diff --git "a/checkpoint-2900160/trainer_state.json" "b/checkpoint-2900160/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2900160/trainer_state.json" @@ -0,0 +1,34313 @@ +{ + "best_metric": 3.8635635375976562, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/2/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2900160, + "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": 10.9166, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8283, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2048, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9964, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8327, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7348, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6227, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5631, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4813, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4183, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3724, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3348, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2877, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2345, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1989, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1625, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1257, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.1041, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0766, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0445, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0345, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 5.0011, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9832, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.956, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9435, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.9146, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8953, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8822, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8622, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8349, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8325, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8213, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.8074, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7883, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7844, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7602, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7506, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7242, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.725, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.7118, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.7087, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6969, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6931, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6733, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6683, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962273063484898e-05, + "loss": 4.661, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6458, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6523, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6296, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.6138, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958081727610012e-05, + "loss": 4.6249, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.6042, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5984, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5776, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5866, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5636, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5956, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5581, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951376245362342e-05, + "loss": 4.5709, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.95053765061129e-05, + "loss": 4.5619, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949699055860238e-05, + "loss": 4.5366, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948860461109186e-05, + "loss": 4.5299, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.948023504238507e-05, + "loss": 4.535, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947184909487455e-05, + "loss": 4.518, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946346314736403e-05, + "loss": 4.5114, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945507719985351e-05, + "loss": 4.5302, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944670763114672e-05, + "loss": 4.5107, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.94383216836362e-05, + "loss": 4.4995, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942993573612568e-05, + "loss": 4.4835, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4833, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4932, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.494, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396408324887336e-05, + "loss": 4.4816, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388022377376816e-05, + "loss": 4.4806, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379636429866296e-05, + "loss": 4.4788, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371250482355776e-05, + "loss": 4.4716, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362880913648985e-05, + "loss": 4.4609, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354494966138465e-05, + "loss": 4.4556, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346109018627945e-05, + "loss": 4.4518, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337723071117425e-05, + "loss": 4.4405, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329337123606905e-05, + "loss": 4.4415, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932095117609638e-05, + "loss": 4.4445, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931256522858586e-05, + "loss": 4.4426, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930417928107534e-05, + "loss": 4.4273, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.9295809712368554e-05, + "loss": 4.4064, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.9287423764858034e-05, + "loss": 4.4256, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.9279037817347514e-05, + "loss": 4.4207, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.9270651869836994e-05, + "loss": 4.4195, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 4.4117, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.4124, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 4.4016, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 4.3898, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 4.3966, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 4.3928, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 4.4008, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 4.3973, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 4.3903, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.3711, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.3732, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.376, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3736, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3631, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3643, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3523, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128156277373076e-05, + "loss": 4.3675, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3378, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.3497, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.9103014813645245e-05, + "loss": 4.35, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909462886613473e-05, + "loss": 4.3402, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908624291862421e-05, + "loss": 4.3381, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907785697111369e-05, + "loss": 4.3407, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906947102360317e-05, + "loss": 4.3324, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906108507609265e-05, + "loss": 4.3383, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905271550738586e-05, + "loss": 4.3341, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904432955987534e-05, + "loss": 4.3254, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903594361236482e-05, + "loss": 4.3291, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3337, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.3227, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.3126, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.3157, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.3178, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.3104, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2997, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.3077, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.3121, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.3025, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2989, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2894, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2931, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2871, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.3012, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2928, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2736, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2811, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2871, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.28, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2854, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2714, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.279, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2809, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2697, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2672, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.268, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2566, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2551, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2694, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2469, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.253, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2581, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2526, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.215147495269775, + "eval_runtime": 304.8841, + "eval_samples_per_second": 1251.593, + "eval_steps_per_second": 39.113, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2344, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.236, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.255, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2389, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2493, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2222, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2406, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.2264, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.8675528036253507e-05, + "loss": 4.2254, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.8667142088742986e-05, + "loss": 4.2283, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2277, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.2317, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642017003818885e-05, + "loss": 4.2154, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633631056308365e-05, + "loss": 4.2123, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.8625245108797845e-05, + "loss": 4.2101, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.8616859161287324e-05, + "loss": 4.2067, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.8608473213776804e-05, + "loss": 4.2051, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860008726626628e-05, + "loss": 4.2084, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.8591701318755764e-05, + "loss": 4.2063, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.8583315371245244e-05, + "loss": 4.229, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.2041, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.2086, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.2011, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.2066, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1972, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1946, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1939, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1859, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1722, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1868, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1856, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1907, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1807, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1859, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.175, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1747, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1618, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1688, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.166, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1645, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1661, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.173, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1625, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1639, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1662, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1513, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.1621, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1495, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1445, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1601, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1463, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1454, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1358, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829830780751368e-05, + "loss": 4.1425, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828992186000316e-05, + "loss": 4.1296, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.1575, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.827314996498212e-05, + "loss": 4.1355, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1476, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1466, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1275, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.1215, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.1332, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.1233, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.1178, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1365, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1314, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.1191, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.1123, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.1137, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1262, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1256, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.123, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.1258, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.125, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.1249, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.1091, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.118, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.1149, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.1022, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808033868745508e-05, + "loss": 4.1144, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807195273994456e-05, + "loss": 4.1136, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.1179, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.099, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.088, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.1055, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.105, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.1073, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801326748617466e-05, + "loss": 4.1008, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800489791746787e-05, + "loss": 4.1016, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799651196995735e-05, + "loss": 4.0987, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798812602244683e-05, + "loss": 4.0874, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.79797400749363e-05, + "loss": 4.0959, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0942, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.1015, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954598611208476e-05, + "loss": 4.1071, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.0982, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.086, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.088, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0892, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0973, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.0829, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0843, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.077, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0957, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0656, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862385946200214e-05, + "loss": 4.0803, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0852, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0736, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.0738, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782885853496187e-05, + "loss": 4.083, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.073, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0778, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780371707123404e-05, + "loss": 4.0805, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779533112372352e-05, + "loss": 4.0713, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.079, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0847, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0737, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0665, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0716, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0716, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0648, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0603, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.063, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0758, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0663, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0652, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0562, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.0592, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.056, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.073, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0694, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0453, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0531, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0651, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0597, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0652, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.0512, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0585, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585780708782906e-05, + "loss": 4.0613, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0534, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569008813761866e-05, + "loss": 4.0516, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0562, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0462, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0457, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753548140252352e-05, + "loss": 4.06, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0409, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0463, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.0508, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.75019703700889e-05, + "loss": 4.0455, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.04611349105835, + "eval_runtime": 306.1519, + "eval_samples_per_second": 1246.411, + "eval_steps_per_second": 38.951, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749358442257838e-05, + "loss": 4.0283, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748519847506786e-05, + "loss": 4.0347, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747681252755734e-05, + "loss": 4.0529, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746842658004682e-05, + "loss": 4.0345, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.74600406325363e-05, + "loss": 4.0531, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745165468502578e-05, + "loss": 4.0278, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744326873751526e-05, + "loss": 4.0451, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743488279000474e-05, + "loss": 4.0256, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742649684249422e-05, + "loss": 4.0388, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0354, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740972494747318e-05, + "loss": 4.0332, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740135537876639e-05, + "loss": 4.0432, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0248, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 4.0242, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737623029384229e-05, + "loss": 4.0223, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736784434633177e-05, + "loss": 4.0183, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735945839882125e-05, + "loss": 4.021, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735107245131073e-05, + "loss": 4.0269, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734268650380021e-05, + "loss": 4.0204, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733430055628969e-05, + "loss": 4.0457, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732591460877917e-05, + "loss": 4.0241, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731752866126865e-05, + "loss": 4.0303, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730914271375813e-05, + "loss": 4.0238, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730077314505134e-05, + "loss": 4.0295, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729238719754082e-05, + "loss": 4.0212, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.72840012500303e-05, + "loss": 4.0171, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727561530251978e-05, + "loss": 4.0213, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 4.0112, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725885978630247e-05, + "loss": 3.9993, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725047383879195e-05, + "loss": 4.0125, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724208789128143e-05, + "loss": 4.0211, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 4.0172, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225332375064127e-05, + "loss": 4.0157, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216946427553606e-05, + "loss": 4.0187, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208560480043086e-05, + "loss": 4.0067, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 4.006, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9989, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183419016315255e-05, + "loss": 4.0015, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175033068804735e-05, + "loss": 3.998, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166663500097945e-05, + "loss": 4.0005, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158277552587424e-05, + "loss": 4.0049, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149891605076904e-05, + "loss": 4.0124, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141505657566384e-05, + "loss": 4.0008, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 4.0052, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 4.0087, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711636419383856e-05, + "loss": 3.9909, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710797824632804e-05, + "loss": 4.0026, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.9968, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9862, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 4.0021, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.9938, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706609764518663e-05, + "loss": 3.9906, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705771169767611e-05, + "loss": 3.9861, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9891, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9741, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 4.0014, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9855, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9965, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9991, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.69990264439062e-05, + "loss": 3.9802, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9723, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9901, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9767, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696549903266785e-05, + "loss": 3.9713, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695711308515733e-05, + "loss": 3.9921, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694872713764681e-05, + "loss": 3.9876, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694034119013629e-05, + "loss": 3.9735, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693197162142951e-05, + "loss": 3.9691, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9721, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.979, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9864, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.6898444210191157e-05, + "loss": 3.9797, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.6890058262680636e-05, + "loss": 3.988, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.6881672315170116e-05, + "loss": 3.9815, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.6873286367659596e-05, + "loss": 3.9879, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.6864916798952806e-05, + "loss": 3.9702, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856530851442285e-05, + "loss": 3.9785, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848144903931765e-05, + "loss": 3.9801, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.6839758956421245e-05, + "loss": 3.9659, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683138938771446e-05, + "loss": 3.9765, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682300344020394e-05, + "loss": 3.9825, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681461749269342e-05, + "loss": 3.9821, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.68062315451829e-05, + "loss": 3.9655, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.679786197647611e-05, + "loss": 3.9529, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678947602896559e-05, + "loss": 3.9726, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678109008145507e-05, + "loss": 3.9654, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.677270413394455e-05, + "loss": 3.9769, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.676433456523776e-05, + "loss": 3.9685, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675596499653097e-05, + "loss": 3.9687, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674757904902045e-05, + "loss": 3.9671, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739193101509935e-05, + "loss": 3.956, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730807153999415e-05, + "loss": 3.9638, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722421206488895e-05, + "loss": 3.9624, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6714035258978375e-05, + "loss": 3.9756, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.6705649311467855e-05, + "loss": 3.9805, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.6697263363957335e-05, + "loss": 3.9688, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.6688893795250544e-05, + "loss": 3.9541, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.6680507847740024e-05, + "loss": 3.963, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.6672121900229504e-05, + "loss": 3.9609, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.6663735952718984e-05, + "loss": 3.9698, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665536638401219e-05, + "loss": 3.9569, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664698043650167e-05, + "loss": 3.9606, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663859448899115e-05, + "loss": 3.9511, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663020854148063e-05, + "loss": 3.971, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662183897277385e-05, + "loss": 3.9422, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661345302526333e-05, + "loss": 3.9585, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660508345655654e-05, + "loss": 3.9545, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659669750904602e-05, + "loss": 3.9569, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65883115615355e-05, + "loss": 3.9498, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657992561402498e-05, + "loss": 3.9613, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657153966651446e-05, + "loss": 3.9568, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656315371900393e-05, + "loss": 3.9521, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655476777149341e-05, + "loss": 3.9605, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.6546398202786626e-05, + "loss": 3.9479, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6538012255276106e-05, + "loss": 3.9643, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529626307765586e-05, + "loss": 3.9694, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212567390588e-05, + "loss": 3.9522, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651287079154828e-05, + "loss": 3.9504, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650448484403776e-05, + "loss": 3.9506, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.6496098896527235e-05, + "loss": 3.9528, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.6487712949016715e-05, + "loss": 3.9464, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479327001506195e-05, + "loss": 3.9465, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470941053995675e-05, + "loss": 3.943, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462555106485155e-05, + "loss": 3.9605, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454185537778364e-05, + "loss": 3.9515, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445799590267844e-05, + "loss": 3.9489, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437413642757324e-05, + "loss": 3.941, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429027695246804e-05, + "loss": 3.9455, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642065812654002e-05, + "loss": 3.9401, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.64122721790295e-05, + "loss": 3.9599, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640390261032271e-05, + "loss": 3.9559, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.639551666281219e-05, + "loss": 3.9361, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.638713071530167e-05, + "loss": 3.9362, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.637874476779115e-05, + "loss": 3.9511, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.637035882028063e-05, + "loss": 3.9445, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636197287277011e-05, + "loss": 3.9571, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.635358692525959e-05, + "loss": 3.9359, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.634520097774907e-05, + "loss": 3.9516, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.633683140904228e-05, + "loss": 3.945, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.632844546153176e-05, + "loss": 3.9465, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320059514021244e-05, + "loss": 3.9431, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311673566510724e-05, + "loss": 3.9447, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303303997803934e-05, + "loss": 3.9362, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.6294918050293413e-05, + "loss": 3.9393, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.6286532102782893e-05, + "loss": 3.9497, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.6278146155272373e-05, + "loss": 3.9389, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626977658656558e-05, + "loss": 3.9349, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626139063905506e-05, + "loss": 3.9408, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625300469154454e-05, + "loss": 3.9381, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9720582962036133, + "eval_runtime": 303.5227, + "eval_samples_per_second": 1257.207, + "eval_steps_per_second": 39.289, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624461874403402e-05, + "loss": 3.9291, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623624917532723e-05, + "loss": 3.9265, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622786322781671e-05, + "loss": 3.947, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.62194772803062e-05, + "loss": 3.9296, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621109133279568e-05, + "loss": 3.9511, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620272176408889e-05, + "loss": 3.9187, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619433581657837e-05, + "loss": 3.9413, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618594986906785e-05, + "loss": 3.9247, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617756392155733e-05, + "loss": 3.9298, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6169194352850536e-05, + "loss": 3.9343, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160808405340016e-05, + "loss": 3.9274, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.6152422457829496e-05, + "loss": 3.9388, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.6144069267926434e-05, + "loss": 3.9238, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613568332041592e-05, + "loss": 3.9195, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.61272973729054e-05, + "loss": 3.9241, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611891142539488e-05, + "loss": 3.9122, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611052547788436e-05, + "loss": 3.922, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610213953037384e-05, + "loss": 3.9251, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609375358286332e-05, + "loss": 3.9186, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.60853676353528e-05, + "loss": 3.9435, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607698168784228e-05, + "loss": 3.9275, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606859574033176e-05, + "loss": 3.9341, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606020979282124e-05, + "loss": 3.9226, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051823845310714e-05, + "loss": 3.9275, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604345427660393e-05, + "loss": 3.9205, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603506832909341e-05, + "loss": 3.9201, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602668238158289e-05, + "loss": 3.9226, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.60183128128761e-05, + "loss": 3.9122, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009926865365585e-05, + "loss": 3.9083, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001540917855065e-05, + "loss": 3.9116, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599315497034454e-05, + "loss": 3.9243, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.5984785401637754e-05, + "loss": 3.9214, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976399454127234e-05, + "loss": 3.922, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5968013506616714e-05, + "loss": 3.9253, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959643937909923e-05, + "loss": 3.9054, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951257990399403e-05, + "loss": 3.9136, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594287204288888e-05, + "loss": 3.9089, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593448609537836e-05, + "loss": 3.9012, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926100147867836e-05, + "loss": 3.9058, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591771420035732e-05, + "loss": 3.9048, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590934463165054e-05, + "loss": 3.9135, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590095868414001e-05, + "loss": 3.9151, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589257273662949e-05, + "loss": 3.9127, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588418678911897e-05, + "loss": 3.9061, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587580084160845e-05, + "loss": 3.9179, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586741489409793e-05, + "loss": 3.8995, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585904532539114e-05, + "loss": 3.9107, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585065937788062e-05, + "loss": 3.9055, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.58422734303701e-05, + "loss": 3.8928, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583388748285958e-05, + "loss": 3.9142, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582550153534906e-05, + "loss": 3.902, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581711558783854e-05, + "loss": 3.9021, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580874601913176e-05, + "loss": 3.893, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580036007162124e-05, + "loss": 3.8982, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579197412411072e-05, + "loss": 3.8843, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.57835881766002e-05, + "loss": 3.9066, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577520222908968e-05, + "loss": 3.8999, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576681628157916e-05, + "loss": 3.9031, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.5758430334068637e-05, + "loss": 3.9092, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.5750060765361846e-05, + "loss": 3.8931, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.5741691196655055e-05, + "loss": 3.882, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.5733305249144535e-05, + "loss": 3.904, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.5724919301634015e-05, + "loss": 3.8882, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.5716533354123495e-05, + "loss": 3.8844, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.5708147406612975e-05, + "loss": 3.9049, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569976145910246e-05, + "loss": 3.8985, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569137551159194e-05, + "loss": 3.8881, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568298956408142e-05, + "loss": 3.8861, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567461999537463e-05, + "loss": 3.8798, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566623404786411e-05, + "loss": 3.8905, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565784810035359e-05, + "loss": 3.9019, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.56494785316468e-05, + "loss": 3.8974, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564109258413628e-05, + "loss": 3.9009, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.563270663662576e-05, + "loss": 3.8929, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.562432068911524e-05, + "loss": 3.9086, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561593474160472e-05, + "loss": 3.8838, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.56075487940942e-05, + "loss": 3.8955, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559916284658368e-05, + "loss": 3.8933, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590793277876895e-05, + "loss": 3.8775, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582407330366375e-05, + "loss": 3.8993, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557402138285585e-05, + "loss": 3.8966, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556563543534533e-05, + "loss": 3.8931, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555724948783481e-05, + "loss": 3.8829, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554886354032429e-05, + "loss": 3.8743, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.55404939716175e-05, + "loss": 3.8874, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553210802410698e-05, + "loss": 3.888, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552372207659646e-05, + "loss": 3.8909, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551533612908594e-05, + "loss": 3.8807, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550695018157542e-05, + "loss": 3.8897, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549858061286863e-05, + "loss": 3.8825, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549019466535811e-05, + "loss": 3.8793, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548180871784759e-05, + "loss": 3.8804, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547342277033707e-05, + "loss": 3.8775, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546505320163028e-05, + "loss": 3.8967, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8953, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544828130660924e-05, + "loss": 3.8939, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543989535909872e-05, + "loss": 3.8717, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54315094115882e-05, + "loss": 3.8851, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542313984288141e-05, + "loss": 3.8799, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541475389537089e-05, + "loss": 3.8857, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540636794786037e-05, + "loss": 3.8774, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539798200034985e-05, + "loss": 3.8769, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389612431643066e-05, + "loss": 3.8699, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381226484132546e-05, + "loss": 3.8907, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372840536622026e-05, + "loss": 3.8632, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364454589111506e-05, + "loss": 3.879, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8781, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347699072894195e-05, + "loss": 3.8771, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8704, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.887, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8765, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314171661655844e-05, + "loss": 3.8749, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305785714145324e-05, + "loss": 3.8868, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297399766634804e-05, + "loss": 3.8723, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289013819124284e-05, + "loss": 3.8844, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.52806442504175e-05, + "loss": 3.891, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527225830290698e-05, + "loss": 3.878, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526387235539646e-05, + "loss": 3.8731, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525548640788594e-05, + "loss": 3.8714, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524711683917915e-05, + "loss": 3.8734, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523873089166863e-05, + "loss": 3.8704, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523034494415811e-05, + "loss": 3.8772, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522195899664759e-05, + "loss": 3.8629, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521357304913707e-05, + "loss": 3.8834, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520520348043028e-05, + "loss": 3.8785, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519681753291976e-05, + "loss": 3.8753, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518843158540924e-05, + "loss": 3.8618, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180045637898725e-05, + "loss": 3.8704, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171676069191934e-05, + "loss": 3.8687, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163290121681414e-05, + "loss": 3.88, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154904174170894e-05, + "loss": 3.8827, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146518226660373e-05, + "loss": 3.8678, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513814865795358e-05, + "loss": 3.8562, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512976271044306e-05, + "loss": 3.8768, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512137676293254e-05, + "loss": 3.868, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511299081542202e-05, + "loss": 3.8832, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510462124671523e-05, + "loss": 3.8621, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509623529920471e-05, + "loss": 3.8745, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508784935169419e-05, + "loss": 3.8729, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507946340418368e-05, + "loss": 3.8761, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507107745667316e-05, + "loss": 3.8702, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506270788796637e-05, + "loss": 3.8704, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505432194045585e-05, + "loss": 3.8622, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504593599294533e-05, + "loss": 3.8658, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.50375500454348e-05, + "loss": 3.8732, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029180476728016e-05, + "loss": 3.8697, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020794529217496e-05, + "loss": 3.8607, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012408581706976e-05, + "loss": 3.87, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500402263419645e-05, + "loss": 3.8628, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9311435222625732, + "eval_runtime": 301.8823, + "eval_samples_per_second": 1264.039, + "eval_steps_per_second": 39.502, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499563668668593e-05, + "loss": 3.8512, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987250739175416e-05, + "loss": 3.8564, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978864791664896e-05, + "loss": 3.874, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970478844154376e-05, + "loss": 3.8584, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962092896643856e-05, + "loss": 3.8741, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953706949133336e-05, + "loss": 3.857, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945321001622816e-05, + "loss": 3.8632, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936935054112296e-05, + "loss": 3.8569, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928565485405505e-05, + "loss": 3.86, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920179537894985e-05, + "loss": 3.862, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911793590384465e-05, + "loss": 3.8576, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903407642873945e-05, + "loss": 3.8679, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489505445297088e-05, + "loss": 3.8551, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488666850546037e-05, + "loss": 3.8523, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487828255794985e-05, + "loss": 3.8532, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486989661043933e-05, + "loss": 3.8438, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486151066292881e-05, + "loss": 3.8535, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485312471541829e-05, + "loss": 3.8562, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484473876790777e-05, + "loss": 3.8485, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483635282039725e-05, + "loss": 3.8751, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482798325169046e-05, + "loss": 3.8593, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481959730417994e-05, + "loss": 3.8642, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481121135666942e-05, + "loss": 3.8544, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.48028254091589e-05, + "loss": 3.8584, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479445584045211e-05, + "loss": 3.8493, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478606989294159e-05, + "loss": 3.8598, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477768394543107e-05, + "loss": 3.8531, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476929799792055e-05, + "loss": 3.8464, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476092842921376e-05, + "loss": 3.8427, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475254248170324e-05, + "loss": 3.8438, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474415653419272e-05, + "loss": 3.8537, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.47357705866822e-05, + "loss": 3.8549, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472740101797541e-05, + "loss": 3.8548, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471901507046489e-05, + "loss": 3.8567, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471062912295437e-05, + "loss": 3.8415, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470224317544385e-05, + "loss": 3.848, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469387360673706e-05, + "loss": 3.8464, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468548765922654e-05, + "loss": 3.8352, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467710171171602e-05, + "loss": 3.8431, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.46687157642055e-05, + "loss": 3.8381, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466034619549872e-05, + "loss": 3.8492, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46519602479882e-05, + "loss": 3.8496, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464357430047768e-05, + "loss": 3.8476, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463518835296716e-05, + "loss": 3.8382, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626818784260366e-05, + "loss": 3.8532, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618432836749846e-05, + "loss": 3.8346, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610046889239326e-05, + "loss": 3.847, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601660941728806e-05, + "loss": 3.8396, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593291373022015e-05, + "loss": 3.8259, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584905425511495e-05, + "loss": 3.8515, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576519478000975e-05, + "loss": 3.8398, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.4568133530490455e-05, + "loss": 3.8377, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455976396178367e-05, + "loss": 3.8331, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455137801427315e-05, + "loss": 3.832, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454299206676263e-05, + "loss": 3.8247, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453460611925211e-05, + "loss": 3.8374, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452623655054532e-05, + "loss": 3.8395, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.45178506030348e-05, + "loss": 3.8399, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450946465552428e-05, + "loss": 3.845, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450107870801376e-05, + "loss": 3.8333, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449270913930697e-05, + "loss": 3.8178, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448432319179645e-05, + "loss": 3.8442, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447593724428593e-05, + "loss": 3.8243, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446755129677541e-05, + "loss": 3.8185, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459181728068624e-05, + "loss": 3.8449, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450795780558104e-05, + "loss": 3.8346, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442409833047584e-05, + "loss": 