.8785, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7482342011697086e-05, + "loss": 3.8787, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7473956064186566e-05, + "loss": 3.8823, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7465570116676046e-05, + "loss": 3.8706, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7457184169165526e-05, + "loss": 3.8667, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7448798221655006e-05, + "loss": 3.8672, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.744041227414449e-05, + "loss": 3.875, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.7432026326633966e-05, + "loss": 3.8846, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.7423640379123446e-05, + "loss": 3.8698, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.7415254431612926e-05, + "loss": 3.8738, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.7406884862906135e-05, + "loss": 3.8771, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.7398498915395615e-05, + "loss": 3.8633, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.73901129678851e-05, + "loss": 3.8752, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738172702037458e-05, + "loss": 3.858, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737334107286406e-05, + "loss": 3.8672, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736495512535354e-05, + "loss": 3.8661, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.7356585556646747e-05, + "loss": 3.8652, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.7348199609136227e-05, + "loss": 3.8855, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.7339813661625707e-05, + "loss": 3.8817, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.733142771411519e-05, + "loss": 3.8739, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.732304176660467e-05, + "loss": 3.876, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7314655819094147e-05, + "loss": 3.8786, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7306269871583627e-05, + "loss": 3.8566, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7297883924073107e-05, + "loss": 3.8756, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7289497976562587e-05, + "loss": 3.875, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7281112029052067e-05, + "loss": 3.8606, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.727272608154155e-05, + "loss": 3.8643, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7264340134031027e-05, + "loss": 3.8657, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.725597056532424e-05, + "loss": 3.8725, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.724758461781372e-05, + "loss": 3.8719, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.72391986703032e-05, + "loss": 3.8701, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7230829101596412e-05, + "loss": 3.8819, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.722245953288962e-05, + "loss": 3.8668, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.72140735853791e-05, + "loss": 3.8786, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.720568763786858e-05, + "loss": 3.8792, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.719730169035806e-05, + "loss": 3.8671, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.718891574284754e-05, + "loss": 3.8605, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.718052979533702e-05, + "loss": 3.8716, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.71721438478265e-05, + "loss": 3.865, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.716375790031598e-05, + "loss": 3.8811, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.715537195280546e-05, + "loss": 3.8733, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7147002384098673e-05, + "loss": 3.8748, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.713861643658815e-05, + "loss": 3.8751, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.713023048907763e-05, + "loss": 3.8703, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7121844541567113e-05, + "loss": 3.8794, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7113458594056593e-05, + "loss": 3.8734, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7105072646546073e-05, + "loss": 3.8418, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7096703077839282e-05, + "loss": 3.8799, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7088317130328762e-05, + "loss": 3.8705, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7079931182818242e-05, + "loss": 3.8817, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7071545235307722e-05, + "loss": 3.8672, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7063159287797205e-05, + "loss": 3.8687, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7054773340286682e-05, + "loss": 3.8601, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704638739277616e-05, + "loss": 3.8737, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.703800144526564e-05, + "loss": 3.8791, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7029631876558854e-05, + "loss": 3.8712, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7021262307852067e-05, + "loss": 3.8893, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.7012876360341547e-05, + "loss": 3.8714, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.7004490412831027e-05, + "loss": 3.8557, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6996104465320503e-05, + "loss": 3.8859, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6987734896613716e-05, + "loss": 3.8611, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6979365327906928e-05, + "loss": 3.8596, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6970979380396408e-05, + "loss": 3.8748, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6962593432885888e-05, + "loss": 3.8754, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6954207485375368e-05, + "loss": 3.8627, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.6945821537864848e-05, + "loss": 3.862, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.6937435590354328e-05, + "loss": 3.8576, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6929049642843804e-05, + "loss": 3.865, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6920663695333284e-05, + "loss": 3.8791, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.69122941266265e-05, + "loss": 3.8718, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6903908179115977e-05, + "loss": 3.8722, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6895522231605457e-05, + "loss": 3.8676, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6887136284094937e-05, + "loss": 3.8837, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6878750336584417e-05, + "loss": 3.8631, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6870364389073897e-05, + "loss": 3.8761, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6861978441563377e-05, + "loss": 3.8727, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.685359249405286e-05, + "loss": 3.8666, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.684522292534607e-05, + "loss": 3.8751, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6836853356639278e-05, + "loss": 3.8761, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6828467409128758e-05, + "loss": 3.869, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6820081461618238e-05, + "loss": 3.8784, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.681169551410772e-05, + "loss": 3.8633, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.68033095665972e-05, + "loss": 3.8682, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.679493999789041e-05, + "loss": 3.8696, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6786570429183623e-05, + "loss": 3.8745, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.67781844816731e-05, + "loss": 3.8679, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6769798534162583e-05, + "loss": 3.8667, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6761412586652063e-05, + "loss": 3.8677, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6753043017945275e-05, + "loss": 3.8733, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6744657070434752e-05, + "loss": 3.873, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6736271122924232e-05, + "loss": 3.858, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6727885175413712e-05, + "loss": 3.8774, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.671949922790319e-05, + "loss": 3.8754, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6711113280392675e-05, + "loss": 3.8742, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6702727332882155e-05, + "loss": 3.8494, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.669434138537163e-05, + "loss": 3.8684, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668595543786111e-05, + "loss": 3.866, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6677585869154324e-05, + "loss": 3.8802, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6669199921643804e-05, + "loss": 3.8743, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6660813974133284e-05, + "loss": 3.8709, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6652428026622764e-05, + "loss": 3.8687, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6644042079112244e-05, + "loss": 3.8651, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6635656131601724e-05, + "loss": 3.8612, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6627270184091204e-05, + "loss": 3.8642, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6618884236580684e-05, + "loss": 3.862, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6610514667873893e-05, + "loss": 3.8728, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6602128720363376e-05, + "loss": 3.86, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6593742772852856e-05, + "loss": 3.8602, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6585356825342336e-05, + "loss": 3.8588, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6576970877831813e-05, + "loss": 3.8663, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6568584930321293e-05, + "loss": 3.8639, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6560198982810773e-05, + "loss": 3.8573, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6551813035300252e-05, + "loss": 3.8745, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6543443466593465e-05, + "loss": 3.8734, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6535057519082945e-05, + "loss": 3.8623, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6526671571572425e-05, + "loss": 3.872, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6518302002865637e-05, + "loss": 3.8639, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6509916055355114e-05, + "loss": 3.8682, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.650154648664833e-05, + "loss": 3.8691, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.649316053913781e-05, + "loss": 3.86, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6484774591627286e-05, + "loss": 3.8679, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6476388644116766e-05, + "loss": 3.8667, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6468002696606246e-05, + "loss": 3.8722, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6459616749095726e-05, + "loss": 3.8684, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6451230801585206e-05, + "loss": 3.8598, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6442844854074686e-05, + "loss": 3.8659, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.643445890656417e-05, + "loss": 3.8531, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6426072959053646e-05, + "loss": 3.8795, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6417687011543126e-05, + "loss": 3.8625, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.640931744283634e-05, + "loss": 3.879, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6400947874129548e-05, + "loss": 3.8611, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.639256192661903e-05, + "loss": 3.8772, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.638417597910851e-05, + "loss": 3.8755, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.637579003159799e-05, + "loss": 3.8606, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6367404084087467e-05, + "loss": 3.8712, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6359018136576947e-05, + "loss": 3.8659, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6350632189066427e-05, + "loss": 3.8757, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6342246241555907e-05, + "loss": 3.8787, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6333860294045387e-05, + "loss": 3.8588, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632547434653487e-05, + "loss": 3.8702, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.631708839902435e-05, + "loss": 3.8665, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.630871883031756e-05, + "loss": 3.877, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630034926161077e-05, + "loss": 3.8656, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.6291963314100252e-05, + "loss": 3.8745, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.6283577366589732e-05, + "loss": 3.8639, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.6275191419079212e-05, + "loss": 3.873, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.6266805471568692e-05, + "loss": 3.8713, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 4.032598495483398, + "eval_runtime": 296.6851, + "eval_samples_per_second": 1286.182, + "eval_steps_per_second": 40.194, + "step": 2060624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6258419524058172e-05, + "loss": 3.8634, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.625003357654765e-05, + "loss": 3.8692, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.624164762903713e-05, + "loss": 3.8726, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.623327806033034e-05, + "loss": 3.8731, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.6224892112819824e-05, + "loss": 3.879, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.62165061653093e-05, + "loss": 3.8649, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.620812021779878e-05, + "loss": 3.8647, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6199750649091993e-05, + "loss": 3.8665, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.6191381080385202e-05, + "loss": 3.8703, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.6182995132874686e-05, + "loss": 3.8772, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.6174609185364166e-05, + "loss": 3.8629, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.6166223237853646e-05, + "loss": 3.8669, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.6157853669146855e-05, + "loss": 3.8746, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6149467721636335e-05, + "loss": 3.8602, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6141081774125815e-05, + "loss": 3.8641, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6132695826615295e-05, + "loss": 3.8562, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6124309879104774e-05, + "loss": 3.8603, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.6115940310397987e-05, + "loss": 3.8636, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.6107554362887467e-05, + "loss": 3.8624, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.6099168415376943e-05, + "loss": 3.8786, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6090782467866423e-05, + "loss": 3.8783, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.608241289915964e-05, + "loss": 3.8678, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.607402695164912e-05, + "loss": 3.871, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6065641004138596e-05, + "loss": 3.8723, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6057255056628076e-05, + "loss": 3.8566, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6048885487921288e-05, + "loss": 3.8704, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6040499540410768e-05, + "loss": 3.8674, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6032113592900248e-05, + "loss": 3.857, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6023727645389728e-05, + "loss": 3.8604, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6015341697879208e-05, + "loss": 3.8617, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6006955750368688e-05, + "loss": 3.8652, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.5998586181661897e-05, + "loss": 3.8674, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5990200234151377e-05, + "loss": 3.8681, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.598181428664086e-05, + "loss": 3.8746, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.597344471793407e-05, + "loss": 3.8613, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.596505877042355e-05, + "loss": 3.8757, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.595667282291303e-05, + "loss": 3.875, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.594828687540251e-05, + "loss": 3.8586, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.593990092789199e-05, + "loss": 3.8604, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.5931531359185202e-05, + "loss": 3.8647, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5923145411674682e-05, + "loss": 3.8599, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.5914759464164162e-05, + "loss": 3.8754, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.5906373516653642e-05, + "loss": 3.8686, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.589798756914312e-05, + "loss": 3.8701, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.5889601621632598e-05, + "loss": 3.8692, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.5881215674122078e-05, + "loss": 3.8686, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.587282972661156e-05, + "loss": 3.8698, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.5864476536708503e-05, + "loss": 3.8677, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.5856090589197983e-05, + "loss": 3.8422, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.5847704641687463e-05, + "loss": 3.8768, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.5839335072980676e-05, + "loss": 3.8631, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.5830949125470156e-05, + "loss": 3.8776, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.5822563177959635e-05, + "loss": 3.8649, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5814177230449115e-05, + "loss": 3.8599, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5805791282938595e-05, + "loss": 3.8589, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5797405335428072e-05, + "loss": 3.8635, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5789019387917552e-05, + "loss": 3.8783, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5780633440407032e-05, + "loss": 3.8624, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5772247492896515e-05, + "loss": 3.8843, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5763861545385995e-05, + "loss": 3.8687, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.5755491976679204e-05, + "loss": 3.8465, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.5747106029168684e-05, + "loss": 3.8823, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5738720081658164e-05, + "loss": 3.8581, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5730334134147644e-05, + "loss": 3.8574, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5721964565440857e-05, + "loss": 3.8709, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.571359499673407e-05, + "loss": 3.8656, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.5705209049223546e-05, + "loss": 3.8578, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.5696823101713026e-05, + "loss": 3.8605, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5688437154202506e-05, + "loss": 3.8501, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5680051206691986e-05, + "loss": 3.8632, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.567166525918147e-05, + "loss": 