3.8271, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443402388553706e-05, + "loss": 3.8253, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442565431683027e-05, + "loss": 3.817, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441726836931975e-05, + "loss": 3.8277, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440888242180923e-05, + "loss": 3.8424, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.4400496474298706e-05, + "loss": 3.8328, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439212690559192e-05, + "loss": 3.8383, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.43837409580814e-05, + "loss": 3.8307, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437535501057088e-05, + "loss": 3.8485, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436696906306036e-05, + "loss": 3.8243, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435859949435358e-05, + "loss": 3.8353, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435021354684306e-05, + "loss": 3.8333, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434182759933253e-05, + "loss": 3.8125, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433344165182201e-05, + "loss": 3.8432, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432507208311523e-05, + "loss": 3.8358, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431668613560471e-05, + "loss": 3.8315, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430830018809418e-05, + "loss": 3.8246, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429991424058366e-05, + "loss": 3.8127, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291544671876876e-05, + "loss": 3.8271, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283158724366356e-05, + "loss": 3.8252, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274772776855836e-05, + "loss": 3.8319, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266386829345316e-05, + "loss": 3.8222, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425801726063853e-05, + "loss": 3.8269, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249631313128005e-05, + "loss": 3.8205, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241245365617485e-05, + "loss": 3.8242, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232859418106965e-05, + "loss": 3.8199, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224473470596445e-05, + "loss": 3.8198, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216103901889654e-05, + "loss": 3.8365, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207717954379134e-05, + "loss": 3.8362, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199332006868614e-05, + "loss": 3.8369, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190946059358094e-05, + "loss": 3.812, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418257649065131e-05, + "loss": 3.8257, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417419054314079e-05, + "loss": 3.8235, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416580459563027e-05, + "loss": 3.8266, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415741864811975e-05, + "loss": 3.8222, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414904907941296e-05, + "loss": 3.8153, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414066313190244e-05, + "loss": 3.8175, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413227718439192e-05, + "loss": 3.8309, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412390761568513e-05, + "loss": 3.8066, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411552166817461e-05, + "loss": 3.8206, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410713572066409e-05, + "loss": 3.816, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409874977315357e-05, + "loss": 3.8249, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090380204446776e-05, + "loss": 3.8135, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408199425693626e-05, + "loss": 3.8269, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407360830942574e-05, + "loss": 3.8226, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406522236191522e-05, + "loss": 3.8158, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405685279320843e-05, + "loss": 3.8292, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404846684569791e-05, + "loss": 3.8173, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404008089818739e-05, + "loss": 3.8279, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403169495067687e-05, + "loss": 3.8308, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402332538197008e-05, + "loss": 3.8189, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401493943445956e-05, + "loss": 3.8157, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400655348694904e-05, + "loss": 3.8162, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399816753943852e-05, + "loss": 3.8145, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989781591928e-05, + "loss": 3.8159, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398141202322122e-05, + "loss": 3.819, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39730260757107e-05, + "loss": 3.8075, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396464012820018e-05, + "loss": 3.8266, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956254180689657e-05, + "loss": 3.8214, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947884611982866e-05, + "loss": 3.8225, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939498664472346e-05, + "loss": 3.8074, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931112716961826e-05, + "loss": 3.8136, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922726769451306e-05, + "loss": 3.8136, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914357200744515e-05, + "loss": 3.8221, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905971253233995e-05, + "loss": 3.8232, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897585305723475e-05, + "loss": 3.8162, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889199358212955e-05, + "loss": 3.802, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388082978950617e-05, + "loss": 3.8224, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387244384199565e-05, + "loss": 3.8133, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386405789448513e-05, + "loss": 3.8251, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385567194697461e-05, + "loss": 3.806, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384730237826782e-05, + "loss": 3.8232, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38389164307573e-05, + "loss": 3.8184, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383053048324678e-05, + "loss": 3.8239, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382216091453999e-05, + "loss": 3.8137, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381377496702947e-05, + "loss": 3.8142, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.8075, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379700307200843e-05, + "loss": 3.8127, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378863350330164e-05, + "loss": 3.8181, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780247555791124e-05, + "loss": 3.8171, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771861608280604e-05, + "loss": 3.8073, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763475660770084e-05, + "loss": 3.8124, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375510609206329e-05, + "loss": 3.8124, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.906532049179077, + "eval_runtime": 304.2477, + "eval_samples_per_second": 1254.211, + "eval_steps_per_second": 39.195, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374672014455277e-05, + "loss": 3.8086, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373833419704225e-05, + "loss": 3.7994, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372994824953173e-05, + "loss": 3.8196, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372156230202121e-05, + "loss": 3.8058, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371319273331442e-05, + "loss": 3.819, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.37048067858039e-05, + "loss": 3.8062, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369642083829338e-05, + "loss": 3.8083, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368805126958659e-05, + "loss": 3.8078, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367966532207607e-05, + "loss": 3.8056, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367127937456556e-05, + "loss": 3.8076, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366289342705504e-05, + "loss": 3.8088, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365452385834825e-05, + "loss": 3.8117, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.3646154289641456e-05, + "loss": 3.8042, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.3637768342130936e-05, + "loss": 3.7979, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629382394620416e-05, + "loss": 3.803, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620996447109896e-05, + "loss": 3.7891, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612610499599376e-05, + "loss": 3.7991, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604224552088856e-05, + "loss": 3.803, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595838604578336e-05, + "loss": 3.7999, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587452657067816e-05, + "loss": 3.8224, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579083088361025e-05, + "loss": 3.8097, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357069714085051e-05, + "loss": 3.8116, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356231119333999e-05, + "loss": 3.8027, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355392524582947e-05, + "loss": 3.805, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354555567712268e-05, + "loss": 3.7993, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353716972961216e-05, + "loss": 3.8069, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352878378210164e-05, + "loss": 3.7988, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352039783459112e-05, + "loss": 3.7972, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351202826588433e-05, + "loss": 3.7922, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350364231837381e-05, + "loss": 3.7927, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349525637086329e-05, + "loss": 3.8003, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348687042335277e-05, + "loss": 3.8056, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347850085464598e-05, + "loss": 3.8008, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470114907135465e-05, + "loss": 3.8078, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461728959624945e-05, + "loss": 3.7898, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453359390918154e-05, + "loss": 3.7983, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444973443407634e-05, + "loss": 3.7946, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436587495897114e-05, + "loss": 3.7857, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428201548386594e-05, + "loss": 3.7961, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.34198319796798e-05, + "loss": 3.7817, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341144603216928e-05, + "loss": 3.7979, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340306008465876e-05, + "loss": 3.8001, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339467413714824e-05, + "loss": 3.8008, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338630456844145e-05, + "loss": 3.7902, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337791862093093e-05, + "loss": 3.8034, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336953267342042e-05, + "loss": 3.7812, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.33611467259099e-05, + "loss": 3.8009, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335277715720311e-05, + "loss": 3.7887, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334439120969259e-05, + "loss": 3.7712, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333600526218207e-05, + "loss": 3.807, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332761931467155e-05, + "loss": 3.7884, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331924974596476e-05, + "loss": 3.7939, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331086379845424e-05, + "loss": 3.7802, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302477850943717e-05, + "loss": 3.7815, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294091903433197e-05, + "loss": 3.7807, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285722334726406e-05, + "loss": 3.7848, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277336387215886e-05, + "loss": 3.7934, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.7889, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.8014, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325219492348806e-05, + "loss": 3.7835, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324380897597754e-05, + "loss": 3.7724, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323542302846702e-05, + "loss": 3.795, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.32270370809565e-05, + "loss": 3.774, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321866751224971e-05, + "loss": 3.774, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321028156473919e-05, + "loss": 3.7947, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320189561722867e-05, + "loss": 3.789, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319350966971815e-05, + "loss": 3.776, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318514010101136e-05, + "loss": 3.7795, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317675415350084e-05, + "loss": 3.769, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168368205990326e-05, + "loss": 3.7787, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.31599822584798e-05, + "loss": 3.7935, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151612689773015e-05, + "loss": 3.7865, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143226742262495e-05, + "loss": 3.7895, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134840794751975e-05, + "loss": 3.7858, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312645484724145e-05, + "loss": 3.7998, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3118085278534664e-05, + "loss": 3.7775, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109699331024144e-05, + "loss": 3.7909, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310131338351362e-05, + "loss": 3.7835, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30929274360031e-05, + "loss": 3.766, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308455786729631e-05, + "loss": 3.7933, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307617191978579e-05, + "loss": 3.7882, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306778597227527e-05, + "loss": 3.785, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305940002476475e-05, + "loss": 3.7804, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305103045605797e-05, + "loss": 3.7701, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304264450854745e-05, + "loss": 3.7727, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303427493984066e-05, + "loss": 3.7792, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302588899233014e-05, + "loss": 3.7861, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301750304481962e-05, + "loss": 3.7753, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300911709730909e-05, + "loss": 3.7821, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300073114979857e-05, + "loss": 3.774, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299234520228805e-05, + "loss": 3.7781, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298395925477753e-05, + "loss": 3.7728, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297557330726702e-05, + "loss": 3.7764, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967203738560227e-05, + "loss": 3.7874, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958817791049707e-05, + "loss": 3.7899, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950431843539186e-05, + "loss": 3.7918, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2942045896028666e-05, + "loss": 3.7659, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933676327321876e-05, + "loss": 3.7823, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925290379811355e-05, + "loss": 3.7719, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916904432300835e-05, + "loss": 3.785, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908518484790315e-05, + "loss": 3.7736, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900148916083525e-05, + "loss": 3.7747, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891762968573004e-05, + "loss": 3.7699, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883377021062484e-05, + "loss": 3.7844, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287499107355197e-05, + "loss": 3.7604, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286662150484518e-05, + "loss": 3.78, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285823555733466e-05, + "loss": 3.7664, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284984960982414e-05, + "loss": 3.7817, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284146366231362e-05, + "loss": 3.7712, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283309409360683e-05, + "loss": 3.775, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282470814609631e-05, + "loss": 3.7768, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281632219858579e-05, + "loss": 3.7771, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807952629879e-05, + "loss": 3.7788, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279956668236848e-05, + "loss": 3.7736, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279118073485796e-05, + "loss": 3.7776, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278279478734744e-05, + "loss": 3.7923, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774425218640654e-05, + "loss": 3.7736, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766039271130134e-05, + "loss": 3.7709, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757653323619614e-05, + "loss": 3.7739, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749267376109094e-05, + "loss": 3.7728, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.27408978074023e-05, + "loss": 3.7637, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273251185989178e-05, + "loss": 3.777, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.7625, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271573996487074e-05, + "loss": 3.7804, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270737039616395e-05, + "loss": 3.7795, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269898444865343e-05, + "loss": 3.7752, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.7654, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.7665, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267384298492561e-05, + "loss": 3.7722, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266545703741509e-05, + "loss": 3.7797, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265707108990457e-05, + "loss": 3.7749, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7784, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640315573687257e-05, + "loss": 3.7578, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631929626176737e-05, + "loss": 3.7778, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623543678666216e-05, + "loss": 3.77, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.7815, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606788162448906e-05, + "loss": 3.762, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598402214938386e-05, + "loss": 3.782, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2590016267427865e-05, + "loss": 3.7723, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581630319917345e-05, + "loss": 3.7819, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257326075121056e-05, + "loss": 3.7644, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256487480370004e-05, + "loss": 3.7797, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255648885618952e-05, + "loss": 3.7587, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548102908679e-05, + "loss": 3.7717, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253973333997221e-05, + "loss": 3.7758, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253134739246169e-05, + "loss": 3.768, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252296144495117e-05, + "loss": 3.7699, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251457549744065e-05, + "loss": 3.7633, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250620592873386e-05, + "loss": 3.7715, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.89036226272583, + "eval_runtime": 303.6875, + "eval_samples_per_second": 1256.525, + "eval_steps_per_second": 39.267, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249781998122334e-05, + "loss": 3.7661, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248943403371282e-05, + "loss": 3.7565, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.24810480862023e-05, + "loss": 3.7719, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247266213869178e-05, + "loss": 3.7629, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464276191181266e-05, + "loss": 3.7766, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455890243670746e-05, + "loss": 3.7613, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447504296160226e-05, + "loss": 3.7666, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.24391183486497e-05, + "loss": 3.767, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430748779942915e-05, + "loss": 3.7627, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422362832432395e-05, + "loss": 3.7655, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413976884921875e-05, + "loss": 3.7662, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240559093741135e-05, + "loss": 3.7694, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239723774750829e-05, + "loss": 3.7615, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238885179999777e-05, + "loss": 3.7562, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238046585248725e-05, + "loss": 3.7639, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237207990497673e-05, + "loss": 3.7461, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236369395746622e-05, + "loss": 3.7573, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.23553080099557e-05, + "loss": 3.7595, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234692206244517e-05, + "loss": 3.7555, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233853611493465e-05, + "loss": 3.7823, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233016654622787e-05, + "loss": 3.7707, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232178059871735e-05, + "loss": 3.7702, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231339465120682e-05, + "loss": 3.7578, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.23050087036963e-05, + "loss": 3.7635, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229663913498952e-05, + "loss": 3.7575, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.2288253187479e-05, + "loss": 3.7639, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227986723996847e-05, + "loss": 3.7588, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227148129245796e-05, + "loss": 3.7593, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226311172375117e-05, + "loss": 3.749, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254725776240646e-05, + "loss": 3.7546, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246339828730126e-05, + "loss": 3.7548, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.2237953881219606e-05, + "loss": 3.766, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222958431251282e-05, + "loss": 3.7629, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221198365002295e-05, + "loss": 3.7678, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212812417491775e-05, + "loss": 3.7502, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220444284878499e-05, + "loss": 3.7539, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219605690127447e-05, + "loss": 3.7575, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187670953763944e-05, + "loss": 3.7451, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179285006253424e-05, + "loss": 3.7529, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217091543754664e-05, + "loss": 3.7474, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216252949003612e-05, + "loss": 3.7551, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.21541435425256e-05, + "loss": 3.76, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214575759501508e-05, + "loss": 3.7587, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137388026308296e-05, + "loss": 3.7524, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212900207879777e-05, + "loss": 3.7579, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212061613128725e-05, + "loss": 3.7477, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211223018377673e-05, + "loss": 3.7582, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210384423626621e-05, + "loss": 3.7504, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209545828875569e-05, + "loss": 3.7304, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208707234124517e-05, + "loss": 3.7733, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207870277253838e-05, + "loss": 3.7459, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070316825027865e-05, + "loss": 3.755, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061947256321074e-05, + "loss": 3.7384, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053561308810554e-05, + "loss": 3.7465, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045175361300034e-05, + "loss": 3.7335, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036789413789514e-05, + "loss": 3.7483, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028403466278993e-05, + "loss": 3.7509, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.20200338975722e-05, + "loss": 3.7513, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201164795006168e-05, + "loss": 3.7591, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200326200255116e-05, + "loss": 3.7446, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199487605504064e-05, + "loss": 3.7336, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198649010753012e-05, + "loss": 3.7587, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.19781041600196e-05, + "loss": 3.7337, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196971821250908e-05, + "loss": 3.7317, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.196133226499856e-05, + "loss": 3.7553, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195296269629178e-05, + "loss": 3.7507, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194457674878126e-05, + "loss": 3.7361, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193619080127074e-05, + "loss": 3.7424, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192780485376022e-05, + "loss": 3.7318, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191943528505343e-05, + "loss": 3.7416, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191104933754291e-05, + "loss": 3.7503, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190266339003239e-05, + "loss": 3.7479, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189427744252187e-05, + "loss": 3.7542, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885924252618805e-05, + "loss": 3.749, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877538305108285e-05, + "loss": 3.757, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869152357597765e-05, + "loss": 3.7363, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186076641008725e-05, + "loss": 3.7545, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185238046257673e-05, + "loss": 3.74, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184399451506621e-05, + "loss": 3.7331, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183560856755569e-05, + "loss": 3.7514, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182722262004517e-05, + "loss": 3.7531, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181885305133838e-05, + "loss": 3.7471, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181046710382786e-05, + "loss": 3.7411, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180208115631734e-05, + "loss": 3.7326, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179371158761055e-05, + "loss": 3.733, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178534201890376e-05, + "loss": 3.7429, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177695607139324e-05, + "loss": 3.7503, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176857012388272e-05, + "loss": 3.7359, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760184176372206e-05, + "loss": 3.7451, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751798228861685e-05, + "loss": 3.7287, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743428660154895e-05, + "loss": 3.7435, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1735042712644375e-05, + "loss": 3.7348, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726656765133854e-05, + "loss": 3.739, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718270817623334e-05, + "loss": 3.7494, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709884870112814e-05, + "loss": 3.7523, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701498922602294e-05, + "loss": 3.752, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693129353895503e-05, + "loss": 3.7274, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684743406384983e-05, + "loss": 3.7453, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167635745887446e-05, + "loss": 3.733, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166797151136394e-05, + "loss": 3.7485, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165960194265716e-05, + "loss": 3.7368, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165121599514664e-05, + "loss": 3.7411, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164283004763612e-05, + "loss": 3.7323, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16344441001256e-05, + "loss": 3.7434, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162607453141881e-05, + "loss": 3.7268, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161768858390829e-05, + "loss": 3.7417, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160930263639777e-05, + "loss": 3.7274, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160091668888725e-05, + "loss": 3.7472, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159253074137672e-05, + "loss": 3.7324, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158416117266994e-05, + "loss": 3.7378, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157577522515942e-05, + "loss": 3.7369, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.15673892776489e-05, + "loss": 3.7418, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155900333013838e-05, + "loss": 3.7408, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155061738262786e-05, + "loss": 3.7382, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154223143511734e-05, + "loss": 3.7437, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153384548760682e-05, + "loss": 3.7497, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254595400963e-05, + "loss": 3.7417, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.1517089971389506e-05, + "loss": 3.7358, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.1508704023878986e-05, + "loss": 3.7324, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500318076368466e-05, + "loss": 3.738, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491932128857946e-05, + "loss": 3.7274, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483562560151155e-05, + "loss": 3.7402, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475176612640635e-05, + "loss": 3.7237, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146680704393385e-05, + "loss": 3.7458, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145842109642333e-05, + "loss": 3.7402, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.145003514891281e-05, + "loss": 3.7392, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144164920140229e-05, + "loss": 3.7286, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143326325389177e-05, + "loss": 3.7296, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142489368518498e-05, + "loss": 3.7354, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141650773767446e-05, + "loss": 3.7449, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140812179016394e-05, + "loss": 3.7365, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139973584265342e-05, + "loss": 3.7394, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.13913498951429e-05, + "loss": 3.7246, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138296394763238e-05, + "loss": 3.7434, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137457800012186e-05, + "loss": 3.7322, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136620843141507e-05, + "loss": 3.7476, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135782248390455e-05, + "loss": 3.726, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349436536394035e-05, + "loss": 3.7429, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1341050588883515e-05, + "loss": 3.7354, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332681020176724e-05, + "loss": 3.7506, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324295072666204e-05, + "loss": 3.7279, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315909125155684e-05, + "loss": 3.7394, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130753955644889e-05, + "loss": 3.7247, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129915360893837e-05, + "loss": 3.7362, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129076766142785e-05, + "loss": 3.7392, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128238171391733e-05, + "loss": 3.7304, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127399576640681e-05, + "loss": 3.7378, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126562619770002e-05, + "loss": 3.7223, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.12572402501895e-05, + "loss": 3.7381, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.878344774246216, + "eval_runtime": 305.0899, + "eval_samples_per_second": 1250.75, + "eval_steps_per_second": 39.087, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124885430267898e-05, + "loss": 3.7328, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.124046835516847e-05, + "loss": 3.7196, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123208240765795e-05, + "loss": 3.7356, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122369646014743e-05, + "loss": 3.7278, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121531051263691e-05, + "loss": 3.7423, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120692456512638e-05, + "loss": 3.7291, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.11985549964196e-05, + "loss": 3.7312, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119016904890908e-05, + "loss": 3.7324, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118178310139856e-05, + "loss": 3.7263, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117339715388803e-05, + "loss": 3.7312, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.1165027585181247e-05, + "loss": 3.7306, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.1156658016474456e-05, + "loss": 3.7333, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114828844776767e-05, + "loss": 3.7305, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113990250025715e-05, + "loss": 3.72, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113151655274663e-05, + "loss": 3.723, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112313060523611e-05, + "loss": 3.7159, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111474465772559e-05, + "loss": 3.7214, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110635871021507e-05, + "loss": 3.7276, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109797276270455e-05, + "loss": 3.719, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108958681519403e-05, + "loss": 3.746, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081200867683504e-05, + "loss": 3.736, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072814920172984e-05, + "loss": 3.7373, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064428972662464e-05, + "loss": 3.7262, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056043025151944e-05, + "loss": 3.7253, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104768983524889e-05, + "loss": 3.7304, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039303887738376e-05, + "loss": 3.7257, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030917940227856e-05, + "loss": 3.7246, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102253199271733e-05, + "loss": 3.7297, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101414604520681e-05, + "loss": 3.7119, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100576009769629e-05, + "loss": 3.7189, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997390528989505e-05, + "loss": 3.7235, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098900458147898e-05, + "loss": 3.7286, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.098061863396846e-05, + "loss": 3.7293, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097223268645794e-05, + "loss": 3.7338, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096384673894742e-05, + "loss": 3.7177, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.09554607914369e-05, + "loss": 3.7175, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094707484392638e-05, + "loss": 3.7271, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938705275219594e-05, + "loss": 3.7111, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930319327709074e-05, + "loss": 3.7203, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921933380198554e-05, + "loss": 3.7099, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913547432688034e-05, + "loss": 3.7232, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905161485177514e-05, + "loss": 3.7197, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896775537666994e-05, + "loss": 3.724, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.08884059689602e-05, + "loss": 3.7235, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.088002002144968e-05, + "loss": 3.7201, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087163407393916e-05, + "loss": 3.7187, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086324812642864e-05, + "loss": 3.7234, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085486217891812e-05, + "loss": 3.716, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.08464762314076e-05, + "loss": 3.6979, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083809028389708e-05, + "loss": 3.7366, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082970433638656e-05, + "loss": 3.7085, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082133476767978e-05, + "loss": 3.7236, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081296519897299e-05, + "loss": 3.7102, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080457925146247e-05, + "loss": 3.7093, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079619330395195e-05, + "loss": 3.6992, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078780735644143e-05, + "loss": 3.7131, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077942140893091e-05, + "loss": 3.7225, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.0771051840224116e-05, + "loss": 3.7155, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.0762665892713596e-05, + "loss": 3.727, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.0754279945203076e-05, + "loss": 3.7175, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.0745893997692556e-05, + "loss": 3.696, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.0737524428985765e-05, + "loss": 3.7215, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072913848147525e-05, + "loss": 3.7036, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072075253396473e-05, + "loss": 3.6967, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071236658645421e-05, + "loss": 3.7249, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070398063894369e-05, + "loss": 3.7155, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695594691433165e-05, + "loss": 3.7029, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0687208743922645e-05, + "loss": 3.7107, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678822796412125e-05, + "loss": 3.6994, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.067046960650907e-05, + "loss": 3.7085, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.066208365899855e-05, + "loss": 3.7156, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.065369771148803e-05, + "loss": 3.7143, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064531176397751e-05, + "loss": 3.7225, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.063694219527072e-05, + "loss": 3.7135, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.06285562477602e-05, + "loss": 3.7255, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620170300249686e-05, + "loss": 3.703, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611784352739166e-05, + "loss": 3.7242, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060339840522864e-05, + "loss": 3.7068, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.0595028836521855e-05, + "loss": 3.7028, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586642889011335e-05, + "loss": 3.7172, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578256941500814e-05, + "loss": 3.7221, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056987099399029e-05, + "loss": 3.7147, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056148504647977e-05, + "loss": 3.7145, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.0553115477772983e-05, + "loss": 3.696, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054472953026246e-05, + "loss": 3.6982, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053634358275194e-05, + "loss": 3.7105, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052795763524142e-05, + "loss": 3.717, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195716877309e-05, + "loss": 3.7046, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051118574022038e-05, + "loss": 3.7126, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050281617151359e-05, + "loss": 3.6987, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049443022400307e-05, + "loss": 3.7126, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048604427649255e-05, + "loss": 3.7034, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047765832898203e-05, + "loss": 3.7068, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046927238147151e-05, + "loss": 3.7164, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046090281276472e-05, + "loss": 3.7191, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.04525168652542e-05, + "loss": 3.7218, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044413091774368e-05, + "loss": 3.6993, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043574497023316e-05, + "loss": 3.7113, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042735902272264e-05, + "loss": 3.7036, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041897307521212e-05, + "loss": 3.713, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041060350650534e-05, + "loss": 3.7042, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040221755899482e-05, + "loss": 3.7115, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.03938316114843e-05, + "loss": 3.7014, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038544566397378e-05, + "loss": 3.7067, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037705971646326e-05, + "loss": 3.7016, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368690147756466e-05, + "loss": 3.7072, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.0360304200245946e-05, + "loss": 3.6943, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.0351918252735426e-05, + "loss": 3.7151, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343532305224906e-05, + "loss": 3.7039, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.0335162736518115e-05, + "loss": 3.7065, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326776789007595e-05, + "loss": 3.705, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318390841497075e-05, + "loss": 3.7092, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.031000489398656e-05, + "loss": 3.7102, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030161894647604e-05, + "loss": 3.7067, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029324937776925e-05, + "loss": 3.7121, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.028486343025873e-05, + "loss": 3.7174, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.027647748274821e-05, + "loss": 3.7051, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.026809153523769e-05, + "loss": 3.7111, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.02597219665309e-05, + "loss": 3.7027, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.025133601902038e-05, + "loss": 3.7046, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.024295007150986e-05, + "loss": 3.7038, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.023456412399934e-05, + "loss": 3.7072, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022617817648882e-05, + "loss": 3.6892, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021780860778203e-05, + "loss": 3.7133, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209422660271515e-05, + "loss": 3.7084, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0201036712760995e-05, + "loss": 3.7102, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192650765250475e-05, + "loss": 3.6996, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018426481773995e-05, + "loss": 3.6999, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.0175895249033164e-05, + "loss": 3.7016, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.0167509301522644e-05, + "loss": 3.7132, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.0159123354012124e-05, + "loss": 3.7082, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.01507374065016e-05, + "loss": 3.7124, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014236783779481e-05, + "loss": 3.6899, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013398189028429e-05, + "loss": 3.7108, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.0125595942773766e-05, + "loss": 3.7036, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011720999526325e-05, + "loss": 3.7164, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010882404775273e-05, + "loss": 3.6992, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010043810024221e-05, + "loss": 3.7079, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009206853153542e-05, + "loss": 3.7026, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.00836825840249e-05, + "loss": 3.7226, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007529663651438e-05, + "loss": 3.6998, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006691068900386e-05, + "loss": 3.7075, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005854112029707e-05, + "loss": 3.6974, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005015517278655e-05, + "loss": 3.7056, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004176922527603e-05, + "loss": 3.7025, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003338327776551e-05, + "loss": 3.7019, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002501370905872e-05, + "loss": 3.706, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016627761548207e-05, + "loss": 3.6898, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008241814037687e-05, + "loss": 3.7124, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.872055768966675, + "eval_runtime": 304.8993, + "eval_samples_per_second": 1251.531, + "eval_steps_per_second": 39.111, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999855866527166e-05, + "loss": 3.6985, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991469919016646e-05, + "loss": 3.6919, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983083971506126e-05, + "loss": 3.7019, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974698023995606e-05, + "loss": 3.6996, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966312076485086e-05, + "loss": 3.7127, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957926128974566e-05, + "loss": 3.6979, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949556560267775e-05, + "loss": 3.7011, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941170612757255e-05, + "loss": 3.7041, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932784665246735e-05, + "loss": 3.6953, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924398717736215e-05, + "loss": 3.702, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9916029149029424e-05, + "loss": 3.6998, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907643201518904e-05, + "loss": 3.702, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989927363281212e-05, + "loss": 3.7039, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.98908876853016e-05, + "loss": 3.684, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988250173779108e-05, + "loss": 3.6957, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987411579028056e-05, + "loss": 3.6827, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986572984277004e-05, + "loss": 3.6945, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985734389525952e-05, + "loss": 3.6965, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848957947749e-05, + "loss": 3.6896, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984057200023848e-05, + "loss": 3.7137, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983218605272795e-05, + "loss": 3.7092, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982380010521743e-05, + "loss": 3.7056, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981541415770691e-05, + "loss": 3.6972, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980704458900013e-05, + "loss": 3.6966, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979865864148961e-05, + "loss": 3.7024, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979027269397909e-05, + "loss": 3.6929, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978188674646857e-05, + "loss": 3.6939, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977350079895805e-05, + "loss": 3.6993, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976513123025126e-05, + "loss": 3.6865, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975674528274074e-05, + "loss": 3.6859, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974835933523022e-05, + "loss": 3.6979, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.97399733877197e-05, + "loss": 3.6999, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973158744020918e-05, + "loss": 3.6941, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972321787150239e-05, + "loss": 3.7086, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.9714831923991867e-05, + "loss": 3.6893, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.9706445976481347e-05, + "loss": 3.6887, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698060028970827e-05, + "loss": 3.6949, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689674081460306e-05, + "loss": 3.6799, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968130451275352e-05, + "loss": 3.6943, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672918565243e-05, + "loss": 3.6834, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966453261773248e-05, + "loss": 3.6898, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965614667022196e-05, + "loss": 3.6936, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964777710151517e-05, + "loss": 3.6968, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963939115400465e-05, + "loss": 3.6953, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963100520649413e-05, + "loss": 3.6907, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962261925898361e-05, + "loss": 3.6899, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961424969027682e-05, + "loss": 3.6911, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.96058637427663e-05, + "loss": 3.6917, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959747779525578e-05, + "loss": 