3.8724, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.566327931167095e-05, + "loss": 3.8661, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.565489336416043e-05, + "loss": 3.8678, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5646507416649905e-05, + "loss": 3.8597, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5638121469139385e-05, + "loss": 3.8804, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5629751900432598e-05, + "loss": 3.8647, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5621365952922078e-05, + "loss": 3.8736, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5612980005411558e-05, + "loss": 3.8626, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5604594057901038e-05, + "loss": 3.8643, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.559622448919425e-05, + "loss": 3.8669, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5587838541683727e-05, + "loss": 3.8739, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.557946897297694e-05, + "loss": 3.8633, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.5571083025466423e-05, + "loss": 3.8775, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5562697077955902e-05, + "loss": 3.855, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.555431113044538e-05, + "loss": 3.8652, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.554592518293486e-05, + "loss": 3.8624, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.553753923542434e-05, + "loss": 3.8742, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.552915328791382e-05, + "loss": 3.8595, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.55207673404033e-05, + "loss": 3.8626, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551238139289278e-05, + "loss": 3.8636, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.550399544538226e-05, + "loss": 3.8653, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.549560949787174e-05, + "loss": 3.867, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.548723992916495e-05, + "loss": 3.8537, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.547885398165443e-05, + "loss": 3.87, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.5470468034143908e-05, + "loss": 3.8736, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.5462082086633388e-05, + "loss": 3.8712, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.5453712517926604e-05, + "loss": 3.847, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5445326570416084e-05, + "loss": 3.8598, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.543694062290556e-05, + "loss": 3.8605, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.542855467539504e-05, + "loss": 3.8734, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.542016872788452e-05, + "loss": 3.8745, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.5411799159177732e-05, + "loss": 3.8615, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5403413211667212e-05, + "loss": 3.8628, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5395027264156692e-05, + "loss": 3.8642, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5386641316646172e-05, + "loss": 3.8547, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5378255369135652e-05, + "loss": 3.8617, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5369869421625132e-05, + "loss": 3.8586, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5361483474114612e-05, + "loss": 3.8677, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5353097526604092e-05, + "loss": 3.8588, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.5344711579093572e-05, + "loss": 3.8536, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.5336325631583052e-05, + "loss": 3.8553, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5327939684072532e-05, + "loss": 3.8577, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5319553736562012e-05, + "loss": 3.8653, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5311167789051492e-05, + "loss": 3.8571, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.53027982203447e-05, + "loss": 3.867, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.529441227283418e-05, + "loss": 3.8647, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5286026325323664e-05, + "loss": 3.8603, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5277640377813144e-05, + "loss": 3.8678, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.526925443030262e-05, + "loss": 3.8589, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.52608684827921e-05, + "loss": 3.8648, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.525248253528158e-05, + "loss": 3.8606, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5244112966574795e-05, + "loss": 3.8568, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5235727019064272e-05, + "loss": 3.8651, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5227341071553751e-05, + "loss": 3.8606, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5218955124043233e-05, + "loss": 3.871, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5210569176532713e-05, + "loss": 3.8629, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5202199607825924e-05, + "loss": 3.857, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5193813660315404e-05, + "loss": 3.858, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5185444091608616e-05, + "loss": 3.8527, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5177058144098095e-05, + "loss": 3.8718, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5168672196587575e-05, + "loss": 3.8604, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5160286249077055e-05, + "loss": 3.8692, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5151900301566534e-05, + "loss": 3.8582, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5143514354056016e-05, + "loss": 3.871, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5135128406545496e-05, + "loss": 3.8688, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5126742459034976e-05, + "loss": 3.8591, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5118356511524454e-05, + "loss": 3.8655, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5109970564013934e-05, + "loss": 3.8596, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5101584616503414e-05, + "loss": 3.8746, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5093198668992894e-05, + "loss": 3.8744, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5084829100286105e-05, + "loss": 3.8586, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5076443152775585e-05, + "loss": 3.8605, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5068057205265065e-05, + "loss": 3.8654, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5059671257754546e-05, + "loss": 3.8727, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.5051301689047756e-05, + "loss": 3.8573, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.5042915741537236e-05, + "loss": 3.8722, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5034529794026717e-05, + "loss": 3.8611, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.5026143846516197e-05, + "loss": 3.8704, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5017774277809408e-05, + "loss": 3.8646, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 4.031010150909424, + "eval_runtime": 296.5128, + "eval_samples_per_second": 1286.929, + "eval_steps_per_second": 40.217, + "step": 2136944 + }, + { + "epoch": 0.0, + "learning_rate": 1.5009388330298888e-05, + "loss": 3.859, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5001002382788368e-05, + "loss": 3.8624, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4992616435277848e-05, + "loss": 3.8649, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4984230487767328e-05, + "loss": 3.8713, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4975844540256806e-05, + "loss": 3.8719, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4967458592746286e-05, + "loss": 3.8619, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4959072645235766e-05, + "loss": 3.861, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.495070307652898e-05, + "loss": 3.8629, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4942317129018457e-05, + "loss": 3.865, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4933931181507937e-05, + "loss": 3.8673, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4925545233997418e-05, + "loss": 3.8638, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4917159286486898e-05, + "loss": 3.8629, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4908773338976378e-05, + "loss": 3.8724, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4900387391465858e-05, + "loss": 3.8569, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.489200144395534e-05, + "loss": 3.8586, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4883615496444816e-05, + "loss": 3.8506, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4875229548934296e-05, + "loss": 3.8557, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4866843601423778e-05, + "loss": 3.8609, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4858457653913258e-05, + "loss": 3.8563, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4850071706402738e-05, + "loss": 3.8716, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4841685758892218e-05, + "loss": 3.8753, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4833299811381696e-05, + "loss": 3.8641, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4824913863871176e-05, + "loss": 3.8651, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4816544295164389e-05, + "loss": 3.8691, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4808158347653869e-05, + "loss": 3.8488, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.479978877894708e-05, + "loss": 3.8712, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.479140283143656e-05, + "loss": 3.8604, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4783016883926041e-05, + "loss": 3.8508, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4774630936415521e-05, + "loss": 3.8624, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4766244988904997e-05, + "loss": 3.8549, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4757859041394479e-05, + "loss": 3.8605, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4749473093883959e-05, + "loss": 3.8602, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4741087146373439e-05, + "loss": 3.8693, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4732701198862919e-05, + "loss": 3.8631, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.472433163015613e-05, + "loss": 3.8565, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4715962061449342e-05, + "loss": 3.8672, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.470757611393882e-05, + "loss": 3.8727, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.46991901664283e-05, + "loss": 3.8574, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.469080421891778e-05, + "loss": 3.8558, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.468241827140726e-05, + "loss": 3.86, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.4674032323896742e-05, + "loss": 3.8532, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4665646376386222e-05, + "loss": 3.8698, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4657260428875699e-05, + "loss": 3.8625, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4648890860168913e-05, + "loss": 3.8707, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.4640504912658393e-05, + "loss": 3.8621, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4632118965147873e-05, + "loss": 3.8643, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4623733017637351e-05, + "loss": 3.8692, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.461534707012683e-05, + "loss": 3.8641, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.4606977501420043e-05, + "loss": 3.8356, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4598591553909525e-05, + "loss": 3.8694, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4590205606399002e-05, + "loss": 3.8595, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4581819658888481e-05, + "loss": 3.873, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4573433711377963e-05, + "loss": 3.8573, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4565064142671172e-05, + "loss": 3.8613, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4556678195160652e-05, + "loss": 3.8489, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4548292247650134e-05, + "loss": 3.8546, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4539906300139614e-05, + "loss": 3.875, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4531536731432825e-05, + "loss": 3.8605, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4523150783922305e-05, + "loss": 3.8758, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4514764836411784e-05, + "loss": 3.8637, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4506378888901264e-05, + "loss": 3.842, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4497992941390744e-05, + "loss": 3.8784, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4489623372683955e-05, + "loss": 3.8546, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4481237425173435e-05, + "loss": 3.8535, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4472851477662915e-05, + "loss": 3.8646, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4464465530152397e-05, + "loss": 3.8624, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4456079582641877e-05, + "loss": 3.8543, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4447693635131353e-05, + "loss": 3.8538, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4439324066424567e-05, + "loss": 3.8449, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4430938118914047e-05, + "loss": 3.86, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4422552171403527e-05, + "loss": 3.8639, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4414166223893006e-05, + "loss": 3.8599, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4405796655186218e-05, + "loss": 3.8648, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4397410707675698e-05, + "loss": 3.8568, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.438902476016518e-05, + "loss": 3.8702, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4380655191458389e-05, + "loss": 3.862, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4372269243947869e-05, + "loss": 3.8668, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.436388329643735e-05, + "loss": 3.8584, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4355497348926827e-05, + "loss": 3.8623, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4347111401416307e-05, + "loss": 3.8677, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4338725453905789e-05, + "loss": 3.8678, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4330339506395269e-05, + "loss": 3.863, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4321953558884749e-05, + "loss": 3.871, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.4313567611374228e-05, + "loss": 3.8534, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.430518166386371e-05, + "loss": 3.8582, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4296795716353187e-05, + "loss": 3.8581, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.42884261476464e-05, + "loss": 3.8708, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.428004020013588e-05, + "loss": 3.854, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.427165425262536e-05, + "loss": 3.8616, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.4263284683918572e-05, + "loss": 3.8601, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.4254898736408052e-05, + "loss": 3.8608, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.4246512788897531e-05, + "loss": 3.8643, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.423812684138701e-05, + "loss": 3.8523, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.422974089387649e-05, + "loss": 3.8645, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.422135494636597e-05, + "loss": 3.8659, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.421296899885545e-05, + "loss": 3.8721, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.420458305134493e-05, + "loss": 3.8385, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.419621348263814e-05, + "loss": 3.8589, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.418782753512762e-05, + "loss": 3.8563, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.41794415876171e-05, + "loss": 3.866, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4171055640106582e-05, + "loss": 3.8706, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4162669692596062e-05, + "loss": 3.8578, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4154283745085542e-05, + "loss": 3.8587, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.414589779757502e-05, + "loss": 3.8579, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.41375118500645e-05, + "loss": 3.854, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4129142281357713e-05, + "loss": 3.8568, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.412075633384719e-05, + "loss": 3.856, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.411237038633667e-05, + "loss": 3.8601, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.410398443882615e-05, + "loss": 3.8564, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4095614870119365e-05, + "loss": 3.8495, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4087245301412574e-05, + "loss": 3.8499, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4078859353902054e-05, + "loss": 3.8527, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4070473406391536e-05, + "loss": 3.8596, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4062087458881012e-05, + "loss": 3.8499, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4053701511370492e-05, + "loss": 3.8634, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4045315563859974e-05, + "loss": 3.8605, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4036929616349454e-05, + "loss": 3.8622, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4028560047642664e-05, + "loss": 3.8614, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4020190478935877e-05, + "loss": 3.854, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4011804531425357e-05, + "loss": 3.8629, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4003418583914837e-05, + "loss": 3.8544, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3995032636404315e-05, + "loss": 3.8521, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3986646688893795e-05, + "loss": 3.8614, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3978277120187008e-05, + "loss": 3.8577, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3969891172676486e-05, + "loss": 3.861, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3961505225165966e-05, + "loss": 3.8573, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3953119277655446e-05, + "loss": 3.8538, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3944733330144927e-05, + "loss": 3.8547, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3936347382634407e-05, + "loss": 3.8525, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3927977813927618e-05, + "loss": 3.8624, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3919591866417098e-05, + "loss": 3.8591, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3911205918906578e-05, + "loss": 3.8682, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3902819971396058e-05, + "loss": 3.8528, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3894434023885538e-05, + "loss": 3.8623, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.388604807637502e-05, + "loss": 3.8691, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3877662128864496e-05, + "loss": 3.856, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.3869276181353976e-05, + "loss": 3.8586, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.386090661264719e-05, + "loss": 3.8601, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3852520665136667e-05, + "loss": 3.8704, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.3844134717626147e-05, + "loss": 3.868, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.3835748770115629e-05, + "loss": 3.8553, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3827362822605108e-05, + "loss": 3.8547, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3818976875094588e-05, + "loss": 3.8596, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3810590927584068e-05, + "loss": 3.868, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.380220498007355e-05, + "loss": 3.8509, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3793835411366759e-05, + "loss": 3.8692, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3785449463856239e-05, + "loss": 3.853, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.377706351634572e-05, + "loss": 3.866, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.37686775688352e-05, + "loss": 3.8633, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 4.029543876647949, + "eval_runtime": 299.1322, + "eval_samples_per_second": 1275.66, + "eval_steps_per_second": 39.865, + "step": 2213264 + }, + { + "epoch": 1.0, + "learning_rate": 1.3760291621324677e-05, + "loss": 3.8591, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3751905673814159e-05, + "loss": 3.8581, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3743536105107371e-05, + "loss": 3.8592, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.373515015759685e-05, + "loss": 3.8677, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.372676421008633e-05, + "loss": 3.867, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.371837826257581e-05, + "loss": 3.8605, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.370999231506529e-05, + "loss": 3.8534, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.37016227463585e-05, + "loss": 3.8557, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.369323679884798e-05, + "loss": 3.8595, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.368485085133746e-05, + "loss": 3.8622, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3676464903826942e-05, + "loss": 3.8598, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3668095335120151e-05, + "loss": 3.862, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3659725766413365e-05, + "loss": 3.8672, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3651339818902845e-05, + "loss": 3.8497, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3642953871392322e-05, + "loss": 3.8536, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3634567923881803e-05, + "loss": 3.8485, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3626181976371283e-05, + "loss": 3.8473, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3617796028860763e-05, + "loss": 3.8579, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3609426460153974e-05, + "loss": 3.8519, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3601040512643454e-05, + "loss": 3.8644, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3592654565132934e-05, + "loss": 3.8707, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3584268617622414e-05, + "loss": 3.8611, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3575882670111894e-05, + "loss": 3.8616, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.3567496722601375e-05, + "loss": 3.8655, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3559110775090855e-05, + "loss": 3.8421, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3550724827580332e-05, + "loss": 3.8657, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3542355258873546e-05, + "loss": 3.8554, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3533985690166755e-05, + "loss": 3.852, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3525599742656237e-05, + "loss": 3.8564, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3517213795145717e-05, + "loss": 3.849, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.3508827847635197e-05, + "loss": 3.852, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3500441900124677e-05, + "loss": 3.857, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.3492055952614155e-05, + "loss": 3.8668, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.3483670005103635e-05, + "loss": 3.8615, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.3475284057593115e-05, + "loss": 3.8519, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.3466914488886326e-05, + "loss": 3.8564, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3458528541375806e-05, + "loss": 3.8706, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.3450142593865286e-05, + "loss": 3.8543, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3441756646354767e-05, + "loss": 3.8528, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3433370698844247e-05, + "loss": 3.8512, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3424984751333727e-05, + "loss": 3.8574, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3416598803823207e-05, + "loss": 3.8561, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3408229235116418e-05, + "loss": 3.8614, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3399843287605898e-05, + "loss": 3.8661, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3391457340095378e-05, + "loss": 3.8586, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.338307139258486e-05, + "loss": 3.8577, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3374685445074336e-05, + "loss": 3.8605, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3366299497563816e-05, + "loss": 3.8603, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.335792992885703e-05, + "loss": 3.8363, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3349543981346507e-05, + "loss": 3.8637, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3341158033835988e-05, + "loss": 3.8563, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3332772086325468e-05, + "loss": 3.8659, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3324386138814948e-05, + "loss": 3.8534, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3316000191304428e-05, + "loss": 3.8562, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3307614243793908e-05, + "loss": 3.8481, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.329922829628339e-05, + "loss": 3.8487, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3290842348772866e-05, + "loss": 3.8731, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3282472780066079e-05, + "loss": 3.8514, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.327408683255556e-05, + "loss": 3.8732, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.326571726384877e-05, + "loss": 3.86, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3257331316338251e-05, + "loss": 3.842, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3248945368827731e-05, + "loss": 3.8737, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3240559421317211e-05, + "loss": 3.8511, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.323217347380669e-05, + "loss": 3.846, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.322378752629617e-05, + "loss": 3.8583, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.321540157878565e-05, + "loss": 3.861, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3207032010078862e-05, + "loss": 3.8502, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.319864606256834e-05, + "loss": 3.8517, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.319026011505782e-05, + "loss": 3.8471, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.31818741675473e-05, + "loss": 3.8485, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3173488220036782e-05, + "loss": 3.867, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3165118651329991e-05, + "loss": 3.858, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.315673270381947e-05, + "loss": 3.8579, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3148346756308952e-05, + "loss": 3.8516, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3139960808798432e-05, + "loss": 3.8672, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.3131591240091643e-05, + "loss": 3.8586, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.3123205292581123e-05, + "loss": 3.8615, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.3114819345070603e-05, + "loss": 3.8522, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3106433397560083e-05, + "loss": 3.8571, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3098047450049563e-05, + "loss": 3.861, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3089677881342774e-05, + "loss": 3.86, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3081291933832254e-05, + "loss": 3.8579, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.3072905986321734e-05, + "loss": 3.8657, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3064520038811215e-05, + "loss": 3.8519, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.3056150470104424e-05, + "loss": 3.8512, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3047764522593906e-05, + "loss": 3.8591, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.3039378575083386e-05, + "loss": 3.863, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.3030992627572866e-05, + "loss": 3.8544, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3022623058866077e-05, + "loss": 3.8548, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3014237111355557e-05, + "loss": 3.8533, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3005851163845037e-05, + "loss": 3.8595, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.2997465216334517e-05, + "loss": 3.8534, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2989079268823995e-05, + "loss": 3.8523, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2980693321313475e-05, + "loss": 3.8582, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2972323752606687e-05, + "loss": 3.8622, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.2963937805096169e-05, + "loss": 3.8659, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.2955551857585646e-05, + "loss": 3.838, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.2947165910075126e-05, + "loss": 3.8519, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.293879634136834e-05, + "loss": 3.849, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2930410393857816e-05, + "loss": 3.8649, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2922024446347298e-05, + "loss": 3.8635, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2913638498836778e-05, + "loss": 3.8556, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2905252551326258e-05, + "loss": 3.8525, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2896882982619469e-05, + "loss": 3.8577, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2888497035108949e-05, + "loss": 3.8518, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2880111087598429e-05, + "loss": 3.8503, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2871725140087909e-05, + "loss": 3.8494, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.286333919257739e-05, + "loss": 3.8573, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.28549696238706e-05, + "loss": 3.8531, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.284658367636008e-05, + "loss": 3.8443, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.283821410765329e-05, + "loss": 3.8475, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.282982816014277e-05, + "loss": 3.8447, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2821442212632252e-05, + "loss": 3.8566, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2813056265121732e-05, + "loss": 3.8488, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2804670317611212e-05, + "loss": 3.8582, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2796284370100692e-05, + "loss": 3.8559, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2787898422590171e-05, + "loss": 3.8578, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.277951247507965e-05, + "loss": 3.8537, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.277112652756913e-05, + "loss": 3.8497, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2762756958862344e-05, + "loss": 3.8593, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2754387390155553e-05, + "loss": 3.8519, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2746001442645033e-05, + "loss": 3.8468, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.2737615495134515e-05, + "loss": 3.857, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.2729229547623995e-05, + "loss": 3.8552, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2720843600113471e-05, + "loss": 3.8546, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.2712457652602953e-05, + "loss": 3.851, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.2704071705092433e-05, + "loss": 3.8535, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2695685757581913e-05, + "loss": 3.8533, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2687332567678856e-05, + "loss": 3.8496, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2678946620168336e-05, + "loss": 3.8495, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2670560672657816e-05, + "loss": 3.8572, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2662174725147294e-05, + "loss": 3.8666, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2653788777636774e-05, + "loss": 3.8494, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2645402830126254e-05, + "loss": 3.8531, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2637016882615734e-05, + "loss": 3.8652, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.2628630935105216e-05, + "loss": 3.8559, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.2620244987594696e-05, + "loss": 3.8501, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.2611875418887906e-05, + "loss": 3.8546, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2603489471377386e-05, + "loss": 3.8666, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2595103523866866e-05, + "loss": 3.8685, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2586717576356346e-05, + "loss": 3.8529, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2578331628845826e-05, + "loss": 3.8475, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2569962060139037e-05, + "loss": 3.8561, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2561576112628517e-05, + "loss": 3.8604, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2553190165117999e-05, + "loss": 3.8469, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2544820596411208e-05, + "loss": 3.868, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2536434648900688e-05, + "loss": 3.8499, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.252804870139017e-05, + "loss": 3.8623, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.251966275387965e-05, + "loss": 3.8573, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 4.02824592590332, + "eval_runtime": 300.2091, + "eval_samples_per_second": 1271.084, + "eval_steps_per_second": 39.722, + "step": 2289584 + }, + { + "epoch": 2.0, + "learning_rate": 1.2511276806369126e-05, + "loss": 3.8595, + "step": 2289664 + }, + { + "epoch": 2.0, + "learning_rate": 1.2502890858858607e-05, + "loss": 3.8503, + "step": 2290176 + }, + { + "epoch": 2.0, + "learning_rate": 1.2494504911348087e-05, + "loss": 3.8556, + "step": 2290688 + }, + { + "epoch": 2.0, + "learning_rate": 1.2486118963837567e-05, + "loss": 3.8635, + "step": 2291200 + }, + { + "epoch": 2.0, + "learning_rate": 1.247774939513078e-05, + "loss": 3.8602, + "step": 2291712 + }, + { + "epoch": 2.0, + "learning_rate": 1.2469363447620258e-05, + "loss": 3.8599, + "step": 2292224 + }, + { + "epoch": 2.0, + "learning_rate": 1.2460977500109738e-05, + "loss": 3.8532, + "step": 2292736 + }, + { + "epoch": 2.0, + "learning_rate": 1.2452591552599218e-05, + "loss": 3.8496, + "step": 2293248 + }, + { + "epoch": 2.0, + "learning_rate": 1.24442056050887e-05, + "loss": 3.8546, + "step": 2293760 + }, + { + "epoch": 2.0, + "learning_rate": 1.2435819657578178e-05, + "loss": 3.8629, + "step": 2294272 + }, + { + "epoch": 2.0, + "learning_rate": 1.2427433710067658e-05, + "loss": 3.8522, + "step": 2294784 + }, + { + "epoch": 2.0, + "learning_rate": 1.241906414136087e-05, + "loss": 3.8611, + "step": 2295296 + }, + { + "epoch": 2.0, + "learning_rate": 1.2410694572654081e-05, + "loss": 3.8647, + "step": 2295808 + }, + { + "epoch": 2.0, + "learning_rate": 1.2402308625143561e-05, + "loss": 3.8418, + "step": 2296320 + }, + { + "epoch": 2.0, + "learning_rate": 1.2393922677633041e-05, + "loss": 3.853, + "step": 2296832 + }, + { + "epoch": 2.0, + "learning_rate": 1.2385536730122521e-05, + "loss": 3.8405, + "step": 2297344 + }, + { + "epoch": 2.0, + "learning_rate": 1.2377150782612e-05, + "loss": 3.8399, + "step": 2297856 + }, + { + "epoch": 2.0, + "learning_rate": 1.2368764835101481e-05, + "loss": 3.8578, + "step": 2298368 + }, + { + "epoch": 2.0, + "learning_rate": 1.2360378887590961e-05, + "loss": 3.8443, + "step": 2298880 + }, + { + "epoch": 2.0, + "learning_rate": 1.235199294008044e-05, + "loss": 3.8618, + "step": 2299392 + }, + { + "epoch": 2.0, + "learning_rate": 1.234360699256992e-05, + "loss": 3.8688, + "step": 2299904 + }, + { + "epoch": 2.0, + "learning_rate": 1.2335237423863132e-05, + "loss": 3.8527, + "step": 2300416 + }, + { + "epoch": 2.0, + "learning_rate": 1.2326851476352612e-05, + "loss": 3.8615, + "step": 2300928 + }, + { + "epoch": 2.0, + "learning_rate": 1.2318465528842092e-05, + "loss": 3.8606, + "step": 2301440 + }, + { + "epoch": 2.0, + "learning_rate": 1.2310079581331572e-05, + "loss": 3.84, + "step": 2301952 + }, + { + "epoch": 2.0, + "learning_rate": 1.2301693633821051e-05, + "loss": 3.8606, + "step": 2302464 + }, + { + "epoch": 2.0, + "learning_rate": 1.229330768631053e-05, + "loss": 3.8521, + "step": 2302976 + }, + { + "epoch": 2.0, + "learning_rate": 1.2284938117603742e-05, + "loss": 3.8467, + "step": 2303488 + }, + { + "epoch": 2.0, + "learning_rate": 1.2276552170093222e-05, + "loss": 3.8527, + "step": 2304000 + }, + { + "epoch": 2.0, + "learning_rate": 1.2268166222582702e-05, + "loss": 3.846, + "step": 2304512 + }, + { + "epoch": 2.01, + "learning_rate": 1.2259780275072182e-05, + "loss": 3.8494, + "step": 2305024 + }, + { + "epoch": 2.01, + "learning_rate": 1.2251394327561662e-05, + "loss": 3.8559, + "step": 2305536 + }, + { + "epoch": 2.01, + "learning_rate": 1.2243008380051142e-05, + "loss": 3.8633, + "step": 2306048 + }, + { + "epoch": 2.01, + "learning_rate": 1.2234622432540622e-05, + "loss": 3.854, + "step": 2306560 + }, + { + "epoch": 2.01, + "learning_rate": 1.2226252863833833e-05, + "loss": 3.849, + "step": 2307072 + }, + { + "epoch": 2.01, + "learning_rate": 1.2217883295127045e-05, + "loss": 3.8528, + "step": 2307584 + }, + { + "epoch": 2.01, + "learning_rate": 1.2209513726420256e-05, + "loss": 3.8699, + "step": 2308096 + }, + { + "epoch": 2.01, + "learning_rate": 1.2201127778909734e-05, + "loss": 3.8479, + "step": 2308608 + }, + { + "epoch": 2.01, + "learning_rate": 1.2192741831399216e-05, + "loss": 3.8485, + "step": 2309120 + }, + { + "epoch": 2.01, + "learning_rate": 1.2184355883888696e-05, + "loss": 3.8503, + "step": 2309632 + }, + { + "epoch": 2.01, + "learning_rate": 1.2175969936378176e-05, + "loss": 3.8487, + "step": 2310144 + }, + { + "epoch": 2.01, + "learning_rate": 1.2167583988867654e-05, + "loss": 3.8511, + "step": 2310656 + }, + { + "epoch": 2.01, + "learning_rate": 1.2159198041357136e-05, + "loss": 3.8581, + "step": 2311168 + }, + { + "epoch": 2.01, + "learning_rate": 1.2150812093846616e-05, + "loss": 3.8639, + "step": 2311680 + }, + { + "epoch": 2.01, + "learning_rate": 1.2142426146336094e-05, + "loss": 3.8578, + "step": 2312192 + }, + { + "epoch": 2.01, + "learning_rate": 1.2134056577629306e-05, + "loss": 3.8549, + "step": 2312704 + }, + { + "epoch": 2.01, + "learning_rate": 1.2125670630118786e-05, + "loss": 3.8509, + "step": 2313216 + }, + { + "epoch": 2.01, + "learning_rate": 1.2117284682608266e-05, + "loss": 3.8605, + "step": 2313728 + }, + { + "epoch": 2.01, + "learning_rate": 1.2108898735097746e-05, + "loss": 3.8324, + "step": 2314240 + }, + { + "epoch": 2.01, + "learning_rate": 1.2100512787587226e-05, + "loss": 3.8585, + "step": 2314752 + }, + { + "epoch": 2.01, + "learning_rate": 