3.669, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958909184774526e-05, + "loss": 3.7044, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958070590023475e-05, + "loss": 3.6825, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957231995272423e-05, + "loss": 3.6981, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563950384017436e-05, + "loss": 3.6828, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555564436506916e-05, + "loss": 3.6793, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547178488996396e-05, + "loss": 3.675, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538792541485876e-05, + "loss": 3.68, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530422972779085e-05, + "loss": 3.6992, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522037025268565e-05, + "loss": 3.6817, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513651077758045e-05, + "loss": 3.7003, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505265130247525e-05, + "loss": 3.6898, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496895561540734e-05, + "loss": 3.6679, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488509614030214e-05, + "loss": 3.6908, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.94801236665197e-05, + "loss": 3.6829, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947173771900918e-05, + "loss": 3.6677, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946335177149866e-05, + "loss": 3.6931, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945496582398814e-05, + "loss": 3.6871, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944657987647762e-05, + "loss": 3.6768, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438193928967094e-05, + "loss": 3.6831, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942982436026031e-05, + "loss": 3.6661, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942143841274979e-05, + "loss": 3.683, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941305246523926e-05, + "loss": 3.6874, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940466651772874e-05, + "loss": 3.6833, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939628057021822e-05, + "loss": 3.6967, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938791100151144e-05, + "loss": 3.6836, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937952505400092e-05, + "loss": 3.6958, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.93711391064904e-05, + "loss": 3.6807, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936275315897988e-05, + "loss": 3.694, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935436721146936e-05, + "loss": 3.6774, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934599764276257e-05, + "loss": 3.6762, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933761169525205e-05, + "loss": 3.6902, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932922574774153e-05, + "loss": 3.6942, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932083980023101e-05, + "loss": 3.6881, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312470231524216e-05, + "loss": 3.6887, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304084284013696e-05, + "loss": 3.668, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295698336503176e-05, + "loss": 3.6711, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287312388992656e-05, + "loss": 3.6866, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927894282028587e-05, + "loss": 3.689, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927055687277535e-05, + "loss": 3.6766, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926217092526483e-05, + "loss": 3.6864, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925378497775431e-05, + "loss": 3.676, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924541540904752e-05, + "loss": 3.6805, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9237029461537e-05, + "loss": 3.6754, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922864351402648e-05, + "loss": 3.6796, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922025756651596e-05, + "loss": 3.6877, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921187161900544e-05, + "loss": 3.6904, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920350205029865e-05, + "loss": 3.6936, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919511610278813e-05, + "loss": 3.6715, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918673015527761e-05, + "loss": 3.6823, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917834420776709e-05, + "loss": 3.6781, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169974639060306e-05, + "loss": 3.6853, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161588691549786e-05, + "loss": 3.6783, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153202744039265e-05, + "loss": 3.6826, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144816796528745e-05, + "loss": 3.6789, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136430849018225e-05, + "loss": 3.676, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128061280311434e-05, + "loss": 3.6723, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119675332800914e-05, + "loss": 3.6787, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111289385290394e-05, + "loss": 3.6675, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102903437779874e-05, + "loss": 3.6865, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094517490269354e-05, + "loss": 3.678, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086147921562563e-05, + "loss": 3.6749, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907776197405204e-05, + "loss": 3.6818, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906937602654152e-05, + "loss": 3.6779, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906099007903101e-05, + "loss": 3.6858, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905262051032422e-05, + "loss": 3.6786, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.90442345628137e-05, + "loss": 3.6873, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903584861530318e-05, + "loss": 3.6903, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902746266779266e-05, + "loss": 3.6817, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901909309908587e-05, + "loss": 3.681, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901070715157535e-05, + "loss": 3.6759, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900232120406483e-05, + "loss": 3.6731, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899393525655431e-05, + "loss": 3.6772, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898556568784752e-05, + "loss": 3.6823, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977179740337e-05, + "loss": 3.6607, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896879379282648e-05, + "loss": 3.6883, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960407845315964e-05, + "loss": 3.6812, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952021897805444e-05, + "loss": 3.6826, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894365232909865e-05, + "loss": 3.6748, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893526638158813e-05, + "loss": 3.6721, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892688043407761e-05, + "loss": 3.6749, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891849448656709e-05, + "loss": 3.6844, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.89101249178603e-05, + "loss": 3.6828, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890173897034978e-05, + "loss": 3.6845, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889335302283926e-05, + "loss": 3.6595, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888496707532874e-05, + "loss": 3.6844, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887659750662195e-05, + "loss": 3.6766, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886821155911143e-05, + "loss": 3.6898, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885982561160092e-05, + "loss": 3.6715, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.88514396640904e-05, + "loss": 3.6776, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884305371657987e-05, + "loss": 3.6806, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883466776906935e-05, + "loss": 3.6954, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882628182155883e-05, + "loss": 3.672, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881789587404831e-05, + "loss": 3.683, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880952630534152e-05, + "loss": 3.6726, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801140357831e-05, + "loss": 3.6856, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879275441032048e-05, + "loss": 3.6739, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.878436846280996e-05, + "loss": 3.6726, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877599889410317e-05, + "loss": 3.6778, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767612946592655e-05, + "loss": 3.6686, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759226999082135e-05, + "loss": 3.683, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.868325710296631, + "eval_runtime": 318.5837, + "eval_samples_per_second": 1197.773, + "eval_steps_per_second": 37.431, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750841051571615e-05, + "loss": 3.6716, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742471482864824e-05, + "loss": 3.6641, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734085535354304e-05, + "loss": 3.6758, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.8725699587843784e-05, + "loss": 3.674, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.8717313640333264e-05, + "loss": 3.6885, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.8708927692822744e-05, + "loss": 3.6725, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870055812411595e-05, + "loss": 3.6714, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869217217660543e-05, + "loss": 3.6824, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868378622909491e-05, + "loss": 3.6697, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867540028158439e-05, + "loss": 3.6761, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866703071287761e-05, + "loss": 3.6751, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865864476536709e-05, + "loss": 3.6783, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.86502751966603e-05, + "loss": 3.6777, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864188924914978e-05, + "loss": 3.66, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863350330163926e-05, + "loss": 3.6685, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862511735412874e-05, + "loss": 3.6564, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861673140661822e-05, + "loss": 3.6684, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.86083454591077e-05, + "loss": 3.6731, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859995951159718e-05, + "loss": 3.6606, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859157356408666e-05, + "loss": 3.6863, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858318761657614e-05, + "loss": 3.6822, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857481804786935e-05, + "loss": 3.6782, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566432100358827e-05, + "loss": 3.6745, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8558046152848307e-05, + "loss": 3.6716, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8549660205337787e-05, + "loss": 3.6742, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541290636631e-05, + "loss": 3.6744, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853290468912048e-05, + "loss": 3.662, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852451874160996e-05, + "loss": 3.6777, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851613279409944e-05, + "loss": 3.6578, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850776322539265e-05, + "loss": 3.6628, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849937727788213e-05, + "loss": 3.6711, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849099133037161e-05, + "loss": 3.6737, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848260538286109e-05, + "loss": 3.6687, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847421943535057e-05, + "loss": 3.6802, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846584986664378e-05, + "loss": 3.6663, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845746391913326e-05, + "loss": 3.6592, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844907797162274e-05, + "loss": 3.6727, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.844069202411223e-05, + "loss": 3.6528, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432322455405436e-05, + "loss": 3.6656, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423936507894916e-05, + "loss": 3.6652, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415550560384396e-05, + "loss": 3.663, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407164612873876e-05, + "loss": 3.6659, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398795044167085e-05, + "loss": 3.6712, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390409096656565e-05, + "loss": 3.6707, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8382023149146045e-05, + "loss": 3.6651, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373637201635525e-05, + "loss": 3.6624, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365267632928734e-05, + "loss": 3.6656, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356881685418214e-05, + "loss": 3.6675, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348495737907694e-05, + "loss": 3.6429, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834010979039718e-05, + "loss": 3.6774, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331723842886654e-05, + "loss": 3.658, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832335427417987e-05, + "loss": 3.667, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831496832666935e-05, + "loss": 3.657, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830658237915883e-05, + "loss": 3.6538, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.82981964316483e-05, + "loss": 3.65, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828982686294152e-05, + "loss": 3.6555, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281440915431e-05, + "loss": 3.6742, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827305496792047e-05, + "loss": 3.6569, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826466902040995e-05, + "loss": 3.6743, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825629945170317e-05, + "loss": 3.666, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824791350419265e-05, + "loss": 3.6425, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823952755668213e-05, + "loss": 3.6642, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823114160917161e-05, + "loss": 3.6535, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822277204046482e-05, + "loss": 3.648, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.82143860929543e-05, + "loss": 3.6647, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8206000145443776e-05, + "loss": 3.6628, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197614197933256e-05, + "loss": 3.6527, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189228250422736e-05, + "loss": 3.658, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180858681715945e-05, + "loss": 3.6445, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172472734205425e-05, + "loss": 3.6526, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.8164086786694905e-05, + "loss": 3.6642, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.8155700839184385e-05, + "loss": 3.6609, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.81473312704776e-05, + "loss": 3.6704, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813894532296708e-05, + "loss": 3.6595, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813055937545656e-05, + "loss": 3.6721, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812217342794604e-05, + "loss": 3.655, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811380385923925e-05, + "loss": 3.6741, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810541791172873e-05, + "loss": 3.6487, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809703196421821e-05, + "loss": 3.6532, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808864601670769e-05, + "loss": 3.6608, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.80802764480009e-05, + "loss": 3.6691, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.807189050049038e-05, + "loss": 3.6636, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806350455297986e-05, + "loss": 3.6654, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805511860546934e-05, + "loss": 3.6429, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046732657958826e-05, + "loss": 3.6438, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038363089252035e-05, + "loss": 3.6631, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029977141741515e-05, + "loss": 3.6618, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021591194230995e-05, + "loss": 3.6518, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013205246720475e-05, + "loss": 3.6614, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004819299209955e-05, + "loss": 3.6539, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996449730503164e-05, + "loss": 3.654, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7988063782992644e-05, + "loss": 3.6527, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979677835482124e-05, + "loss": 3.6544, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971291887971604e-05, + "loss": 3.6667, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796292231926481e-05, + "loss": 3.6672, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795453637175429e-05, + "loss": 3.6691, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794615042424377e-05, + "loss": 3.6474, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793776447673326e-05, + "loss": 3.6588, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792939490802647e-05, + "loss": 3.6523, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792100896051595e-05, + "loss": 3.6638, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791262301300543e-05, + "loss": 3.6562, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790423706549491e-05, + "loss": 3.6552, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789586749678812e-05, + "loss": 3.6534, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.78874815492776e-05, + "loss": 3.6505, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787909560176708e-05, + "loss": 3.6512, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787070965425656e-05, + "loss": 3.6541, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862340085549766e-05, + "loss": 3.6468, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853954138039246e-05, + "loss": 3.6618, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845568190528726e-05, + "loss": 3.6562, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783718224301821e-05, + "loss": 3.6512, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782881267431142e-05, + "loss": 3.6526, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.78204267268009e-05, + "loss": 3.6543, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781204077929038e-05, + "loss": 3.6621, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780365483177986e-05, + "loss": 3.6528, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779528526307307e-05, + "loss": 3.6637, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778689931556255e-05, + "loss": 3.6644, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777851336805203e-05, + "loss": 3.6577, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777012742054151e-05, + "loss": 3.6552, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776175785183472e-05, + "loss": 3.6546, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.77533719043242e-05, + "loss": 3.6483, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774498595681368e-05, + "loss": 3.6571, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773660000930317e-05, + "loss": 3.6521, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728230440596376e-05, + "loss": 3.6419, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719844493085856e-05, + "loss": 3.6608, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711458545575336e-05, + "loss": 3.6597, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.7703072598064816e-05, + "loss": 3.6573, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694686650554296e-05, + "loss": 3.6527, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686317081847505e-05, + "loss": 3.6464, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677931134336985e-05, + "loss": 3.6536, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.7669545186826465e-05, + "loss": 3.6623, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.7661159239315945e-05, + "loss": 3.658, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652789670609154e-05, + "loss": 3.6644, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644403723098634e-05, + "loss": 3.6353, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763601777558812e-05, + "loss": 3.6645, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.76276318280776e-05, + "loss": 3.652, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761926225937081e-05, + "loss": 3.6633, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761087631186029e-05, + "loss": 3.651, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760249036434977e-05, + "loss": 3.6506, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759410441683925e-05, + "loss": 3.6568, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758571846932873e-05, + "loss": 3.6725, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757734890062194e-05, + "loss": 3.6478, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756896295311142e-05, + "loss": 3.6598, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.75605770056009e-05, + "loss": 3.6484, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755220743689411e-05, + "loss": 3.6581, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754382148938359e-05, + "loss": 3.6484, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535435541873074e-05, + "loss": 3.6501, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7527049594362554e-05, + "loss": 3.6551, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751866364685203e-05, + "loss": 3.6477, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751029407814524e-05, + "loss": 3.6615, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.865407705307007, + "eval_runtime": 313.9966, + "eval_samples_per_second": 1215.271, + "eval_steps_per_second": 37.978, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750190813063472e-05, + "loss": 3.6485, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.74935221831242e-05, + "loss": 3.64, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485136235613676e-05, + "loss": 3.6515, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476750288103156e-05, + "loss": 3.6502, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746838071939637e-05, + "loss": 3.6645, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459994771885845e-05, + "loss": 3.6492, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451608824375325e-05, + "loss": 3.6497, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744322287686481e-05, + "loss": 3.6585, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743483692935429e-05, + "loss": 3.6476, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.74264673606475e-05, + "loss": 3.6459, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741808141313698e-05, + "loss": 3.6561, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740969546562646e-05, + "loss": 3.6527, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740132589691968e-05, + "loss": 3.6567, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739293994940915e-05, + "loss": 3.635, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738455400189863e-05, + "loss": 3.646, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737616805438811e-05, + "loss": 3.6306, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736778210687759e-05, + "loss": 3.6469, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735939615936707e-05, + "loss": 3.6529, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735101021185655e-05, + "loss": 3.6349, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734262426434603e-05, + "loss": 3.6626, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733423831683551e-05, + "loss": 3.6599, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325868748128725e-05, + "loss": 3.6552, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317482800618205e-05, + "loss": 3.6498, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309096853107685e-05, + "loss": 3.6487, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300710905597165e-05, + "loss": 3.653, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.7292341336890374e-05, + "loss": 3.6482, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.7283955389379854e-05, + "loss": 3.6415, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7275569441869334e-05, + "loss": 3.6549, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267183494358814e-05, + "loss": 3.6378, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725881392565202e-05, + "loss": 3.635, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.72504279781415e-05, + "loss": 3.6511, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724204203063098e-05, + "loss": 3.648, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723365608312046e-05, + "loss": 3.6507, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722528651441368e-05, + "loss": 3.6552, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721690056690316e-05, + "loss": 3.6434, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720851461939264e-05, + "loss": 3.643, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720012867188212e-05, + "loss": 3.6465, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719175910317533e-05, + "loss": 3.6323, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718337315566481e-05, + "loss": 3.6435, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717498720815429e-05, + "loss": 3.6442, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716660126064377e-05, + "loss": 3.6384, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715821531313325e-05, + "loss": 3.6446, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714984574442646e-05, + "loss": 3.6536, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714145979691594e-05, + "loss": 3.6442, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713307384940542e-05, + "loss": 3.6426, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.71246879018949e-05, + "loss": 3.6385, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711631833318811e-05, + "loss": 3.6433, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710793238567759e-05, + "loss": 3.6436, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709954643816707e-05, + "loss": 3.6259, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709116049065655e-05, + "loss": 3.6525, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708279092194976e-05, + "loss": 3.6352, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707440497443924e-05, + "loss": 3.6472, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706601902692872e-05, + "loss": 3.637, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.70576330794182e-05, + "loss": 3.6288, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704926351071141e-05, + "loss": 3.6258, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704087756320089e-05, + "loss": 3.6327, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703249161569037e-05, + "loss": 3.6537, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702410566817985e-05, + "loss": 3.6346, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701571972066934e-05, + "loss": 3.651, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.7007350151962546e-05, + "loss": 3.645, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.6998964204452026e-05, + "loss": 3.6222, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.6990578256941506e-05, + "loss": 3.6404, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982192309430986e-05, + "loss": 3.6332, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973822740724195e-05, + "loss": 3.6237, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965436793213675e-05, + "loss": 3.6383, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6957050845703155e-05, + "loss": 3.6413, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694866489819263e-05, + "loss": 3.63, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694027895068211e-05, + "loss": 3.6395, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931909381975324e-05, + "loss": 3.6207, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923523434464804e-05, + "loss": 3.6332, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915137486954284e-05, + "loss": 3.6398, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906751539443764e-05, + "loss": 3.6404, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689838197073698e-05, + "loss": 3.643, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688999602322646e-05, + "loss": 3.6396, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688161007571593e-05, + "loss": 3.6477, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687322412820541e-05, + "loss": 3.6343, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686485455949863e-05, + "loss": 3.65, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.68564686119881e-05, + "loss": 3.6264, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684808266447758e-05, + "loss": 3.6328, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683969671696706e-05, + "loss": 3.6406, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683132714826028e-05, + "loss": 3.6429, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682294120074976e-05, + "loss": 3.6424, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681455525323924e-05, + "loss": 3.6428, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680616930572872e-05, + "loss": 3.6259, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679779973702193e-05, + "loss": 3.6195, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678941378951141e-05, + "loss": 3.6404, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678102784200089e-05, + "loss": 3.6377, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677264189449037e-05, + "loss": 3.6323, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764272325783576e-05, + "loss": 3.6394, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6755886378273056e-05, + "loss": 3.6337, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747500430762536e-05, + "loss": 3.6305, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739114483252016e-05, + "loss": 3.6321, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673074491454523e-05, + "loss": 3.6327, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672235896703471e-05, + "loss": 3.646, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671397301952419e-05, + "loss": 3.6437, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670558707201367e-05, + "loss": 3.648, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669721750330688e-05, + "loss": 3.6233, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668883155579636e-05, + "loss": 3.6362, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668044560828584e-05, + "loss": 3.6333, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667205966077532e-05, + "loss": 3.6375, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666369009206853e-05, + "loss": 3.6367, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665530414455801e-05, + "loss": 3.6343, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664691819704749e-05, + "loss": 3.6337, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663853224953697e-05, + "loss": 3.6273, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630162680830185e-05, + "loss": 3.6311, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621776733319665e-05, + "loss": 3.6307, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613390785809145e-05, + "loss": 3.6284, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6605004838298625e-05, + "loss": 3.6377, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596635269591834e-05, + "loss": 3.6344, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588249322081314e-05, + "loss": 3.6278, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579863374570794e-05, + "loss": 3.6345, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571477427060274e-05, + "loss": 3.6292, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656310785835348e-05, + "loss": 3.6401, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655472191084296e-05, + "loss": 3.637, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654633596333244e-05, + "loss": 3.6361, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653795001582192e-05, + "loss": 3.6475, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652958044711514e-05, + "loss": 3.637, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652119449960462e-05, + "loss": 3.6315, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.65128085520941e-05, + "loss": 3.636, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650442260458358e-05, + "loss": 3.6257, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649605303587679e-05, + "loss": 3.636, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648766708836627e-05, + "loss": 3.6275, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647928114085575e-05, + "loss": 3.6216, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647089519334523e-05, + "loss": 3.6403, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646250924583471e-05, + "loss": 3.6401, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.645413967712792e-05, + "loss": 3.634, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.64457537296174e-05, + "loss": 3.6306, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643736778210688e-05, + "loss": 3.6281, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428981834596357e-05, + "loss": 3.627, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642061226588957e-05, + "loss": 3.6413, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641222631837905e-05, + "loss": 3.6363, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640384037086853e-05, + "loss": 3.6411, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639545442335801e-05, + "loss": 3.6133, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638708485465122e-05, + "loss": 3.6438, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.63786989071407e-05, + "loss": 3.6286, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637031295963018e-05, + "loss": 3.6472, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636192701211966e-05, + "loss": 3.6293, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635355744341287e-05, + "loss": 3.6276, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634517149590235e-05, + "loss": 3.636, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633678554839183e-05, + "loss": 3.6525, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632839960088131e-05, + "loss": 3.6263, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.6320030032174526e-05, + "loss": 3.6398, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.6311644084664006e-05, + "loss": 3.6241, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.6303258137153486e-05, + "loss": 3.6374, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.6294872189642966e-05, + "loss": 3.6272, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.6286502620936175e-05, + "loss": 3.6309, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.6278116673425655e-05, + "loss": 3.6322, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269730725915135e-05, + "loss": 3.6269, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261344778404615e-05, + "loss": 3.6385, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.864579677581787, + "eval_runtime": 304.5694, + "eval_samples_per_second": 1252.887, + "eval_steps_per_second": 39.154, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252958830894095e-05, + "loss": 3.6283, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244589262187304e-05, + "loss": 3.6186, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236203314676784e-05, + "loss": 3.6328, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227817367166264e-05, + "loss": 3.6289, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219431419655744e-05, + "loss": 3.6436, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621106185094896e-05, + "loss": 3.6287, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620267590343844e-05, + "loss": 3.6299, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619428995592792e-05, + "loss": 3.6352, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.61859040084174e-05, + "loss": 3.627, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617753443971061e-05, + "loss": 3.6229, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616914849220009e-05, + "loss": 3.6384, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616076254468957e-05, + "loss": 3.6284, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615239297598278e-05, + "loss": 3.6388, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614400702847226e-05, + "loss": 3.6144, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613562108096174e-05, + "loss": 3.621, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612723513345122e-05, + "loss": 3.6154, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.61188491859407e-05, + "loss": 3.6271, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110463238430184e-05, + "loss": 3.6259, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610207729091966e-05, + "loss": 3.6205, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609369134340914e-05, + "loss": 3.6366, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608532177470235e-05, + "loss": 3.6449, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607693582719183e-05, + "loss": 3.633, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068549879681306e-05, + "loss": 3.6292, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060163932170786e-05, + "loss": 3.6282, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051794363464e-05, + "loss": 3.6338, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043408415953475e-05, + "loss": 3.6271, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6035022468442955e-05, + "loss": 3.6206, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026636520932435e-05, + "loss": 3.6334, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601826695222565e-05, + "loss": 3.6166, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600988100471513e-05, + "loss": 3.6146, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600149505720461e-05, + "loss": 3.6293, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599310910969409e-05, + "loss": 3.6262, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598473954098731e-05, + "loss": 3.6329, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597635359347678e-05, + "loss": 3.6314, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596796764596626e-05, + "loss": 3.6213, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595958169845574e-05, + "loss": 3.6237, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595121212974895e-05, + "loss": 3.624, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594282618223843e-05, + "loss": 3.6146, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593444023472791e-05, + "loss": 3.6263, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592605428721739e-05, + "loss": 3.6173, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.5917684718510605e-05, + "loss": 3.6186, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909298771000085e-05, + "loss": 3.6236, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.5900912823489565e-05, + "loss": 3.6354, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892526875979045e-05, + "loss": 3.6205, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884157307272254e-05, + "loss": 3.6241, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875771359761734e-05, + "loss": 3.6214, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867385412251214e-05, + "loss": 3.6198, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858999464740694e-05, + "loss": 3.6214, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.58506298960339e-05, + "loss": 3.6077, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584224394852338e-05, + "loss": 3.631, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583385800101286e-05, + "loss": 3.6174, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582547205350234e-05, + "loss": 3.6271, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581708610599183e-05, + "loss": 3.6158, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580871653728504e-05, + "loss": 3.6072, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580033058977452e-05, + "loss": 3.6068, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791944642264e-05, + "loss": 3.6101, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.578355869475348e-05, + "loss": 3.633, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577518912604669e-05, + "loss": 3.6152, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576680317853617e-05, + "loss": 3.6309, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575841723102565e-05, + "loss": 3.6233, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.575003128351513e-05, + "loss": 3.6069, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741661714808336e-05, + "loss": 3.6202, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733275767297816e-05, + "loss": 3.6122, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724889819787296e-05, + "loss": 3.6067, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571650387227678e-05, + "loss": 3.619, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570813430356999e-05, + "loss": 3.6227, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569974835605947e-05, + "loss": 3.6096, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569136240854895e-05, + "loss": 3.6184, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568297646103843e-05, + "loss": 3.598, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567460689233164e-05, + "loss": 3.6144, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566622094482112e-05, + "loss": 3.62, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.56578349973106e-05, + "loss": 3.6224, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564944904980008e-05, + "loss": 3.6226, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564107948109329e-05, + "loss": 3.6184, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563269353358277e-05, + "loss": 3.6292, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562430758607225e-05, + "loss": 3.6157, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561592163856174e-05, + "loss": 3.631, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.5607552069854946e-05, + "loss": 3.6097, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599166122344426e-05, + "loss": 3.6131, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590780174833906e-05, + "loss": 3.6176, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.5582394227323386e-05, + "loss": 3.6205, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.5574024658616595e-05, + "loss": 3.6218, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.5565638711106075e-05, + "loss": 3.6266, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.5557252763595555e-05, + "loss": 3.6078, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.5548866816085035e-05, + "loss": 3.5983, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.5540497247378244e-05, + "loss": 3.6171, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5532111299867724e-05, + "loss": 3.6222, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523725352357204e-05, + "loss": 3.6112, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515339404846684e-05, + "loss": 3.62, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.55069698361399e-05, + "loss": 3.6128, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549858388862938e-05, + "loss": 3.6109, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549019794111886e-05, + "loss": 3.6147, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548181199360834e-05, + "loss": 3.6128, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.547342604609782e-05, + "loss": 3.6239, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.546505647739103e-05, + "loss": 3.6269, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545667052988051e-05, + "loss": 3.6277, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544828458236999e-05, + "loss": 3.6037, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543989863485947e-05, + "loss": 3.6202, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543152906615268e-05, + "loss": 3.6102, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542314311864216e-05, + "loss": 3.6181, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541475717113164e-05, + "loss": 3.6162, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406371223621124e-05, + "loss": 3.6129, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539800165491433e-05, + "loss": 3.6121, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538961570740381e-05, + "loss": 3.6077, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538122975989329e-05, + "loss": 3.6102, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537284381238277e-05, + "loss": 3.6125, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536447424367598e-05, + "loss": 3.6081, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535608829616546e-05, + "loss": 3.6167, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534770234865494e-05, + "loss": 3.6158, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533931640114442e-05, + "loss": 3.6077, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533094683243763e-05, + "loss": 3.6142, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532256088492711e-05, + "loss": 3.6107, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531417493741659e-05, + "loss": 3.6216, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530578898990608e-05, + "loss": 3.6166, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529740304239556e-05, + "loss": 3.6136, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528903347368877e-05, + "loss": 3.6249, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.528064752617825e-05, + "loss": 3.6243, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527226157866773e-05, + "loss": 3.6094, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5263875631157207e-05, + "loss": 3.6166, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.5255506062450416e-05, + "loss": 3.6049, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.5247120114939896e-05, + "loss": 3.6164, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.5238734167429376e-05, + "loss": 3.6099, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230348219918856e-05, + "loss": 3.6022, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221978651212065e-05, + "loss": 3.6193, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213592703701545e-05, + "loss": 3.6192, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520520675619103e-05, + "loss": 3.6156, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.5196820808680505e-05, + "loss": 3.6137, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518845123997372e-05, + "loss": 3.6061, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.51800652924632e-05, + "loss": 3.6043, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517167934495268e-05, + "loss": 3.6217, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163293397442153e-05, + "loss": 3.6179, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515492382873537e-05, + "loss": 3.6235, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.514653788122485e-05, + "loss": 3.5967, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513815193371433e-05, + "loss": 3.6187, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.51297659862038e-05, + "loss": 3.6149, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512139641749702e-05, + "loss": 3.6228, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.51130104699865e-05, + "loss": 3.6111, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510462452247598e-05, + "loss": 3.6092, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509623857496546e-05, + "loss": 3.618, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087869006258674e-05, + "loss": 3.632, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079483058748154e-05, + "loss": 3.6088, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507109711123763e-05, + "loss": 3.6189, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506271116372711e-05, + "loss": 3.605, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505434159502032e-05, + "loss": 3.6162, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.50459556475098e-05, + "loss": 3.6091, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037569699999276e-05, + "loss": 3.6121, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029183752488756e-05, + "loss": 3.613, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502081418378197e-05, + "loss": 3.6122, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501242823627145e-05, + "loss": 3.616, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8642096519470215, + "eval_runtime": 305.1809, + "eval_samples_per_second": 1250.376, + "eval_steps_per_second": 39.075, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500404228876093e-05, + "loss": 3.6271, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499565634125041e-05, + "loss": 3.5928, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498727039373989e-05, + "loss": 3.6135, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497888444622937e-05, + "loss": 3.6125, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.497051487752258e-05, + "loss": 3.6203, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496212893001206e-05, + "loss": 3.6152, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.495374298250154e-05, + "loss": 3.6078, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.494535703499102e-05, + "loss": 3.6161, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.49369710874805e-05, + "loss": 3.6076, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492860151877371e-05, + "loss": 3.6109, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492021557126319e-05, + "loss": 3.6158, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911829623752676e-05, + "loss": 3.6104, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.4903460055045886e-05, + "loss": 3.6208, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.4895074107535366e-05, + "loss": 3.5939, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.4886688160024845e-05, + "loss": 3.5998, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.4878302212514325e-05, + "loss": 3.5972, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.4869916265003805e-05, + "loss": 3.6098, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.4861530317493285e-05, + "loss": 3.6055, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.4853144369982765e-05, + "loss": 3.6049, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.4844758422472245e-05, + "loss": 3.6131, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.4836388853765454e-05, + "loss": 3.6274, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.4828002906254934e-05, + "loss": 3.6132, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.4819616958744414e-05, + "loss": 3.6085, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.4811231011233894e-05, + "loss": 3.6111, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480286144252711e-05, + "loss": 3.6177, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479447549501659e-05, + "loss": 3.6045, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478608954750607e-05, + "loss": 3.6021, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477770359999555e-05, + "loss": 3.6156, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476931765248503e-05, + "loss": 3.5942, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.476094808377824e-05, + "loss": 3.5997, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.475256213626772e-05, + "loss": 3.6084, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.47441761887572e-05, + "loss": 3.6064, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473580662005041e-05, + "loss": 3.6145, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472742067253989e-05, + "loss": 3.6101, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471903472502937e-05, + "loss": 3.6054, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471064877751885e-05, + "loss": 3.6039, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.4702279208812064e-05, + "loss": 3.6066, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.4693893261301544e-05, + "loss": 3.5913, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.4685507313791024e-05, + "loss": 3.608, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.4677121366280504e-05, + "loss": 3.5996, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466875179757371e-05, + "loss": 3.6017, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466036585006319e-05, + "loss": 3.6051, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465197990255267e-05, + "loss": 3.6191, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464359395504215e-05, + "loss": 3.6018, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463522438633536e-05, + "loss": 3.6058, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462683843882484e-05, + "loss": 3.6052, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461845249131432e-05, + "loss": 3.6001, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.46100665438038e-05, + "loss": 3.6051, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460168059629328e-05, + "loss": 3.5884, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.45933110275865e-05, + "loss": 3.6071, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458492508007598e-05, + "loss": 3.6012, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457653913256546e-05, + "loss": 3.6061, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456815318505494e-05, + "loss": 3.5988, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559783616348146e-05, + "loss": 3.5916, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551397668837626e-05, + "loss": 3.5869, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4543011721327106e-05, + "loss": 3.5903, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534642152620315e-05, + "loss": 3.6179, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526256205109795e-05, + "loss": 3.5951, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517870257599275e-05, + "loss": 3.6114, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509484310088755e-05, + "loss": 3.605, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450111474138197e-05, + "loss": 3.5869, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449272879387145e-05, + "loss": 3.5998, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448434284636093e-05, + "loss": 3.5941, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447595689885041e-05, + "loss": 3.5898, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446758733014362e-05, + "loss": 3.5966, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.44592013826331e-05, + "loss": 3.6034, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445081543512258e-05, + "loss": 3.5945, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444242948761205e-05, + "loss": 3.5976, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443405991890527e-05, + "loss": 3.5813, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442567397139475e-05, + "loss": 3.5951, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441728802388423e-05, + "loss": 3.6019, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440890207637371e-05, + "loss": 3.6028, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400532507666925e-05, + "loss": 3.6056, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392146560156405e-05, + "loss": 3.6019, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383760612645885e-05, + "loss": 3.6065, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437537466513536e-05, + "loss": 3.5973, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436698871762484e-05, + "loss": 3.6098, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358619148918054e-05, + "loss": 3.5929, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435023320140753e-05, + "loss": 3.5982, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434184725389701e-05, + "loss": 3.5965, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433346130638649e-05, + "loss": 3.6007, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.43250917376797e-05, + "loss": 3.6081, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316705790169176e-05, + "loss": 3.6073, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430831984265866e-05, + "loss": 3.5902, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429993389514814e-05, + "loss": 3.5782, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429156432644136e-05, + "loss": 3.5994, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428317837893083e-05, + "loss": 3.6027, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427479243142031e-05, + "loss": 3.5926, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426640648390979e-05, + "loss": 3.6013, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4258036915203e-05, + "loss": 3.5963, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424965096769248e-05, + "loss": 3.5896, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424126502018196e-05, + "loss": 3.5986, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423287907267144e-05, + "loss": 3.5941, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422450950396465e-05, + "loss": 3.6023, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421612355645413e-05, + "loss": 3.6092, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207737608943616e-05, + "loss": 3.6105, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199351661433096e-05, + "loss": 3.5856, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.4190982092726305e-05, + "loss": 3.6004, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182596145215785e-05, + "loss": 3.5944, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4174210197705265e-05, + "loss": 3.5979, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165824250194745e-05, + "loss": 3.5974, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157454681487954e-05, + "loss": 3.5972, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4149068733977434e-05, + "loss": 3.5936, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140682786466914e-05, + "loss": 3.5899, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132296838956394e-05, + "loss": 3.5945, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.41239272702496e-05, + "loss": 3.5925, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411554132273908e-05, + "loss": 3.5916, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410715537522857e-05, + "loss": 3.5998, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409876942771805e-05, + "loss": 3.5984, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409038348020753e-05, + "loss": 3.5878, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408201391150074e-05, + "loss": 3.5969, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407362796399022e-05, + "loss": 3.5897, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.40652420164797e-05, + "loss": 3.603, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405687244777291e-05, + "loss": 3.5986, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404848650026239e-05, + "loss": 3.597, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.404010055275187e-05, + "loss": 3.6008, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403171460524135e-05, + "loss": 3.6084, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402334503653456e-05, + "loss": 3.5927, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401495908902404e-05, + "loss": 3.5976, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006573141513524e-05, + "loss": 3.589, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998187194003004e-05, + "loss": 3.5999, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398981762529621e-05, + "loss": 3.5936, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398143167778569e-05, + "loss": 3.5824, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397304573027517e-05, + "loss": 3.5956, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396465978276465e-05, + "loss": 3.6023, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395629021405786e-05, + "loss": 3.5993, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394790426654734e-05, + "loss": 3.5935, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393951831903682e-05, + "loss": 3.5858, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.39311323715263e-05, + "loss": 3.5897, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392276280281951e-05, + "loss": 3.6056, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391437685530899e-05, + "loss": 3.5988, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390599090779848e-05, + "loss": 3.6068, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389760496028796e-05, + "loss": 3.5789, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388921901277744e-05, + "loss": 3.6004, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880849444070646e-05, + "loss": 3.5988, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872463496560126e-05, + "loss": 3.6022, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3864077549049606e-05, + "loss": 3.5921, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855691601539086e-05, + "loss": 3.5925, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3847322032832295e-05, + "loss": 3.598, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838936085321775e-05, + "loss": 3.6145, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830550137811255e-05, + "loss": 3.593, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.3822164190300735e-05, + "loss": 3.6001, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.3813794621593944e-05, + "loss": 3.5908, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.3805408674083424e-05, + "loss": 3.5982, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379702272657291e-05, + "loss": 3.5893, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378863677906239e-05, + "loss": 3.5976, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.37802672103556e-05, + "loss": 3.5913, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377188126284508e-05, + "loss": 3.5936, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376349531533456e-05, + "loss": 3.5965, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8635635375976562, + "eval_runtime": 314.5023, + "eval_samples_per_second": 1213.317, + "eval_steps_per_second": 37.917, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375510936782404e-05, + "loss": 3.5962, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374673979911725e-05, + "loss": 3.5781, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373835385160673e-05, + "loss": 3.591, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372996790409621e-05, + "loss": 3.6013, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372158195658569e-05, + "loss": 3.5979, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.37132123878789e-05, + "loss": 3.6007, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370482644036838e-05, + "loss": 3.5882, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696440492857865e-05, + "loss": 3.601, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3688054545347344e-05, + "loss": 3.5909, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679684976640554e-05, + "loss": 3.5907, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671299029130034e-05, + "loss": 3.5981, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662913081619513e-05, + "loss": 3.5924, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365454351291272e-05, + "loss": 3.6053, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.36461575654022e-05, + "loss": 3.5794, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363777161789168e-05, + "loss": 3.5785, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362938567038116e-05, + "loss": 3.5851, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362099972287064e-05, + "loss": 3.5931, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361261377536012e-05, + "loss": 3.5847, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.36042278278496e-05, + "loss": 3.5871, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359584188033908e-05, + "loss": 3.5973, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.35874723116323e-05, + "loss": 3.6048, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357908636412178e-05, + "loss": 3.5981, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357070041661126e-05, + "loss": 3.5921, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356231446910073e-05, + "loss": 3.5939, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355394490039395e-05, + "loss": 3.6004, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354555895288343e-05, + "loss": 3.5881, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.35371730053729e-05, + "loss": 3.5821, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352878705786238e-05, + "loss": 3.6005, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520417489155596e-05, + "loss": 3.5756, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3512031541645076e-05, + "loss": 3.5827, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503645594134556e-05, + "loss": 3.5865, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495259646624036e-05, + "loss": 3.5945, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348689007791725e-05, + "loss": 3.5941, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347850413040673e-05, + "loss": 3.593, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3470118182896205e-05, + "loss": 3.59, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461732235385685e-05, + "loss": 3.5865, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.34533626666789e-05, + "loss": 3.586, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444976719168374e-05, + "loss": 3.574, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.3436590771657854e-05, + "loss": 3.5942, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428204824147334e-05, + "loss": 3.5803, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341983525544055e-05, + "loss": 3.5863, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341144930793002e-05, + "loss": 3.5841, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340306336041951e-05, + "loss": 3.6001, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339467741290899e-05, + "loss": 3.5868, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386307844202205e-05, + "loss": 3.5866, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337792189669168e-05, + "loss": 3.5874, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336953594918116e-05, + "loss": 3.5833, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336115000167064e-05, + "loss": 3.5854, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335276405416012e-05, + "loss": 3.5721, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334439448545333e-05, + "loss": 3.588, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333600853794281e-05, + "loss": 3.5886, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332762259043229e-05, + "loss": 3.5857, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331923664292177e-05, + "loss": 3.581, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310867074214977e-05, + "loss": 3.5708, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330248112670446e-05, + "loss": 3.5753, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329409517919394e-05, + "loss": 3.5694, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328570923168342e-05, + "loss": 3.6018, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327733966297663e-05, + "loss": 3.5767, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326895371546611e-05, + "loss": 3.5977, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326056776795559e-05, + "loss": 3.5831, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.32521981992488e-05, + "loss": 3.5718, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324381225173828e-05, + "loss": 3.5796, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323542630422776e-05, + "loss": 3.5769, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322704035671724e-05, + "loss": 3.5758, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321867078801045e-05, + "loss": 3.5756, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321028484049993e-05, + "loss": 3.5901, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320189889298942e-05, + "loss": 3.5809, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.31935129454789e-05, + "loss": 3.5769, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3185143376772106e-05, + "loss": 3.5682, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176757429261586e-05, + "loss": 3.5778, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168371481751066e-05, + "loss": 3.5804, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3159985534240546e-05, + "loss": 3.5894, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3151615965533755e-05, + "loss": 3.5875, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3143230018023235e-05, + "loss": 3.5859, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134844070512715e-05, + "loss": 3.587, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126458123002195e-05, + "loss": 3.581, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3118088554295404e-05, + "loss": 3.5901, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109702606784884e-05, + "loss": 3.5755, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310131665927437e-05, + "loss": 3.5842, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309293071176385e-05, + "loss": 3.579, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308456114305706e-05, + "loss": 3.5846, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307617519554654e-05, + "loss": 3.593, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306778924803602e-05, + "loss": 3.5888, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.30594033005255e-05, + "loss": 3.5765, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305103373181871e-05, + "loss": 3.5568, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304264778430819e-05, + "loss": 3.5848, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303426183679767e-05, + "loss": 3.5846, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302587588928715e-05, + "loss": 3.5795, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301750632058036e-05, + "loss": 3.5808, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300912037306984e-05, + "loss": 3.5849, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000734425559324e-05, + "loss": 3.5723, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.2992348478048804e-05, + "loss": 3.5801, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298397890934201e-05, + "loss": 3.5792, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297559296183149e-05, + "loss": 3.5859, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296720701432097e-05, + "loss": 3.5911, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295882106681045e-05, + "loss": 3.591, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295045149810366e-05, + "loss": 3.571, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294206555059314e-05, + "loss": 3.582, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293367960308262e-05, + "loss": 3.5791, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.29252936555721e-05, + "loss": 3.5818, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291692408686531e-05, + "loss": 3.579, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290853813935479e-05, + "loss": 3.583, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290015219184427e-05, + "loss": 3.5738, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289176624433376e-05, + "loss": 3.5731, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288339667562697e-05, + "loss": 3.5811, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287501072811645e-05, + "loss": 3.5706, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286662478060593e-05, + "loss": 3.576, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285823883309541e-05, + "loss": 3.5821, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2849869264388616e-05, + "loss": 3.579, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841483316878096e-05, + "loss": 3.5737, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2833097369367576e-05, + "loss": 3.5856, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824711421857056e-05, + "loss": 3.5704, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2816341853150265e-05, + "loss": 3.5864, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807955905639745e-05, + "loss": 3.5817, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799569958129225e-05, + "loss": 3.5772, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279118401061871e-05, + "loss": 3.5863, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278281444191192e-05, + "loss": 3.5903, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.27744284944014e-05, + "loss": 3.5744, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276604254689088e-05, + "loss": 3.5818, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275765659938036e-05, + "loss": 3.5724, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274927065186984e-05, + "loss": 3.5806, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274090108316305e-05, + "loss": 3.5773, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273251513565253e-05, + "loss": 3.5706, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272412918814201e-05, + "loss": 3.5776, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271574324063149e-05, + "loss": 3.5871, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.27073736719247e-05, + "loss": 3.5798, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269898772441418e-05, + "loss": 3.5788, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690601776903665e-05, + "loss": 3.5702, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2682232208196874e-05, + "loss": 3.5733, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673846260686354e-05, + "loss": 3.5847, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2665460313175834e-05, + "loss": 3.5819, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2657074365665314e-05, + "loss": 3.5935, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264870479695852e-05, + "loss": 3.5643, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2640318849448e-05, + "loss": 3.5827, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263193290193748e-05, + "loss": 3.5818, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262354695442696e-05, + "loss": 3.5828, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261517738572017e-05, + "loss": 3.574, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260679143820965e-05, + "loss": 3.5748, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259840549069913e-05, + "loss": 3.5887, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.259001954318862e-05, + "loss": 3.5952, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.25816335956781e-05, + "loss": 3.5788, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257326402697131e-05, + "loss": 3.5799, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256487807946079e-05, + "loss": 3.5758, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255649213195027e-05, + "loss": 3.5815, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254810618443975e-05, + "loss": 3.575, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253973661573296e-05, + "loss": 3.5843, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253135066822244e-05, + "loss": 3.5718, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252296472071192e-05, + "loss": 3.579, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.25145787732014e-05, + "loss": 3.578, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8643624782562256, + "eval_runtime": 315.7578, + "eval_samples_per_second": 1208.493, + "eval_steps_per_second": 37.766, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2506209204494606e-05, + "loss": 3.5677, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497823256984086e-05, + "loss": 3.5686, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248943730947357e-05, + "loss": 3.5718, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248105136196305e-05, + "loss": 3.5831, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247268179325626e-05, + "loss": 3.5794, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246429584574574e-05, + "loss": 3.5858, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245590989823522e-05, + "loss": 3.5699, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.24475239507247e-05, + "loss": 3.5834, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2439138003214175e-05, + "loss": 3.5727, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243076843450739e-05, + "loss": 3.5737, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242238248699687e-05, + "loss": 3.5778, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2413996539486344e-05, + "loss": 3.5775, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240562697077956e-05, + "loss": 3.5895, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239724102326904e-05, + "loss": 3.5655, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388855075758526e-05, + "loss": 3.5594, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380469128248e-05, + "loss": 3.5692, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2372099559541215e-05, + "loss": 3.5703, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363713612030695e-05, + "loss": 3.5719, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355327664520175e-05, + "loss": 3.5711, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234694171700965e-05, + "loss": 3.579, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338572148302864e-05, + "loss": 3.5918, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.2330186200792344e-05, + "loss": 3.5781, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232180025328182e-05, + "loss": 3.5787, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.23134143057713e-05, + "loss": 3.5748, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230502835826078e-05, + "loss": 3.5859, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229665878955399e-05, + "loss": 3.5685, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228827284204347e-05, + "loss": 3.5714, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227988689453295e-05, + "loss": 3.5807, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227150094702243e-05, + "loss": 3.5613, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226313137831564e-05, + "loss": 3.564, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225474543080512e-05, + "loss": 3.5694, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.22463594832946e-05, + "loss": 3.5781, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223797353578408e-05, + "loss": 3.5822, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222960396707729e-05, + "loss": 3.5686, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222121801956677e-05, + "loss": 3.5797, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221283207205625e-05, + "loss": 3.5685, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220444612454573e-05, + "loss": 3.5662, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219607655583895e-05, + "loss": 3.5593, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218769060832843e-05, + "loss": 3.5757, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217930466081791e-05, + "loss": 3.5618, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217091871330739e-05, + "loss": 3.5688, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162549144600596e-05, + "loss": 3.5718, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2154163197090076e-05, + "loss": 3.5838, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145777249579556e-05, + "loss": 3.5676, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137391302069036e-05, + "loss": 3.5716, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.2129021733362245e-05, + "loss": 3.5737, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120635785851725e-05, + "loss": 3.5653, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2112249838341205e-05, + "loss": 3.57, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.2103863890830685e-05, + "loss": 3.5566, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.20954943221239e-05, + "loss": 3.5693, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208710837461338e-05, + "loss": 3.575, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207872242710286e-05, + "loss": 3.5676, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207033647959234e-05, + "loss": 3.5646, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206196691088555e-05, + "loss": 3.5517, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205358096337503e-05, + "loss": 3.5626, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204519501586451e-05, + "loss": 3.5496, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203680906835399e-05, + "loss": 3.5877, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.20284394996472e-05, + "loss": 3.5626, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.202005355213668e-05, + "loss": 3.5829, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201166760462616e-05, + "loss": 3.5669, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200328165711564e-05, + "loss": 3.5526, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199489570960512e-05, + "loss": 3.5638, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986526140898334e-05, + "loss": 3.5659, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1978140193387814e-05, + "loss": 3.5572, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969754245877294e-05, + "loss": 3.5524, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.1961368298366774e-05, + "loss": 3.5776, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195299872965998e-05, + "loss": 3.5691, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194461278214946e-05, + "loss": 3.5577, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193622683463894e-05, + "loss": 3.5535, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192784088712842e-05, + "loss": 3.5606, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191947131842163e-05, + "loss": 3.5646, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191108537091111e-05, + "loss": 3.5749, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190269942340059e-05, + "loss": 3.5678, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189431347589007e-05, + "loss": 3.5692, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188594390718329e-05, + "loss": 3.5698, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187755795967277e-05, + "loss": 3.5672, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186917201216225e-05, + "loss": 3.5729, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186078606465173e-05, + "loss": 3.5605, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185241649594494e-05, + "loss": 3.5698, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184403054843442e-05, + "loss": 3.5624, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.18356446009239e-05, + "loss": 3.5635, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182725865341338e-05, + "loss": 3.5756, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818889084706586e-05, + "loss": 3.5757, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810503137196066e-05, + "loss": 3.5608, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1802117189685546e-05, + "loss": 3.5421, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.1793731242175026e-05, + "loss": 3.5702, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178536167346824e-05, + "loss": 3.5639, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177697572595772e-05, + "loss": 3.5697, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.17685897784472e-05, + "loss": 3.5625, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176020383093668e-05, + "loss": 3.5669, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175183426222989e-05, + "loss": 3.561, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174344831471937e-05, + "loss": 3.5581, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173506236720885e-05, + "loss": 3.563, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172667641969833e-05, + "loss": 3.5693, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171830685099154e-05, + "loss": 3.5744, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170992090348102e-05, + "loss": 3.5729, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.17015349559705e-05, + "loss": 3.5582, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169314900845998e-05, + "loss": 3.5648, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684779439753195e-05, + "loss": 3.5641, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676393492242675e-05, + "loss": 3.568, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1668007544732155e-05, + "loss": 3.5606, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659621597221635e-05, + "loss": 3.5673, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1651252028514844e-05, + "loss": 3.5587, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642866081004324e-05, + "loss": 3.556, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634480133493804e-05, + "loss": 3.5682, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1626094185983284e-05, + "loss": 3.5498, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161772461727649e-05, + "loss": 3.5585, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160933866976597e-05, + "loss": 3.5723, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160095272225545e-05, + "loss": 3.5602, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159256677474493e-05, + "loss": 3.556, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158419720603815e-05, + "loss": 3.571, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157581125852763e-05, + "loss": 3.553, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156742531101711e-05, + "loss": 3.5697, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155903936350659e-05, + "loss": 3.5658, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.15506697947998e-05, + "loss": 3.5642, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154228384728928e-05, + "loss": 3.5689, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153389789977876e-05, + "loss": 3.5749, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152551195226824e-05, + "loss": 3.5623, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151714238356145e-05, + "loss": 3.5642, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150875643605093e-05, + "loss": 3.5581, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150037048854041e-05, + "loss": 3.5652, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149198454102989e-05, + "loss": 3.5574, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.14836149723231e-05, + "loss": 3.5589, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147522902481258e-05, + "loss": 3.5596, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146684307730206e-05, + "loss": 3.5698, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145845712979154e-05, + "loss": 3.5631, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.145008756108475e-05, + "loss": 3.5633, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144170161357423e-05, + "loss": 3.5553, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143331566606371e-05, + "loss": 3.5587, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142492971855319e-05, + "loss": 3.5666, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.14165601498464e-05, + "loss": 3.5705, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140817420233588e-05, + "loss": 3.5727, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139978825482536e-05, + "loss": 3.55, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139140230731484e-05, + "loss": 3.5698, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1383032738608056e-05, + "loss": 3.5653, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374646791097536e-05, + "loss": 3.5668, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366260843587016e-05, + "loss": 3.556, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357874896076496e-05, + "loss": 3.5631, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349505327369705e-05, + "loss": 3.5709, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.1341119379859185e-05, + "loss": 3.5774, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332733432348665e-05, + "loss": 3.5625, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132434748483814e-05, + "loss": 3.5626, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315977916131354e-05, + "loss": 3.5612, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307591968620834e-05, + "loss": 3.563, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299206021110314e-05, + "loss": 3.5569, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290820073599794e-05, + "loss": 3.573, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128245050489301e-05, + "loss": 3.5539, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127406455738249e-05, + "loss": 3.5701, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126567860987197e-05, + "loss": 3.5575, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.864409923553467, + "eval_runtime": 331.6943, + "eval_samples_per_second": 1150.43, + "eval_steps_per_second": 35.952, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125729266236144e-05, + "loss": 3.5617, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124892309365466e-05, + "loss": 3.5542, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124053714614414e-05, + "loss": 3.5532, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123215119863361e-05, + "loss": 3.5679, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122376525112309e-05, + "loss": 3.565, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121539568241631e-05, + "loss": 3.5706, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120700973490579e-05, + "loss": 3.555, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119862378739527e-05, + "loss": 3.5681, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119023783988475e-05, + "loss": 3.5538, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181868271177964e-05, + "loss": 3.5609, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173482323667443e-05, + "loss": 3.5623, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116509637615692e-05, + "loss": 3.564, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156710428646397e-05, + "loss": 3.5654, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114834085993961e-05, + "loss": 3.5584, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.1139954912429086e-05, + "loss": 3.5483, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1131568964918566e-05, + "loss": 3.5554, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1123183017408046e-05, + "loss": 3.5483, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114797069897526e-05, + "loss": 3.5558, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106411122387005e-05, + "loss": 3.5582, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1098025174876485e-05, + "loss": 3.5564, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.10896556061697e-05, + "loss": 3.5786, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108126965865918e-05, + "loss": 3.5629, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107288371114866e-05, + "loss": 3.5628, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106449776363814e-05, + "loss": 3.5621, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105611181612762e-05, + "loss": 3.5696, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104774224742083e-05, + "loss": 3.551, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103935629991031e-05, + "loss": 3.5592, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103097035239979e-05, + "loss": 3.5619, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102258440488927e-05, + "loss": 3.5534, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101421483618248e-05, + "loss": 3.5444, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100582888867196e-05, + "loss": 3.5544, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099744294116144e-05, + "loss": 3.5634, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098905699365092e-05, + "loss": 3.5637, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980687424944135e-05, + "loss": 3.559, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972301477433615e-05, + "loss": 3.5625, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963915529923095e-05, + "loss": 3.5537, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955529582412575e-05, + "loss": 3.5496, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0947160013705784e-05, + "loss": 3.5443, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938774066195264e-05, + "loss": 3.5606, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0930388118684744e-05, + "loss": 3.5474, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0922002171174224e-05, + "loss": 3.5558, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091363260246743e-05, + "loss": 3.5533, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090524665495691e-05, + "loss": 3.572, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089686070744639e-05, + "loss": 3.5501, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088847475993587e-05, + "loss": 3.556, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.088010519122909e-05, + "loss": 3.5597, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087171924371857e-05, + "loss": 3.5493, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086333329620805e-05, + "loss": 3.5586, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085494734869753e-05, + "loss": 3.5409, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084657777999074e-05, + "loss": 3.5568, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083819183248022e-05, + "loss": 3.5562, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.08298058849697e-05, + "loss": 3.5537, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082141993745918e-05, + "loss": 3.5506, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0813050368752387e-05, + "loss": 3.5354, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804664421241866e-05, + "loss": 3.5512, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796278473731346e-05, + "loss": 3.5354, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787892526220826e-05, + "loss": 3.5674, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077952295751404e-05, + "loss": 3.5479, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077113701000352e-05, + "loss": 3.5609, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762751062493e-05, + "loss": 3.557, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075436511498248e-05, + "loss": 3.5403, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074599554627569e-05, + "loss": 3.5455, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073760959876517e-05, + "loss": 3.5496, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072922365125465e-05, + "loss": 3.5434, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072083770374413e-05, + "loss": 3.5325, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071246813503734e-05, + "loss": 3.5616, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070408218752682e-05, + "loss": 3.5566, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.06956962400163e-05, + "loss": 3.5424, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0687326671309516e-05, + "loss": 3.5343, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678940723798996e-05, + "loss": 3.5451, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670554776288476e-05, + "loss": 3.5483, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0662168828777956e-05, + "loss": 3.5617, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653782881267436e-05, + "loss": 3.5522, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645413312560645e-05, + "loss": 3.5565, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0637027365050125e-05, + "loss": 3.5506, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628641417539605e-05, + "loss": 3.557, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.0620255470029085e-05, + "loss": 3.5543, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.0611885901322294e-05, + "loss": 3.5464, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603499953811774e-05, + "loss": 3.5574, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.0595114006301254e-05, + "loss": 3.5451, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586728058790734e-05, + "loss": 3.5507, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057835849008395e-05, + "loss": 3.5612, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056997254257343e-05, + "loss": 3.5565, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056158659506291e-05, + "loss": 3.5453, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.055320064755239e-05, + "loss": 3.5279, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.05448310788456e-05, + "loss": 3.5532, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053644513133508e-05, + "loss": 3.5529, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052805918382456e-05, + "loss": 3.5504, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051967323631404e-05, + "loss": 3.5509, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.051130366760725e-05, + "loss": 3.5508, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.050291772009673e-05, + "loss": 3.5479, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.049453177258621e-05, + "loss": 3.5386, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048614582507569e-05, + "loss": 3.5488, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.04777762563689e-05, + "loss": 3.5542, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046939030885838e-05, + "loss": 3.5605, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.046100436134786e-05, + "loss": 3.5566, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452618413837343e-05, + "loss": 3.5508, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444248845130552e-05, + "loss": 3.5456, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435862897620032e-05, + "loss": 3.5494, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427476950109512e-05, + "loss": 3.5513, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0419091002598992e-05, + "loss": 3.5477, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410721433892205e-05, + "loss": 3.5502, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402335486381685e-05, + "loss": 3.5456, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393949538871164e-05, + "loss": 3.5372, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385563591360638e-05, + "loss": 3.5536, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0377177643850118e-05, + "loss": 3.5319, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368808075143333e-05, + "loss": 3.5464, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360422127632813e-05, + "loss": 3.5543, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035203618012229e-05, + "loss": 3.5475, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034365023261177e-05, + "loss": 3.5425, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335280663904986e-05, + "loss": 3.551, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032689471639446e-05, + "loss": 3.545, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318508768883942e-05, + "loss": 3.5519, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310122821373422e-05, + "loss": 3.5494, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301753252666638e-05, + "loss": 3.5502, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.029336730515611e-05, + "loss": 3.5536, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.028498135764559e-05, + "loss": 3.56, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.027659541013507e-05, + "loss": 3.5454, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268225841428287e-05, + "loss": 3.5465, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259839893917764e-05, + "loss": 3.547, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251453946407244e-05, + "loss": 3.5498, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0243067998896724e-05, + "loss": 3.5402, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234698430189933e-05, + "loss": 3.5443, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226312482679413e-05, + "loss": 3.5454, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217926535168896e-05, + "loss": 3.5545, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209556966462112e-05, + "loss": 3.5473, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201171018951585e-05, + "loss": 3.5491, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192785071441065e-05, + "loss": 3.5418, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184399123930545e-05, + "loss": 3.5443, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0176013176420025e-05, + "loss": 3.5472, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167643607713237e-05, + "loss": 3.5568, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159257660202717e-05, + "loss": 3.5581, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150871712692197e-05, + "loss": 3.5361, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142485765181677e-05, + "loss": 3.5479, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0134116196474886e-05, + "loss": 3.5551, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125730248964366e-05, + "loss": 3.5513, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011734430145385e-05, + "loss": 3.5457, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010895835394333e-05, + "loss": 3.5437, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010058878523654e-05, + "loss": 3.5585, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009220283772602e-05, + "loss": 3.5605, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.00838168902155e-05, + "loss": 3.5484, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.007543094270498e-05, + "loss": 3.5509, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006706137399819e-05, + "loss": 3.5464, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005867542648767e-05, + "loss": 3.5451, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.005028947897715e-05, + "loss": 3.5439, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.004190353146663e-05, + "loss": 3.5607, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.003353396275984e-05, + "loss": 3.5393, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002514801524932e-05, + "loss": 3.5537, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016762067738803e-05, + "loss": 3.5424, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008376120228283e-05, + "loss": 3.5489, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8660314083099365, + "eval_runtime": 324.8523, + "eval_samples_per_second": 1174.66, + "eval_steps_per_second": 36.709, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999990172717763e-05, + "loss": 3.5378, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991604225207243e-05, + "loss": 3.5395, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983218277696723e-05, + "loss": 3.5548, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974832330186203e-05, + "loss": 3.547, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966462761479412e-05, + "loss": 