1.2092126840076706e-05, + "loss": 3.856, + "step": 2315264 + }, + { + "epoch": 2.01, + "learning_rate": 1.2083740892566184e-05, + "loss": 3.8641, + "step": 2315776 + }, + { + "epoch": 2.01, + "learning_rate": 1.2075354945055666e-05, + "loss": 3.8471, + "step": 2316288 + }, + { + "epoch": 2.01, + "learning_rate": 1.2066968997545146e-05, + "loss": 3.8493, + "step": 2316800 + }, + { + "epoch": 2.01, + "learning_rate": 1.2058599428838357e-05, + "loss": 3.8484, + "step": 2317312 + }, + { + "epoch": 2.01, + "learning_rate": 1.2050213481327837e-05, + "loss": 3.8441, + "step": 2317824 + }, + { + "epoch": 2.01, + "learning_rate": 1.2041827533817317e-05, + "loss": 3.8652, + "step": 2318336 + }, + { + "epoch": 2.01, + "learning_rate": 1.2033441586306797e-05, + "loss": 3.8561, + "step": 2318848 + }, + { + "epoch": 2.01, + "learning_rate": 1.2025055638796277e-05, + "loss": 3.8685, + "step": 2319360 + }, + { + "epoch": 2.01, + "learning_rate": 1.2016669691285757e-05, + "loss": 3.8521, + "step": 2319872 + }, + { + "epoch": 2.01, + "learning_rate": 1.2008283743775237e-05, + "loss": 3.8413, + "step": 2320384 + }, + { + "epoch": 2.01, + "learning_rate": 1.1999897796264715e-05, + "loss": 3.869, + "step": 2320896 + }, + { + "epoch": 2.01, + "learning_rate": 1.1991528227557927e-05, + "loss": 3.8452, + "step": 2321408 + }, + { + "epoch": 2.01, + "learning_rate": 1.1983142280047407e-05, + "loss": 3.8421, + "step": 2321920 + }, + { + "epoch": 2.01, + "learning_rate": 1.197477271134062e-05, + "loss": 3.8521, + "step": 2322432 + }, + { + "epoch": 2.01, + "learning_rate": 1.1966386763830098e-05, + "loss": 3.8576, + "step": 2322944 + }, + { + "epoch": 2.01, + "learning_rate": 1.1958000816319578e-05, + "loss": 3.8419, + "step": 2323456 + }, + { + "epoch": 2.01, + "learning_rate": 1.1949614868809058e-05, + "loss": 3.8487, + "step": 2323968 + }, + { + "epoch": 2.01, + "learning_rate": 1.194122892129854e-05, + "loss": 3.8397, + "step": 2324480 + }, + { + "epoch": 2.01, + "learning_rate": 1.1932859352591749e-05, + "loss": 3.8432, + "step": 2324992 + }, + { + "epoch": 2.01, + "learning_rate": 1.192447340508123e-05, + "loss": 3.865, + "step": 2325504 + }, + { + "epoch": 2.01, + "learning_rate": 1.191608745757071e-05, + "loss": 3.8536, + "step": 2326016 + }, + { + "epoch": 2.01, + "learning_rate": 1.1907701510060189e-05, + "loss": 3.8543, + "step": 2326528 + }, + { + "epoch": 2.01, + "learning_rate": 1.1899315562549669e-05, + "loss": 3.8479, + "step": 2327040 + }, + { + "epoch": 2.01, + "learning_rate": 1.189092961503915e-05, + "loss": 3.8619, + "step": 2327552 + }, + { + "epoch": 2.01, + "learning_rate": 1.188254366752863e-05, + "loss": 3.8535, + "step": 2328064 + }, + { + "epoch": 2.01, + "learning_rate": 1.1874190477625572e-05, + "loss": 3.8609, + "step": 2328576 + }, + { + "epoch": 2.01, + "learning_rate": 1.1865804530115052e-05, + "loss": 3.8508, + "step": 2329088 + }, + { + "epoch": 2.01, + "learning_rate": 1.1857418582604532e-05, + "loss": 3.8535, + "step": 2329600 + }, + { + "epoch": 2.01, + "learning_rate": 1.1849032635094012e-05, + "loss": 3.8562, + "step": 2330112 + }, + { + "epoch": 2.01, + "learning_rate": 1.1840646687583492e-05, + "loss": 3.8537, + "step": 2330624 + }, + { + "epoch": 2.01, + "learning_rate": 1.1832260740072972e-05, + "loss": 3.8542, + "step": 2331136 + }, + { + "epoch": 2.01, + "learning_rate": 1.1823874792562452e-05, + "loss": 3.8633, + "step": 2331648 + }, + { + "epoch": 2.01, + "learning_rate": 1.1815488845051931e-05, + "loss": 3.8575, + "step": 2332160 + }, + { + "epoch": 2.01, + "learning_rate": 1.1807102897541411e-05, + "loss": 3.8436, + "step": 2332672 + }, + { + "epoch": 2.01, + "learning_rate": 1.1798733328834622e-05, + "loss": 3.8537, + "step": 2333184 + }, + { + "epoch": 2.01, + "learning_rate": 1.1790347381324104e-05, + "loss": 3.8595, + "step": 2333696 + }, + { + "epoch": 2.01, + "learning_rate": 1.1781961433813582e-05, + "loss": 3.848, + "step": 2334208 + }, + { + "epoch": 2.01, + "learning_rate": 1.1773575486303062e-05, + "loss": 3.8537, + "step": 2334720 + }, + { + "epoch": 2.01, + "learning_rate": 1.1765205917596275e-05, + "loss": 3.8465, + "step": 2335232 + }, + { + "epoch": 2.02, + "learning_rate": 1.1756819970085753e-05, + "loss": 3.8539, + "step": 2335744 + }, + { + "epoch": 2.02, + "learning_rate": 1.1748434022575233e-05, + "loss": 3.8513, + "step": 2336256 + }, + { + "epoch": 2.02, + "learning_rate": 1.1740048075064713e-05, + "loss": 3.8491, + "step": 2336768 + }, + { + "epoch": 2.02, + "learning_rate": 1.1731662127554193e-05, + "loss": 3.8598, + "step": 2337280 + }, + { + "epoch": 2.02, + "learning_rate": 1.1723292558847403e-05, + "loss": 3.8549, + "step": 2337792 + }, + { + "epoch": 2.02, + "learning_rate": 1.1714906611336885e-05, + "loss": 3.8664, + "step": 2338304 + }, + { + "epoch": 2.02, + "learning_rate": 1.1706520663826365e-05, + "loss": 3.8294, + "step": 2338816 + }, + { + "epoch": 2.02, + "learning_rate": 1.1698134716315843e-05, + "loss": 3.852, + "step": 2339328 + }, + { + "epoch": 2.02, + "learning_rate": 1.1689748768805323e-05, + "loss": 3.8453, + "step": 2339840 + }, + { + "epoch": 2.02, + "learning_rate": 1.1681362821294805e-05, + "loss": 3.8585, + "step": 2340352 + }, + { + "epoch": 2.02, + "learning_rate": 1.1672976873784283e-05, + "loss": 3.8645, + "step": 2340864 + }, + { + "epoch": 2.02, + "learning_rate": 1.1664590926273763e-05, + "loss": 3.8492, + "step": 2341376 + }, + { + "epoch": 2.02, + "learning_rate": 1.1656221357566976e-05, + "loss": 3.8454, + "step": 2341888 + }, + { + "epoch": 2.02, + "learning_rate": 1.1647851788860186e-05, + "loss": 3.8527, + "step": 2342400 + }, + { + "epoch": 2.02, + "learning_rate": 1.1639465841349666e-05, + "loss": 3.8487, + "step": 2342912 + }, + { + "epoch": 2.02, + "learning_rate": 1.1631079893839146e-05, + "loss": 3.8491, + "step": 2343424 + }, + { + "epoch": 2.02, + "learning_rate": 1.1622693946328626e-05, + "loss": 3.8439, + "step": 2343936 + }, + { + "epoch": 2.02, + "learning_rate": 1.1614307998818106e-05, + "loss": 3.8511, + "step": 2344448 + }, + { + "epoch": 2.02, + "learning_rate": 1.1605938430111317e-05, + "loss": 3.8515, + "step": 2344960 + }, + { + "epoch": 2.02, + "learning_rate": 1.1597552482600797e-05, + "loss": 3.845, + "step": 2345472 + }, + { + "epoch": 2.02, + "learning_rate": 1.1589166535090277e-05, + "loss": 3.8484, + "step": 2345984 + }, + { + "epoch": 2.02, + "learning_rate": 1.1580780587579757e-05, + "loss": 3.8366, + "step": 2346496 + }, + { + "epoch": 2.02, + "learning_rate": 1.1572411018872968e-05, + "loss": 3.857, + "step": 2347008 + }, + { + "epoch": 2.02, + "learning_rate": 1.1564025071362448e-05, + "loss": 3.8423, + "step": 2347520 + }, + { + "epoch": 2.02, + "learning_rate": 1.155563912385193e-05, + "loss": 3.8503, + "step": 2348032 + }, + { + "epoch": 2.02, + "learning_rate": 1.1547253176341408e-05, + "loss": 3.8527, + "step": 2348544 + }, + { + "epoch": 2.02, + "learning_rate": 1.153888360763462e-05, + "loss": 3.8568, + "step": 2349056 + }, + { + "epoch": 2.02, + "learning_rate": 1.15304976601241e-05, + "loss": 3.8469, + "step": 2349568 + }, + { + "epoch": 2.02, + "learning_rate": 1.152211171261358e-05, + "loss": 3.8501, + "step": 2350080 + }, + { + "epoch": 2.02, + "learning_rate": 1.1513725765103058e-05, + "loss": 3.8555, + "step": 2350592 + }, + { + "epoch": 2.02, + "learning_rate": 1.150533981759254e-05, + "loss": 3.843, + "step": 2351104 + }, + { + "epoch": 2.02, + "learning_rate": 1.149695387008202e-05, + "loss": 3.8427, + "step": 2351616 + }, + { + "epoch": 2.02, + "learning_rate": 1.1488584301375229e-05, + "loss": 3.8555, + "step": 2352128 + }, + { + "epoch": 2.02, + "learning_rate": 1.148019835386471e-05, + "loss": 3.8536, + "step": 2352640 + }, + { + "epoch": 2.02, + "learning_rate": 1.147181240635419e-05, + "loss": 3.854, + "step": 2353152 + }, + { + "epoch": 2.02, + "learning_rate": 1.146342645884367e-05, + "loss": 3.8484, + "step": 2353664 + }, + { + "epoch": 2.02, + "learning_rate": 1.145504051133315e-05, + "loss": 3.8506, + "step": 2354176 + }, + { + "epoch": 2.02, + "learning_rate": 1.144665456382263e-05, + "loss": 3.8476, + "step": 2354688 + }, + { + "epoch": 2.02, + "learning_rate": 1.1438284995115841e-05, + "loss": 3.8442, + "step": 2355200 + }, + { + "epoch": 2.02, + "learning_rate": 1.1429899047605321e-05, + "loss": 3.8402, + "step": 2355712 + }, + { + "epoch": 2.02, + "learning_rate": 1.1421513100094801e-05, + "loss": 3.8617, + "step": 2356224 + }, + { + "epoch": 2.02, + "learning_rate": 1.1413127152584281e-05, + "loss": 3.8614, + "step": 2356736 + }, + { + "epoch": 2.02, + "learning_rate": 1.1404741205073761e-05, + "loss": 3.8457, + "step": 2357248 + }, + { + "epoch": 2.02, + "learning_rate": 1.1396355257563241e-05, + "loss": 3.8463, + "step": 2357760 + }, + { + "epoch": 2.02, + "learning_rate": 1.1387985688856452e-05, + "loss": 3.8621, + "step": 2358272 + }, + { + "epoch": 2.02, + "learning_rate": 1.1379599741345932e-05, + "loss": 3.8521, + "step": 2358784 + }, + { + "epoch": 2.02, + "learning_rate": 1.1371213793835412e-05, + "loss": 3.8484, + "step": 2359296 + }, + { + "epoch": 2.02, + "learning_rate": 1.1362827846324892e-05, + "loss": 3.8485, + "step": 2359808 + }, + { + "epoch": 2.02, + "learning_rate": 1.1354458277618102e-05, + "loss": 3.8645, + "step": 2360320 + }, + { + "epoch": 2.02, + "learning_rate": 1.1346072330107584e-05, + "loss": 3.8596, + "step": 2360832 + }, + { + "epoch": 2.02, + "learning_rate": 1.1337686382597062e-05, + "loss": 3.8507, + "step": 2361344 + }, + { + "epoch": 2.02, + "learning_rate": 1.1329300435086542e-05, + "loss": 3.8421, + "step": 2361856 + }, + { + "epoch": 2.02, + "learning_rate": 1.1320930866379755e-05, + "loss": 3.8556, + "step": 2362368 + }, + { + "epoch": 2.02, + "learning_rate": 1.1312544918869235e-05, + "loss": 3.8584, + "step": 2362880 + }, + { + "epoch": 2.02, + "learning_rate": 1.1304158971358713e-05, + "loss": 3.8424, + "step": 2363392 + }, + { + "epoch": 2.02, + "learning_rate": 1.1295773023848195e-05, + "loss": 3.8646, + "step": 2363904 + }, + { + "epoch": 2.02, + "learning_rate": 1.1287403455141405e-05, + "loss": 3.8448, + "step": 2364416 + }, + { + "epoch": 2.02, + "learning_rate": 1.1279017507630885e-05, + "loss": 3.858, + "step": 2364928 + }, + { + "epoch": 2.02, + "learning_rate": 1.1270647938924096e-05, + "loss": 3.853, + "step": 2365440 + }, + { + "epoch": 2.03, + "eval_loss": 4.02750825881958, + "eval_runtime": 302.3679, + "eval_samples_per_second": 1262.009, + "eval_steps_per_second": 39.439, + "step": 2365904 + }, + { + "epoch": 0.0, + "learning_rate": 1.1262261991413576e-05, + "loss": 3.891, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1253876043903056e-05, + "loss": 3.8463, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1245490096392536e-05, + "loss": 3.8498, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1237104148882016e-05, + "loss": 3.862, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1228718201371496e-05, + "loss": 3.8583, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1220332253860976e-05, + "loss": 3.8545, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1211946306350456e-05, + "loss": 3.8489, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1203560358839936e-05, + "loss": 3.8488, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1195174411329416e-05, + "loss": 3.8511, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1186788463818896e-05, + "loss": 3.8582, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1178402516308376e-05, + "loss": 3.85, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1170016568797856e-05, + "loss": 3.8574, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1161647000091066e-05, + "loss": 3.8607, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1153261052580546e-05, + "loss": 3.8394, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1144875105070026e-05, + "loss": 3.8511, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1136489157559506e-05, + "loss": 3.8381, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1128103210048986e-05, + "loss": 3.8411, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1119717262538466e-05, + "loss": 3.8507, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1111331315027946e-05, + "loss": 3.8451, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1102945367517426e-05, + "loss": 3.8513, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1094559420006906e-05, + "loss": 3.8658, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1086173472496386e-05, + "loss": 3.85, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1077787524985864e-05, + "loss": 3.8554, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1069401577475346e-05, + "loss": 3.8581, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1061032008768557e-05, + "loss": 3.8436, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1052646061258037e-05, + "loss": 3.8565, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1044292871354978e-05, + "loss": 3.8399, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.103590692384446e-05, + "loss": 3.8512, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.102752097633394e-05, + "loss": 3.846, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.101913502882342e-05, + "loss": 3.8395, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1010749081312898e-05, + "loss": 3.8474, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.100236313380238e-05, + "loss": 3.8455, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.099397718629186e-05, + "loss": 3.8603, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0985591238781338e-05, + "loss": 3.8569, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0977205291270818e-05, + "loss": 3.8423, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.096883572256403e-05, + "loss": 3.848, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.096044977505351e-05, + "loss": 3.8688, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.095206382754299e-05, + "loss": 3.843, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0943694258836201e-05, + "loss": 3.8474, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0935308311325681e-05, + "loss": 3.8478, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0926922363815161e-05, + "loss": 3.8425, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0918536416304641e-05, + "loss": 3.8482, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0910150468794121e-05, + "loss": 3.8585, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0901764521283601e-05, + "loss": 3.8582, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0893378573773081e-05, + "loss": 3.8525, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.088499262626256e-05, + "loss": 3.852, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.087660667875204e-05, + "loss": 3.8449, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0868220731241519e-05, + "loss": 3.8605, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0859834783731e-05, + "loss": 3.8275, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0851465215024212e-05, + "loss": 3.8522, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0843079267513691e-05, + "loss": 3.8522, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0834693320003171e-05, + "loss": 3.8596, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0826307372492651e-05, + "loss": 3.8472, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0817921424982131e-05, + "loss": 3.8386, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0809551856275342e-05, + "loss": 3.8498, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0801165908764822e-05, + "loss": 3.8368, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0792779961254302e-05, + "loss": 3.8676, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0784394013743784e-05, + "loss": 3.8479, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0776024445036993e-05, + "loss": 3.8649, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0767638497526473e-05, + "loss": 3.85, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0759252550015954e-05, + "loss": 3.8373, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0750882981309165e-05, + "loss": 3.8615, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0742497033798645e-05, + "loss": 3.8375, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0734111086288125e-05, + "loss": 3.845, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0725725138777605e-05, + "loss": 3.8464, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0717339191267083e-05, + "loss": 3.8584, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0708953243756565e-05, + "loss": 3.8383, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0700567296246045e-05, + "loss": 3.8454, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0692181348735523e-05, + "loss": 3.837, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0683811780028736e-05, + "loss": 3.8412, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0675425832518216e-05, + "loss": 3.858, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0667039885007696e-05, + "loss": 3.8524, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0658653937497176e-05, + "loss": 3.849, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0650284368790386e-05, + "loss": 3.8478, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0641898421279866e-05, + "loss": 3.8568, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0633512473769346e-05, + "loss": 3.8498, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0625142905062557e-05, + "loss": 3.8543, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0616756957552037e-05, + "loss": 3.8503, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0608371010041519e-05, + "loss": 3.8485, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0599985062530997e-05, + "loss": 3.8545, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0591599115020477e-05, + "loss": 3.851, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0583213167509957e-05, + "loss": 3.8482, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.057484359880317e-05, + "loss": 3.8589, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0566457651292648e-05, + "loss": 3.8558, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.055807170378213e-05, + "loss": 3.8348, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0549685756271609e-05, + "loss": 3.8491, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0541299808761087e-05, + "loss": 3.8541, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0532913861250567e-05, + "loss": 3.8496, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.052454429254378e-05, + "loss": 3.8481, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.051615834503326e-05, + "loss": 3.8478, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0507772397522738e-05, + "loss": 3.8489, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.049938645001222e-05, + "loss": 3.8449, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.04910005025017e-05, + "loss": 3.8487, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.048263093379491e-05, + "loss": 3.8507, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.047424498628439e-05, + "loss": 3.8494, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.046585903877387e-05, + "loss": 3.8648, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.045747309126335e-05, + "loss": 3.829, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.044908714375283e-05, + "loss": 3.8456, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.044070119624231e-05, + "loss": 3.8473, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.043231524873179e-05, + "loss": 3.8494, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0423929301221268e-05, + "loss": 3.8601, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.041554335371075e-05, + "loss": 3.8485, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.040715740620023e-05, + "loss": 3.8412, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0398804216297173e-05, + "loss": 3.8484, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0390418268786652e-05, + "loss": 3.8503, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0382032321276132e-05, + "loss": 