3.5601, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958076813968892e-05, + "loss": 3.5372, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949690866458376e-05, + "loss": 3.5523, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941304918947855e-05, + "loss": 3.5428, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932935350241065e-05, + "loss": 3.5464, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924549402730545e-05, + "loss": 3.5473, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9916163455220025e-05, + "loss": 3.548, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907777507709504e-05, + "loss": 3.5518, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899424317806446e-05, + "loss": 3.541, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9891038370295926e-05, + "loss": 3.5338, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882652422785406e-05, + "loss": 3.542, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874266475274886e-05, + "loss": 3.5304, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865880527764366e-05, + "loss": 3.5425, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857494580253846e-05, + "loss": 3.5437, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984910863274333e-05, + "loss": 3.5406, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984072268523281e-05, + "loss": 3.5655, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832353116526018e-05, + "loss": 3.5496, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823967169015498e-05, + "loss": 3.5482, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815581221504978e-05, + "loss": 3.5443, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807195273994458e-05, + "loss": 3.5537, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979882570528767e-05, + "loss": 3.541, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.979043975777715e-05, + "loss": 3.5408, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978205381026663e-05, + "loss": 3.5462, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977366786275611e-05, + "loss": 3.5392, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976529829404932e-05, + "loss": 3.5247, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.97569123465388e-05, + "loss": 3.5412, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748526399028283e-05, + "loss": 3.5468, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740156830321492e-05, + "loss": 3.5516, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731770882810972e-05, + "loss": 3.5473, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723384935300452e-05, + "loss": 3.5507, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714998987789932e-05, + "loss": 3.5353, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706629419083144e-05, + "loss": 3.5386, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698243471572624e-05, + "loss": 3.5274, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689857524062104e-05, + "loss": 3.5456, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681471576551584e-05, + "loss": 3.5352, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9673102007844793e-05, + "loss": 3.5411, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664716060334273e-05, + "loss": 3.5392, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656330112823753e-05, + "loss": 3.5512, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647944165313237e-05, + "loss": 3.5435, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639574596606446e-05, + "loss": 3.5398, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631188649095926e-05, + "loss": 3.5452, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622802701585406e-05, + "loss": 3.535, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614416754074886e-05, + "loss": 3.5442, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9606047185368098e-05, + "loss": 3.5259, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597661237857578e-05, + "loss": 3.5363, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589275290347058e-05, + "loss": 3.5451, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580889342836538e-05, + "loss": 3.5355, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572519774129747e-05, + "loss": 3.5387, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564133826619227e-05, + "loss": 3.5239, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555747879108707e-05, + "loss": 3.5365, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954736193159819e-05, + "loss": 3.5191, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.95389923628914e-05, + "loss": 3.5534, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.953060641538088e-05, + "loss": 3.5329, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952222046787036e-05, + "loss": 3.5497, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951383452035984e-05, + "loss": 3.5433, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.950546495165305e-05, + "loss": 3.5281, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.949707900414253e-05, + "loss": 3.5295, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948869305663201e-05, + "loss": 3.5369, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480307109121485e-05, + "loss": 3.5278, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.94719375404147e-05, + "loss": 3.5209, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946355159290418e-05, + "loss": 3.5476, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945516564539366e-05, + "loss": 3.5409, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446779697883137e-05, + "loss": 3.5286, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438410129176353e-05, + "loss": 3.5223, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9430024181665833e-05, + "loss": 3.5291, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421638234155313e-05, + "loss": 3.5375, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941325228664479e-05, + "loss": 3.5433, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404882717938005e-05, + "loss": 3.5382, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396496770427485e-05, + "loss": 3.5421, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938811082291696e-05, + "loss": 3.5403, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937972487540644e-05, + "loss": 3.542, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371355306699654e-05, + "loss": 3.5369, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362969359189134e-05, + "loss": 3.5373, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935458341167861e-05, + "loss": 3.541, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934619746416809e-05, + "loss": 3.5323, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337827895461307e-05, + "loss": 3.5353, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329441947950787e-05, + "loss": 3.5433, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932105600044026e-05, + "loss": 3.5469, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312670052929743e-05, + "loss": 3.5297, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930430048422296e-05, + "loss": 3.518, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295914536712432e-05, + "loss": 3.5346, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287528589201912e-05, + "loss": 3.5383, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9279142641691392e-05, + "loss": 3.5368, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270773072984608e-05, + "loss": 3.5351, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262387125474085e-05, + "loss": 3.5372, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9254001177963564e-05, + "loss": 3.5297, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245615230453044e-05, + "loss": 3.5237, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.923724566174626e-05, + "loss": 3.5355, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228859714235733e-05, + "loss": 3.5368, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220473766725213e-05, + "loss": 3.544, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9212087819214697e-05, + "loss": 3.5461, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203718250507906e-05, + "loss": 3.5411, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195332302997386e-05, + "loss": 3.5258, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186946355486866e-05, + "loss": 3.5379, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178560407976346e-05, + "loss": 3.5371, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170190839269558e-05, + "loss": 3.5362, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161804891759038e-05, + "loss": 3.5356, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153418944248518e-05, + "loss": 3.5313, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9145032996737998e-05, + "loss": 3.526, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136663428031207e-05, + "loss": 3.5422, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128277480520687e-05, + "loss": 3.5185, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119891533010167e-05, + "loss": 3.5346, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.911150558549965e-05, + "loss": 3.542, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910313601679286e-05, + "loss": 3.532, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.909475006928234e-05, + "loss": 3.5287, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908636412177182e-05, + "loss": 3.5394, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.90779781742613e-05, + "loss": 3.5281, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069608605554512e-05, + "loss": 3.5408, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061222658043992e-05, + "loss": 3.5367, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052836710533472e-05, + "loss": 3.5336, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044450763022952e-05, + "loss": 3.5368, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903608119431616e-05, + "loss": 3.5492, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902769524680564e-05, + "loss": 3.5304, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901930929929512e-05, + "loss": 3.5319, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.90109233517846e-05, + "loss": 3.5336, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002553783077813e-05, + "loss": 3.5338, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994167835567293e-05, + "loss": 3.5293, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985781888056773e-05, + "loss": 3.5268, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977395940546253e-05, + "loss": 3.5323, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8969026371839466e-05, + "loss": 3.5408, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960640424328946e-05, + "loss": 3.5384, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952254476818425e-05, + "loss": 3.5344, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943868529307905e-05, + "loss": 3.5262, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935498960601115e-05, + "loss": 3.5286, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.8927113013090594e-05, + "loss": 3.5325, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918727065580074e-05, + "loss": 3.5443, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910341118069554e-05, + "loss": 3.5449, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901971549362767e-05, + "loss": 3.5262, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893585601852247e-05, + "loss": 3.5303, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885199654341727e-05, + "loss": 3.5395, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876813706831207e-05, + "loss": 3.5315, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868444138124416e-05, + "loss": 3.5403, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.88600581906139e-05, + "loss": 3.5295, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885167224310338e-05, + "loss": 3.544, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884328629559286e-05, + "loss": 3.5441, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834916726886068e-05, + "loss": 3.5355, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826530779375548e-05, + "loss": 3.5355, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818144831865028e-05, + "loss": 3.535, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809758884354508e-05, + "loss": 3.5296, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.880138931564772e-05, + "loss": 3.5294, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.87930033681372e-05, + "loss": 3.5459, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.878461742062668e-05, + "loss": 3.5267, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877623147311616e-05, + "loss": 3.5365, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876786190440937e-05, + "loss": 3.5322, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759475956898853e-05, + "loss": 3.5313, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.866630792617798, + "eval_runtime": 303.8587, + "eval_samples_per_second": 1255.817, + "eval_steps_per_second": 39.245, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8751090009388333e-05, + "loss": 3.5225, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742704061877813e-05, + "loss": 3.5265, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734318114367293e-05, + "loss": 3.5431, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725932166856773e-05, + "loss": 3.5297, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717562598149982e-05, + "loss": 3.5461, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709176650639462e-05, + "loss": 3.521, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700790703128945e-05, + "loss": 3.5393, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692404755618425e-05, + "loss": 3.5302, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8684035186911634e-05, + "loss": 3.531, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675649239401114e-05, + "loss": 3.5378, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8667263291890594e-05, + "loss": 3.5309, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658877344380074e-05, + "loss": 3.5378, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650507775673286e-05, + "loss": 3.5257, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8642121828162766e-05, + "loss": 3.5241, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.8633735880652246e-05, + "loss": 3.5252, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.8625349933141726e-05, + "loss": 3.5223, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.8616980364434935e-05, + "loss": 3.523, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.8608594416924415e-05, + "loss": 3.5287, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.86002084694139e-05, + "loss": 3.5282, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859182252190338e-05, + "loss": 3.5557, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583452953196588e-05, + "loss": 3.534, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8575067005686068e-05, + "loss": 3.5358, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566681058175548e-05, + "loss": 3.5328, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558295110665028e-05, + "loss": 3.5376, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.854992554195824e-05, + "loss": 3.5281, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.854153959444772e-05, + "loss": 3.5301, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.85331536469372e-05, + "loss": 3.53, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.852478407823041e-05, + "loss": 3.5273, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.851639813071989e-05, + "loss": 3.51, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.850801218320937e-05, + "loss": 3.5311, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499626235698852e-05, + "loss": 3.5317, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.849125666699206e-05, + "loss": 3.538, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.848287071948154e-05, + "loss": 3.5328, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.847448477197102e-05, + "loss": 3.5343, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.84660988244605e-05, + "loss": 3.5237, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457729255753714e-05, + "loss": 3.5276, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449343308243194e-05, + "loss": 3.5152, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440957360732674e-05, + "loss": 3.5302, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432571413222154e-05, + "loss": 3.5227, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8424201844515363e-05, + "loss": 3.5235, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415815897004843e-05, + "loss": 3.5267, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407429949494323e-05, + "loss": 3.5365, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8399044001983806e-05, + "loss": 3.5303, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.839065805447328e-05, + "loss": 3.528, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.8382288485766495e-05, + "loss": 3.5327, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.8373902538255975e-05, + "loss": 3.521, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.8365516590745455e-05, + "loss": 3.5287, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835713064323493e-05, + "loss": 3.517, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348761074528147e-05, + "loss": 3.5181, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340375127017627e-05, + "loss": 3.532, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331989179507107e-05, + "loss": 3.5222, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832360323199658e-05, + "loss": 3.524, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.8315233663289796e-05, + "loss": 3.5125, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.8306847715779276e-05, + "loss": 3.521, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.8298461768268753e-05, + "loss": 3.5081, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8290075820758233e-05, + "loss": 3.5361, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.828170625205145e-05, + "loss": 3.5222, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.827332030454093e-05, + "loss": 3.5301, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264934357030405e-05, + "loss": 3.5306, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256548409519885e-05, + "loss": 3.5173, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.82481788408131e-05, + "loss": 3.5124, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.823979289330258e-05, + "loss": 3.5241, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231406945792054e-05, + "loss": 3.5131, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8223020998281534e-05, + "loss": 3.5089, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.821465142957475e-05, + "loss": 3.529, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206265482064227e-05, + "loss": 3.5294, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197879534553707e-05, + "loss": 3.5142, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189493587043187e-05, + "loss": 3.5107, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8181124018336402e-05, + "loss": 3.5147, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172738070825876e-05, + "loss": 3.5246, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.816435212331536e-05, + "loss": 3.527, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.815596617580484e-05, + "loss": 3.5239, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147596607098055e-05, + "loss": 3.5301, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8139210659587528e-05, + "loss": 3.5265, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130824712077008e-05, + "loss": 3.5325, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122438764566488e-05, + "loss": 3.5189, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.81140691958597e-05, + "loss": 3.5259, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810568324834918e-05, + "loss": 3.5281, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809729730083866e-05, + "loss": 3.5147, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808891135332814e-05, + "loss": 3.5279, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808054178462135e-05, + "loss": 3.5283, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807215583711083e-05, + "loss": 3.5337, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806376988960031e-05, + "loss": 3.5148, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055383942089793e-05, + "loss": 3.5071, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.8047014373383002e-05, + "loss": 3.5201, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803862842587248e-05, + "loss": 3.5241, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.803024247836196e-05, + "loss": 3.5274, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.802185653085144e-05, + "loss": 3.5212, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013486962144654e-05, + "loss": 3.5216, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8005101014634134e-05, + "loss": 3.52, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996715067123614e-05, + "loss": 3.5125, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988329119613094e-05, + "loss": 3.5209, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979959550906303e-05, + "loss": 3.5211, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971573603395783e-05, + "loss": 3.5314, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963187655885263e-05, + "loss": 3.5316, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954801708374746e-05, + "loss": 3.5295, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946432139667955e-05, + "loss": 3.517, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7938046192157435e-05, + "loss": 3.5217, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929660244646915e-05, + "loss": 3.5187, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921274297136395e-05, + "loss": 3.5286, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912904728429608e-05, + "loss": 3.5199, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904518780919088e-05, + "loss": 3.5181, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7896132833408568e-05, + "loss": 3.5124, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887746885898048e-05, + "loss": 3.5279, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879377317191257e-05, + "loss": 3.5037, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870991369680737e-05, + "loss": 3.522, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7862605422170217e-05, + "loss": 3.5253, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.78542194746597e-05, + "loss": 3.515, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.784584990595291e-05, + "loss": 3.5152, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.783746395844239e-05, + "loss": 3.5286, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.782907801093187e-05, + "loss": 3.5151, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.782069206342135e-05, + "loss": 3.5216, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.781232249471456e-05, + "loss": 3.5262, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.780393654720404e-05, + "loss": 3.5154, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.779555059969352e-05, + "loss": 3.5264, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787164652183e-05, + "loss": 3.5353, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777879508347621e-05, + "loss": 3.518, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.777040913596569e-05, + "loss": 3.5208, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.776202318845517e-05, + "loss": 3.522, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753637240944654e-05, + "loss": 3.5198, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745267672237863e-05, + "loss": 3.5164, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736881724727343e-05, + "loss": 3.513, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728495777216823e-05, + "loss": 3.5169, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7720109829706303e-05, + "loss": 3.5328, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711723882195783e-05, + "loss": 3.5233, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703354313488995e-05, + "loss": 3.522, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694968365978475e-05, + "loss": 3.5153, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.7686582418467955e-05, + "loss": 3.5143, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7678212849761164e-05, + "loss": 3.5202, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669826902250644e-05, + "loss": 3.5329, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661440954740124e-05, + "loss": 3.5327, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7653055007229607e-05, + "loss": 3.5112, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.7644669059719087e-05, + "loss": 3.5159, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.7636299491012296e-05, + "loss": 3.5277, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.7627913543501776e-05, + "loss": 3.5191, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.7619527595991256e-05, + "loss": 3.53, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.7611141648480736e-05, + "loss": 3.5159, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760277207977395e-05, + "loss": 3.5292, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759438613226343e-05, + "loss": 3.5299, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.758600018475291e-05, + "loss": 3.5212, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757761423724239e-05, + "loss": 3.5233, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569244668535598e-05, + "loss": 3.5227, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560858721025078e-05, + "loss": 3.5171, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.755247277351456e-05, + "loss": 3.5177, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.754408682600404e-05, + "loss": 3.5315, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.753571725729725e-05, + "loss": 3.513, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.752733130978673e-05, + "loss": 3.5233, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.751894536227621e-05, + "loss": 3.5212, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.751055941476569e-05, + "loss": 3.5161, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.867504835128784, + "eval_runtime": 310.9372, + "eval_samples_per_second": 1227.228, + "eval_steps_per_second": 38.352, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502189846058902e-05, + "loss": 3.5134, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493803898548382e-05, + "loss": 3.5151, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485417951037862e-05, + "loss": 3.5302, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7477032003527342e-05, + "loss": 3.5134, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.746866243482055e-05, + "loss": 3.5353, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.746027648731003e-05, + "loss": 3.5105, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451890539799515e-05, + "loss": 3.5257, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443504592288995e-05, + "loss": 3.5129, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7435135023582204e-05, + "loss": 3.5231, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.7426749076071684e-05, + "loss": 3.5226, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7418363128561164e-05, + "loss": 3.516, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409977181050644e-05, + "loss": 3.5277, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401607612343856e-05, + "loss": 3.5107, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393221664833336e-05, + "loss": 3.5108, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384835717322816e-05, + "loss": 3.5148, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.7376449769812296e-05, + "loss": 3.5077, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.7368080201105505e-05, + "loss": 3.5141, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.7359694253594985e-05, + "loss": 3.5158, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.7351308306084468e-05, + "loss": 3.5151, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342922358573948e-05, + "loss": 3.5389, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334552789867157e-05, + "loss": 3.5216, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326166842356637e-05, + "loss": 3.5241, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317780894846117e-05, + "loss": 3.5183, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309394947335597e-05, + "loss": 3.5252, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.730102537862881e-05, + "loss": 3.5154, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729263943111829e-05, + "loss": 3.5143, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.728425348360777e-05, + "loss": 3.5186, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.727586753609725e-05, + "loss": 3.5128, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.726749796739046e-05, + "loss": 3.5001, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.725911201987994e-05, + "loss": 3.5155, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.725072607236942e-05, + "loss": 3.5233, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242340124858902e-05, + "loss": 3.5216, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.723397055615211e-05, + "loss": 3.5237, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.722558460864159e-05, + "loss": 3.5236, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.721719866113107e-05, + "loss": 3.5085, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.720881271362055e-05, + "loss": 3.5124, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200443144913763e-05, + "loss": 3.5055, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7192057197403243e-05, + "loss": 3.5124, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183671249892723e-05, + "loss": 3.509, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7175285302382196e-05, + "loss": 3.5119, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166915733675412e-05, + "loss": 3.5137, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158529786164892e-05, + "loss": 3.5236, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7150143838654372e-05, + "loss": 3.5149, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.714175789114385e-05, + "loss": 3.5154, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133388322437065e-05, + "loss": 3.5218, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.7125002374926545e-05, + "loss": 3.5058, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.7116616427416018e-05, + "loss": 3.5167, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.71082304799055e-05, + "loss": 3.5082, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.7099860911198717e-05, + "loss": 3.5026, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.7091474963688197e-05, + "loss": 3.519, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708308901617767e-05, + "loss": 3.5101, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.707470306866715e-05, + "loss": 3.5098, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.7066333499960366e-05, + "loss": 3.5039, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.7057947552449846e-05, + "loss": 3.5078, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049561604939322e-05, + "loss": 3.4939, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.7041175657428802e-05, + "loss": 3.5195, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703280608872202e-05, + "loss": 3.5112, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.702442014121149e-05, + "loss": 3.5162, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.701603419370097e-05, + "loss": 3.5211, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007648246190455e-05, + "loss": 3.5055, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.699927867748367e-05, + "loss": 3.4963, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990892729973144e-05, + "loss": 3.5147, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982506782462624e-05, + "loss": 3.5001, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6974120834952104e-05, + "loss": 3.4962, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.696575126624532e-05, + "loss": 3.5188, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957365318734796e-05, + "loss": 3.518, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948979371224276e-05, + "loss": 3.4995, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940593423713756e-05, + "loss": 3.4981, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6932223855006965e-05, + "loss": 3.5011, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923837907496445e-05, + "loss": 3.5077, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915451959985925e-05, + "loss": 3.515, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.690706601247541e-05, + "loss": 3.5097, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898696443768618e-05, + "loss": 3.519, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890310496258098e-05, + "loss": 3.5112, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881924548747577e-05, + "loss": 3.5213, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873538601237057e-05, + "loss": 3.5079, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.686516903253027e-05, + "loss": 3.5108, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.685678308501975e-05, + "loss": 3.5155, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684839713750923e-05, + "loss": 3.4995, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.684001118999871e-05, + "loss": 3.5139, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683164162129192e-05, + "loss": 3.5202, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.68232556737814e-05, + "loss": 3.5187, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681486972627088e-05, + "loss": 3.5021, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.6806483778760362e-05, + "loss": 3.4936, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679811421005357e-05, + "loss": 3.5086, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678972826254305e-05, + "loss": 3.5047, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.678134231503253e-05, + "loss": 3.5161, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.677295636752201e-05, + "loss": 3.5084, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764586798815224e-05, + "loss": 3.5123, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756200851304704e-05, + "loss": 3.5054, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747814903794184e-05, + "loss": 3.497, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739445335087393e-05, + "loss": 3.5088, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6731059387576873e-05, + "loss": 3.5062, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722673440066353e-05, + "loss": 3.5222, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714287492555832e-05, + "loss": 3.5223, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705901545045316e-05, + "loss": 3.5141, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697531976338525e-05, + "loss": 3.5009, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6689146028828005e-05, + "loss": 3.5124, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.6680760081317485e-05, + "loss": 3.5061, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672374133806965e-05, + "loss": 3.5159, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6664004565100177e-05, + "loss": 3.5031, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.6655618617589657e-05, + "loss": 3.5099, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.6647232670079137e-05, + "loss": 3.4987, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638846722568617e-05, + "loss": 3.5148, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630477153861826e-05, + "loss": 3.4909, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.6622091206351306e-05, + "loss": 3.5131, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.6613705258840786e-05, + "loss": 3.5037, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660531931133027e-05, + "loss": 3.5074, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659694974262348e-05, + "loss": 3.5012, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658856379511296e-05, + "loss": 3.5142, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.658017784760244e-05, + "loss": 3.5088, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657179190009192e-05, + "loss": 3.503, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.656342233138513e-05, + "loss": 3.5141, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.655503638387461e-05, + "loss": 3.5007, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.654665043636409e-05, + "loss": 3.5182, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.653826448885357e-05, + "loss": 3.525, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.652989492014678e-05, + "loss": 3.504, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.652150897263626e-05, + "loss": 3.5065, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.651312302512574e-05, + "loss": 3.5075, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504737077615223e-05, + "loss": 3.5065, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496367508908432e-05, + "loss": 3.4999, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487981561397912e-05, + "loss": 3.504, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479595613887392e-05, + "loss": 3.5044, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471209666376872e-05, + "loss": 3.5188, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462840097670085e-05, + "loss": 3.5111, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454454150159565e-05, + "loss": 3.5092, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6446068202649045e-05, + "loss": 3.4998, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.6437682255138524e-05, + "loss": 3.5035, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.6429312686431734e-05, + "loss": 3.5023, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420926738921214e-05, + "loss": 3.523, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412540791410693e-05, + "loss": 3.518, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6404154843900177e-05, + "loss": 3.5025, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395785275193386e-05, + "loss": 3.4995, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387399327682866e-05, + "loss": 3.5138, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.6379013380172346e-05, + "loss": 3.5064, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.6370627432661826e-05, + "loss": 3.5186, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.6362257863955038e-05, + "loss": 3.5003, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.6353871916444518e-05, + "loss": 3.5188, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345485968933998e-05, + "loss": 3.5115, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6337100021423478e-05, + "loss": 3.512, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328730452716687e-05, + "loss": 3.5112, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320344505206167e-05, + "loss": 3.5113, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.6311958557695647e-05, + "loss": 3.5033, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.6303572610185127e-05, + "loss": 3.5061, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629520304147834e-05, + "loss": 3.5168, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628681709396782e-05, + "loss": 3.5061, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.62784311464573e-05, + "loss": 3.5069, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.627004519894678e-05, + "loss": 3.5049, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.626167563023999e-05, + "loss": 3.5035, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.868683338165283, + "eval_runtime": 314.7917, + "eval_samples_per_second": 1212.201, + "eval_steps_per_second": 37.882, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253289682729472e-05, + "loss": 3.4975, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244903735218952e-05, + "loss": 3.4994, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236517787708432e-05, + "loss": 3.5164, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6228131840197912e-05, + "loss": 3.4999, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.621976227149112e-05, + "loss": 3.5249, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.62113763239806e-05, + "loss": 3.4961, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.620299037647008e-05, + "loss": 3.5148, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194604428959564e-05, + "loss": 3.5018, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6186234860252773e-05, + "loss": 3.5072, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177848912742253e-05, + "loss": 3.5109, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169462965231733e-05, + "loss": 3.4996, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6161077017721213e-05, + "loss": 3.5123, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152723827818155e-05, + "loss": 3.5019, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144337880307635e-05, + "loss": 3.4965, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135951932797115e-05, + "loss": 3.502, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127565985286595e-05, + "loss": 3.4935, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.6119180037776075e-05, + "loss": 3.5002, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.6110794090265554e-05, + "loss": 3.5019, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.6102408142755034e-05, + "loss": 3.5007, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.6094022195244518e-05, + "loss": 3.5238, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085652626537727e-05, + "loss": 3.5112, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6077266679027207e-05, + "loss": 3.5133, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068880731516687e-05, + "loss": 3.5052, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060494784006167e-05, + "loss": 3.5104, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605212521529938e-05, + "loss": 3.5029, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604373926778886e-05, + "loss": 3.5027, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603535332027834e-05, + "loss": 3.5082, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.602696737276782e-05, + "loss": 3.4978, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018597804061028e-05, + "loss": 3.4923, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6010211856550508e-05, + "loss": 3.4969, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001825909039988e-05, + "loss": 3.5098, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993439961529465e-05, + "loss": 3.509, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598507039282268e-05, + "loss": 3.5128, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597668444531216e-05, + "loss": 3.512, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596829849780164e-05, + "loss": 3.4932, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959912550291117e-05, + "loss": 3.5006, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951542981584333e-05, + "loss": 3.4987, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5943157034073813e-05, + "loss": 3.4948, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934771086563293e-05, + "loss": 3.4987, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926385139052766e-05, + "loss": 3.4951, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5918015570345982e-05, + "loss": 3.5035, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909629622835462e-05, + "loss": 3.5072, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590124367532494e-05, + "loss": 3.5055, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589285772781442e-05, + "loss": 3.4989, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884488159107634e-05, + "loss": 3.5103, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.5876102211597114e-05, + "loss": 3.4949, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867716264086587e-05, + "loss": 3.5021, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.585933031657607e-05, + "loss": 3.4963, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850960747869287e-05, + "loss": 3.4876, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842574800358767e-05, + "loss": 3.5072, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.583418885284824e-05, + "loss": 3.4977, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582580290533772e-05, + "loss": 3.4985, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817433336630936e-05, + "loss": 3.4889, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5809047389120412e-05, + "loss": 3.4942, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800661441609892e-05, + "loss": 3.4821, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5792275494099372e-05, + "loss": 3.5033, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783905925392588e-05, + "loss": 3.5006, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.577551997788206e-05, + "loss": 3.502, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.576713403037154e-05, + "loss": 3.5082, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758748082861024e-05, + "loss": 3.4944, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750378514154233e-05, + "loss": 3.4848, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741992566643713e-05, + "loss": 3.5061, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733606619133193e-05, + "loss": 3.4867, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5725220671622673e-05, + "loss": 3.4849, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716851102915886e-05, + "loss": 3.5053, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708465155405366e-05, + "loss": 3.5029, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5700079207894846e-05, + "loss": 3.4906, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691693260384326e-05, + "loss": 3.4888, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5683323691677535e-05, + "loss": 3.4849, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674937744167015e-05, + "loss": 3.4918, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666551796656495e-05, + "loss": 3.5037, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.5658165849145978e-05, + "loss": 3.5018, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649796280439187e-05, + "loss": 3.5064, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641410332928667e-05, + "loss": 3.4965, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5633024385418147e-05, + "loss": 3.5125, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624638437907627e-05, + "loss": 3.4927, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.561626886920084e-05, + "loss": 3.5032, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.560788292169032e-05, + "loss": 3.5008, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.55994969741798e-05, + "loss": 3.4858, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.559111102666928e-05, + "loss": 3.5069, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558274145796249e-05, + "loss": 3.5047, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557435551045197e-05, + "loss": 3.5013, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.556596956294145e-05, + "loss": 3.4886, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555758361543093e-05, + "loss": 3.4831, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.554921404672414e-05, + "loss": 3.4963, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.554082809921362e-05, + "loss": 3.4963, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.55324421517031e-05, + "loss": 3.5047, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.552405620419258e-05, + "loss": 3.4906, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515686635485793e-05, + "loss": 3.5005, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507300687975273e-05, + "loss": 3.4931, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498914740464753e-05, + "loss": 3.4914, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490528792954233e-05, + "loss": 3.4955, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5482159224247442e-05, + "loss": 3.4904, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473773276736922e-05, + "loss": 3.513, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465387329226402e-05, + "loss": 3.5069, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5457001381715885e-05, + "loss": 3.5054, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448631813009094e-05, + "loss": 3.4849, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440245865498574e-05, + "loss": 3.501, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431859917988054e-05, + "loss": 3.4941, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423473970477534e-05, + "loss": 3.5019, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.5415104401770747e-05, + "loss": 3.4919, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.5406718454260227e-05, + "loss": 3.4954, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398332506749707e-05, + "loss": 3.4876, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.5389946559239187e-05, + "loss": 3.5027, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.5381576990532396e-05, + "loss": 3.4796, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.5373191043021876e-05, + "loss": 3.4975, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.5364805095511356e-05, + "loss": 3.4938, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.5356419148000836e-05, + "loss": 3.4948, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5348049579294048e-05, + "loss": 3.4885, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.5339663631783528e-05, + "loss": 3.5054, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331277684273008e-05, + "loss": 3.4939, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322891736762488e-05, + "loss": 3.4923, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314522168055697e-05, + "loss": 3.5045, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.530613622054518e-05, + "loss": 3.4889, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.529775027303466e-05, + "loss": 3.5038, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.528936432552414e-05, + "loss": 3.5105, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.528099475681735e-05, + "loss": 3.4949, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.527260880930683e-05, + "loss": 3.493, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.526422286179631e-05, + "loss": 3.4925, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.525583691428579e-05, + "loss": 3.4931, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247467345579002e-05, + "loss": 3.4899, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5239081398068482e-05, + "loss": 3.4968, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.523069545055796e-05, + "loss": 3.485, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.522230950304744e-05, + "loss": 3.5044, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.521393993434065e-05, + "loss": 3.5023, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205553986830134e-05, + "loss": 3.4972, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197168039319614e-05, + "loss": 3.4847, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188782091809094e-05, + "loss": 3.492, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180412523102303e-05, + "loss": 3.492, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5172026575591783e-05, + "loss": 3.504, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163640628081263e-05, + "loss": 3.5102, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5155254680570743e-05, + "loss": 3.4956, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146885111863955e-05, + "loss": 3.4829, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138499164353435e-05, + "loss": 3.5011, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.5130113216842915e-05, + "loss": 3.4922, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.5121727269332395e-05, + "loss": 3.5083, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113341321821875e-05, + "loss": 3.4888, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104971753115088e-05, + "loss": 3.5033, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096585805604568e-05, + "loss": 3.501, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5088199858094048e-05, + "loss": 3.5043, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079813910583528e-05, + "loss": 3.4986, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071444341876737e-05, + "loss": 3.4967, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5063058394366217e-05, + "loss": 3.492, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054672446855697e-05, + "loss": 3.4942, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.504628649934518e-05, + "loss": 3.5036, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503791693063839e-05, + "loss": 3.4967, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.502953098312787e-05, + "loss": 3.4923, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.502114503561735e-05, + "loss": 3.4969, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.501275908810683e-05, + "loss": 3.4905, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8709216117858887, + "eval_runtime": 306.8304, + "eval_samples_per_second": 1243.654, + "eval_steps_per_second": 38.865, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500438951940004e-05, + "loss": 3.4854, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499600357188952e-05, + "loss": 3.4874, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987617624378998e-05, + "loss": 3.5008, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979231676868478e-05, + "loss": 3.492, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497086210816169e-05, + "loss": 3.508, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496247616065117e-05, + "loss": 3.4902, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495409021314065e-05, + "loss": 3.4983, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494570426563013e-05, + "loss": 3.4924, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937334696923343e-05, + "loss": 3.4939, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492894874941282e-05, + "loss": 3.4957, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.49205628019023e-05, + "loss": 3.4914, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491217685439178e-05, + "loss": 3.4999, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903823664488724e-05, + "loss": 3.4894, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895437716978204e-05, + "loss": 3.4871, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4887051769467684e-05, + "loss": 3.4918, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878665821957164e-05, + "loss": 3.4813, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487027987444664e-05, + "loss": 3.4892, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486189392693612e-05, + "loss": 3.4899, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853507979425604e-05, + "loss": 3.4885, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4845122031915084e-05, + "loss": 3.5135, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836752463208293e-05, + "loss": 3.4983, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.4828366515697773e-05, + "loss": 3.5027, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819980568187253e-05, + "loss": 3.4948, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811594620676733e-05, + "loss": 3.4996, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803225051969945e-05, + "loss": 3.4879, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794839104459425e-05, + "loss": 3.4977, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786453156948905e-05, + "loss": 3.4927, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4778067209438385e-05, + "loss": 3.4868, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769697640731594e-05, + "loss": 3.484, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761311693221074e-05, + "loss": 3.486, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752925745710558e-05, + "loss": 3.4942, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744539798200038e-05, + "loss": 3.4979, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736170229493247e-05, + "loss": 3.4981, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727784281982727e-05, + "loss": 3.4986, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719398334472207e-05, + "loss": 3.4785, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4711012386961687e-05, + "loss": 3.4912, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.47026428182549e-05, + "loss": 3.4882, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469425687074438e-05, + "loss": 3.4814, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468587092323386e-05, + "loss": 3.4894, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467748497572334e-05, + "loss": 3.4821, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669115407016548e-05, + "loss": 3.4941, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660729459506028e-05, + "loss": 3.4943, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.465234351199551e-05, + "loss": 3.4952, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464395756448499e-05, + "loss": 3.4846, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.46355879957782e-05, + "loss": 3.4987, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462720204826768e-05, + "loss": 3.4835, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461881610075716e-05, + "loss": 3.4914, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.461043015324664e-05, + "loss": 3.484, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4602060584539853e-05, + "loss": 3.4733, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593674637029333e-05, + "loss": 3.4997, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585288689518813e-05, + "loss": 3.4868, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576902742008293e-05, + "loss": 3.4881, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.45685331733015e-05, + "loss": 3.4797, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456014722579098e-05, + "loss": 3.4783, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551761278280465e-05, + "loss": 3.4732, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543375330769945e-05, + "loss": 3.4867, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4535005762063154e-05, + "loss": 3.4908, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526619814552634e-05, + "loss": 3.4899, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4518233867042114e-05, + "loss": 3.4932, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509847919531594e-05, + "loss": 3.4842, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4501478350824806e-05, + "loss": 3.4715, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4493092403314286e-05, + "loss": 3.4955, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484706455803766e-05, + "loss": 3.474, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4476320508293243e-05, + "loss": 3.4708, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467950939586455e-05, + "loss": 3.4968, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459564992075935e-05, + "loss": 3.4884, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445117904456542e-05, + "loss": 3.4793, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442793097054895e-05, + "loss": 3.4784, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434423528348108e-05, + "loss": 3.4721, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4426037580837588e-05, + "loss": 3.4792, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417651633327064e-05, + "loss": 3.4941, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409265685816544e-05, + "loss": 3.4865, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440089611710976e-05, + "loss": 3.4956, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439251016959924e-05, + "loss": 3.4836, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4384124222088717e-05, + "loss": 3.5032, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375738274578197e-05, + "loss": 3.4806, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.436736870587141e-05, + "loss": 3.4923, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.435898275836089e-05, + "loss": 3.4894, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.435059681085037e-05, + "loss": 3.4692, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.434222724214358e-05, + "loss": 3.4994, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433384129463306e-05, + "loss": 3.4928, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325455347122538e-05, + "loss": 3.4908, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4317069399612018e-05, + "loss": 3.4812, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308699830905234e-05, + "loss": 3.4704, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300313883394714e-05, + "loss": 3.4832, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429192793588419e-05, + "loss": 3.4826, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428354198837367e-05, + "loss": 3.4946, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4275172419666883e-05, + "loss": 3.4817, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266786472156363e-05, + "loss": 3.4882, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258400524645843e-05, + "loss": 3.4791, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4250014577135323e-05, + "loss": 3.4814, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241645008428535e-05, + "loss": 3.4794, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423325906091801e-05, + "loss": 3.4817, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422487311340749e-05, + "loss": 3.4948, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421648716589697e-05, + "loss": 3.496, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4208117597190187e-05, + "loss": 3.4973, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199731649679664e-05, + "loss": 3.4755, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191345702169144e-05, + "loss": 3.4876, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182959754658624e-05, + "loss": 3.4817, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174590185951836e-05, + "loss": 3.4889, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4166204238441313e-05, + "loss": 3.4843, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157818290930796e-05, + "loss": 3.4808, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149432343420276e-05, + "loss": 3.479, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4141062774713485e-05, + "loss": 3.4912, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132676827202965e-05, + "loss": 3.4688, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124290879692445e-05, + "loss": 3.4847, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115904932181925e-05, + "loss": 3.4791, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107535363475138e-05, + "loss": 3.4894, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4099149415964618e-05, + "loss": 3.4777, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090763468454098e-05, + "loss": 3.4895, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082377520943578e-05, + "loss": 3.4853, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4074007952236787e-05, + "loss": 3.4808, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065622004726267e-05, + "loss": 3.4912, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405723605721575e-05, + "loss": 3.4805, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404885010970523e-05, + "loss": 3.4907, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.404048054099844e-05, + "loss": 3.4978, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403209459348792e-05, + "loss": 3.4828, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.40237086459774e-05, + "loss": 3.4813, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.401532269846688e-05, + "loss": 3.4827, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.400695312976009e-05, + "loss": 3.4813, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399856718224957e-05, + "loss": 3.4793, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.399018123473905e-05, + "loss": 3.4829, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398179528722853e-05, + "loss": 3.4761, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.397342571852174e-05, + "loss": 3.4916, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.396503977101122e-05, + "loss": 3.4873, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956653823500704e-05, + "loss": 3.4896, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948267875990184e-05, + "loss": 3.4736, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939898307283393e-05, + "loss": 3.4804, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931512359772873e-05, + "loss": 3.4823, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3923126412262353e-05, + "loss": 3.4894, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914740464751833e-05, + "loss": 3.4957, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906370896045045e-05, + "loss": 3.4847, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897984948534525e-05, + "loss": 3.4724, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889599001024005e-05, + "loss": 3.49, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881213053513485e-05, + "loss": 3.4802, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872843484806694e-05, + "loss": 3.4956, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864457537296174e-05, + "loss": 3.4744, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3856071589785657e-05, + "loss": 3.4918, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847685642275137e-05, + "loss": 3.4899, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839316073568346e-05, + "loss": 3.4944, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830930126057826e-05, + "loss": 3.4845, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822544178547306e-05, + "loss": 3.4864, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3814158231036786e-05, + "loss": 3.4776, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380578866233e-05, + "loss": 3.4843, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379740271481948e-05, + "loss": 3.4894, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378901676730896e-05, + "loss": 3.4872, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780630819798435e-05, + "loss": 3.482, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3772261251091648e-05, + "loss": 3.4813, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763875303581128e-05, + "loss": 3.4821, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.873481512069702, + "eval_runtime": 307.0036, + "eval_samples_per_second": 1242.953, + "eval_steps_per_second": 38.843, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375548935607061e-05, + "loss": 3.4812, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3747103408560088e-05, + "loss": 3.4741, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.37387338398533e-05, + "loss": 3.4879, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.373034789234278e-05, + "loss": 3.4776, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372196194483226e-05, + "loss": 3.4937, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713575997321736e-05, + "loss": 3.4817, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3705206428614952e-05, + "loss": 3.4827, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696820481104432e-05, + "loss": 3.4848, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.368843453359391e-05, + "loss": 3.4799, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.368006496488712e-05, + "loss": 3.4836, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.36716790173766e-05, + "loss": 3.4833, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.366329306986608e-05, + "loss": 3.4872, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654923501159294e-05, + "loss": 3.4809, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646537553648774e-05, + "loss": 3.4753, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3638151606138254e-05, + "loss": 3.4798, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629765658627734e-05, + "loss": 3.4679, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362137971111721e-05, + "loss": 3.4772, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361299376360669e-05, + "loss": 3.4766, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604607816096173e-05, + "loss": 3.4765, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3596221868585653e-05, + "loss": 3.501, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587852299878863e-05, + "loss": 3.4887, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3579466352368343e-05, + "loss": 3.489, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3571080404857822e-05, + "loss": 3.4806, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562694457347302e-05, + "loss": 3.4852, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3554324888640515e-05, + "loss": 3.48, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545938941129995e-05, + "loss": 3.4865, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537552993619475e-05, + "loss": 3.4784, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3529167046108955e-05, + "loss": 3.4774, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520797477402164e-05, + "loss": 3.4745, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3512411529891644e-05, + "loss": 3.4744, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3504025582381127e-05, + "loss": 3.4793, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495639634870607e-05, + "loss": 3.4879, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3487270066163816e-05, + "loss": 3.4852, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478884118653296e-05, + "loss": 3.49, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3470498171142776e-05, + "loss": 3.4694, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3462112223632256e-05, + "loss": 3.479, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345374265492547e-05, + "loss": 3.4744, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344535670741495e-05, + "loss": 3.4711, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343697075990443e-05, + "loss": 3.4809, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.342858481239391e-05, + "loss": 3.4645, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3420215243687118e-05, + "loss": 3.4833, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411829296176597e-05, + "loss": 3.4809, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340344334866608e-05, + "loss": 3.4866, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.339505740115556e-05, + "loss": 3.4751, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.338668783244877e-05, + "loss": 3.4878, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337830188493825e-05, + "loss": 3.469, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336991593742773e-05, + "loss": 3.485, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.336152998991721e-05, + "loss": 3.4713, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3353160421210422e-05, + "loss": 3.4566, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344774473699902e-05, + "loss": 3.492, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336388526189382e-05, + "loss": 3.4733, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3328002578678862e-05, + "loss": 3.4815, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.331963300997207e-05, + "loss": 3.4684, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331124706246155e-05, + "loss": 3.4666, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302861114951034e-05, + "loss": 3.465, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329447516744051e-05, + "loss": 3.4719, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3286105598733724e-05, + "loss": 3.4826, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277719651223204e-05, + "loss": 3.4743, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3269333703712683e-05, + "loss": 3.4862, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.326094775620216e-05, + "loss": 3.4733, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252578187495376e-05, + "loss": 3.4607, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3244192239984856e-05, + "loss": 3.4827, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235806292474336e-05, + "loss": 3.4592, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3227420344963812e-05, + "loss": 3.4598, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3219050776257025e-05, + "loss": 3.4828, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3210664828746505e-05, + "loss": 3.4782, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3202278881235985e-05, + "loss": 3.4676, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193892933725465e-05, + "loss": 3.4675, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.3185523365018677e-05, + "loss": 3.4616, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3177137417508157e-05, + "loss": 3.4688, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168751469997634e-05, + "loss": 3.4843, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3160365522487114e-05, + "loss": 3.473, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315199595378033e-05, + "loss": 3.4822, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143610006269806e-05, + "loss": 3.476, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3135224058759286e-05, + "loss": 3.4889, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126838111248766e-05, + "loss": 3.4694, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311846854254198e-05, + "loss": 3.4813, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.311008259503146e-05, + "loss": 3.4765, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310169664752094e-05, + "loss": 3.457, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309331070001042e-05, + "loss": 3.4838, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308494113130363e-05, + "loss": 3.484, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076555183793107e-05, + "loss": 3.4779, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3068169236282587e-05, + "loss": 3.4712, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059783288772067e-05, + "loss": 3.4637, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.305141372006528e-05, + "loss": 3.4644, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304302777255476e-05, + "loss": 3.4717, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303464182504424e-05, + "loss": 3.4804, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.302625587753372e-05, + "loss": 3.4685, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.301788630882693e-05, + "loss": 3.4774, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009500361316412e-05, + "loss": 3.4677, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3001114413805892e-05, + "loss": 3.4726, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992728466295372e-05, + "loss": 3.4671, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298435889758858e-05, + "loss": 3.4707, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297597295007806e-05, + "loss": 3.4836, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.296758700256754e-05, + "loss": 3.485, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.295920105505702e-05, + "loss": 3.4862, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950831486350234e-05, + "loss": 3.4594, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942445538839713e-05, + "loss": 3.4788, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2934059591329193e-05, + "loss": 3.4669, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925673643818673e-05, + "loss": 3.4808, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2917304075111882e-05, + "loss": 3.4711, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908918127601366e-05, + "loss": 3.4729, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900532180090846e-05, + "loss": 3.4653, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2892162611384055e-05, + "loss": 3.475, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883776663873535e-05, + "loss": 3.458, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2875390716363015e-05, + "loss": 3.4776, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2867004768852495e-05, + "loss": 3.462, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858635200145707e-05, + "loss": 3.4779, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2850249252635187e-05, + "loss": 3.4689, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841863305124667e-05, + "loss": 3.4712, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833477357614147e-05, + "loss": 3.4729, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2825107788907356e-05, + "loss": 3.474, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.2816721841396836e-05, + "loss": 3.4762, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280833589388632e-05, + "loss": 3.4719, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.27999499463758e-05, + "loss": 3.4752, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279158037766901e-05, + "loss": 3.4894, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278319443015849e-05, + "loss": 3.4717, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277480848264797e-05, + "loss": 3.4689, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276642253513745e-05, + "loss": 3.4732, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275805296643066e-05, + "loss": 3.4728, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274966701892014e-05, + "loss": 3.4625, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274128107140962e-05, + "loss": 3.4746, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.27328951238991e-05, + "loss": 3.4629, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.272452555519231e-05, + "loss": 3.4804, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271613960768179e-05, + "loss": 3.4793, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707753660171273e-05, + "loss": 3.4737, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2699367712660753e-05, + "loss": 3.466, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690998143953962e-05, + "loss": 3.4672, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682612196443442e-05, + "loss": 3.4714, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2674226248932922e-05, + "loss": 3.48, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665840301422402e-05, + "loss": 3.4771, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657470732715615e-05, + "loss": 3.4815, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2649084785205095e-05, + "loss": 3.4612, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640698837694574e-05, + "loss": 3.4822, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2632312890184054e-05, + "loss": 3.4692, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623943321477264e-05, + "loss": 3.4832, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615557373966743e-05, + "loss": 3.4626, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2607171426456223e-05, + "loss": 3.4851, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598785478945707e-05, + "loss": 3.474, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590415910238916e-05, + "loss": 3.4862, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2582029962728396e-05, + "loss": 3.4684, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2573644015217876e-05, + "loss": 3.4815, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2565258067707352e-05, + "loss": 3.4603, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2556888499000568e-05, + "loss": 3.4764, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548502551490048e-05, + "loss": 3.4777, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2540116603979528e-05, + "loss": 3.4716, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531730656469005e-05, + "loss": 3.4758, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2523361087762217e-05, + "loss": 3.4642, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.2514975140251697e-05, + "loss": 3.472, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.875202178955078, + "eval_runtime": 306.3677, + "eval_samples_per_second": 1245.533, + "eval_steps_per_second": 38.924, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506589192741177e-05, + "loss": 3.4697, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2498203245230657e-05, + "loss": 3.4633, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489817297720137e-05, + "loss": 3.4742, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481431350209617e-05, + "loss": 3.4692, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2473061781502826e-05, + "loss": 3.4817, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464675833992306e-05, + "loss": 3.4675, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245628988648179e-05, + "loss": 3.4733, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244790393897127e-05, + "loss": 3.4744, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243953437026448e-05, + "loss": 3.469, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243114842275396e-05, + "loss": 3.4724, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242276247524344e-05, + "loss": 3.4724, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414376527732918e-05, + "loss": 3.4736, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2406023337829863e-05, + "loss": 3.47, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397637390319343e-05, + "loss": 3.4629, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2389251442808823e-05, + "loss": 3.4691, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.23808654952983e-05, + "loss": 3.4551, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237247954778778e-05, + "loss": 3.4648, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236409360027726e-05, + "loss": 3.4658, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355707652766743e-05, + "loss": 3.4627, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2347321705256223e-05, + "loss": 3.4914, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338952136549432e-05, + "loss": 3.4805, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330566189038912e-05, + "loss": 3.4788, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2322180241528392e-05, + "loss": 3.4683, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313794294017872e-05, + "loss": 3.4715, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305424725311084e-05, + "loss": 3.4685, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2297038777800564e-05, + "loss": 3.4747, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288652830290044e-05, + "loss": 3.4683, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280266882779524e-05, + "loss": 3.472, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271897314072733e-05, + "loss": 3.4616, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263511366562213e-05, + "loss": 3.4635, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2255125419051697e-05, + "loss": 3.4648, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246739471541177e-05, + "loss": 3.4774, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238369902834386e-05, + "loss": 3.4746, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229983955323866e-05, + "loss": 3.4797, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221598007813346e-05, + "loss": 3.46, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2213212060302826e-05, + "loss": 3.4633, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204842491596038e-05, + "loss": 3.4677, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196456544085518e-05, + "loss": 3.4598, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2188070596574998e-05, + "loss": 3.4659, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179684649064478e-05, + "loss": 3.4589, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171315080357687e-05, + "loss": 3.4685, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162929132847167e-05, + "loss": 3.4732, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154543185336647e-05, + "loss": 3.4703, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214615723782613e-05, + "loss": 3.4648, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.213778766911934e-05, + "loss": 3.4719, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212940172160882e-05, + "loss": 3.463, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.21210157740983e-05, + "loss": 3.4694, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112629826587776e-05, + "loss": 3.4616, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2104260257880992e-05, + "loss": 3.4434, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095874310370472e-05, + "loss": 3.4866, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208748836285995e-05, + "loss": 3.4579, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2079102415349428e-05, + "loss": 3.4704, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.207073284664264e-05, + "loss": 3.4534, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206234689913212e-05, + "loss": 3.4588, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.20539609516216e-05, + "loss": 3.4472, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204557500411108e-05, + "loss": 3.4623, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2037205435404293e-05, + "loss": 3.4698, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028819487893773e-05, + "loss": 3.4658, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202043354038325e-05, + "loss": 3.4746, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.201204759287273e-05, + "loss": 3.4609, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003678024165945e-05, + "loss": 3.451, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995292076655425e-05, + "loss": 3.4757, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986906129144902e-05, + "loss": 3.4467, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978520181634382e-05, + "loss": 3.4481, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1970150612927594e-05, + "loss": 3.4724, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961764665417074e-05, + "loss": 3.4675, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953378717906554e-05, + "loss": 3.4552, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944992770396034e-05, + "loss": 3.4577, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936623201689247e-05, + "loss": 3.4512, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1928237254178723e-05, + "loss": 3.4546, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919851306668203e-05, + "loss": 3.4682, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911465359157683e-05, + "loss": 3.4641, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.19030957904509e-05, + "loss": 3.4734, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894709842940376e-05, + "loss": 3.4654, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886323895429856e-05, + "loss": 3.474, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877937947919336e-05, + "loss": 3.4566, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869568379212545e-05, + "loss": 3.4733, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1861182431702028e-05, + "loss": 3.4598, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852796484191508e-05, + "loss": 3.4526, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844410536680988e-05, + "loss": 3.469, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1836040967974197e-05, + "loss": 3.4724, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827655020463677e-05, + "loss": 3.4692, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819269072953157e-05, + "loss": 3.4622, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810883125442637e-05, + "loss": 3.4513, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180251355673585e-05, + "loss": 3.4516, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179412760922533e-05, + "loss": 3.4622, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178574166171481e-05, + "loss": 3.471, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177737209300802e-05, + "loss": 3.4571, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.17689861454975e-05, + "loss": 3.467, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.176060019798698e-05, + "loss": 3.4485, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175221425047646e-05, + "loss": 3.4639, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.174384468176967e-05, + "loss": 3.4582, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173545873425915e-05, + "loss": 3.4604, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172707278674863e-05, + "loss": 3.4713, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171868683923811e-05, + "loss": 3.4728, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1710317270531323e-05, + "loss": 3.4749, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701931323020803e-05, + "loss": 3.4493, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693545375510283e-05, + "loss": 3.4687, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1685159427999763e-05, + "loss": 3.4525, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676789859292972e-05, + "loss": 3.4695, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1668403911782452e-05, + "loss": 3.4566, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1660017964271932e-05, + "loss": 3.4652, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651632016761415e-05, + "loss": 3.4538, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643262448054624e-05, + "loss": 3.4636, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634876500544104e-05, + "loss": 3.4497, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626490553033584e-05, + "loss": 3.4652, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1618104605523064e-05, + "loss": 3.4501, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609735036816277e-05, + "loss": 3.4689, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601349089305757e-05, + "loss": 3.459, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592963141795237e-05, + "loss": 3.4623, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584577194284717e-05, + "loss": 3.4595, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1576207625577926e-05, + "loss": 3.4643, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567821678067406e-05, + "loss": 3.466, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559435730556886e-05, + "loss": 3.4581, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155104978304637e-05, + "loss": 3.4672, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542680214339578e-05, + "loss": 3.4746, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1534294266829058e-05, + "loss": 3.4642, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525908319318538e-05, + "loss": 3.4574, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517522371808018e-05, + "loss": 3.4581, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150915280310123e-05, + "loss": 3.4641, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150076685559071e-05, + "loss": 3.4517, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149238090808019e-05, + "loss": 3.4638, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148399496056967e-05, + "loss": 3.4498, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.147562539186288e-05, + "loss": 3.471, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146723944435236e-05, + "loss": 3.4653, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145885349684184e-05, + "loss": 3.4644, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450467549331323e-05, + "loss": 3.4548, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1442097980624532e-05, + "loss": 3.4552, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433712033114012e-05, + "loss": 3.4611, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142532608560349e-05, + "loss": 3.4722, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141694013809297e-05, + "loss": 3.465, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408570569386184e-05, + "loss": 3.4661, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1400184621875664e-05, + "loss": 3.4496, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391798674365144e-05, + "loss": 3.4716, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138341272685462e-05, + "loss": 3.4573, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1375043158147833e-05, + "loss": 3.4736, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366657210637313e-05, + "loss": 3.4538, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358271263126793e-05, + "loss": 3.47, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349885315616273e-05, + "loss": 3.4618, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341515746909485e-05, + "loss": 3.4801, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1333129799398965e-05, + "loss": 3.4552, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324743851888445e-05, + "loss": 3.4675, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316357904377922e-05, + "loss": 3.4526, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307988335671138e-05, + "loss": 3.4653, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299602388160618e-05, + "loss": 3.4658, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1291216440650094e-05, + "loss": 3.4588, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282830493139574e-05, + "loss": 3.4685, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274460924432787e-05, + "loss": 3.4495, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1266074976922267e-05, + "loss": 3.4657, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.876225709915161, + "eval_runtime": 306.4958, + "eval_samples_per_second": 1245.012, + "eval_steps_per_second": 38.908, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257689029411747e-05, + "loss": 3.4606, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1249303081901227e-05, + "loss": 3.4525, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240917134390707e-05, + "loss": 3.4616, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232531186880187e-05, + "loss": 3.4592, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1224161618173396e-05, + "loss": 3.4723, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215775670662876e-05, + "loss": 3.459, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207389723152356e-05, + "loss": 3.4599, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119900377564184e-05, + "loss": 3.4648, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190634206935048e-05, + "loss": 3.4573, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182248259424528e-05, + "loss": 3.4622, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173862311914008e-05, + "loss": 3.4602, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165476364403488e-05, + "loss": 3.4641, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1157123174500433e-05, + "loss": 3.4625, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148737226989913e-05, + "loss": 3.4516, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.114035127947939e-05, + "loss": 3.4556, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113196533196887e-05, + "loss": 3.4476, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.112357938445835e-05, + "loss": 3.4523, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.111519343694783e-05, + "loss": 3.4606, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.110680748943731e-05, + "loss": 3.4483, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098421541926793e-05, + "loss": 3.4775, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.109005197322e-05, + "loss": 3.4689, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108166602570948e-05, + "loss": 3.4701, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107328007819896e-05, + "loss": 3.4576, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.106489413068844e-05, + "loss": 3.4589, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056524561981654e-05, + "loss": 3.464, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1048138614471134e-05, + "loss": 3.4588, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039752666960614e-05, + "loss": 3.4581, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031366719450094e-05, + "loss": 3.4665, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022997150743303e-05, + "loss": 3.4455, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014611203232783e-05, + "loss": 3.4515, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1006225255722263e-05, + "loss": 3.4573, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997839308211746e-05, + "loss": 3.4615, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989469739504955e-05, + "loss": 3.4656, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0981083791994435e-05, + "loss": 3.4676, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972697844483915e-05, + "loss": 3.4495, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964311896973395e-05, + "loss": 3.4514, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955942328266608e-05, + "loss": 3.4601, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947556380756088e-05, + "loss": 3.4505, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0939170433245568e-05, + "loss": 3.4569, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930784485735044e-05, + "loss": 3.4435, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922414917028257e-05, + "loss": 3.4584, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0914028969517737e-05, + "loss": 3.457, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905643022007217e-05, + "loss": 3.4616, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0897257074496696e-05, + "loss": 3.4595, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.088888750578991e-05, + "loss": 3.4578, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.088050155827939e-05, + "loss": 3.4534, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087211561076887e-05, + "loss": 3.4581, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863729663258345e-05, + "loss": 3.451, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085536009455156e-05, + "loss": 3.4352, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084697414704104e-05, + "loss": 3.4735, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838588199530518e-05, + "loss": 3.4453, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0830202252019998e-05, + "loss": 3.4621, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082183268331321e-05, + "loss": 3.4468, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.081344673580269e-05, + "loss": 3.4439, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.080506078829217e-05, + "loss": 3.4354, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079667484078165e-05, + "loss": 3.4492, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0788305272074863e-05, + "loss": 3.4609, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779919324564343e-05, + "loss": 3.4544, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077153337705382e-05, + "loss": 3.463, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.07631474295433e-05, + "loss": 3.4578, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754777860836515e-05, + "loss": 3.4357, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074639191332599e-05, + "loss": 3.4595, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073800596581547e-05, + "loss": 3.4395, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072962001830495e-05, + "loss": 3.4346, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0721250449598164e-05, + "loss": 3.4651, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071286450208764e-05, + "loss": 3.4556, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704478554577124e-05, + "loss": 3.4434, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0696092607066604e-05, + "loss": 3.4475, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687723038359816e-05, + "loss": 3.4417, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679337090849293e-05, + "loss": 3.4459, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670951143338773e-05, + "loss": 3.4561, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662565195828253e-05, + "loss": 3.4516, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0654195627121465e-05, + "loss": 3.4628, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645809679610945e-05, + "loss": 3.4536, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637423732100425e-05, + "loss": 3.4647, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0629054163393638e-05, + "loss": 3.4446, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620668215883114e-05, + "loss": 3.4651, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0612282268372594e-05, + "loss": 3.4471, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603896320862078e-05, + "loss": 3.4442, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.059552675215529e-05, + "loss": 3.4596, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0587140804644767e-05, + "loss": 3.4623, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578754857134247e-05, + "loss": 3.4568, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570368909623726e-05, + "loss": 3.4555, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.056199934091694e-05, + "loss": 3.4371, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.055361339340642e-05, + "loss": 3.4406, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.05452274458959e-05, + "loss": 3.4517, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.053684149838538e-05, + "loss": 3.4603, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528471929678588e-05, + "loss": 3.4459, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0520085982168068e-05, + "loss": 3.4548, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511700034657548e-05, + "loss": 3.4397, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.050331408714703e-05, + "loss": 3.4531, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049494451844024e-05, + "loss": 3.448, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048655857092972e-05, + "loss": 3.4494, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.04781726234192e-05, + "loss": 3.461, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046978667590868e-05, + "loss": 3.4583, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461417107201893e-05, + "loss": 3.4664, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0453031159691373e-05, + "loss": 3.4404, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444645212180853e-05, + "loss": 3.4552, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0436259264670332e-05, + "loss": 3.4455, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042788969596354e-05, + "loss": 3.4549, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041950374845302e-05, + "loss": 3.447, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.04111178009425e-05, + "loss": 3.4572, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402731853431985e-05, + "loss": 3.4429, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0394362284725194e-05, + "loss": 3.4483, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385976337214674e-05, + "loss": 3.4439, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377590389704154e-05, + "loss": 3.4495, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.0369204442193634e-05, + "loss": 3.4393, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360834873486846e-05, + "loss": 3.4587, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352448925976326e-05, + "loss": 3.4487, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0344062978465806e-05, + "loss": 