3.8424, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0373646373765612e-05, + "loss": 3.8397, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0365260426255092e-05, + "loss": 3.8487, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0356874478744571e-05, + "loss": 3.8508, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0348488531234051e-05, + "loss": 3.8351, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0340102583723531e-05, + "loss": 3.848, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0331716636213011e-05, + "loss": 3.8355, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0323330688702491e-05, + "loss": 3.8514, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0314944741191971e-05, + "loss": 3.8409, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0306575172485182e-05, + "loss": 3.8445, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0298189224974662e-05, + "loss": 3.8497, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0289803277464142e-05, + "loss": 3.8509, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0281417329953624e-05, + "loss": 3.8463, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0273031382443102e-05, + "loss": 3.8471, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0264645434932582e-05, + "loss": 3.8495, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0256259487422062e-05, + "loss": 3.8427, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0247906297519005e-05, + "loss": 3.8403, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0239520350008485e-05, + "loss": 3.8519, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0231134402497965e-05, + "loss": 3.8491, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0222748454987445e-05, + "loss": 3.8557, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0214362507476923e-05, + "loss": 3.8393, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0205976559966405e-05, + "loss": 3.8486, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0197590612455885e-05, + "loss": 3.8448, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0189221043749096e-05, + "loss": 3.8408, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0180835096238576e-05, + "loss": 3.8352, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0172449148728056e-05, + "loss": 3.8587, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0164063201217535e-05, + "loss": 3.8582, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0155677253707015e-05, + "loss": 3.8457, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0147291306196495e-05, + "loss": 3.8447, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0138905358685975e-05, + "loss": 3.8517, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0130519411175454e-05, + "loss": 3.8513, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0122133463664935e-05, + "loss": 3.8438, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0113747516154415e-05, + "loss": 3.8499, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0105377947447626e-05, + "loss": 3.8621, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0096991999937106e-05, + "loss": 3.8535, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0088606052426586e-05, + "loss": 3.848, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0080220104916066e-05, + "loss": 3.8402, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0071834157405546e-05, + "loss": 3.8519, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0063448209895026e-05, + "loss": 3.8513, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0055062262384506e-05, + "loss": 3.8385, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0046676314873986e-05, + "loss": 3.8633, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0038306746167196e-05, + "loss": 3.8451, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0029920798656676e-05, + "loss": 3.8531, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0021534851146156e-05, + "loss": 3.8467, + "step": 2441728 + }, + { + "epoch": 0.03, + "eval_loss": 4.026543617248535, + "eval_runtime": 304.7737, + "eval_samples_per_second": 1252.047, + "eval_steps_per_second": 39.127, + "step": 2442224 + }, + { + "epoch": 1.0, + "learning_rate": 1.0013148903635636e-05, + "loss": 3.8502, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0004779334928847e-05, + "loss": 3.8431, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.996393387418327e-06, + "loss": 3.8484, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.988007439907809e-06, + "loss": 3.8618, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.979621492397287e-06, + "loss": 3.8555, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.971251923690498e-06, + "loss": 3.85, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.96286597617998e-06, + "loss": 3.8438, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.954480028669458e-06, + "loss": 3.8443, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.946094081158938e-06, + "loss": 3.8446, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.93772451245215e-06, + "loss": 3.8596, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.92933856494163e-06, + "loss": 3.8453, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.920952617431108e-06, + "loss": 3.8529, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91258304872432e-06, + "loss": 3.8565, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.9041971012138e-06, + "loss": 3.8387, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.89581115370328e-06, + "loss": 3.846, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.88742520619276e-06, + "loss": 3.832, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.87903925868224e-06, + "loss": 3.8376, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.87065331117172e-06, + "loss": 3.8484, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.8622673636612e-06, + "loss": 3.8438, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.853897794954411e-06, + "loss": 3.8453, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.845511847443891e-06, + "loss": 3.8657, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.837125899933371e-06, + "loss": 3.8449, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.828739952422851e-06, + "loss": 3.8538, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.820370383716062e-06, + "loss": 3.8516, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.811984436205544e-06, + "loss": 3.8454, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.803598488695022e-06, + "loss": 3.8484, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.795212541184502e-06, + "loss": 3.8366, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.786826593673982e-06, + "loss": 3.8501, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.778440646163463e-06, + "loss": 3.8443, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.770054698652942e-06, + "loss": 3.8369, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.761668751142422e-06, + "loss": 3.8476, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.753282803631902e-06, + "loss": 3.8381, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.744896856121382e-06, + "loss": 3.8539, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.736510908610862e-06, + "loss": 3.8542, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.728141339904074e-06, + "loss": 3.843, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.719771771197285e-06, + "loss": 3.8454, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.711385823686763e-06, + "loss": 3.8629, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.702999876176245e-06, + "loss": 3.8373, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.694613928665725e-06, + "loss": 3.8452, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.686227981155203e-06, + "loss": 3.8455, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.677842033644683e-06, + "loss": 3.8382, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.669456086134165e-06, + "loss": 3.8439, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.661070138623645e-06, + "loss": 3.8592, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.652684191113123e-06, + "loss": 3.8502, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.644298243602603e-06, + "loss": 3.8443, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.635928674895815e-06, + "loss": 3.8549, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.627542727385294e-06, + "loss": 3.8405, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.619156779874775e-06, + "loss": 3.8573, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.610770832364255e-06, + "loss": 3.826, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.602384884853735e-06, + "loss": 3.8466, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.594015316146946e-06, + "loss": 3.8563, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.585629368636426e-06, + "loss": 3.8512, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.577243421125906e-06, + "loss": 3.8454, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.568857473615386e-06, + "loss": 3.8336, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.560471526104866e-06, + "loss": 3.8483, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.552101957398076e-06, + "loss": 3.831, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.543716009887556e-06, + "loss": 3.8649, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.535330062377036e-06, + "loss": 3.8439, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.526944114866516e-06, + "loss": 3.8627, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.518558167355996e-06, + "loss": 3.8419, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.510188598649209e-06, + "loss": 3.8406, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.501802651138687e-06, + "loss": 3.8511, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.493416703628167e-06, + "loss": 3.8402, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.485030756117649e-06, + "loss": 3.843, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.476644808607127e-06, + "loss": 3.8424, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.46827523990034e-06, + "loss": 3.8511, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.45988929238982e-06, + "loss": 3.8394, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.4515033448793e-06, + "loss": 3.8442, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.443117397368778e-06, + "loss": 3.8321, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.43473144985826e-06, + "loss": 3.8354, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.42636188115147e-06, + "loss": 3.8559, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.417975933640948e-06, + "loss": 3.8532, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.40958998613043e-06, + "loss": 3.8408, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.40120403861991e-06, + "loss": 3.846, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.39281809110939e-06, + "loss": 3.851, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.384432143598868e-06, + "loss": 3.85, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.37606257489208e-06, + "loss": 3.8447, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.367693006185291e-06, + "loss": 3.8502, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.359307058674773e-06, + "loss": 3.8488, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.350921111164251e-06, + "loss": 3.8502, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.342535163653731e-06, + "loss": 3.8477, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.334165594946944e-06, + "loss": 3.8463, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.325779647436422e-06, + "loss": 3.8601, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.317393699925902e-06, + "loss": 3.8488, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.309007752415384e-06, + "loss": 3.8306, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.300621804904862e-06, + "loss": 3.8514, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.292235857394342e-06, + "loss": 3.849, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.283849909883822e-06, + "loss": 3.8446, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.275463962373303e-06, + "loss": 3.8474, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.267078014862782e-06, + "loss": 3.8397, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.258692067352262e-06, + "loss": 3.8507, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.250322498645474e-06, + "loss": 3.8414, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.241936551134952e-06, + "loss": 3.8438, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.233550603624432e-06, + "loss": 3.8488, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.225164656113914e-06, + "loss": 3.8421, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.216778708603394e-06, + "loss": 3.8597, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.208392761092872e-06, + "loss": 3.8342, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.200023192386085e-06, + "loss": 3.8358, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.191637244875565e-06, + "loss": 3.8465, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.183251297365043e-06, + "loss": 3.8476, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.174865349854523e-06, + "loss": 3.8562, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.166479402344004e-06, + "loss": 3.8472, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.158093454833484e-06, + "loss": 3.8374, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.149723886126695e-06, + "loss": 3.846, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.141337938616175e-06, + "loss": 3.8475, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.132951991105655e-06, + "loss": 3.8336, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.124566043595133e-06, + "loss": 3.8385, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.116180096084615e-06, + "loss": 3.8477, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.107810527377826e-06, + "loss": 3.8493, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.099424579867306e-06, + "loss": 3.8342, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.091038632356786e-06, + "loss": 3.8355, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.082652684846266e-06, + "loss": 3.8361, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.074266737335746e-06, + "loss": 3.8483, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.065880789825226e-06, + "loss": 3.8378, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.057494842314706e-06, + "loss": 3.8396, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.049108894804186e-06, + "loss": 3.8451, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.040739326097396e-06, + "loss": 3.8522, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.032369757390607e-06, + "loss": 3.8386, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.02400018868382e-06, + "loss": 3.8443, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.0156142411733e-06, + "loss": 3.8457, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.00722829366278e-06, + "loss": 3.8456, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 8.998842346152258e-06, + "loss": 3.8297, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.99045639864174e-06, + "loss": 3.8482, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.98207045113122e-06, + "loss": 3.8441, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.97370088242443e-06, + "loss": 3.8528, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.96531493491391e-06, + "loss": 3.838, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.95692898740339e-06, + "loss": 3.8451, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.94854303989287e-06, + "loss": 3.8415, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.94017347118608e-06, + "loss": 3.8395, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.93178752367556e-06, + "loss": 3.8297, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.92340157616504e-06, + "loss": 3.8543, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.915015628654522e-06, + "loss": 3.8563, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.906629681144e-06, + "loss": 3.8446, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.89824373363348e-06, + "loss": 3.8374, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.88985778612296e-06, + "loss": 3.8513, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.88147183861244e-06, + "loss": 3.8488, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.87308589110192e-06, + "loss": 3.8437, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.8646999435914e-06, + "loss": 3.8442, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.85631399608088e-06, + "loss": 3.8561, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.847944427374091e-06, + "loss": 3.8488, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.839574858667304e-06, + "loss": 3.8462, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.831188911156784e-06, + "loss": 3.8375, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.822802963646262e-06, + "loss": 3.848, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.814417016135742e-06, + "loss": 3.8486, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.806031068625223e-06, + "loss": 3.8357, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.797645121114703e-06, + "loss": 3.8609, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.789259173604182e-06, + "loss": 3.8415, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.780873226093662e-06, + "loss": 3.8479, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.772487278583143e-06, + "loss": 3.8479, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.764117709876352e-06, + "loss": 3.8425, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 4.025439739227295, + "eval_runtime": 302.8081, + "eval_samples_per_second": 1260.174, + "eval_steps_per_second": 39.381, + "step": 2518544 + }, + { + "epoch": 2.0, + "learning_rate": 8.755731762365834e-06, + "loss": 3.842, + "step": 2519040 + }, + { + "epoch": 2.0, + "learning_rate": 8.747362193659045e-06, + "loss": 3.8468, + "step": 2519552 + }, + { + "epoch": 2.0, + "learning_rate": 8.738976246148525e-06, + "loss": 3.8561, + "step": 2520064 + }, + { + "epoch": 2.0, + "learning_rate": 8.730590298638005e-06, + "loss": 3.8494, + "step": 2520576 + }, + { + "epoch": 2.0, + "learning_rate": 8.722204351127485e-06, + "loss": 3.8511, + "step": 2521088 + }, + { + "epoch": 2.0, + "learning_rate": 8.713818403616965e-06, + "loss": 3.8379, + "step": 2521600 + }, + { + "epoch": 2.0, + "learning_rate": 8.705432456106443e-06, + "loss": 3.8444, + "step": 2522112 + }, + { + "epoch": 2.0, + "learning_rate": 8.697046508595925e-06, + "loss": 3.8399, + "step": 2522624 + }, + { + "epoch": 2.0, + "learning_rate": 8.688660561085405e-06, + "loss": 3.8579, + "step": 2523136 + }, + { + "epoch": 2.0, + "learning_rate": 8.680274613574883e-06, + "loss": 3.8391, + "step": 2523648 + }, + { + "epoch": 2.0, + "learning_rate": 8.671905044868095e-06, + "loss": 3.8535, + "step": 2524160 + }, + { + "epoch": 2.0, + "learning_rate": 8.663535476161306e-06, + "loss": 3.8515, + "step": 2524672 + }, + { + "epoch": 2.0, + "learning_rate": 8.655165907454519e-06, + "loss": 3.8401, + "step": 2525184 + }, + { + "epoch": 2.0, + "learning_rate": 8.646779959943999e-06, + "loss": 3.8385, + "step": 2525696 + }, + { + "epoch": 2.0, + "learning_rate": 8.638394012433477e-06, + "loss": 3.8317, + "step": 2526208 + }, + { + "epoch": 2.0, + "learning_rate": 8.630008064922958e-06, + "loss": 3.8372, + "step": 2526720 + }, + { + "epoch": 2.0, + "learning_rate": 8.621622117412438e-06, + "loss": 3.8423, + "step": 2527232 + }, + { + "epoch": 2.0, + "learning_rate": 8.613236169901917e-06, + "loss": 3.8396, + "step": 2527744 + }, + { + "epoch": 2.0, + "learning_rate": 8.604850222391397e-06, + "loss": 3.8406, + "step": 2528256 + }, + { + "epoch": 2.0, + "learning_rate": 8.596464274880878e-06, + "loss": 3.8643, + "step": 2528768 + }, + { + "epoch": 2.0, + "learning_rate": 8.588078327370357e-06, + "loss": 3.8421, + "step": 2529280 + }, + { + "epoch": 2.0, + "learning_rate": 8.579692379859836e-06, + "loss": 3.846, + "step": 2529792 + }, + { + "epoch": 2.0, + "learning_rate": 8.571306432349316e-06, + "loss": 3.8501, + "step": 2530304 + }, + { + "epoch": 2.0, + "learning_rate": 8.562920484838798e-06, + "loss": 3.8414, + "step": 2530816 + }, + { + "epoch": 2.0, + "learning_rate": 8.554534537328276e-06, + "loss": 3.8441, + "step": 2531328 + }, + { + "epoch": 2.0, + "learning_rate": 8.546148589817756e-06, + "loss": 3.8342, + "step": 2531840 + }, + { + "epoch": 2.0, + "learning_rate": 8.537762642307238e-06, + "loss": 3.8429, + "step": 2532352 + }, + { + "epoch": 2.0, + "learning_rate": 8.529393073600447e-06, + "loss": 3.8458, + "step": 2532864 + }, + { + "epoch": 2.0, + "learning_rate": 8.521007126089927e-06, + "loss": 3.8307, + "step": 2533376 + }, + { + "epoch": 2.01, + "learning_rate": 8.512621178579409e-06, + "loss": 3.8453, + "step": 2533888 + }, + { + "epoch": 2.01, + "learning_rate": 8.504235231068889e-06, + "loss": 3.8354, + "step": 2534400 + }, + { + "epoch": 2.01, + "learning_rate": 8.495849283558367e-06, + "loss": 3.8513, + "step": 2534912 + }, + { + "epoch": 2.01, + "learning_rate": 8.48747971485158e-06, + "loss": 3.8509, + "step": 2535424 + }, + { + "epoch": 2.01, + "learning_rate": 8.47911014614479e-06, + "loss": 3.8355, + "step": 2535936 + }, + { + "epoch": 2.01, + "learning_rate": 8.470740577438003e-06, + "loss": 3.8455, + "step": 2536448 + }, + { + "epoch": 2.01, + "learning_rate": 8.462354629927481e-06, + "loss": 3.8587, + "step": 2536960 + }, + { + "epoch": 2.01, + "learning_rate": 8.45396868241696e-06, + "loss": 3.8313, + "step": 2537472 + }, + { + "epoch": 2.01, + "learning_rate": 8.445582734906442e-06, + "loss": 3.8445, + "step": 2537984 + }, + { + "epoch": 2.01, + "learning_rate": 8.43719678739592e-06, + "loss": 3.8406, + "step": 2538496 + }, + { + "epoch": 2.01, + "learning_rate": 8.4288108398854e-06, + "loss": 3.8332, + "step": 2539008 + }, + { + "epoch": 2.01, + "learning_rate": 8.42042489237488e-06, + "loss": 3.844, + "step": 2539520 + }, + { + "epoch": 2.01, + "learning_rate": 8.412038944864362e-06, + "loss": 3.8549, + "step": 2540032 + }, + { + "epoch": 2.01, + "learning_rate": 8.403669376157571e-06, + "loss": 3.8477, + "step": 2540544 + }, + { + "epoch": 2.01, + "learning_rate": 8.395283428647051e-06, + "loss": 3.8406, + "step": 2541056 + }, + { + "epoch": 2.01, + "learning_rate": 8.386897481136533e-06, + "loss": 3.8524, + "step": 2541568 + }, + { + "epoch": 2.01, + "learning_rate": 8.378511533626011e-06, + "loss": 3.8418, + "step": 2542080 + }, + { + "epoch": 2.01, + "learning_rate": 8.370125586115491e-06, + "loss": 3.8474, + "step": 2542592 + }, + { + "epoch": 2.01, + "learning_rate": 8.361756017408704e-06, + "loss": 3.8286, + "step": 2543104 + }, + { + "epoch": 2.01, + "learning_rate": 8.353370069898184e-06, + "loss": 3.8408, + "step": 2543616 + }, + { + "epoch": 2.01, + "learning_rate": 8.344984122387662e-06, + "loss": 3.8519, + "step": 2544128 + }, + { + "epoch": 2.01, + "learning_rate": 8.336598174877144e-06, + "loss": 3.848, + "step": 2544640 + }, + { + "epoch": 2.01, + "learning_rate": 8.328212227366624e-06, + "loss": 3.8417, + "step": 2545152 + }, + { + "epoch": 2.01, + "learning_rate": 8.319842658659834e-06, + "loss": 3.8345, + "step": 2545664 + }, + { + "epoch": 2.01, + "learning_rate": 8.311456711149314e-06, + "loss": 3.8459, + "step": 2546176 + }, + { + "epoch": 2.01, + "learning_rate": 8.303070763638794e-06, + "loss": 3.8287, + "step": 2546688 + }, + { + "epoch": 2.01, + "learning_rate": 8.294684816128274e-06, + "loss": 3.8569, + "step": 2547200 + }, + { + "epoch": 2.01, + "learning_rate": 8.286315247421485e-06, + "loss": 3.8395, + "step": 2547712 + }, + { + "epoch": 2.01, + "learning_rate": 8.277929299910965e-06, + "loss": 3.8589, + "step": 2548224 + }, + { + "epoch": 2.01, + "learning_rate": 8.269543352400445e-06, + "loss": 3.841, + "step": 2548736 + }, + { + "epoch": 2.01, + "learning_rate": 8.261157404889925e-06, + "loss": 3.8398, + "step": 2549248 + }, + { + "epoch": 2.01, + "learning_rate": 8.252787836183136e-06, + "loss": 3.8442, + "step": 2549760 + }, + { + "epoch": 2.01, + "learning_rate": 8.244401888672616e-06, + "loss": 3.8427, + "step": 2550272 + }, + { + "epoch": 2.01, + "learning_rate": 8.236015941162097e-06, + "loss": 3.8386, + "step": 2550784 + }, + { + "epoch": 2.01, + "learning_rate": 8.227629993651576e-06, + "loss": 3.8354, + "step": 2551296 + }, + { + "epoch": 2.01, + "learning_rate": 8.219244046141055e-06, + "loss": 3.852, + "step": 2551808 + }, + { + "epoch": 2.01, + "learning_rate": 8.210858098630535e-06, + "loss": 3.8367, + "step": 2552320 + }, + { + "epoch": 2.01, + "learning_rate": 8.202472151120017e-06, + "loss": 3.8338, + "step": 2552832 + }, + { + "epoch": 2.01, + "learning_rate": 8.194086203609495e-06, + "loss": 3.8331, + "step": 2553344 + }, + { + "epoch": 2.01, + "learning_rate": 8.185700256098975e-06, + "loss": 3.8322, + "step": 2553856 + }, + { + "epoch": 2.01, + "learning_rate": 8.177330687392188e-06, + "loss": 3.854, + "step": 2554368 + }, + { + "epoch": 2.01, + "learning_rate": 8.168944739881666e-06, + "loss": 3.8492, + "step": 2554880 + }, + { + "epoch": 2.01, + "learning_rate": 8.160558792371146e-06, + "loss": 3.8397, + "step": 2555392 + }, + { + "epoch": 2.01, + "learning_rate": 8.152189223664358e-06, + "loss": 3.8417, + "step": 2555904 + }, + { + "epoch": 2.01, + "learning_rate": 8.14381965495757e-06, + "loss": 3.8472, + "step": 2556416 + }, + { + "epoch": 2.01, + "learning_rate": 8.13543370744705e-06, + "loss": 3.8442, + "step": 2556928 + }, + { + "epoch": 2.01, + "learning_rate": 8.12704775993653e-06, + "loss": 3.8427, + "step": 2557440 + }, + { + "epoch": 2.01, + "learning_rate": 8.118661812426009e-06, + "loss": 3.8443, + "step": 2557952 + }, + { + "epoch": 2.01, + "learning_rate": 8.110275864915489e-06, + "loss": 3.845, + "step": 2558464 + }, + { + "epoch": 2.01, + "learning_rate": 8.101889917404969e-06, + "loss": 3.8488, + "step": 2558976 + }, + { + "epoch": 2.01, + "learning_rate": 8.093503969894449e-06, + "loss": 3.8409, + "step": 2559488 + }, + { + "epoch": 2.01, + "learning_rate": 8.085118022383929e-06, + "loss": 3.8461, + "step": 2560000 + }, + { + "epoch": 2.01, + "learning_rate": 8.076732074873409e-06, + "loss": 3.8512, + "step": 2560512 + }, + { + "epoch": 2.01, + "learning_rate": 8.068346127362889e-06, + "loss": 3.8457, + "step": 2561024 + }, + { + "epoch": 2.01, + "learning_rate": 8.059960179852369e-06, + "loss": 3.8274, + "step": 2561536 + }, + { + "epoch": 2.01, + "learning_rate": 8.051574232341847e-06, + "loss": 3.8489, + "step": 2562048 + }, + { + "epoch": 2.01, + "learning_rate": 8.043188284831329e-06, + "loss": 3.8446, + "step": 2562560 + }, + { + "epoch": 2.01, + "learning_rate": 8.03481871612454e-06, + "loss": 3.8444, + "step": 2563072 + }, + { + "epoch": 2.01, + "learning_rate": 8.02643276861402e-06, + "loss": 3.8444, + "step": 2563584 + }, + { + "epoch": 2.01, + "learning_rate": 8.0180468211035e-06, + "loss": 3.8361, + "step": 2564096 + }, + { + "epoch": 2.02, + "learning_rate": 8.00966087359298e-06, + "loss": 3.845, + "step": 2564608 + }, + { + "epoch": 2.02, + "learning_rate": 8.00127492608246e-06, + "loss": 3.8359, + "step": 2565120 + }, + { + "epoch": 2.02, + "learning_rate": 7.99290535737567e-06, + "loss": 3.8457, + "step": 2565632 + }, + { + "epoch": 2.02, + "learning_rate": 7.98451940986515e-06, + "loss": 3.8391, + "step": 2566144 + }, + { + "epoch": 2.02, + "learning_rate": 7.97613346235463e-06, + "loss": 3.8406, + "step": 2566656 + }, + { + "epoch": 2.02, + "learning_rate": 7.96774751484411e-06, + "loss": 3.8533, + "step": 2567168 + }, + { + "epoch": 2.02, + "learning_rate": 7.95936156733359e-06, + "loss": 3.8379, + "step": 2567680 + }, + { + "epoch": 2.02, + "learning_rate": 7.95097561982307e-06, + "loss": 3.8264, + "step": 2568192 + }, + { + "epoch": 2.02, + "learning_rate": 7.942606051116282e-06, + "loss": 3.8444, + "step": 2568704 + }, + { + "epoch": 2.02, + "learning_rate": 7.93422010360576e-06, + "loss": 3.8462, + "step": 2569216 + }, + { + "epoch": 2.02, + "learning_rate": 7.92583415609524e-06, + "loss": 3.8532, + "step": 2569728 + }, + { + "epoch": 2.02, + "learning_rate": 7.91744820858472e-06, + "loss": 3.8397, + "step": 2570240 + }, + { + "epoch": 2.02, + "learning_rate": 7.909062261074202e-06, + "loss": 3.8375, + "step": 2570752 + }, + { + "epoch": 2.02, + "learning_rate": 7.90067631356368e-06, + "loss": 3.8375, + "step": 2571264 + }, + { + "epoch": 2.02, + "learning_rate": 7.89229036605316e-06, + "loss": 3.8478, + "step": 2571776 + }, + { + "epoch": 2.02, + "learning_rate": 7.883920797346373e-06, + "loss": 3.831, + "step": 2572288 + }, + { + "epoch": 2.02, + "learning_rate": 7.875534849835851e-06, + "loss": 3.8341, + "step": 2572800 + }, + { + "epoch": 2.02, + "learning_rate": 7.867148902325331e-06, + "loss": 3.8438, + "step": 2573312 + }, + { + "epoch": 2.02, + "learning_rate": 7.858779333618544e-06, + "loss": 3.848, + "step": 2573824 + }, + { + "epoch": 2.02, + "learning_rate": 7.850409764911754e-06, + "loss": 3.8273, + "step": 2574336 + }, + { + "epoch": 2.02, + "learning_rate": 7.842023817401234e-06, + "loss": 3.8341, + "step": 2574848 + }, + { + "epoch": 2.02, + "learning_rate": 7.833637869890714e-06, + "loss": 3.8339, + "step": 2575360 + }, + { + "epoch": 2.02, + "learning_rate": 7.825251922380194e-06, + "loss": 3.8434, + "step": 2575872 + }, + { + "epoch": 2.02, + "learning_rate": 7.816865974869674e-06, + "loss": 3.8367, + "step": 2576384 + }, + { + "epoch": 2.02, + "learning_rate": 7.808480027359154e-06, + "loss": 3.8324, + "step": 2576896 + }, + { + "epoch": 2.02, + "learning_rate": 7.800094079848634e-06, + "loss": 3.8484, + "step": 2577408 + }, + { + "epoch": 2.02, + "learning_rate": 7.791708132338114e-06, + "loss": 3.8454, + "step": 2577920 + }, + { + "epoch": 2.02, + "learning_rate": 7.783338563631325e-06, + "loss": 3.8363, + "step": 2578432 + }, + { + "epoch": 2.02, + "learning_rate": 7.774952616120805e-06, + "loss": 3.841, + "step": 2578944 + }, + { + "epoch": 2.02, + "learning_rate": 7.766566668610285e-06, + "loss": 3.8399, + "step": 2579456 + }, + { + "epoch": 2.02, + "learning_rate": 7.758180721099766e-06, + "loss": 3.8419, + "step": 2579968 + }, + { + "epoch": 2.02, + "learning_rate": 7.749794773589245e-06, + "loss": 3.827, + "step": 2580480 + }, + { + "epoch": 2.02, + "learning_rate": 7.741408826078725e-06, + "loss": 3.8478, + "step": 2580992 + }, + { + "epoch": 2.02, + "learning_rate": 7.733039257371937e-06, + "loss": 3.8419, + "step": 2581504 + }, + { + "epoch": 2.02, + "learning_rate": 7.724653309861415e-06, + "loss": 3.8461, + "step": 2582016 + }, + { + "epoch": 2.02, + "learning_rate": 7.716267362350895e-06, + "loss": 3.8354, + "step": 2582528 + }, + { + "epoch": 2.02, + "learning_rate": 7.707881414840375e-06, + "loss": 3.8427, + "step": 2583040 + }, + { + "epoch": 2.02, + "learning_rate": 7.699495467329857e-06, + "loss": 3.8368, + "step": 2583552 + }, + { + "epoch": 2.02, + "learning_rate": 7.691125898623066e-06, + "loss": 3.8366, + "step": 2584064 + }, + { + "epoch": 2.02, + "learning_rate": 7.682739951112548e-06, + "loss": 3.8226, + "step": 2584576 + }, + { + "epoch": 2.02, + "learning_rate": 7.674354003602028e-06, + "loss": 3.8556, + "step": 2585088 + }, + { + "epoch": 2.02, + "learning_rate": 7.665968056091506e-06, + "loss": 3.8516, + "step": 2585600 + }, + { + "epoch": 2.02, + "learning_rate": 7.657582108580986e-06, + "loss": 3.8424, + "step": 2586112 + }, + { + "epoch": 2.02, + "learning_rate": 7.649212539874198e-06, + "loss": 3.8291, + "step": 2586624 + }, + { + "epoch": 2.02, + "learning_rate": 7.640826592363678e-06, + "loss": 3.854, + "step": 2587136 + }, + { + "epoch": 2.02, + "learning_rate": 7.632440644853157e-06, + "loss": 3.8447, + "step": 2587648 + }, + { + "epoch": 2.02, + "learning_rate": 7.624054697342637e-06, + "loss": 3.8405, + "step": 2588160 + }, + { + "epoch": 2.02, + "learning_rate": 7.615668749832118e-06, + "loss": 3.8388, + "step": 2588672 + }, + { + "epoch": 2.02, + "learning_rate": 7.607315559929061e-06, + "loss": 3.8514, + "step": 2589184 + }, + { + "epoch": 2.02, + "learning_rate": 7.59892961241854e-06, + "loss": 3.8424, + "step": 2589696 + }, + { + "epoch": 2.02, + "learning_rate": 7.590543664908021e-06, + "loss": 3.8468, + "step": 2590208 + }, + { + "epoch": 2.02, + "learning_rate": 7.5821577173975005e-06, + "loss": 3.8323, + "step": 2590720 + }, + { + "epoch": 2.02, + "learning_rate": 7.57377176988698e-06, + "loss": 3.8431, + "step": 2591232 + }, + { + "epoch": 2.02, + "learning_rate": 7.56538582237646e-06, + "loss": 3.8461, + "step": 2591744 + }, + { + "epoch": 2.02, + "learning_rate": 7.55699987486594e-06, + "loss": 3.8363, + "step": 2592256 + }, + { + "epoch": 2.02, + "learning_rate": 7.548613927355419e-06, + "loss": 3.8569, + "step": 2592768 + }, + { + "epoch": 2.02, + "learning_rate": 7.5402279798448995e-06, + "loss": 3.8386, + "step": 2593280 + }, + { + "epoch": 2.02, + "learning_rate": 7.5318420323343794e-06, + "loss": 3.8422, + "step": 2593792 + }, + { + "epoch": 2.02, + "learning_rate": 7.523472463627591e-06, + "loss": 3.8421, + "step": 2594304 + }, + { + "epoch": 2.02, + "learning_rate": 7.51508651611707e-06, + "loss": 3.843, + "step": 2594816 + }, + { + "epoch": 2.03, + "eval_loss": 4.02437162399292, + "eval_runtime": 295.9583, + "eval_samples_per_second": 1289.34, + "eval_steps_per_second": 40.293, + "step": 2594864 + }, + { + "epoch": 0.0, + "learning_rate": 7.506700568606551e-06, + "loss": 3.836, + "step": 2595328 + }, + { + "epoch": 0.0, + "learning_rate": 7.498314621096031e-06, + "loss": 3.8457, + "step": 2595840 + }, + { + "epoch": 0.0, + "learning_rate": 7.48992867358551e-06, + "loss": 3.8512, + "step": 2596352 + }, + { + "epoch": 0.0, + "learning_rate": 7.48154272607499e-06, + "loss": 3.8482, + "step": 2596864 + }, + { + "epoch": 0.0, + "learning_rate": 7.473156778564471e-06, + "loss": 3.8494, + "step": 2597376 + }, + { + "epoch": 0.0, + "learning_rate": 7.464770831053951e-06, + "loss": 3.8321, + "step": 2597888 + }, + { + "epoch": 0.0, + "learning_rate": 7.45638488354343e-06, + "loss": 3.8406, + "step": 2598400 + }, + { + "epoch": 0.0, + "learning_rate": 7.44799893603291e-06, + "loss": 3.8378, + "step": 2598912 + }, + { + "epoch": 0.0, + "learning_rate": 7.439612988522391e-06, + "loss": 3.8512, + "step": 2599424 + }, + { + "epoch": 0.0, + "learning_rate": 7.431227041011869e-06, + "loss": 3.8422, + "step": 2599936 + }, + { + "epoch": 0.0, + "learning_rate": 7.42284109350135e-06, + "loss": 3.845, + "step": 2600448 + }, + { + "epoch": 0.0, + "learning_rate": 7.41445514599083e-06, + "loss": 3.8508, + "step": 2600960 + }, + { + "epoch": 0.0, + "learning_rate": 7.406085577284041e-06, + "loss": 3.8345, + "step": 2601472 + }, + { + "epoch": 0.0, + "learning_rate": 7.39769962977352e-06, + "loss": 3.8383, + "step": 2601984 + }, + { + "epoch": 0.0, + "learning_rate": 7.389313682263e-06, + "loss": 3.828, + "step": 2602496 + }, + { + "epoch": 0.0, + "learning_rate": 7.380927734752481e-06, + "loss": 3.8365, + "step": 2603008 + }, + { + "epoch": 0.0, + "learning_rate": 7.37254178724196e-06, + "loss": 3.8385, + "step": 2603520 + }, + { + "epoch": 0.0, + "learning_rate": 7.36415583973144e-06, + "loss": 3.8342, + "step": 2604032 + }, + { + "epoch": 0.0, + "learning_rate": 7.355769892220921e-06, + "loss": 3.8381, + "step": 2604544 + }, + { + "epoch": 0.0, + "learning_rate": 7.347400323514133e-06, + "loss": 3.858, + "step": 2605056 + }, + { + "epoch": 0.0, + "learning_rate": 7.339030754807343e-06, + "loss": 3.8408, + "step": 2605568 + }, + { + "epoch": 0.0, + "learning_rate": 7.3306448072968225e-06, + "loss": 3.8426, + "step": 2606080 + }, + { + "epoch": 0.0, + "learning_rate": 7.322258859786303e-06, + "loss": 3.8476, + "step": 2606592 + }, + { + "epoch": 0.0, + "learning_rate": 7.3138729122757825e-06, + "loss": 3.8413, + "step": 2607104 + }, + { + "epoch": 0.0, + "learning_rate": 7.305486964765262e-06, + "loss": 3.8424, + "step": 2607616 + }, + { + "epoch": 0.0, + "learning_rate": 7.297101017254742e-06, + "loss": 3.8325, + "step": 2608128 + }, + { + "epoch": 0.0, + "learning_rate": 7.288715069744223e-06, + "loss": 3.8404, + "step": 2608640 + }, + { + "epoch": 0.0, + "learning_rate": 7.280329122233702e-06, + "loss": 3.8389, + "step": 2609152 + }, + { + "epoch": 0.0, + "learning_rate": 7.271959553526914e-06, + "loss": 3.8264, + "step": 2609664 + }, + { + "epoch": 0.01, + "learning_rate": 7.263573606016394e-06, + "loss": 3.8456, + "step": 2610176 + }, + { + "epoch": 0.01, + "learning_rate": 7.255187658505873e-06, + "loss": 3.8304, + "step": 2610688 + }, + { + "epoch": 0.01, + "learning_rate": 7.246801710995353e-06, + "loss": 3.8475, + "step": 2611200 + }, + { + "epoch": 0.01, + "learning_rate": 7.238415763484834e-06, + "loss": 3.8466, + "step": 2611712 + }, + { + "epoch": 0.01, + "learning_rate": 7.230046194778045e-06, + "loss": 3.8312, + "step": 2612224 + }, + { + "epoch": 0.01, + "learning_rate": 7.221676626071255e-06, + "loss": 3.8418, + "step": 2612736 + }, + { + "epoch": 0.01, + "learning_rate": 7.213290678560736e-06, + "loss": 3.858, + "step": 2613248 + }, + { + "epoch": 0.01, + "learning_rate": 7.204904731050216e-06, + "loss": 3.829, + "step": 2613760 + }, + { + "epoch": 0.01, + "learning_rate": 7.196518783539696e-06, + "loss": 3.8431, + "step": 2614272 + }, + { + "epoch": 0.01, + "learning_rate": 7.188132836029175e-06, + "loss": 3.8336, + "step": 2614784 + }, + { + "epoch": 0.01, + "learning_rate": 7.179746888518656e-06, + "loss": 3.8336, + "step": 2615296 + }, + { + "epoch": 0.01, + "learning_rate": 7.171360941008136e-06, + "loss": 3.8369, + "step": 2615808 + }, + { + "epoch": 0.01, + "learning_rate": 7.162974993497615e-06, + "loss": 3.852, + "step": 2616320 + }, + { + "epoch": 0.01, + "learning_rate": 7.154589045987095e-06, + "loss": 3.8438, + "step": 2616832 + }, + { + "epoch": 0.01, + "learning_rate": 7.146203098476576e-06, + "loss": 3.8389, + "step": 2617344 + }, + { + "epoch": 0.01, + "learning_rate": 7.137833529769787e-06, + "loss": 3.8473, + "step": 2617856 + }, + { + "epoch": 0.01, + "learning_rate": 7.129447582259266e-06, + "loss": 3.8362, + "step": 2618368 + }, + { + "epoch": 0.01, + "learning_rate": 7.1210616347487465e-06, + "loss": 3.8468, + "step": 2618880 + }, + { + "epoch": 0.01, + "learning_rate": 7.112692066041958e-06, + "loss": 3.8272, + "step": 2619392 + }, + { + "epoch": 0.01, + "learning_rate": 7.104306118531437e-06, + "loss": 3.8317, + "step": 2619904 + }, + { + "epoch": 0.01, + "learning_rate": 7.095920171020917e-06, + "loss": 3.849, + "step": 2620416 + }, + { + "epoch": 0.01, + "learning_rate": 7.087534223510397e-06, + "loss": 3.8471, + "step": 2620928 + }, + { + "epoch": 0.01, + "learning_rate": 7.079148275999878e-06, + "loss": 3.8344, + "step": 2621440 + }, + { + "epoch": 0.01, + "learning_rate": 7.070762328489357e-06, + "loss": 3.8326, + "step": 2621952 + }, + { + "epoch": 0.01, + "learning_rate": 7.062376380978837e-06, + "loss": 3.8434, + "step": 2622464 + }, + { + "epoch": 0.01, + "learning_rate": 7.053990433468318e-06, + "loss": 3.8233, + "step": 2622976 + }, + { + "epoch": 0.01, + "learning_rate": 7.045604485957796e-06, + "loss": 3.8508, + "step": 2623488 + }, + { + "epoch": 0.01, + "learning_rate": 7.037234917251008e-06, + "loss": 3.8422, + "step": 2624000 + }, + { + "epoch": 0.01, + "learning_rate": 7.0288489697404885e-06, + "loss": 3.8538, + "step": 2624512 + }, + { + "epoch": 0.01, + "learning_rate": 7.0204630222299685e-06, + "loss": 3.8422, + "step": 2625024 + }, + { + "epoch": 0.01, + "learning_rate": 7.012093453523179e-06, + "loss": 3.8339, + "step": 2625536 + }, + { + "epoch": 0.01, + "learning_rate": 7.003707506012659e-06, + "loss": 3.8396, + "step": 2626048 + }, + { + "epoch": 0.01, + "learning_rate": 6.995321558502139e-06, + "loss": 3.8423, + "step": 2626560 + }, + { + "epoch": 0.01, + "learning_rate": 6.986935610991618e-06, + "loss": 3.8334, + "step": 2627072 + }, + { + "epoch": 0.01, + "learning_rate": 6.978549663481099e-06, + "loss": 3.8353, + "step": 2627584 + }, + { + "epoch": 0.01, + "learning_rate": 6.970163715970579e-06, + "loss": 3.8462, + "step": 2628096 + }, + { + "epoch": 0.01, + "learning_rate": 6.961777768460058e-06, + "loss": 3.8389, + "step": 2628608 + }, + { + "epoch": 0.01, + "learning_rate": 6.953391820949538e-06, + "loss": 3.8269, + "step": 2629120 + }, + { + "epoch": 0.01, + "learning_rate": 6.945005873439019e-06, + "loss": 3.8322, + "step": 2629632 + }, + { + "epoch": 0.01, + "learning_rate": 6.9366363047322305e-06, + "loss": 3.8281, + "step": 2630144 + }, + { + "epoch": 0.01, + "learning_rate": 6.928250357221709e-06, + "loss": 3.8491, + "step": 2630656 + }, + { + "epoch": 0.01, + "learning_rate": 6.91986440971119e-06, + "loss": 3.8482, + "step": 2631168 + }, + { + "epoch": 0.01, + "learning_rate": 6.9114784622006695e-06, + "loss": 3.8364, + "step": 2631680 + }, + { + "epoch": 0.01, + "learning_rate": 6.903108893493881e-06, + "loss": 3.8408, + "step": 2632192 + }, + { + "epoch": 0.01, + "learning_rate": 6.89472294598336e-06, + "loss": 3.8417, + "step": 2632704 + }, + { + "epoch": 0.01, + "learning_rate": 6.886336998472841e-06, + "loss": 3.8418, + "step": 2633216 + }, + { + "epoch": 0.01, + "learning_rate": 6.877951050962321e-06, + "loss": 3.8389, + "step": 2633728 + }, + { + "epoch": 0.01, + "learning_rate": 6.8695651034518e-06, + "loss": 3.8461, + "step": 2634240 + }, + { + "epoch": 0.01, + "learning_rate": 6.861195534745012e-06, + "loss": 3.8404, + "step": 2634752 + }, + { + "epoch": 0.01, + "learning_rate": 6.852809587234492e-06, + "loss": 3.8468, + "step": 2635264 + }, + { + "epoch": 0.01, + "learning_rate": 6.8444236397239726e-06, + "loss": 3.8378, + "step": 2635776 + }, + { + "epoch": 0.01, + "learning_rate": 6.836037692213451e-06, + "loss": 3.8426, + "step": 2636288 + }, + { + "epoch": 0.01, + "learning_rate": 6.827651744702932e-06, + "loss": 3.8448, + "step": 2636800 + }, + { + "epoch": 0.01, + "learning_rate": 6.819265797192412e-06, + "loss": 3.8439, + "step": 2637312 + }, + { + "epoch": 0.01, + "learning_rate": 6.810896228485622e-06, + "loss": 3.8311, + "step": 2637824 + }, + { + "epoch": 0.01, + "learning_rate": 6.802510280975102e-06, + "loss": 3.8413, + "step": 2638336 + }, + { + "epoch": 0.01, + "learning_rate": 6.794124333464582e-06, + "loss": 3.8419, + "step": 2638848 + }, + { + "epoch": 0.01, + "learning_rate": 6.785738385954063e-06, + "loss": 3.8423, + "step": 2639360 + }, + { + "epoch": 0.01, + "learning_rate": 6.777368817247273e-06, + "loss": 3.8434, + "step": 2639872 + }, + { + "epoch": 0.01, + "learning_rate": 6.768982869736754e-06, + "loss": 3.8283, + "step": 2640384 + }, + { + "epoch": 0.02, + "learning_rate": 6.760596922226234e-06, + "loss": 3.8415, + "step": 2640896 + }, + { + "epoch": 0.02, + "learning_rate": 6.752210974715713e-06, + "loss": 3.837, + "step": 2641408 + }, + { + "epoch": 0.02, + "learning_rate": 6.743825027205193e-06, + "loss": 3.8431, + "step": 2641920 + }, + { + "epoch": 0.02, + "learning_rate": 6.735439079694674e-06, + "loss": 3.8299, + "step": 2642432 + }, + { + "epoch": 0.02, + "learning_rate": 6.727053132184154e-06, + "loss": 3.8399, + "step": 2642944 + }, + { + "epoch": 0.02, + "learning_rate": 6.718667184673633e-06, + "loss": 3.8522, + "step": 2643456 + }, + { + "epoch": 0.02, + "learning_rate": 6.710297615966844e-06, + "loss": 3.8361, + "step": 2643968 + }, + { + "epoch": 0.02, + "learning_rate": 6.701928047260056e-06, + "loss": 3.8234, + "step": 2644480 + }, + { + "epoch": 0.02, + "learning_rate": 6.693542099749536e-06, + "loss": 3.8425, + "step": 2644992 + }, + { + "epoch": 0.02, + "learning_rate": 6.685156152239015e-06, + "loss": 3.8412, + "step": 2645504 + }, + { + "epoch": 0.02, + "learning_rate": 6.676770204728496e-06, + "loss": 3.8455, + "step": 2646016 + }, + { + "epoch": 0.02, + "learning_rate": 6.668384257217976e-06, + "loss": 3.8404, + "step": 2646528 + }, + { + "epoch": 0.02, + "learning_rate": 6.660014688511186e-06, + "loss": 3.8351, + "step": 2647040 + }, + { + "epoch": 0.02, + "learning_rate": 6.651645119804397e-06, + "loss": 3.8326, + "step": 2647552 + }, + { + "epoch": 0.02, + "learning_rate": 6.643259172293878e-06, + "loss": 3.8468, + "step": 2648064 + }, + { + "epoch": 0.02, + "learning_rate": 6.634873224783358e-06, + "loss": 3.8244, + "step": 2648576 + }, + { + "epoch": 0.02, + "learning_rate": 6.626487277272837e-06, + "loss": 3.8319, + "step": 2649088 + }, + { + "epoch": 0.02, + "learning_rate": 6.618101329762317e-06, + "loss": 3.8413, + "step": 2649600 + }, + { + "epoch": 0.02, + "learning_rate": 6.609715382251798e-06, + "loss": 3.8458, + "step": 2650112 + }, + { + "epoch": 0.02, + "learning_rate": 6.601329434741277e-06, + "loss": 3.8221, + "step": 2650624 + }, + { + "epoch": 0.02, + "learning_rate": 6.592943487230757e-06, + "loss": 3.8392, + "step": 2651136 + }, + { + "epoch": 0.02, + "learning_rate": 6.584557539720238e-06, + "loss": 3.8253, + "step": 2651648 + }, + { + "epoch": 0.02, + "learning_rate": 6.576171592209718e-06, + "loss": 3.8428, + "step": 2652160 + }, + { + "epoch": 0.02, + "learning_rate": 6.567785644699197e-06, + "loss": 3.833, + "step": 2652672 + }, + { + "epoch": 0.02, + "learning_rate": 6.559399697188677e-06, + "loss": 3.8297, + "step": 2653184 + }, + { + "epoch": 0.02, + "learning_rate": 6.5510301284818885e-06, + "loss": 3.845, + "step": 2653696 + }, + { + "epoch": 0.02, + "learning_rate": 6.5426605597751e-06, + "loss": 3.8438, + "step": 2654208 + }, + { + "epoch": 0.02, + "learning_rate": 6.534274612264579e-06, + "loss": 3.8307, + "step": 2654720 + }, + { + "epoch": 0.02, + "learning_rate": 6.525888664754059e-06, + "loss": 3.8418, + "step": 2655232 + }, + { + "epoch": 0.02, + "learning_rate": 6.51750271724354e-06, + "loss": 3.8345, + "step": 2655744 + }, + { + "epoch": 0.02, + "learning_rate": 6.509116769733019e-06, + "loss": 3.8399, + "step": 2656256 + }, + { + "epoch": 0.02, + "learning_rate": 6.500730822222499e-06, + "loss": 3.823, + "step": 2656768 + }, + { + "epoch": 0.02, + "learning_rate": 6.492344874711979e-06, + "loss": 3.8443, + "step": 2657280 + }, + { + "epoch": 0.02, + "learning_rate": 6.483975306005191e-06, + "loss": 3.8371, + "step": 2657792 + }, + { + "epoch": 0.02, + "learning_rate": 6.4756057372984015e-06, + "loss": 3.8437, + "step": 2658304 + }, + { + "epoch": 0.02, + "learning_rate": 6.4672197897878815e-06, + "loss": 3.8347, + "step": 2658816 + }, + { + "epoch": 0.02, + "learning_rate": 6.458833842277362e-06, + "loss": 3.8393, + "step": 2659328 + }, + { + "epoch": 0.02, + "learning_rate": 6.4504478947668405e-06, + "loss": 3.8312, + "step": 2659840 + }, + { + "epoch": 0.02, + "learning_rate": 6.442078326060052e-06, + "loss": 3.8348, + "step": 2660352 + }, + { + "epoch": 0.02, + "learning_rate": 6.433708757353265e-06, + "loss": 3.8234, + "step": 2660864 + }, + { + "epoch": 0.02, + "learning_rate": 6.425322809842745e-06, + "loss": 3.8505, + "step": 2661376 + }, + { + "epoch": 0.02, + "learning_rate": 6.416936862332224e-06, + "loss": 3.8463, + "step": 2661888 + }, + { + "epoch": 0.02, + "learning_rate": 6.408550914821704e-06, + "loss": 3.8409, + "step": 2662400 + }, + { + "epoch": 0.02, + "learning_rate": 6.4001649673111845e-06, + "loss": 3.8295, + "step": 2662912 + }, + { + "epoch": 0.02, + "learning_rate": 6.391779019800664e-06, + "loss": 3.8468, + "step": 2663424 + }, + { + "epoch": 0.02, + "learning_rate": 6.3833930722901435e-06, + "loss": 3.8439, + "step": 2663936 + }, + { + "epoch": 0.02, + "learning_rate": 6.3750071247796235e-06, + "loss": 3.8362, + "step": 2664448 + }, + { + "epoch": 0.02, + "learning_rate": 6.366621177269104e-06, + "loss": 3.8377, + "step": 2664960 + }, + { + "epoch": 0.02, + "learning_rate": 6.358251608562314e-06, + "loss": 3.8441, + "step": 2665472 + }, + { + "epoch": 0.02, + "learning_rate": 6.349865661051794e-06, + "loss": 3.8431, + "step": 2665984 + }, + { + "epoch": 0.02, + "learning_rate": 6.341479713541275e-06, + "loss": 3.8465, + "step": 2666496 + }, + { + "epoch": 0.02, + "learning_rate": 6.333093766030754e-06, + "loss": 3.8284, + "step": 2667008 + }, + { + "epoch": 0.02, + "learning_rate": 6.324707818520234e-06, + "loss": 3.8423, + "step": 2667520 + }, + { + "epoch": 0.02, + "learning_rate": 6.316321871009714e-06, + "loss": 3.841, + "step": 2668032 + }, + { + "epoch": 0.02, + "learning_rate": 6.307952302302926e-06, + "loss": 3.833, + "step": 2668544 + }, + { + "epoch": 0.02, + "learning_rate": 6.299566354792405e-06, + "loss": 3.8525, + "step": 2669056 + }, + { + "epoch": 0.02, + "learning_rate": 6.2911804072818856e-06, + "loss": 3.8341, + "step": 2669568 + }, + { + "epoch": 0.02, + "learning_rate": 6.2827944597713655e-06, + "loss": 3.8409, + "step": 2670080 + }, + { + "epoch": 0.02, + "learning_rate": 6.274408512260845e-06, + "loss": 3.8408, + "step": 2670592 + }, + { + "epoch": 0.02, + "learning_rate": 6.2660225647503246e-06, + "loss": 3.837, + "step": 2671104 + }, + { + "epoch": 0.03, + "eval_loss": 4.023423194885254, + "eval_runtime": 297.1414, + "eval_samples_per_second": 1284.207, + "eval_steps_per_second": 40.132, + "step": 2671184 + }, + { + "epoch": 1.0, + "learning_rate": 6.257636617239805e-06, + "loss": 3.8374, + "step": 2671616 + }, + { + "epoch": 1.0, + "learning_rate": 6.2492506697292845e-06, + "loss": 3.8427, + "step": 2672128 + }, + { + "epoch": 1.0, + "learning_rate": 6.240881101022496e-06, + "loss": 3.8466, + "step": 2672640 + }, + { + "epoch": 1.0, + "learning_rate": 6.232511532315708e-06, + "loss": 3.8434, + "step": 2673152 + }, + { + "epoch": 1.0, + "learning_rate": 6.224125584805188e-06, + "loss": 3.8506, + "step": 2673664 + }, + { + "epoch": 1.0, + "learning_rate": 6.215739637294668e-06, + "loss": 3.831, + "step": 2674176 + }, + { + "epoch": 1.0, + "learning_rate": 6.207353689784148e-06, + "loss": 3.837, + "step": 2674688 + }, + { + "epoch": 1.0, + "learning_rate": 6.198984121077358e-06, + "loss": 3.8293, + "step": 2675200 + }, + { + "epoch": 1.0, + "learning_rate": 6.190598173566839e-06, + "loss": 3.8486, + "step": 2675712 + }, + { + "epoch": 1.0, + "learning_rate": 6.182212226056318e-06, + "loss": 3.838, + "step": 2676224 + }, + { + "epoch": 1.0, + "learning_rate": 6.17384265734953e-06, + "loss": 3.845, + "step": 2676736 + }, + { + "epoch": 1.0, + "learning_rate": 6.16545670983901e-06, + "loss": 3.8455, + "step": 2677248 + }, + { + "epoch": 1.0, + "learning_rate": 6.1570871411322216e-06, + "loss": 3.8289, + "step": 2677760 + }, + { + "epoch": 1.0, + "learning_rate": 6.148701193621701e-06, + "loss": 3.8326, + "step": 2678272 + }, + { + "epoch": 1.0, + "learning_rate": 6.140315246111181e-06, + "loss": 3.829, + "step": 2678784 + }, + { + "epoch": 1.0, + "learning_rate": 6.1319292986006614e-06, + "loss": 3.8295, + "step": 2679296 + }, + { + "epoch": 1.0, + "learning_rate": 6.1235433510901405e-06, + "loss": 3.8363, + "step": 2679808 + }, + { + "epoch": 1.0, + "learning_rate": 6.115157403579621e-06, + "loss": 3.8306, + "step": 2680320 + }, + { + "epoch": 1.0, + "learning_rate": 6.1067714560691004e-06, + "loss": 3.8345, + "step": 2680832 + }, + { + "epoch": 1.0, + "learning_rate": 6.09838550855858e-06, + "loss": 3.8555, + "step": 2681344 + }, + { + "epoch": 1.0, + "learning_rate": 6.08999956104806e-06, + "loss": 3.8391, + "step": 2681856 + }, + { + "epoch": 1.0, + "learning_rate": 6.08161361353754e-06, + "loss": 3.8418, + "step": 2682368 + }, + { + "epoch": 1.0, + "learning_rate": 6.073227666027019e-06, + "loss": 3.844, + "step": 2682880 + }, + { + "epoch": 1.0, + "learning_rate": 6.0648417185165e-06, + "loss": 3.8429, + "step": 2683392 + }, + { + "epoch": 1.0, + "learning_rate": 6.056472149809711e-06, + "loss": 3.8324, + "step": 2683904 + }, + { + "epoch": 1.0, + "learning_rate": 6.048086202299191e-06, + "loss": 3.8271, + "step": 2684416 + }, + { + "epoch": 1.0, + "learning_rate": 6.039700254788671e-06, + "loss": 3.8461, + "step": 2684928 + }, + { + "epoch": 1.0, + "learning_rate": 6.031314307278151e-06, + "loss": 3.831, + "step": 2685440 + }, + { + "epoch": 1.0, + "learning_rate": 6.022928359767631e-06, + "loss": 3.8271, + "step": 2685952 + }, + { + "epoch": 1.01, + "learning_rate": 6.0145587910608425e-06, + "loss": 3.838, + "step": 2686464 + }, + { + "epoch": 1.01, + "learning_rate": 6.0061728435503224e-06, + "loss": 3.83, + "step": 2686976 + }, + { + "epoch": 1.01, + "learning_rate": 5.997803274843534e-06, + "loss": 3.8398, + "step": 2687488 + }, + { + "epoch": 1.01, + "learning_rate": 5.989417327333013e-06, + "loss": 3.8412, + "step": 2688000 + }, + { + "epoch": 1.01, + "learning_rate": 5.981031379822493e-06, + "loss": 3.8318, + "step": 2688512 + }, + { + "epoch": 1.01, + "learning_rate": 5.972661811115705e-06, + "loss": 3.841, + "step": 2689024 + }, + { + "epoch": 1.01, + "learning_rate": 5.964275863605185e-06, + "loss": 3.8518, + "step": 2689536 + }, + { + "epoch": 1.01, + "learning_rate": 5.955889916094665e-06, + "loss": 3.8276, + "step": 2690048 + }, + { + "epoch": 1.01, + "learning_rate": 5.947503968584145e-06, + "loss": 3.8442, + "step": 2690560 + }, + { + "epoch": 1.01, + "learning_rate": 5.939118021073625e-06, + "loss": 3.8279, + "step": 2691072 + }, + { + "epoch": 1.01, + "learning_rate": 5.9307320735631045e-06, + "loss": 3.8354, + "step": 2691584 + }, + { + "epoch": 1.01, + "learning_rate": 5.922346126052584e-06, + "loss": 3.8313, + "step": 2692096 + }, + { + "epoch": 1.01, + "learning_rate": 5.9139601785420645e-06, + "loss": 3.8503, + "step": 2692608 + }, + { + "epoch": 1.01, + "learning_rate": 5.9055742310315436e-06, + "loss": 3.8409, + "step": 2693120 + }, + { + "epoch": 1.01, + "learning_rate": 5.897188283521024e-06, + "loss": 3.8404, + "step": 2693632 + }, + { + "epoch": 1.01, + "learning_rate": 5.8888023360105035e-06, + "loss": 3.843, + "step": 2694144 + }, + { + "epoch": 1.01, + "learning_rate": 5.8804163884999834e-06, + "loss": 3.8346, + "step": 2694656 + }, + { + "epoch": 1.01, + "learning_rate": 5.872030440989463e-06, + "loss": 3.8483, + "step": 2695168 + }, + { + "epoch": 1.01, + "learning_rate": 5.863660872282674e-06, + "loss": 3.8256, + "step": 2695680 + }, + { + "epoch": 1.01, + "learning_rate": 5.855274924772155e-06, + "loss": 3.8294, + "step": 2696192 + }, + { + "epoch": 1.01, + "learning_rate": 5.846888977261634e-06, + "loss": 3.8458, + "step": 2696704 + }, + { + "epoch": 1.01, + "learning_rate": 5.838503029751115e-06, + "loss": 3.841, + "step": 2697216 + }, + { + "epoch": 1.01, + "learning_rate": 5.830117082240594e-06, + "loss": 3.8368, + "step": 2697728 + }, + { + "epoch": 1.01, + "learning_rate": 5.821731134730074e-06, + "loss": 3.8283, + "step": 2698240 + }, + { + "epoch": 1.01, + "learning_rate": 5.813345187219555e-06, + "loss": 3.8388, + "step": 2698752 + }, + { + "epoch": 1.01, + "learning_rate": 5.804959239709034e-06, + "loss": 3.8235, + "step": 2699264 + }, + { + "epoch": 1.01, + "learning_rate": 5.7965896710022455e-06, + "loss": 3.8439, + "step": 2699776 + }, + { + "epoch": 1.01, + "learning_rate": 5.788220102295456e-06, + "loss": 3.8414, + "step": 2700288 + }, + { + "epoch": 1.01, + "learning_rate": 5.779834154784937e-06, + "loss": 3.8495, + "step": 2700800 + }, + { + "epoch": 1.01, + "learning_rate": 5.771448207274416e-06, + "loss": 3.8443, + "step": 2701312 + }, + { + "epoch": 1.01, + "learning_rate": 5.763062259763897e-06, + "loss": 3.8363, + "step": 2701824 + }, + { + "epoch": 1.01, + "learning_rate": 5.754676312253376e-06, + "loss": 3.8312, + "step": 2702336 + }, + { + "epoch": 1.01, + "learning_rate": 5.746290364742856e-06, + "loss": 3.8435, + "step": 2702848 + }, + { + "epoch": 1.01, + "learning_rate": 5.737904417232336e-06, + "loss": 3.8271, + "step": 2703360 + }, + { + "epoch": 1.01, + "learning_rate": 5.729534848525548e-06, + "loss": 3.8332, + "step": 2703872 + }, + { + "epoch": 1.01, + "learning_rate": 5.721148901015028e-06, + "loss": 3.8411, + "step": 2704384 + }, + { + "epoch": 1.01, + "learning_rate": 5.712779332308238e-06, + "loss": 3.8381, + "step": 2704896 + }, + { + "epoch": 1.01, + "learning_rate": 5.704393384797719e-06, + "loss": 3.8217, + "step": 2705408 + }, + { + "epoch": 1.01, + "learning_rate": 5.696007437287198e-06, + "loss": 3.8267, + "step": 2705920 + }, + { + "epoch": 1.01, + "learning_rate": 5.687621489776679e-06, + "loss": 3.8275, + "step": 2706432 + }, + { + "epoch": 1.01, + "learning_rate": 5.679235542266158e-06, + "loss": 3.8457, + "step": 2706944 + }, + { + "epoch": 1.01, + "learning_rate": 5.670849594755638e-06, + "loss": 3.8459, + "step": 2707456 + }, + { + "epoch": 1.01, + "learning_rate": 5.66248002604885e-06, + "loss": 3.8338, + "step": 2707968 + }, + { + "epoch": 1.01, + "learning_rate": 5.65409407853833e-06, + "loss": 3.8393, + "step": 2708480 + }, + { + "epoch": 1.01, + "learning_rate": 5.64570813102781e-06, + "loss": 3.8343, + "step": 2708992 + }, + { + "epoch": 1.01, + "learning_rate": 5.63732218351729e-06, + "loss": 3.8475, + "step": 2709504 + }, + { + "epoch": 1.01, + "learning_rate": 5.628952614810501e-06, + "loss": 3.828, + "step": 2710016 + }, + { + "epoch": 1.01, + "learning_rate": 5.6205666672999804e-06, + "loss": 3.8484, + "step": 2710528 + }, + { + "epoch": 1.01, + "learning_rate": 5.612180719789461e-06, + "loss": 3.8374, + "step": 2711040 + }, + { + "epoch": 1.01, + "learning_rate": 5.60379477227894e-06, + "loss": 3.8434, + "step": 2711552 + }, + { + "epoch": 1.01, + "learning_rate": 5.59540882476842e-06, + "loss": 3.8341, + "step": 2712064 + }, + { + "epoch": 1.01, + "learning_rate": 5.5870228772579e-06, + "loss": 3.8383, + "step": 2712576 + }, + { + "epoch": 1.01, + "learning_rate": 5.57863692974738e-06, + "loss": 3.8461, + "step": 2713088 + }, + { + "epoch": 1.01, + "learning_rate": 5.57025098223686e-06, + "loss": 3.8446, + "step": 2713600 + }, + { + "epoch": 1.01, + "learning_rate": 5.56186503472634e-06, + "loss": 3.8291, + "step": 2714112 + }, + { + "epoch": 1.01, + "learning_rate": 5.553479087215819e-06, + "loss": 3.8381, + "step": 2714624 + }, + { + "epoch": 1.01, + "learning_rate": 5.5450931397053e-06, + "loss": 3.8376, + "step": 2715136 + }, + { + "epoch": 1.01, + "learning_rate": 5.536707192194779e-06, + "loss": 3.8408, + "step": 2715648 + }, + { + "epoch": 1.01, + "learning_rate": 5.528337623487991e-06, + "loss": 3.8416, + "step": 2716160 + }, + { + "epoch": 1.01, + "learning_rate": 5.5199680547812024e-06, + "loss": 3.8296, + "step": 2716672 + }, + { + "epoch": 1.02, + "learning_rate": 5.511582107270682e-06, + "loss": 3.8392, + "step": 2717184 + }, + { + "epoch": 1.02, + "learning_rate": 5.503196159760162e-06, + "loss": 3.832, + "step": 2717696 + }, + { + "epoch": 1.02, + "learning_rate": 5.494810212249642e-06, + "loss": 3.8414, + "step": 2718208 + }, + { + "epoch": 1.02, + "learning_rate": 5.486424264739122e-06, + "loss": 3.826, + "step": 2718720 + }, + { + "epoch": 1.02, + "learning_rate": 5.478038317228601e-06, + "loss": 3.8418, + "step": 2719232 + }, + { + "epoch": 1.02, + "learning_rate": 5.469652369718082e-06, + "loss": 3.8471, + "step": 2719744 + }, + { + "epoch": 1.02, + "learning_rate": 5.461266422207561e-06, + "loss": 3.835, + "step": 2720256 + }, + { + "epoch": 1.02, + "learning_rate": 5.452896853500773e-06, + "loss": 3.8199, + "step": 2720768 + }, + { + "epoch": 1.02, + "learning_rate": 5.444510905990253e-06, + "loss": 3.8378, + "step": 2721280 + }, + { + "epoch": 1.02, + "learning_rate": 5.436124958479733e-06, + "loss": 3.8365, + "step": 2721792 + }, + { + "epoch": 1.02, + "learning_rate": 5.4277553897729445e-06, + "loss": 3.8471, + "step": 2722304 + }, + { + "epoch": 1.02, + "learning_rate": 5.4193694422624236e-06, + "loss": 3.839, + "step": 2722816 + }, + { + "epoch": 1.02, + "learning_rate": 5.410983494751904e-06, + "loss": 3.8297, + "step": 2723328 + }, + { + "epoch": 1.02, + "learning_rate": 5.4025975472413835e-06, + "loss": 3.8314, + "step": 2723840 + }, + { + "epoch": 1.02, + "learning_rate": 5.394211599730864e-06, + "loss": 3.8434, + "step": 2724352 + }, + { + "epoch": 1.02, + "learning_rate": 5.385825652220343e-06, + "loss": 3.8219, + "step": 2724864 + }, + { + "epoch": 1.02, + "learning_rate": 5.377439704709823e-06, + "loss": 3.8316, + "step": 2725376 + }, + { + "epoch": 1.02, + "learning_rate": 5.369086514806766e-06, + "loss": 3.8353, + "step": 2725888 + }, + { + "epoch": 1.02, + "learning_rate": 5.360700567296247e-06, + "loss": 3.8444, + "step": 2726400 + }, + { + "epoch": 