3.4527, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335677030955286e-05, + "loss": 3.4493, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327307462248495e-05, + "loss": 3.452, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318921514737975e-05, + "loss": 3.4556, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310535567227455e-05, + "loss": 3.4498, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030214961971694e-05, + "loss": 3.456, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293780051010148e-05, + "loss": 3.4636, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285394103499628e-05, + "loss": 3.4481, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0277008155989108e-05, + "loss": 3.4536, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268622208478587e-05, + "loss": 3.4444, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.02602526397718e-05, + "loss": 3.4504, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025186669226128e-05, + "loss": 3.4482, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024348074475076e-05, + "loss": 3.4513, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023509479724024e-05, + "loss": 3.4385, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.022672522853345e-05, + "loss": 3.4579, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.021833928102293e-05, + "loss": 3.4547, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.020995333351241e-05, + "loss": 3.4568, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.020156738600189e-05, + "loss": 3.4462, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.01931978172951e-05, + "loss": 3.444, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.018481186978458e-05, + "loss": 3.448, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.017642592227406e-05, + "loss": 3.4592, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0168039974763538e-05, + "loss": 3.454, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159670406056754e-05, + "loss": 3.4598, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151284458546234e-05, + "loss": 3.438, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142898511035714e-05, + "loss": 3.4583, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013451256352519e-05, + "loss": 3.4487, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0126142994818403e-05, + "loss": 3.4623, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117757047307883e-05, + "loss": 3.4425, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0109371099797363e-05, + "loss": 3.4556, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100985152286842e-05, + "loss": 3.4514, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092615583580055e-05, + "loss": 3.4694, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0084229636069535e-05, + "loss": 3.4473, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007584368855901e-05, + "loss": 3.4546, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.006745774104849e-05, + "loss": 3.4436, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0059088172341707e-05, + "loss": 3.4536, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050702224831187e-05, + "loss": 3.4492, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042316277320664e-05, + "loss": 3.4507, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033946708613876e-05, + "loss": 3.4574, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025560761103356e-05, + "loss": 3.4363, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0017174813592833e-05, + "loss": 3.4571, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.87790584564209, + "eval_runtime": 307.1355, + "eval_samples_per_second": 1242.419, + "eval_steps_per_second": 38.827, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.0008788866082316e-05, + "loss": 3.4475, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 2.000041929737553e-05, + "loss": 3.4422, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.999203334986501e-05, + "loss": 3.4489, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983647402354485e-05, + "loss": 3.449, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.9975261454843965e-05, + "loss": 3.4635, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.9966891886137178e-05, + "loss": 3.4476, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995850593862666e-05, + "loss": 3.4504, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.9950119991116138e-05, + "loss": 3.4539, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941734043605617e-05, + "loss": 3.4472, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993336447489883e-05, + "loss": 3.4535, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.9924978527388307e-05, + "loss": 3.4485, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916592579877786e-05, + "loss": 3.4527, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990820663236727e-05, + "loss": 3.4564, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989982068485675e-05, + "loss": 3.4361, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989143473734623e-05, + "loss": 3.4469, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988304878983571e-05, + "loss": 3.4358, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.987467922112892e-05, + "loss": 3.4442, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.986630965242213e-05, + "loss": 3.4474, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985792370491161e-05, + "loss": 3.4397, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984953775740109e-05, + "loss": 3.4663, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984115180989057e-05, + "loss": 3.462, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.983276586238005e-05, + "loss": 3.4581, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.982437991486953e-05, + "loss": 3.4477, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.981599396735901e-05, + "loss": 3.4502, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807608019848488e-05, + "loss": 3.4546, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9799238451141703e-05, + "loss": 3.4461, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790852503631183e-05, + "loss": 3.4452, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782466556120663e-05, + "loss": 3.4544, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977408060861014e-05, + "loss": 3.4384, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765711039903352e-05, + "loss": 3.4384, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9757325092392832e-05, + "loss": 3.4493, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748939144882312e-05, + "loss": 3.4518, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740553197371792e-05, + "loss": 3.4486, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9732183628665005e-05, + "loss": 3.4619, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723797681154485e-05, + "loss": 3.4378, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.971541173364396e-05, + "loss": 3.4415, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.970702578613344e-05, + "loss": 3.4487, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698656217426657e-05, + "loss": 3.4361, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9690270269916137e-05, + "loss": 3.4496, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681884322405614e-05, + "loss": 3.4383, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673498374895094e-05, + "loss": 3.4446, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9665128806188306e-05, + "loss": 3.445, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656742858677786e-05, + "loss": 3.4514, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9648356911167266e-05, + "loss": 3.4484, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639970963656746e-05, + "loss": 3.4469, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.963160139494996e-05, + "loss": 3.443, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9623215447439435e-05, + "loss": 3.4435, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614829499928915e-05, + "loss": 3.4469, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.9606443552418395e-05, + "loss": 3.4223, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959807398371161e-05, + "loss": 3.4577, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589688036201087e-05, + "loss": 3.4365, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9581302088690567e-05, + "loss": 3.4517, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572916141180047e-05, + "loss": 3.4368, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564546572473256e-05, + "loss": 3.4328, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955616062496274e-05, + "loss": 3.4298, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954777467745222e-05, + "loss": 3.4343, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.95393887299417e-05, + "loss": 3.4528, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953101916123491e-05, + "loss": 3.4377, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.952263321372439e-05, + "loss": 3.4561, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951424726621387e-05, + "loss": 3.4442, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.950586131870335e-05, + "loss": 3.4265, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949749174999656e-05, + "loss": 3.4466, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948910580248604e-05, + "loss": 3.4353, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.948071985497552e-05, + "loss": 3.4232, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9472333907465e-05, + "loss": 3.4498, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946396433875821e-05, + "loss": 3.4447, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455578391247693e-05, + "loss": 3.4342, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9447192443737173e-05, + "loss": 3.4407, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438806496226653e-05, + "loss": 3.4278, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430436927519862e-05, + "loss": 3.4358, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9422050980009342e-05, + "loss": 3.4444, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413665032498822e-05, + "loss": 3.4379, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9405279084988302e-05, + "loss": 3.4539, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396909516281515e-05, + "loss": 3.4391, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388523568770995e-05, + "loss": 3.4529, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9380137621260475e-05, + "loss": 3.44, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371751673749955e-05, + "loss": 3.4536, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.9363382105043164e-05, + "loss": 3.4344, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.9354996157532647e-05, + "loss": 3.4355, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346610210022127e-05, + "loss": 3.448, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9338224262511607e-05, + "loss": 3.4541, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329854693804816e-05, + "loss": 3.4453, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321468746294296e-05, + "loss": 3.4469, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9313082798783776e-05, + "loss": 3.4262, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304696851273256e-05, + "loss": 3.4302, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.929632728256647e-05, + "loss": 3.4433, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.928794133505595e-05, + "loss": 3.4484, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.927955538754543e-05, + "loss": 3.4343, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9271169440034908e-05, + "loss": 3.4476, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262799871328117e-05, + "loss": 3.4316, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.92544139238176e-05, + "loss": 3.4398, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924602797630708e-05, + "loss": 3.4376, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923764202879656e-05, + "loss": 3.4405, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922927246008977e-05, + "loss": 3.4497, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.922088651257925e-05, + "loss": 3.4497, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.921250056506873e-05, + "loss": 3.4562, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920411461755821e-05, + "loss": 3.4296, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195745048851422e-05, + "loss": 3.4435, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9187359101340902e-05, + "loss": 3.4367, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178973153830382e-05, + "loss": 3.4438, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.917058720631986e-05, + "loss": 3.4374, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.916221763761307e-05, + "loss": 3.4457, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153831690102554e-05, + "loss": 3.436, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145445742592034e-05, + "loss": 3.4361, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.913705979508151e-05, + "loss": 3.4347, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128690226374723e-05, + "loss": 3.4378, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9120304278864203e-05, + "loss": 3.4296, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.911191833135368e-05, + "loss": 3.447, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103532383843163e-05, + "loss": 3.4433, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9095162815136376e-05, + "loss": 3.4379, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086776867625856e-05, + "loss": 3.4424, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9078390920115332e-05, + "loss": 3.4369, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.9070021351408545e-05, + "loss": 3.4477, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061635403898025e-05, + "loss": 3.4373, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9053249456387508e-05, + "loss": 3.4454, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044863508876985e-05, + "loss": 3.4534, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036493940170197e-05, + "loss": 3.4434, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.9028107992659677e-05, + "loss": 3.4383, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.9019722045149154e-05, + "loss": 3.4374, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9011336097638634e-05, + "loss": 3.4363, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.900296652893185e-05, + "loss": 3.4394, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.899458058142133e-05, + "loss": 3.4396, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8986194633910806e-05, + "loss": 3.4262, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977808686400286e-05, + "loss": 3.4484, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.89694391176935e-05, + "loss": 3.4434, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896105317018298e-05, + "loss": 3.4462, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895266722267246e-05, + "loss": 3.4375, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.8944281275161938e-05, + "loss": 3.4327, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893591170645515e-05, + "loss": 3.439, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927525758944627e-05, + "loss": 3.4472, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8919139811434107e-05, + "loss": 3.4462, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910753863923587e-05, + "loss": 3.4478, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.8902384295216803e-05, + "loss": 3.4253, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889399834770628e-05, + "loss": 3.4485, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888561240019576e-05, + "loss": 3.4372, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887722645268524e-05, + "loss": 3.4535, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868856883978452e-05, + "loss": 3.435, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860470936467932e-05, + "loss": 3.4404, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8852084988957412e-05, + "loss": 3.4434, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843699041446892e-05, + "loss": 3.4583, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.88353294727401e-05, + "loss": 3.4366, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.882694352522958e-05, + "loss": 3.4443, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.881855757771906e-05, + "loss": 3.4352, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.881017163020854e-05, + "loss": 3.4501, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801802061501753e-05, + "loss": 3.4374, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8793416113991233e-05, + "loss": 3.4376, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8785030166480713e-05, + "loss": 3.4454, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776644218970193e-05, + "loss": 3.4303, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8768274650263402e-05, + "loss": 3.4455, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.879502773284912, + "eval_runtime": 306.4377, + "eval_samples_per_second": 1245.248, + "eval_steps_per_second": 38.915, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759888702752886e-05, + "loss": 3.4322, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751502755242366e-05, + "loss": 3.4303, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8743116807731846e-05, + "loss": 3.4377, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734730860221326e-05, + "loss": 3.4391, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8726361291514535e-05, + "loss": 3.4541, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717975344004015e-05, + "loss": 3.4381, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.8709589396493495e-05, + "loss": 3.4357, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8701203448982978e-05, + "loss": 3.4485, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692833880276187e-05, + "loss": 3.4363, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.86844643115694e-05, + "loss": 3.4418, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8676078364058876e-05, + "loss": 3.4391, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667692416548356e-05, + "loss": 3.441, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865930646903784e-05, + "loss": 3.4442, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.865092052152732e-05, + "loss": 3.4272, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.86425345740168e-05, + "loss": 3.4336, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.863414862650628e-05, + "loss": 3.4233, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862577905779949e-05, + "loss": 3.4326, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8617393110288968e-05, + "loss": 3.4405, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8609007162778448e-05, + "loss": 3.4287, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600621215267928e-05, + "loss": 3.4546, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.859225164656114e-05, + "loss": 3.4495, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858386569905062e-05, + "loss": 3.446, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.85754797515401e-05, + "loss": 3.4382, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8567093804029577e-05, + "loss": 3.4399, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558724235322793e-05, + "loss": 3.4437, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.8550338287812273e-05, + "loss": 3.441, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541952340301753e-05, + "loss": 3.4273, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853356639279123e-05, + "loss": 3.4474, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8525196824084442e-05, + "loss": 3.4253, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516810876573922e-05, + "loss": 3.4299, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8508424929063402e-05, + "loss": 3.4386, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8500038981552882e-05, + "loss": 3.4383, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491669412846094e-05, + "loss": 3.4379, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8483283465335574e-05, + "loss": 3.449, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474913896628783e-05, + "loss": 3.4319, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466527949118263e-05, + "loss": 3.4255, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8458142001607743e-05, + "loss": 3.4424, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449756054097227e-05, + "loss": 3.4251, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8441370106586703e-05, + "loss": 3.435, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432984159076183e-05, + "loss": 3.4329, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424598211565663e-05, + "loss": 3.4318, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8416228642858876e-05, + "loss": 3.4348, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407842695348356e-05, + "loss": 3.4416, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399456747837836e-05, + "loss": 3.4401, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8391070800327315e-05, + "loss": 3.434, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382701231620525e-05, + "loss": 3.4321, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8374315284110005e-05, + "loss": 3.4341, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.8365929336599484e-05, + "loss": 3.4349, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8357543389088964e-05, + "loss": 3.4126, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8349173820382177e-05, + "loss": 3.4457, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340787872871657e-05, + "loss": 3.4272, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8332401925361137e-05, + "loss": 3.4379, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8324015977850617e-05, + "loss": 3.4266, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315646409143826e-05, + "loss": 3.4231, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830726046163331e-05, + "loss": 3.4191, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829887451412279e-05, + "loss": 3.4254, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829048856661227e-05, + "loss": 3.4441, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8282118997905478e-05, + "loss": 3.4272, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273733050394958e-05, + "loss": 3.4458, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8265347102884438e-05, + "loss": 3.4367, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256961155373918e-05, + "loss": 3.4138, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824859158666713e-05, + "loss": 3.4345, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.824020563915661e-05, + "loss": 3.4198, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.823181969164609e-05, + "loss": 3.4194, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.822343374413557e-05, + "loss": 3.4366, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.821506417542878e-05, + "loss": 3.435, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206678227918263e-05, + "loss": 3.4235, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8198292280407743e-05, + "loss": 3.4312, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189906332897223e-05, + "loss": 3.4207, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.8181536764190432e-05, + "loss": 3.4208, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8173150816679912e-05, + "loss": 3.435, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164781247973124e-05, + "loss": 3.4322, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8156395300462604e-05, + "loss": 3.4412, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8148009352952084e-05, + "loss": 3.429, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139623405441564e-05, + "loss": 3.4438, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8131237457931044e-05, + "loss": 3.4261, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122851510420524e-05, + "loss": 3.4482, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114465562910004e-05, + "loss": 3.4204, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.810607961539948e-05, + "loss": 3.4256, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097710046692697e-05, + "loss": 3.4325, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8089324099182176e-05, + "loss": 3.4433, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080938151671653e-05, + "loss": 3.4369, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072552204161133e-05, + "loss": 3.4367, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8064182635454346e-05, + "loss": 3.4158, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055796687943825e-05, + "loss": 3.4182, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8047410740433305e-05, + "loss": 3.435, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8039024792922785e-05, + "loss": 3.4349, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030655224215998e-05, + "loss": 3.4235, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.8022269276705478e-05, + "loss": 3.4355, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.8013883329194954e-05, + "loss": 3.4309, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005497381684434e-05, + "loss": 3.4263, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.799712781297765e-05, + "loss": 3.427, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988741865467127e-05, + "loss": 3.4299, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.7980355917956607e-05, + "loss": 3.4391, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971969970446087e-05, + "loss": 3.4405, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.79636004017393e-05, + "loss": 3.4427, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795521445422878e-05, + "loss": 3.4204, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794682850671826e-05, + "loss": 3.4344, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793844255920774e-05, + "loss": 3.4264, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7930072990500948e-05, + "loss": 3.4344, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921687042990428e-05, + "loss": 3.4287, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7913301095479908e-05, + "loss": 3.4309, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904915147969388e-05, + "loss": 3.4263, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.78965455792626e-05, + "loss": 3.4211, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.788815963175208e-05, + "loss": 3.4258, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.787977368424156e-05, + "loss": 3.4292, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.787138773673104e-05, + "loss": 3.423, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.786301816802425e-05, + "loss": 3.4346, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854632220513733e-05, + "loss": 3.4312, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7846246273003213e-05, + "loss": 3.4269, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837860325492693e-05, + "loss": 3.4299, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829490756785902e-05, + "loss": 3.4281, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7821104809275382e-05, + "loss": 3.4374, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812718861764862e-05, + "loss": 3.4275, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.780433291425434e-05, + "loss": 3.4353, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795963345547554e-05, + "loss": 3.442, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787577398037034e-05, + "loss": 3.4368, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7779191450526514e-05, + "loss": 3.4282, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770805503015994e-05, + "loss": 3.4299, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7762435934309203e-05, + "loss": 3.4243, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7754049986798686e-05, + "loss": 3.4319, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745664039288166e-05, + "loss": 3.4245, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7737278091777646e-05, + "loss": 3.4193, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728908523070855e-05, + "loss": 3.4394, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720522575560335e-05, + "loss": 3.4346, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7712136628049815e-05, + "loss": 3.4338, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703750680539295e-05, + "loss": 3.4267, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7695381111832508e-05, + "loss": 3.4211, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686995164321988e-05, + "loss": 3.4274, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.7678609216811468e-05, + "loss": 3.4389, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.7670239648104677e-05, + "loss": 3.4341, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.7661853700594157e-05, + "loss": 3.4401, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.7653467753083637e-05, + "loss": 3.4145, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764508180557312e-05, + "loss": 3.4414, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763671223686633e-05, + "loss": 3.4267, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.762832628935581e-05, + "loss": 3.4399, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761994034184529e-05, + "loss": 3.4275, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.761155439433477e-05, + "loss": 3.4232, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760318482562798e-05, + "loss": 3.435, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759479887811746e-05, + "loss": 3.4512, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758641293060694e-05, + "loss": 3.4258, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757802698309642e-05, + "loss": 3.435, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756965741438963e-05, + "loss": 3.4246, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756127146687911e-05, + "loss": 3.4354, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.755288551936859e-05, + "loss": 3.426, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.7544499571858074e-05, + "loss": 3.429, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.7536130003151283e-05, + "loss": 3.4337, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.7527744055640763e-05, + "loss": 3.4244, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7519358108130243e-05, + "loss": 3.4391, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.881646156311035, + "eval_runtime": 305.8448, + "eval_samples_per_second": 1247.662, + "eval_steps_per_second": 38.99, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510972160619723e-05, + "loss": 3.4246, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502602591912935e-05, + "loss": 3.4214, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7494216644402415e-05, + "loss": 3.4282, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485830696891895e-05, + "loss": 3.4286, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477444749381375e-05, + "loss": 3.4436, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7469075180674584e-05, + "loss": 3.426, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460689233164064e-05, + "loss": 3.4272, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7452303285653544e-05, + "loss": 3.4384, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443917338143024e-05, + "loss": 3.4261, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435547769436237e-05, + "loss": 3.4261, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7427161821925716e-05, + "loss": 3.4345, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418775874415196e-05, + "loss": 3.4328, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.7410389926904673e-05, + "loss": 3.4346, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7402003979394156e-05, + "loss": 3.4155, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393618031883636e-05, + "loss": 3.4243, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7385232084373116e-05, + "loss": 3.411, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376846136862596e-05, + "loss": 3.4239, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368476568155805e-05, + "loss": 3.4298, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.7360106999449018e-05, + "loss": 3.4158, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.7351721051938498e-05, + "loss": 3.4412, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7343335104427978e-05, + "loss": 3.4405, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334949156917458e-05, + "loss": 3.4373, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7326563209406938e-05, + "loss": 3.4309, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7318177261896418e-05, + "loss": 3.4288, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309791314385898e-05, + "loss": 3.4333, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730142174567911e-05, + "loss": 3.4292, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729303579816859e-05, + "loss": 3.419, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.728464985065807e-05, + "loss": 3.4358, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727626390314755e-05, + "loss": 3.4186, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.726789433444076e-05, + "loss": 3.4176, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.725950838693024e-05, + "loss": 3.4307, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.725112243941972e-05, + "loss": 3.4254, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.72427364919092e-05, + "loss": 3.4329, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.723436692320241e-05, + "loss": 3.4358, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.722599735449562e-05, + "loss": 3.4195, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.72176114069851e-05, + "loss": 3.4216, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.720922545947458e-05, + "loss": 3.4277, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.720083951196406e-05, + "loss": 3.4149, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192453564453544e-05, + "loss": 3.424, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7184067616943024e-05, + "loss": 3.4245, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.71756816694325e-05, + "loss": 3.418, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.7167312100725713e-05, + "loss": 3.4262, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158926153215193e-05, + "loss": 3.4357, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150540205704673e-05, + "loss": 3.4267, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7142154258194152e-05, + "loss": 3.4251, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133784689487365e-05, + "loss": 3.4204, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7125398741976845e-05, + "loss": 3.4236, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7117012794466325e-05, + "loss": 3.4245, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.71086268469558e-05, + "loss": 3.406, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7100257278249014e-05, + "loss": 3.4359, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091871330738497e-05, + "loss": 3.4175, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083485383227974e-05, + "loss": 3.428, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7075099435717454e-05, + "loss": 3.4179, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066729867010666e-05, + "loss": 3.4103, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7058343919500146e-05, + "loss": 3.4074, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.7049957971989626e-05, + "loss": 3.4132, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041572024479106e-05, + "loss": 3.4366, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.703320245577232e-05, + "loss": 3.4173, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.70248165082618e-05, + "loss": 3.4346, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7016430560751275e-05, + "loss": 3.4268, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.7008044613240755e-05, + "loss": 3.4057, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.6999675044533968e-05, + "loss": 3.4246, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.6991289097023448e-05, + "loss": 3.413, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982903149512928e-05, + "loss": 3.407, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.6974517202002407e-05, + "loss": 3.4213, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.696614763329562e-05, + "loss": 3.4264, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6957761685785097e-05, + "loss": 3.4127, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694937573827458e-05, + "loss": 3.4234, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694098979076406e-05, + "loss": 3.4076, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.6932620222057272e-05, + "loss": 3.4151, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.692423427454675e-05, + "loss": 3.423, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.691584832703623e-05, + "loss": 3.4246, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.690746237952571e-05, + "loss": 3.4263, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.689909281081892e-05, + "loss": 3.4247, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.68907068633084e-05, + "loss": 3.4328, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688232091579788e-05, + "loss": 3.4189, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.687393496828736e-05, + "loss": 3.4347, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.686556539958057e-05, + "loss": 3.4112, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.685717945207005e-05, + "loss": 3.4186, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848793504559534e-05, + "loss": 3.4236, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6840407557049013e-05, + "loss": 3.427, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.6832037988342223e-05, + "loss": 3.4263, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.6823652040831703e-05, + "loss": 3.428, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6815266093321183e-05, + "loss": 3.4116, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806880145810662e-05, + "loss": 3.4031, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798510577103875e-05, + "loss": 3.424, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6790141008397087e-05, + "loss": 3.4236, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781755060886567e-05, + "loss": 3.4174, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6773369113376044e-05, + "loss": 3.4248, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764983165865524e-05, + "loss": 3.4198, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756597218355004e-05, + "loss": 3.4156, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6748211270844484e-05, + "loss": 3.4178, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739825323333967e-05, + "loss": 3.4172, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6731439375823447e-05, + "loss": 3.4311, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6723069807116656e-05, + "loss": 3.4296, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714683859606136e-05, + "loss": 3.4322, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6706297912095616e-05, + "loss": 3.4098, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697911964585096e-05, + "loss": 3.4197, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.668954239587831e-05, + "loss": 3.4181, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.668115644836779e-05, + "loss": 3.4214, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.667277050085727e-05, + "loss": 3.4197, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.666438455334675e-05, + "loss": 3.4208, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6656014984639958e-05, + "loss": 3.4197, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6647629037129437e-05, + "loss": 3.4111, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663924308961892e-05, + "loss": 3.4178, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630857142108397e-05, + "loss": 3.4169, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.662248757340161e-05, + "loss": 3.4147, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661410162589109e-05, + "loss": 3.423, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.660571567838057e-05, + "loss": 3.4189, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.659732973087005e-05, + "loss": 3.4154, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588960162163262e-05, + "loss": 3.4218, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6580574214652742e-05, + "loss": 3.4119, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.6572188267142222e-05, + "loss": 3.427, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.65638023196317e-05, + "loss": 3.4215, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655543275092491e-05, + "loss": 3.4197, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654704680341439e-05, + "loss": 3.433, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653866085590387e-05, + "loss": 3.4266, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.6530291287197084e-05, + "loss": 3.4156, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.6521905339686564e-05, + "loss": 3.4222, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.6513519392176044e-05, + "loss": 3.4122, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.650513344466552e-05, + "loss": 3.4231, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496763875958736e-05, + "loss": 3.4149, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6488377928448216e-05, + "loss": 3.4121, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479991980937696e-05, + "loss": 3.426, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471606033427172e-05, + "loss": 3.4266, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6463236464720385e-05, + "loss": 3.4233, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454850517209865e-05, + "loss": 3.4163, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6446464569699345e-05, + "loss": 3.4133, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6438078622188825e-05, + "loss": 3.4137, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429709053482037e-05, + "loss": 3.4295, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6421323105971517e-05, + "loss": 3.4232, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412937158460994e-05, + "loss": 3.4296, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6404551210950474e-05, + "loss": 3.4027, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.639618164224369e-05, + "loss": 3.4323, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.638779569473317e-05, + "loss": 3.4145, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6379409747222646e-05, + "loss": 3.4339, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6371023799712126e-05, + "loss": 3.415, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.636265423100534e-05, + "loss": 3.4146, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.635426828349482e-05, + "loss": 3.4241, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.63458823359843e-05, + "loss": 3.4393, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.633749638847378e-05, + "loss": 3.415, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.632912681976699e-05, + "loss": 3.4278, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320740872256467e-05, + "loss": 3.4118, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6312354924745947e-05, + "loss": 3.4245, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303968977235427e-05, + "loss": 3.4151, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6295599408528643e-05, + "loss": 3.4217, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628721346101812e-05, + "loss": 3.4218, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.62788275135076e-05, + "loss": 3.4157, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.627044156599708e-05, + "loss": 3.4253, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8816885948181152, + "eval_runtime": 304.7162, + "eval_samples_per_second": 1252.283, + "eval_steps_per_second": 39.135, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626207199729029e-05, + "loss": 3.4185, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625368604977977e-05, + "loss": 3.4081, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6245300102269252e-05, + "loss": 3.4198, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236914154758732e-05, + "loss": 3.4153, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622854458605194e-05, + "loss": 3.4336, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.622015863854142e-05, + "loss": 3.4169, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.62117726910309e-05, + "loss": 3.4171, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.620338674352038e-05, + "loss": 3.425, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6195017174813594e-05, + "loss": 3.4153, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186647606106806e-05, + "loss": 3.4128, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6178261658596286e-05, + "loss": 3.4276, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.6169875711085763e-05, + "loss": 3.4187, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161489763575243e-05, + "loss": 3.4266, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6153103816064722e-05, + "loss": 3.4048, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144717868554206e-05, + "loss": 3.4106, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6136331921043686e-05, + "loss": 3.4057, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127945973533166e-05, + "loss": 3.415, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119576404826375e-05, + "loss": 3.4165, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6111206836119587e-05, + "loss": 3.4092, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102820888609067e-05, + "loss": 3.4249, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6094434941098547e-05, + "loss": 3.4356, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6086048993588027e-05, + "loss": 3.4239, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077663046077507e-05, + "loss": 3.4196, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6069277098566987e-05, + "loss": 3.4206, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060891151056467e-05, + "loss": 3.426, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052505203545944e-05, + "loss": 3.4181, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604413563483916e-05, + "loss": 3.4093, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.603574968732864e-05, + "loss": 3.4235, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602736373981812e-05, + "loss": 3.4095, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018977792307596e-05, + "loss": 3.4057, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.601060822360081e-05, + "loss": 3.4196, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.600222227609029e-05, + "loss": 3.4151, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.59938527073835e-05, + "loss": 3.4235, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598546675987298e-05, + "loss": 3.4218, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597708081236246e-05, + "loss": 3.4101, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596869486485194e-05, + "loss": 3.4133, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5960308917341417e-05, + "loss": 3.4141, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951922969830897e-05, + "loss": 3.4066, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594353702232038e-05, + "loss": 3.4187, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593515107480986e-05, + "loss": 3.4081, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.592678150610307e-05, + "loss": 3.4107, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.591839555859255e-05, + "loss": 3.4154, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.591000961108203e-05, + "loss": 3.4286, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.590162366357151e-05, + "loss": 3.4099, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5893254094864722e-05, + "loss": 3.4164, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884868147354202e-05, + "loss": 3.415, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5876482199843682e-05, + "loss": 3.4109, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5868096252333162e-05, + "loss": 3.4134, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.585972668362637e-05, + "loss": 3.3972, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.585134073611585e-05, + "loss": 3.424, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.584295478860533e-05, + "loss": 3.4089, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834568841094814e-05, + "loss": 3.4184, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5826199272388023e-05, + "loss": 3.4093, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817813324877503e-05, + "loss": 3.3994, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5809427377366983e-05, + "loss": 3.397, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5801057808660192e-05, + "loss": 3.401, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792671861149676e-05, + "loss": 3.4268, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5784285913639156e-05, + "loss": 3.4097, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775899966128636e-05, + "loss": 3.4241, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767530397421845e-05, + "loss": 3.4142, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5759144449911325e-05, + "loss": 3.4002, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5750758502400805e-05, + "loss": 3.4135, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5742372554890285e-05, + "loss": 3.4031, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5734002986183497e-05, + "loss": 3.3991, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725617038672977e-05, + "loss": 3.4125, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5717231091162457e-05, + "loss": 3.4157, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708845143651937e-05, + "loss": 3.4045, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700475574945146e-05, + "loss": 3.4129, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.569208962743463e-05, + "loss": 3.3954, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568370367992411e-05, + "loss": 3.4068, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567531773241359e-05, + "loss": 3.412, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.56669481637068e-05, + "loss": 3.4151, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565856221619628e-05, + "loss": 3.4157, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.5650176268685758e-05, + "loss": 3.4125, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.5641790321175238e-05, + "loss": 3.4241, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.563342075246845e-05, + "loss": 3.4099, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562503480495793e-05, + "loss": 3.4254, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561664885744741e-05, + "loss": 3.4041, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560826290993689e-05, + "loss": 3.4098, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.55998933412301e-05, + "loss": 3.412, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591507393719583e-05, + "loss": 3.4166, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5583121446209063e-05, + "loss": 3.4154, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574735498698543e-05, + "loss": 3.4197, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5566365929991752e-05, + "loss": 3.4014, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557979982481232e-05, + "loss": 3.3944, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549594034970712e-05, + "loss": 