1.02, + "learning_rate": 5.352314619785726e-06, + "loss": 3.8173, + "step": 2726912 + }, + { + "epoch": 1.02, + "learning_rate": 5.343928672275206e-06, + "loss": 3.8357, + "step": 2727424 + }, + { + "epoch": 1.02, + "learning_rate": 5.3355427247646865e-06, + "loss": 3.8291, + "step": 2727936 + }, + { + "epoch": 1.02, + "learning_rate": 5.327156777254166e-06, + "loss": 3.8332, + "step": 2728448 + }, + { + "epoch": 1.02, + "learning_rate": 5.318770829743646e-06, + "loss": 3.8322, + "step": 2728960 + }, + { + "epoch": 1.02, + "learning_rate": 5.3103848822331255e-06, + "loss": 3.8288, + "step": 2729472 + }, + { + "epoch": 1.02, + "learning_rate": 5.302015313526337e-06, + "loss": 3.8483, + "step": 2729984 + }, + { + "epoch": 1.02, + "learning_rate": 5.293629366015817e-06, + "loss": 3.8372, + "step": 2730496 + }, + { + "epoch": 1.02, + "learning_rate": 5.285259797309029e-06, + "loss": 3.8303, + "step": 2731008 + }, + { + "epoch": 1.02, + "learning_rate": 5.276873849798508e-06, + "loss": 3.8367, + "step": 2731520 + }, + { + "epoch": 1.02, + "learning_rate": 5.268487902287988e-06, + "loss": 3.8359, + "step": 2732032 + }, + { + "epoch": 1.02, + "learning_rate": 5.260101954777468e-06, + "loss": 3.8363, + "step": 2732544 + }, + { + "epoch": 1.02, + "learning_rate": 5.251716007266948e-06, + "loss": 3.8207, + "step": 2733056 + }, + { + "epoch": 1.02, + "learning_rate": 5.243330059756428e-06, + "loss": 3.843, + "step": 2733568 + }, + { + "epoch": 1.02, + "learning_rate": 5.234944112245908e-06, + "loss": 3.8339, + "step": 2734080 + }, + { + "epoch": 1.02, + "learning_rate": 5.226574543539119e-06, + "loss": 3.8404, + "step": 2734592 + }, + { + "epoch": 1.02, + "learning_rate": 5.218188596028599e-06, + "loss": 3.8342, + "step": 2735104 + }, + { + "epoch": 1.02, + "learning_rate": 5.209802648518078e-06, + "loss": 3.8397, + "step": 2735616 + }, + { + "epoch": 1.02, + "learning_rate": 5.20143307981129e-06, + "loss": 3.8297, + "step": 2736128 + }, + { + "epoch": 1.02, + "learning_rate": 5.19304713230077e-06, + "loss": 3.8292, + "step": 2736640 + }, + { + "epoch": 1.02, + "learning_rate": 5.18466118479025e-06, + "loss": 3.8242, + "step": 2737152 + }, + { + "epoch": 1.02, + "learning_rate": 5.17627523727973e-06, + "loss": 3.8435, + "step": 2737664 + }, + { + "epoch": 1.02, + "learning_rate": 5.16788928976921e-06, + "loss": 3.8438, + "step": 2738176 + }, + { + "epoch": 1.02, + "learning_rate": 5.15950334225869e-06, + "loss": 3.8397, + "step": 2738688 + }, + { + "epoch": 1.02, + "learning_rate": 5.15111739474817e-06, + "loss": 3.8281, + "step": 2739200 + }, + { + "epoch": 1.02, + "learning_rate": 5.14273144723765e-06, + "loss": 3.8424, + "step": 2739712 + }, + { + "epoch": 1.02, + "learning_rate": 5.13434549972713e-06, + "loss": 3.8416, + "step": 2740224 + }, + { + "epoch": 1.02, + "learning_rate": 5.1259595522166096e-06, + "loss": 3.8324, + "step": 2740736 + }, + { + "epoch": 1.02, + "learning_rate": 5.1175736047060895e-06, + "loss": 3.8351, + "step": 2741248 + }, + { + "epoch": 1.02, + "learning_rate": 5.109187657195569e-06, + "loss": 3.8397, + "step": 2741760 + }, + { + "epoch": 1.02, + "learning_rate": 5.1008017096850494e-06, + "loss": 3.8416, + "step": 2742272 + }, + { + "epoch": 1.02, + "learning_rate": 5.0924157621745285e-06, + "loss": 3.8435, + "step": 2742784 + }, + { + "epoch": 1.02, + "learning_rate": 5.084029814664009e-06, + "loss": 3.8268, + "step": 2743296 + }, + { + "epoch": 1.02, + "learning_rate": 5.07566024595722e-06, + "loss": 3.8386, + "step": 2743808 + }, + { + "epoch": 1.02, + "learning_rate": 5.0672742984467e-06, + "loss": 3.8365, + "step": 2744320 + }, + { + "epoch": 1.02, + "learning_rate": 5.05888835093618e-06, + "loss": 3.8311, + "step": 2744832 + }, + { + "epoch": 1.02, + "learning_rate": 5.050502403425659e-06, + "loss": 3.85, + "step": 2745344 + }, + { + "epoch": 1.02, + "learning_rate": 5.042132834718871e-06, + "loss": 3.8317, + "step": 2745856 + }, + { + "epoch": 1.02, + "learning_rate": 5.033746887208351e-06, + "loss": 3.8409, + "step": 2746368 + }, + { + "epoch": 1.02, + "learning_rate": 5.0253609396978315e-06, + "loss": 3.8363, + "step": 2746880 + }, + { + "epoch": 1.02, + "learning_rate": 5.016974992187311e-06, + "loss": 3.8397, + "step": 2747392 + }, + { + "epoch": 1.03, + "eval_loss": 4.022671222686768, + "eval_runtime": 290.742, + "eval_samples_per_second": 1312.473, + "eval_steps_per_second": 41.016, + "step": 2747504 + }, + { + "epoch": 2.0, + "learning_rate": 5.008605423480522e-06, + "loss": 3.8333, + "step": 2747904 + }, + { + "epoch": 2.0, + "learning_rate": 5.000219475970002e-06, + "loss": 3.8378, + "step": 2748416 + }, + { + "epoch": 2.0, + "learning_rate": 4.991833528459482e-06, + "loss": 3.8453, + "step": 2748928 + }, + { + "epoch": 2.0, + "learning_rate": 4.983447580948962e-06, + "loss": 3.8415, + "step": 2749440 + }, + { + "epoch": 2.0, + "learning_rate": 4.975061633438441e-06, + "loss": 3.8477, + "step": 2749952 + }, + { + "epoch": 2.0, + "learning_rate": 4.966675685927922e-06, + "loss": 3.8287, + "step": 2750464 + }, + { + "epoch": 2.0, + "learning_rate": 4.958289738417401e-06, + "loss": 3.8359, + "step": 2750976 + }, + { + "epoch": 2.0, + "learning_rate": 4.949903790906882e-06, + "loss": 3.8241, + "step": 2751488 + }, + { + "epoch": 2.0, + "learning_rate": 4.941534222200093e-06, + "loss": 3.8479, + "step": 2752000 + }, + { + "epoch": 2.0, + "learning_rate": 4.933164653493304e-06, + "loss": 3.8365, + "step": 2752512 + }, + { + "epoch": 2.0, + "learning_rate": 4.924778705982784e-06, + "loss": 3.8399, + "step": 2753024 + }, + { + "epoch": 2.0, + "learning_rate": 4.916392758472264e-06, + "loss": 3.8391, + "step": 2753536 + }, + { + "epoch": 2.0, + "learning_rate": 4.908023189765475e-06, + "loss": 3.8353, + "step": 2754048 + }, + { + "epoch": 2.0, + "learning_rate": 4.899637242254956e-06, + "loss": 3.826, + "step": 2754560 + }, + { + "epoch": 2.0, + "learning_rate": 4.891251294744435e-06, + "loss": 3.8271, + "step": 2755072 + }, + { + "epoch": 2.0, + "learning_rate": 4.882881726037647e-06, + "loss": 3.8265, + "step": 2755584 + }, + { + "epoch": 2.0, + "learning_rate": 4.874495778527127e-06, + "loss": 3.8354, + "step": 2756096 + }, + { + "epoch": 2.0, + "learning_rate": 4.8661098310166066e-06, + "loss": 3.8308, + "step": 2756608 + }, + { + "epoch": 2.0, + "learning_rate": 4.8577238835060865e-06, + "loss": 3.8278, + "step": 2757120 + }, + { + "epoch": 2.0, + "learning_rate": 4.8493379359955665e-06, + "loss": 3.8553, + "step": 2757632 + }, + { + "epoch": 2.0, + "learning_rate": 4.840951988485046e-06, + "loss": 3.8335, + "step": 2758144 + }, + { + "epoch": 2.0, + "learning_rate": 4.832566040974526e-06, + "loss": 3.838, + "step": 2758656 + }, + { + "epoch": 2.0, + "learning_rate": 4.8241800934640055e-06, + "loss": 3.8467, + "step": 2759168 + }, + { + "epoch": 2.0, + "learning_rate": 4.815810524757217e-06, + "loss": 3.8381, + "step": 2759680 + }, + { + "epoch": 2.0, + "learning_rate": 4.807424577246697e-06, + "loss": 3.8329, + "step": 2760192 + }, + { + "epoch": 2.0, + "learning_rate": 4.799038629736177e-06, + "loss": 3.8273, + "step": 2760704 + }, + { + "epoch": 2.0, + "learning_rate": 4.790652682225657e-06, + "loss": 3.8424, + "step": 2761216 + }, + { + "epoch": 2.0, + "learning_rate": 4.782266734715136e-06, + "loss": 3.8232, + "step": 2761728 + }, + { + "epoch": 2.0, + "learning_rate": 4.773880787204617e-06, + "loss": 3.8306, + "step": 2762240 + }, + { + "epoch": 2.0, + "learning_rate": 4.765494839694096e-06, + "loss": 3.8322, + "step": 2762752 + }, + { + "epoch": 2.01, + "learning_rate": 4.757108892183577e-06, + "loss": 3.8281, + "step": 2763264 + }, + { + "epoch": 2.01, + "learning_rate": 4.748722944673056e-06, + "loss": 3.8433, + "step": 2763776 + }, + { + "epoch": 2.01, + "learning_rate": 4.740336997162536e-06, + "loss": 3.8388, + "step": 2764288 + }, + { + "epoch": 2.01, + "learning_rate": 4.7319674284557475e-06, + "loss": 3.8295, + "step": 2764800 + }, + { + "epoch": 2.01, + "learning_rate": 4.723597859748959e-06, + "loss": 3.8385, + "step": 2765312 + }, + { + "epoch": 2.01, + "learning_rate": 4.715211912238439e-06, + "loss": 3.8477, + "step": 2765824 + }, + { + "epoch": 2.01, + "learning_rate": 4.706842343531651e-06, + "loss": 3.8283, + "step": 2766336 + }, + { + "epoch": 2.01, + "learning_rate": 4.69845639602113e-06, + "loss": 3.8417, + "step": 2766848 + }, + { + "epoch": 2.01, + "learning_rate": 4.69007044851061e-06, + "loss": 3.8236, + "step": 2767360 + }, + { + "epoch": 2.01, + "learning_rate": 4.68168450100009e-06, + "loss": 3.8391, + "step": 2767872 + }, + { + "epoch": 2.01, + "learning_rate": 4.67329855348957e-06, + "loss": 3.8264, + "step": 2768384 + }, + { + "epoch": 2.01, + "learning_rate": 4.66491260597905e-06, + "loss": 3.8476, + "step": 2768896 + }, + { + "epoch": 2.01, + "learning_rate": 4.65652665846853e-06, + "loss": 3.8373, + "step": 2769408 + }, + { + "epoch": 2.01, + "learning_rate": 4.64814071095801e-06, + "loss": 3.8354, + "step": 2769920 + }, + { + "epoch": 2.01, + "learning_rate": 4.6397547634474896e-06, + "loss": 3.8403, + "step": 2770432 + }, + { + "epoch": 2.01, + "learning_rate": 4.6313688159369695e-06, + "loss": 3.8293, + "step": 2770944 + }, + { + "epoch": 2.01, + "learning_rate": 4.6229828684264495e-06, + "loss": 3.8411, + "step": 2771456 + }, + { + "epoch": 2.01, + "learning_rate": 4.6145969209159294e-06, + "loss": 3.8255, + "step": 2771968 + }, + { + "epoch": 2.01, + "learning_rate": 4.606227352209141e-06, + "loss": 3.8235, + "step": 2772480 + }, + { + "epoch": 2.01, + "learning_rate": 4.59784140469862e-06, + "loss": 3.8455, + "step": 2772992 + }, + { + "epoch": 2.01, + "learning_rate": 4.589471835991832e-06, + "loss": 3.8347, + "step": 2773504 + }, + { + "epoch": 2.01, + "learning_rate": 4.581085888481312e-06, + "loss": 3.8343, + "step": 2774016 + }, + { + "epoch": 2.01, + "learning_rate": 4.572699940970791e-06, + "loss": 3.8273, + "step": 2774528 + }, + { + "epoch": 2.01, + "learning_rate": 4.564313993460272e-06, + "loss": 3.8372, + "step": 2775040 + }, + { + "epoch": 2.01, + "learning_rate": 4.555928045949752e-06, + "loss": 3.8235, + "step": 2775552 + }, + { + "epoch": 2.01, + "learning_rate": 4.547542098439232e-06, + "loss": 3.8383, + "step": 2776064 + }, + { + "epoch": 2.01, + "learning_rate": 4.5391561509287115e-06, + "loss": 3.8374, + "step": 2776576 + }, + { + "epoch": 2.01, + "learning_rate": 4.530770203418191e-06, + "loss": 3.8479, + "step": 2777088 + }, + { + "epoch": 2.01, + "learning_rate": 4.522400634711402e-06, + "loss": 3.8406, + "step": 2777600 + }, + { + "epoch": 2.01, + "learning_rate": 4.514014687200882e-06, + "loss": 3.8333, + "step": 2778112 + }, + { + "epoch": 2.01, + "learning_rate": 4.505628739690362e-06, + "loss": 3.8291, + "step": 2778624 + }, + { + "epoch": 2.01, + "learning_rate": 4.497242792179842e-06, + "loss": 3.8386, + "step": 2779136 + }, + { + "epoch": 2.01, + "learning_rate": 4.488856844669322e-06, + "loss": 3.8245, + "step": 2779648 + }, + { + "epoch": 2.01, + "learning_rate": 4.480487275962533e-06, + "loss": 3.8333, + "step": 2780160 + }, + { + "epoch": 2.01, + "learning_rate": 4.472101328452014e-06, + "loss": 3.8377, + "step": 2780672 + }, + { + "epoch": 2.01, + "learning_rate": 4.463715380941493e-06, + "loss": 3.8389, + "step": 2781184 + }, + { + "epoch": 2.01, + "learning_rate": 4.455329433430973e-06, + "loss": 3.8205, + "step": 2781696 + }, + { + "epoch": 2.01, + "learning_rate": 4.446943485920453e-06, + "loss": 3.8264, + "step": 2782208 + }, + { + "epoch": 2.01, + "learning_rate": 4.438557538409933e-06, + "loss": 3.8214, + "step": 2782720 + }, + { + "epoch": 2.01, + "learning_rate": 4.430187969703144e-06, + "loss": 3.8464, + "step": 2783232 + }, + { + "epoch": 2.01, + "learning_rate": 4.421802022192624e-06, + "loss": 3.8374, + "step": 2783744 + }, + { + "epoch": 2.01, + "learning_rate": 4.413416074682104e-06, + "loss": 3.8337, + "step": 2784256 + }, + { + "epoch": 2.01, + "learning_rate": 4.405030127171584e-06, + "loss": 3.8389, + "step": 2784768 + }, + { + "epoch": 2.01, + "learning_rate": 4.396660558464796e-06, + "loss": 3.832, + "step": 2785280 + }, + { + "epoch": 2.01, + "learning_rate": 4.388274610954275e-06, + "loss": 3.8479, + "step": 2785792 + }, + { + "epoch": 2.01, + "learning_rate": 4.379888663443755e-06, + "loss": 3.8226, + "step": 2786304 + }, + { + "epoch": 2.01, + "learning_rate": 4.371502715933235e-06, + "loss": 3.8452, + "step": 2786816 + }, + { + "epoch": 2.01, + "learning_rate": 4.363116768422715e-06, + "loss": 3.8411, + "step": 2787328 + }, + { + "epoch": 2.01, + "learning_rate": 4.3547471997159264e-06, + "loss": 3.8344, + "step": 2787840 + }, + { + "epoch": 2.01, + "learning_rate": 4.346361252205406e-06, + "loss": 3.8393, + "step": 2788352 + }, + { + "epoch": 2.01, + "learning_rate": 4.337991683498618e-06, + "loss": 3.8362, + "step": 2788864 + }, + { + "epoch": 2.01, + "learning_rate": 4.329605735988097e-06, + "loss": 3.8422, + "step": 2789376 + }, + { + "epoch": 2.01, + "learning_rate": 4.321219788477578e-06, + "loss": 3.8373, + "step": 2789888 + }, + { + "epoch": 2.01, + "learning_rate": 4.312833840967057e-06, + "loss": 3.8261, + "step": 2790400 + }, + { + "epoch": 2.01, + "learning_rate": 4.304447893456537e-06, + "loss": 3.8388, + "step": 2790912 + }, + { + "epoch": 2.01, + "learning_rate": 4.296078324749749e-06, + "loss": 3.8268, + "step": 2791424 + }, + { + "epoch": 2.01, + "learning_rate": 4.287692377239228e-06, + "loss": 3.8419, + "step": 2791936 + }, + { + "epoch": 2.01, + "learning_rate": 4.2793064297287086e-06, + "loss": 3.8366, + "step": 2792448 + }, + { + "epoch": 2.01, + "learning_rate": 4.270920482218188e-06, + "loss": 3.8237, + "step": 2792960 + }, + { + "epoch": 2.02, + "learning_rate": 4.262534534707668e-06, + "loss": 3.838, + "step": 2793472 + }, + { + "epoch": 2.02, + "learning_rate": 4.2541485871971484e-06, + "loss": 3.8324, + "step": 2793984 + }, + { + "epoch": 2.02, + "learning_rate": 4.2457626396866275e-06, + "loss": 3.836, + "step": 2794496 + }, + { + "epoch": 2.02, + "learning_rate": 4.237376692176108e-06, + "loss": 3.8238, + "step": 2795008 + }, + { + "epoch": 2.02, + "learning_rate": 4.2289907446655874e-06, + "loss": 3.8387, + "step": 2795520 + }, + { + "epoch": 2.02, + "learning_rate": 4.220604797155067e-06, + "loss": 3.8458, + "step": 2796032 + }, + { + "epoch": 2.02, + "learning_rate": 4.212218849644547e-06, + "loss": 3.8325, + "step": 2796544 + }, + { + "epoch": 2.02, + "learning_rate": 4.203849280937758e-06, + "loss": 3.821, + "step": 2797056 + }, + { + "epoch": 2.02, + "learning_rate": 4.195463333427239e-06, + "loss": 3.8344, + "step": 2797568 + }, + { + "epoch": 2.02, + "learning_rate": 4.187077385916718e-06, + "loss": 3.83, + "step": 2798080 + }, + { + "epoch": 2.02, + "learning_rate": 4.178691438406199e-06, + "loss": 3.8462, + "step": 2798592 + }, + { + "epoch": 2.02, + "learning_rate": 4.17032186969941e-06, + "loss": 3.8367, + "step": 2799104 + }, + { + "epoch": 2.02, + "learning_rate": 4.16193592218889e-06, + "loss": 3.8324, + "step": 2799616 + }, + { + "epoch": 2.02, + "learning_rate": 4.1535499746783696e-06, + "loss": 3.8265, + "step": 2800128 + }, + { + "epoch": 2.02, + "learning_rate": 4.1451640271678495e-06, + "loss": 3.8416, + "step": 2800640 + }, + { + "epoch": 2.02, + "learning_rate": 4.1367780796573295e-06, + "loss": 3.8187, + "step": 2801152 + }, + { + "epoch": 2.02, + "learning_rate": 4.1283921321468094e-06, + "loss": 3.8268, + "step": 2801664 + }, + { + "epoch": 2.02, + "learning_rate": 4.120022563440021e-06, + "loss": 3.8335, + "step": 2802176 + }, + { + "epoch": 2.02, + "learning_rate": 4.1116366159295e-06, + "loss": 3.8401, + "step": 2802688 + }, + { + "epoch": 2.02, + "learning_rate": 4.103250668418981e-06, + "loss": 3.8159, + "step": 2803200 + }, + { + "epoch": 2.02, + "learning_rate": 4.094881099712192e-06, + "loss": 3.8348, + "step": 2803712 + }, + { + "epoch": 2.02, + "learning_rate": 4.086495152201672e-06, + "loss": 3.8274, + "step": 2804224 + }, + { + "epoch": 2.02, + "learning_rate": 4.078109204691152e-06, + "loss": 3.8322, + "step": 2804736 + }, + { + "epoch": 2.02, + "learning_rate": 4.069723257180632e-06, + "loss": 3.8293, + "step": 2805248 + }, + { + "epoch": 2.02, + "learning_rate": 4.061337309670112e-06, + "loss": 3.824, + "step": 2805760 + }, + { + "epoch": 2.02, + "learning_rate": 4.0529513621595915e-06, + "loss": 3.8437, + "step": 2806272 + }, + { + "epoch": 2.02, + "learning_rate": 4.0445654146490715e-06, + "loss": 3.839, + "step": 2806784 + }, + { + "epoch": 2.02, + "learning_rate": 4.036195845942282e-06, + "loss": 3.8289, + "step": 2807296 + }, + { + "epoch": 2.02, + "learning_rate": 4.027809898431763e-06, + "loss": 3.8315, + "step": 2807808 + }, + { + "epoch": 2.02, + "learning_rate": 4.019423950921242e-06, + "loss": 3.832, + "step": 2808320 + }, + { + "epoch": 2.02, + "learning_rate": 4.011038003410722e-06, + "loss": 3.8369, + "step": 2808832 + }, + { + "epoch": 2.02, + "learning_rate": 4.002652055900202e-06, + "loss": 3.8165, + "step": 2809344 + }, + { + "epoch": 2.02, + "learning_rate": 3.994266108389682e-06, + "loss": 3.8417, + "step": 2809856 + }, + { + "epoch": 2.02, + "learning_rate": 3.985880160879162e-06, + "loss": 3.8319, + "step": 2810368 + }, + { + "epoch": 2.02, + "learning_rate": 3.977494213368642e-06, + "loss": 3.8367, + "step": 2810880 + }, + { + "epoch": 2.02, + "learning_rate": 3.969108265858121e-06, + "loss": 3.8291, + "step": 2811392 + }, + { + "epoch": 2.02, + "learning_rate": 3.960722318347602e-06, + "loss": 3.84, + "step": 2811904 + }, + { + "epoch": 2.02, + "learning_rate": 3.952336370837081e-06, + "loss": 3.8298, + "step": 2812416 + }, + { + "epoch": 2.02, + "learning_rate": 3.943983180934024e-06, + "loss": 3.8285, + "step": 2812928 + }, + { + "epoch": 2.02, + "learning_rate": 3.935597233423504e-06, + "loss": 3.8196, + "step": 2813440 + }, + { + "epoch": 2.02, + "learning_rate": 3.927211285912984e-06, + "loss": 3.843, + "step": 2813952 + }, + { + "epoch": 2.02, + "learning_rate": 3.918825338402464e-06, + "loss": 3.8353, + "step": 2814464 + }, + { + "epoch": 2.02, + "learning_rate": 3.910455769695676e-06, + "loss": 3.8373, + "step": 2814976 + }, + { + "epoch": 2.02, + "learning_rate": 3.902069822185155e-06, + "loss": 3.8264, + "step": 2815488 + }, + { + "epoch": 2.02, + "learning_rate": 3.893683874674636e-06, + "loss": 3.8396, + "step": 2816000 + }, + { + "epoch": 2.02, + "learning_rate": 3.885297927164115e-06, + "loss": 3.8419, + "step": 2816512 + }, + { + "epoch": 2.02, + "learning_rate": 3.8769283584573265e-06, + "loss": 3.8295, + "step": 2817024 + }, + { + "epoch": 2.02, + "learning_rate": 3.8685424109468064e-06, + "loss": 3.8333, + "step": 2817536 + }, + { + "epoch": 2.02, + "learning_rate": 3.860156463436286e-06, + "loss": 3.8377, + "step": 2818048 + }, + { + "epoch": 2.02, + "learning_rate": 3.851770515925766e-06, + "loss": 3.8392, + "step": 2818560 + }, + { + "epoch": 2.02, + "learning_rate": 3.843384568415246e-06, + "loss": 3.8417, + "step": 2819072 + }, + { + "epoch": 2.02, + "learning_rate": 3.834998620904726e-06, + "loss": 3.8264, + "step": 2819584 + }, + { + "epoch": 2.02, + "learning_rate": 3.826612673394206e-06, + "loss": 3.8359, + "step": 2820096 + }, + { + "epoch": 2.02, + "learning_rate": 3.818226725883685e-06, + "loss": 3.8311, + "step": 2820608 + }, + { + "epoch": 2.02, + "learning_rate": 3.8098407783731657e-06, + "loss": 3.835, + "step": 2821120 + }, + { + "epoch": 2.02, + "learning_rate": 3.8014548308626457e-06, + "loss": 3.8421, + "step": 2821632 + }, + { + "epoch": 2.02, + "learning_rate": 3.7930688833521256e-06, + "loss": 3.8293, + "step": 2822144 + }, + { + "epoch": 2.02, + "learning_rate": 3.784699314645337e-06, + "loss": 3.8391, + "step": 2822656 + }, + { + "epoch": 2.02, + "learning_rate": 3.776313367134817e-06, + "loss": 3.8283, + "step": 2823168 + }, + { + "epoch": 2.02, + "learning_rate": 3.7679274196242967e-06, + "loss": 3.8417, + "step": 2823680 + }, + { + "epoch": 2.03, + "eval_loss": 4.022037506103516, + "eval_runtime": 291.5673, + "eval_samples_per_second": 1308.758, + "eval_steps_per_second": 40.9, + "step": 2823824 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.0871951614431593e+18, + "trial_name": null, + "trial_params": null +}