3.41, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5541224466263924e-05, + "loss": 3.4164, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532838518753404e-05, + "loss": 3.4073, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524452571242884e-05, + "loss": 3.4157, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5516066623732364e-05, + "loss": 3.4081, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.550768067622184e-05, + "loss": 3.4064, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.549929472871132e-05, + "loss": 3.408, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.54909087812008e-05, + "loss": 3.4095, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5482522833690284e-05, + "loss": 3.4168, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5474153264983493e-05, + "loss": 3.421, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465767317472973e-05, + "loss": 3.4227, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5457381369962453e-05, + "loss": 3.3992, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448995422451933e-05, + "loss": 3.4143, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440625853745146e-05, + "loss": 3.4062, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5432239906234626e-05, + "loss": 3.4114, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423853958724105e-05, + "loss": 3.4103, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415468011213585e-05, + "loss": 3.409, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5407098442506795e-05, + "loss": 3.4054, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398712494996274e-05, + "loss": 3.4034, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5390326547485754e-05, + "loss": 3.4052, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381940599975238e-05, + "loss": 3.4074, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373571031268447e-05, + "loss": 3.4063, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5365185083757927e-05, + "loss": 3.4112, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356799136247407e-05, + "loss": 3.4125, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5348413188736887e-05, + "loss": 3.4038, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.53400436200301e-05, + "loss": 3.4093, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.533165767251958e-05, + "loss": 3.4074, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.532327172500906e-05, + "loss": 3.4163, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.531488577749854e-05, + "loss": 3.4105, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306516208791748e-05, + "loss": 3.4093, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5298130261281228e-05, + "loss": 3.4215, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289744313770708e-05, + "loss": 3.4208, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.528135836626019e-05, + "loss": 3.405, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.52729887975534e-05, + "loss": 3.4128, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.526460285004288e-05, + "loss": 3.401, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.525621690253236e-05, + "loss": 3.4125, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.524783095502184e-05, + "loss": 3.4042, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239461386315051e-05, + "loss": 3.3984, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5231075438804531e-05, + "loss": 3.4155, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222689491294013e-05, + "loss": 3.4161, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5214319922587222e-05, + "loss": 3.4132, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205933975076702e-05, + "loss": 3.4091, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5197548027566184e-05, + "loss": 3.4012, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5189162080055663e-05, + "loss": 3.4018, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180776132545143e-05, + "loss": 3.4202, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5172390185034622e-05, + "loss": 3.4125, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5164004237524102e-05, + "loss": 3.4225, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155618290013582e-05, + "loss": 3.3961, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5147248721306792e-05, + "loss": 3.4164, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138862773796272e-05, + "loss": 3.4099, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130476826285752e-05, + "loss": 3.4198, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5122090878775232e-05, + "loss": 3.4038, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113721310068443e-05, + "loss": 3.4057, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5105335362557923e-05, + "loss": 3.4149, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096949415047405e-05, + "loss": 3.4277, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088563467536885e-05, + "loss": 3.4062, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5080193898830094e-05, + "loss": 3.4158, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071807951319575e-05, + "loss": 3.4026, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5063422003809055e-05, + "loss": 3.4133, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5055036056298535e-05, + "loss": 3.4063, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046666487591746e-05, + "loss": 3.4115, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5038280540081226e-05, + "loss": 3.4117, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029894592570706e-05, + "loss": 3.4115, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021508645060186e-05, + "loss": 3.4134, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.883629322052002, + "eval_runtime": 307.8691, + "eval_samples_per_second": 1239.459, + "eval_steps_per_second": 38.734, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5013139076353397e-05, + "loss": 3.4114, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004753128842877e-05, + "loss": 3.3939, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4996367181332358e-05, + "loss": 3.4093, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987981233821838e-05, + "loss": 3.4096, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979611665115047e-05, + "loss": 3.4187, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4971225717604529e-05, + "loss": 3.4125, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962839770094009e-05, + "loss": 3.407, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4954453822583489e-05, + "loss": 3.4149, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.49460842538767e-05, + "loss": 3.4076, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937714685169912e-05, + "loss": 3.4081, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.492932873765939e-05, + "loss": 3.4128, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.492094279014887e-05, + "loss": 3.4071, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.491255684263835e-05, + "loss": 3.4172, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.490417089512783e-05, + "loss": 3.3946, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.489578494761731e-05, + "loss": 3.3995, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4887399000106792e-05, + "loss": 3.3962, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4879013052596272e-05, + "loss": 3.4087, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870643483889483e-05, + "loss": 3.4038, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4862273915182692e-05, + "loss": 3.4023, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853887967672173e-05, + "loss": 3.4114, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845502020161653e-05, + "loss": 3.4255, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4837116072651133e-05, + "loss": 3.4121, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828730125140613e-05, + "loss": 3.4065, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4820344177630093e-05, + "loss": 3.4108, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811958230119572e-05, + "loss": 3.4204, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803572282609051e-05, + "loss": 3.4042, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4795202713902264e-05, + "loss": 3.4005, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786816766391746e-05, + "loss": 3.4173, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778430818881222e-05, + "loss": 3.3938, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4770044871370702e-05, + "loss": 3.4, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761675302663916e-05, + "loss": 3.408, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4753289355153393e-05, + "loss": 3.4046, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744903407642875e-05, + "loss": 3.4143, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736533838936087e-05, + "loss": 3.4106, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4728147891425567e-05, + "loss": 3.4064, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719761943915045e-05, + "loss": 3.4029, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4711375996404525e-05, + "loss": 3.405, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4703006427697738e-05, + "loss": 3.3955, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694620480187216e-05, + "loss": 3.4092, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4686234532676696e-05, + "loss": 3.3983, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677848585166176e-05, + "loss": 3.402, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.466947901645939e-05, + "loss": 3.4055, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4661093068948867e-05, + "loss": 3.4192, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652707121438347e-05, + "loss": 3.3992, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4644321173927828e-05, + "loss": 3.4069, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.463595160522104e-05, + "loss": 3.4051, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627565657710517e-05, + "loss": 3.4009, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4619179710199999e-05, + "loss": 3.4059, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610793762689479e-05, + "loss": 3.3884, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.460242419398269e-05, + "loss": 3.4091, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.459403824647217e-05, + "loss": 3.4014, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.458565229896165e-05, + "loss": 3.4068, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.457726635145113e-05, + "loss": 3.3998, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.456889678274434e-05, + "loss": 3.392, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.456051083523382e-05, + "loss": 3.3862, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.45521248877233e-05, + "loss": 3.3908, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4543738940212782e-05, + "loss": 3.4186, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4535369371505991e-05, + "loss": 3.3983, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526983423995471e-05, + "loss": 3.4123, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518597476484953e-05, + "loss": 3.4044, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4510211528974433e-05, + "loss": 3.3906, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501841960267643e-05, + "loss": 3.4026, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493456012757123e-05, + "loss": 3.3922, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4485070065246603e-05, + "loss": 3.3896, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476684117736083e-05, + "loss": 3.3984, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4468314549029294e-05, + "loss": 3.4068, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459928601518774e-05, + "loss": 3.3982, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451542654008254e-05, + "loss": 3.4016, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4443156706497734e-05, + "loss": 3.3831, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434787137790945e-05, + "loss": 3.3974, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4426401190280425e-05, + "loss": 3.4015, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4418015242769906e-05, + "loss": 3.4065, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409629295259386e-05, + "loss": 3.4072, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4401259726552597e-05, + "loss": 3.4025, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392873779042077e-05, + "loss": 3.4094, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384487831531557e-05, + "loss": 3.4008, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4376101884021037e-05, + "loss": 3.4137, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367732315314248e-05, + "loss": 3.3963, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4359346367803728e-05, + "loss": 3.4032, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350960420293208e-05, + "loss": 3.4, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342574472782688e-05, + "loss": 3.404, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4334204904075898e-05, + "loss": 3.4088, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325818956565378e-05, + "loss": 3.4089, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.431743300905486e-05, + "loss": 3.395, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.430904706154434e-05, + "loss": 3.3818, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300693871641283e-05, + "loss": 3.402, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.429230792413076e-05, + "loss": 3.4065, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.428392197662024e-05, + "loss": 3.3949, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4275536029109721e-05, + "loss": 3.4058, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4267150081599201e-05, + "loss": 3.3996, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4258764134088681e-05, + "loss": 3.3924, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4250378186578161e-05, + "loss": 3.4012, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241992239067641e-05, + "loss": 3.3993, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233622670360852e-05, + "loss": 3.4052, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4225236722850332e-05, + "loss": 3.411, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216850775339814e-05, + "loss": 3.4147, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.420846482782929e-05, + "loss": 3.3895, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4200095259122503e-05, + "loss": 3.4035, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191709311611984e-05, + "loss": 3.3993, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4183323364101464e-05, + "loss": 3.4022, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.417493741659094e-05, + "loss": 3.401, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166567847884155e-05, + "loss": 3.4013, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4158181900373635e-05, + "loss": 3.394, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149795952863115e-05, + "loss": 3.3951, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4141410005352593e-05, + "loss": 3.3969, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4133040436645806e-05, + "loss": 3.3964, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124654489135286e-05, + "loss": 3.3977, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4116268541624764e-05, + "loss": 3.4027, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107882594114244e-05, + "loss": 3.4008, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099513025407456e-05, + "loss": 3.3938, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4091127077896938e-05, + "loss": 3.4022, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082741130386415e-05, + "loss": 3.3932, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4074355182875894e-05, + "loss": 3.4088, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065985614169109e-05, + "loss": 3.4011, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057599666658585e-05, + "loss": 3.3992, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4049213719148067e-05, + "loss": 3.4056, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040827771637547e-05, + "loss": 3.4145, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403245820293076e-05, + "loss": 3.3956, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4024072255420238e-05, + "loss": 3.4022, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015686307909718e-05, + "loss": 3.3944, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400731673920293e-05, + "loss": 3.4038, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399893079169241e-05, + "loss": 3.3946, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990544844181888e-05, + "loss": 3.3889, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3982158896671368e-05, + "loss": 3.4029, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973789327964582e-05, + "loss": 3.4071, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3965403380454059e-05, + "loss": 3.4058, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3957017432943539e-05, + "loss": 3.3993, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948631485433019e-05, + "loss": 3.3908, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3940261916726233e-05, + "loss": 3.3937, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3931892348019444e-05, + "loss": 3.4114, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923506400508924e-05, + "loss": 3.4016, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3915120452998404e-05, + "loss": 3.4132, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3906734505487884e-05, + "loss": 3.3852, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3898348557977362e-05, + "loss": 3.4074, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889962610466842e-05, + "loss": 3.404, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881576662956322e-05, + "loss": 3.407, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3873190715445802e-05, + "loss": 3.3968, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864821146739013e-05, + "loss": 3.3963, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3856435199228493e-05, + "loss": 3.4041, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3848049251717972e-05, + "loss": 3.4192, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3839663304207454e-05, + "loss": 3.3987, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3831293735500663e-05, + "loss": 3.4051, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822907787990145e-05, + "loss": 3.3971, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814521840479625e-05, + "loss": 3.4026, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3806135892969105e-05, + "loss": 3.3942, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797766324262316e-05, + "loss": 3.4051, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3789380376751796e-05, + "loss": 3.397, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780994429241276e-05, + "loss": 3.3993, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772608481730755e-05, + "loss": 3.4028, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8853416442871094, + "eval_runtime": 307.5516, + "eval_samples_per_second": 1240.738, + "eval_steps_per_second": 38.774, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3764238913023966e-05, + "loss": 3.4059, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755852965513446e-05, + "loss": 3.3852, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747467018002926e-05, + "loss": 3.3955, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3739081070492408e-05, + "loss": 3.4068, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730711501785617e-05, + "loss": 3.4041, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3722325554275099e-05, + "loss": 3.405, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713939606764579e-05, + "loss": 3.3929, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705553659254058e-05, + "loss": 3.4089, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.369718409054727e-05, + "loss": 3.3957, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688814521840478e-05, + "loss": 3.3975, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.368042857432996e-05, + "loss": 3.4028, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.367204262681944e-05, + "loss": 3.4006, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.366365667930892e-05, + "loss": 3.411, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.36552707317984e-05, + "loss": 3.3843, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.364688478428788e-05, + "loss": 3.3856, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638498836777361e-05, + "loss": 3.3904, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3630112889266838e-05, + "loss": 3.3983, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621743320560052e-05, + "loss": 3.3913, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3613373751853261e-05, + "loss": 3.394, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604987804342741e-05, + "loss": 3.4063, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.3596601856832223e-05, + "loss": 3.4123, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3588215909321703e-05, + "loss": 3.4075, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579829961811183e-05, + "loss": 3.3964, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.3571444014300661e-05, + "loss": 3.4014, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3563058066790141e-05, + "loss": 3.409, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554672119279621e-05, + "loss": 3.3965, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3546302550572834e-05, + "loss": 3.3879, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537916603062312e-05, + "loss": 3.4091, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529530655551792e-05, + "loss": 3.3833, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3521144708041272e-05, + "loss": 3.3893, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512775139334486e-05, + "loss": 3.3931, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3504389191823962e-05, + "loss": 3.4003, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3496003244313442e-05, + "loss": 3.4042, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487617296802924e-05, + "loss": 3.399, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3479264106899867e-05, + "loss": 3.3978, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470878159389347e-05, + "loss": 3.3929, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462492211878827e-05, + "loss": 3.3918, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3454106264368307e-05, + "loss": 3.3832, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445720316857785e-05, + "loss": 3.404, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3437334369347265e-05, + "loss": 3.3878, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428948421836745e-05, + "loss": 3.3947, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420562474326225e-05, + "loss": 3.3938, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3412192905619436e-05, + "loss": 3.4076, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403806958108916e-05, + "loss": 3.394, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3395421010598396e-05, + "loss": 3.395, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3387051441891607e-05, + "loss": 3.3965, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378665494381087e-05, + "loss": 3.3941, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3370279546870568e-05, + "loss": 3.3913, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361893599360048e-05, + "loss": 3.3808, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353524030653257e-05, + "loss": 3.3966, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3345138083142739e-05, + "loss": 3.3966, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336752135632219e-05, + "loss": 3.3938, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3328366188121699e-05, + "loss": 3.3893, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.331999661941491e-05, + "loss": 3.3789, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.331161067190439e-05, + "loss": 3.3823, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330322472439387e-05, + "loss": 3.3782, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.329483877688335e-05, + "loss": 3.4108, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.328646920817656e-05, + "loss": 3.3856, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.327808326066604e-05, + "loss": 3.406, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269697313155522e-05, + "loss": 3.3926, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3261311365645002e-05, + "loss": 3.3836, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3252941796938211e-05, + "loss": 3.388, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244555849427693e-05, + "loss": 3.3857, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3236169901917173e-05, + "loss": 3.3846, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227783954406653e-05, + "loss": 3.3855, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219414385699864e-05, + "loss": 3.3999, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3211028438189343e-05, + "loss": 3.3908, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202642490678823e-05, + "loss": 3.3882, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3194256543168303e-05, + "loss": 3.3769, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185886974461514e-05, + "loss": 3.3872, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177501026950994e-05, + "loss": 3.3902, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3169115079440476e-05, + "loss": 3.3988, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160729131929956e-05, + "loss": 3.3969, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3152359563223165e-05, + "loss": 3.3973, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143973615712646e-05, + "loss": 3.3947, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135587668202126e-05, + "loss": 3.3925, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3127201720691606e-05, + "loss": 3.3999, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118832151984817e-05, + "loss": 3.3863, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3110446204474297e-05, + "loss": 3.395, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3102060256963777e-05, + "loss": 3.3897, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093674309453257e-05, + "loss": 3.3922, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3085304740746468e-05, + "loss": 3.402, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076918793235948e-05, + "loss": 3.3982, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068532845725428e-05, + "loss": 3.386, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.306014689821491e-05, + "loss": 3.3679, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.305179370831185e-05, + "loss": 3.3964, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.304340776080133e-05, + "loss": 3.3954, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.303502181329081e-05, + "loss": 3.3885, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026635865780291e-05, + "loss": 3.3892, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.301824991826977e-05, + "loss": 3.396, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.300986397075925e-05, + "loss": 3.3819, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.300147802324873e-05, + "loss": 3.3896, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2993092075738209e-05, + "loss": 3.3901, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984722507031422e-05, + "loss": 3.3952, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2976336559520901e-05, + "loss": 3.4014, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2967950612010381e-05, + "loss": 3.4031, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.295956466449986e-05, + "loss": 3.3816, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2951195095793072e-05, + "loss": 3.3913, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2942809148282554e-05, + "loss": 3.3917, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.293442320077203e-05, + "loss": 3.3925, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.292603725326151e-05, + "loss": 3.3882, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917667684554725e-05, + "loss": 3.3939, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2909281737044204e-05, + "loss": 3.3841, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2900895789533681e-05, + "loss": 3.3842, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892509842023163e-05, + "loss": 3.3904, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2884140273316375e-05, + "loss": 3.3796, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875754325805855e-05, + "loss": 3.3883, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2867368378295333e-05, + "loss": 3.3925, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858982430784813e-05, + "loss": 3.3895, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850612862078026e-05, + "loss": 3.3871, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2842226914567504e-05, + "loss": 3.3958, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833840967056984e-05, + "loss": 3.3796, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2825455019546464e-05, + "loss": 3.3963, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2817085450839678e-05, + "loss": 3.3933, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808699503329155e-05, + "loss": 3.3861, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2800313555818635e-05, + "loss": 3.3965, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791927608308116e-05, + "loss": 3.4047, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783558039601329e-05, + "loss": 3.3877, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2775172092090807e-05, + "loss": 3.3941, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766786144580287e-05, + "loss": 3.3835, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2758400197069767e-05, + "loss": 3.3916, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2750030628362978e-05, + "loss": 3.3857, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741644680852458e-05, + "loss": 3.3826, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2733258733341938e-05, + "loss": 3.3888, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724872785831418e-05, + "loss": 3.3994, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716503217124628e-05, + "loss": 3.3936, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2708117269614108e-05, + "loss": 3.3888, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699731322103588e-05, + "loss": 3.3818, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.26913617533968e-05, + "loss": 3.3872, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682975805886279e-05, + "loss": 3.3989, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.267458985837576e-05, + "loss": 3.3914, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.266620391086524e-05, + "loss": 3.4066, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.265783434215845e-05, + "loss": 3.3771, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2649448394647931e-05, + "loss": 3.3959, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2641062447137411e-05, + "loss": 3.3938, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632676499626891e-05, + "loss": 3.3943, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2624306930920102e-05, + "loss": 3.384, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2615920983409582e-05, + "loss": 3.3871, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2607535035899062e-05, + "loss": 3.4005, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2599149088388542e-05, + "loss": 3.4051, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590779519681753e-05, + "loss": 3.3899, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2582393572171233e-05, + "loss": 3.3916, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2574007624660713e-05, + "loss": 3.3877, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565621677150194e-05, + "loss": 3.3941, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2557252108443403e-05, + "loss": 3.385, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2548866160932885e-05, + "loss": 3.3985, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540480213422365e-05, + "loss": 3.3868, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2532094265911845e-05, + "loss": 3.3916, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523724697205056e-05, + "loss": 3.3929, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.886073589324951, + "eval_runtime": 313.406, + "eval_samples_per_second": 1217.561, + "eval_steps_per_second": 38.05, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2515338749694536e-05, + "loss": 3.389, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506952802184016e-05, + "loss": 3.3834, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498566854673496e-05, + "loss": 3.3838, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2490197285966706e-05, + "loss": 3.3964, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481811338456186e-05, + "loss": 3.3941, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2473425390945666e-05, + "loss": 3.3973, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2465039443435146e-05, + "loss": 3.3828, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2456669874728357e-05, + "loss": 3.3967, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2448283927217839e-05, + "loss": 3.3868, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.243991435851105e-05, + "loss": 3.3885, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431528411000528e-05, + "loss": 3.3911, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.242314246349001e-05, + "loss": 3.3906, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.241475651597949e-05, + "loss": 3.3982, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.240637056846897e-05, + "loss": 3.3783, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.239798462095845e-05, + "loss": 3.3721, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.238959867344793e-05, + "loss": 3.3846, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.238121272593741e-05, + "loss": 3.3847, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.237284315723062e-05, + "loss": 3.3847, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2364473588523831e-05, + "loss": 3.3833, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.235608764101331e-05, + "loss": 3.3929, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347701693502792e-05, + "loss": 3.4052, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.233931574599227e-05, + "loss": 3.3931, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.233092979848175e-05, + "loss": 3.3908, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.232254385097123e-05, + "loss": 3.3913, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.231415790346071e-05, + "loss": 3.4, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.230577195595019e-05, + "loss": 3.383, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2297402387243401e-05, + "loss": 3.385, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2289016439732883e-05, + "loss": 3.3943, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.2280630492222361e-05, + "loss": 3.3792, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2272244544711841e-05, + "loss": 3.3758, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2263874976005054e-05, + "loss": 3.3849, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255489028494534e-05, + "loss": 3.3922, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2247119459787744e-05, + "loss": 3.3988, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238733512277224e-05, + "loss": 3.3863, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2230347564766704e-05, + "loss": 3.3943, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221961617256184e-05, + "loss": 3.3837, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213575669745664e-05, + "loss": 3.3791, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2205206101038875e-05, + "loss": 3.3756, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196820153528355e-05, + "loss": 3.3919, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2188434206017835e-05, + "loss": 3.3782, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2180048258507315e-05, + "loss": 3.3836, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171662310996795e-05, + "loss": 3.3878, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2163276363486275e-05, + "loss": 3.4009, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154890415975755e-05, + "loss": 3.3807, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146504468465235e-05, + "loss": 3.3884, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2138134899758447e-05, + "loss": 3.3872, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129748952247925e-05, + "loss": 3.3808, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2121363004737405e-05, + "loss": 3.3862, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112977057226885e-05, + "loss": 3.3725, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104607488520098e-05, + "loss": 3.3842, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2096221541009576e-05, + "loss": 3.39, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2087835593499058e-05, + "loss": 3.381, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2079449645988538e-05, + "loss": 3.3812, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2071080077281747e-05, + "loss": 3.3676, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062694129771228e-05, + "loss": 3.3778, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2054308182260708e-05, + "loss": 3.3636, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045922234750187e-05, + "loss": 3.4039, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.20375526660434e-05, + "loss": 3.3766, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.202916671853288e-05, + "loss": 3.3969, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020780771022359e-05, + "loss": 3.3821, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2012394823511839e-05, + "loss": 3.3674, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.200402525480505e-05, + "loss": 3.3804, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.199563930729453e-05, + "loss": 3.3792, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.198725335978401e-05, + "loss": 3.3719, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.197886741227349e-05, + "loss": 3.3666, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.19704978435667e-05, + "loss": 3.3925, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1962111896056182e-05, + "loss": 3.3838, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.195372594854566e-05, + "loss": 3.3718, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.194534000103514e-05, + "loss": 3.3689, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1936970432328353e-05, + "loss": 3.377, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1928584484817833e-05, + "loss": 3.3809, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1920198537307311e-05, + "loss": 3.3904, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911828968600524e-05, + "loss": 3.3831, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1903443021090004e-05, + "loss": 3.388, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1895057073579483e-05, + "loss": 3.3844, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1886671126068963e-05, + "loss": 3.3839, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1878301557362174e-05, + "loss": 3.3899, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869915609851654e-05, + "loss": 3.3773, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861529662341134e-05, + "loss": 3.3867, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1853143714830614e-05, + "loss": 3.3805, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844774146123825e-05, + "loss": 3.3801, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1836388198613307e-05, + "loss": 3.3949, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1828002251102785e-05, + "loss": 3.3899, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819616303592265e-05, + "loss": 3.377, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1811246734885477e-05, + "loss": 3.3593, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802877166178688e-05, + "loss": 3.3864, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1794491218668168e-05, + "loss": 3.38, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1786105271157648e-05, + "loss": 3.3853, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777719323647128e-05, + "loss": 3.378, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1769333376136608e-05, + "loss": 3.3854, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760947428626088e-05, + "loss": 3.3761, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752561481115568e-05, + "loss": 3.3762, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1744175533605048e-05, + "loss": 3.3801, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735805964898259e-05, + "loss": 3.3862, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1727420017387738e-05, + "loss": 3.3912, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1719034069877218e-05, + "loss": 3.3906, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710648122366698e-05, + "loss": 3.3762, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.170227855365991e-05, + "loss": 3.382, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693892606149389e-05, + "loss": 3.3832, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.168550665863887e-05, + "loss": 3.3815, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1677120711128349e-05, + "loss": 3.3766, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.166875114242156e-05, + "loss": 3.3863, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1660365194911041e-05, + "loss": 3.3751, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651979247400521e-05, + "loss": 3.3739, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.164359329989e-05, + "loss": 3.3856, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1635223731183212e-05, + "loss": 3.3689, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.1626837783672692e-05, + "loss": 3.3761, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.161845183616217e-05, + "loss": 3.3891, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1610065888651652e-05, + "loss": 3.3763, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1601696319944863e-05, + "loss": 3.3754, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1593310372434343e-05, + "loss": 3.388, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1584924424923823e-05, + "loss": 3.3716, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1576538477413303e-05, + "loss": 3.387, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1568168908706513e-05, + "loss": 3.3824, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559782961195995e-05, + "loss": 3.3806, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1551397013685473e-05, + "loss": 3.3874, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1543011066174953e-05, + "loss": 3.3946, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534641497468166e-05, + "loss": 3.3799, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1526255549957644e-05, + "loss": 3.3823, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517869602447124e-05, + "loss": 3.3757, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509483654936606e-05, + "loss": 3.3829, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1501114086229816e-05, + "loss": 3.3746, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492728138719295e-05, + "loss": 3.3759, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1484342191208776e-05, + "loss": 3.3777, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475956243698256e-05, + "loss": 3.3884, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1467586674991467e-05, + "loss": 3.3843, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1459200727480947e-05, + "loss": 3.3805, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450814779970427e-05, + "loss": 3.3742, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.144244521126364e-05, + "loss": 3.3773, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1434059263753118e-05, + "loss": 3.3839, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425673316242598e-05, + "loss": 3.3856, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1417287368732078e-05, + "loss": 3.395, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.140891780002529e-05, + "loss": 3.3693, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400531852514768e-05, + "loss": 3.3865, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1392145905004248e-05, + "loss": 3.3841, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.138375995749373e-05, + "loss": 3.3853, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.137539038878694e-05, + "loss": 3.374, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.136700444127642e-05, + "loss": 3.3805, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.13586184937659e-05, + "loss": 3.3889, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.135023254625538e-05, + "loss": 3.3935, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341862977548592e-05, + "loss": 3.38, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333477030038071e-05, + "loss": 3.3799, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1325091082527551e-05, + "loss": 3.3806, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316705135017031e-05, + "loss": 3.3815, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.1308335566310242e-05, + "loss": 3.376, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1299949618799722e-05, + "loss": 3.391, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1291563671289202e-05, + "loss": 3.3752, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1283177723778682e-05, + "loss": 3.3886, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1274808155071893e-05, + "loss": 3.3786, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.886558771133423, + "eval_runtime": 316.1254, + "eval_samples_per_second": 1207.087, + "eval_steps_per_second": 37.722, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.1266422207561374e-05, + "loss": 3.3512, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1258036260050854e-05, + "loss": 3.3742, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1249650312540333e-05, + "loss": 3.3725, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1241264365029813e-05, + "loss": 3.3842, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232894796323025e-05, + "loss": 3.3838, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224508848812503e-05, + "loss": 3.3882, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1216122901301983e-05, + "loss": 3.3739, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207736953791465e-05, + "loss": 3.3877, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1199367385084676e-05, + "loss": 3.3748, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190997816377887e-05, + "loss": 3.3828, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182611868867367e-05, + "loss": 3.3807, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1174225921356847e-05, + "loss": 3.3835, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165839973846328e-05, + "loss": 3.3842, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1157454026335806e-05, + "loss": 3.3749, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1149068078825286e-05, + "loss": 3.3652, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140682131314766e-05, + "loss": 3.3725, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1132296183804246e-05, + "loss": 3.3692, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123926615097457e-05, + "loss": 3.3744, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1115540667586937e-05, + "loss": 3.3768, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1107154720076419e-05, + "loss": 3.3777, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098768772565897e-05, + "loss": 3.3984, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.109039920385911e-05, + "loss": 3.3844, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.108201325634859e-05, + "loss": 3.3821, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073627308838068e-05, + "loss": 3.3817, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1065241361327548e-05, + "loss": 3.3905, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.105687179262076e-05, + "loss": 3.3728, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.104848584511024e-05, + "loss": 3.3766, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1040099897599718e-05, + "loss": 3.3827, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.10317139500892e-05, + "loss": 3.3759, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.102334438138241e-05, + "loss": 3.3627, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.101495843387189e-05, + "loss": 3.3738, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.100657248636137e-05, + "loss": 3.3837, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0998202917654581e-05, + "loss": 3.3846, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989816970144063e-05, + "loss": 3.3778, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0981431022633541e-05, + "loss": 3.3824, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0973045075123021e-05, + "loss": 3.3711, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964659127612501e-05, + "loss": 3.3692, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0956273180101983e-05, + "loss": 3.3659, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0947887232591461e-05, + "loss": 3.3837, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939501285080941e-05, + "loss": 3.3662, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0931131716374154e-05, + "loss": 3.3771, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922745768863632e-05, + "loss": 3.373, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.0914359821353112e-05, + "loss": 3.3905, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905973873842592e-05, + "loss": 3.3708, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897604305135804e-05, + "loss": 3.3767, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0889218357625283e-05, + "loss": 3.3803, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880832410114764e-05, + "loss": 3.3705, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0872446462604244e-05, + "loss": 3.3771, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0864076893897455e-05, + "loss": 3.3631, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855690946386935e-05, + "loss": 3.3749, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0847304998876415e-05, + "loss": 3.377, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838919051365895e-05, + "loss": 3.3746, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830549482659106e-05, + "loss": 3.3729, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0822163535148586e-05, + "loss": 3.3564, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813777587638066e-05, + "loss": 3.3709, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0805391640127545e-05, + "loss": 3.3554, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0797022071420756e-05, + "loss": 3.3887, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788636123910236e-05, + "loss": 3.3689, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0780250176399718e-05, + "loss": 3.3825, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771864228889196e-05, + "loss": 3.3771, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763494660182407e-05, + "loss": 3.3613, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0755108712671889e-05, + "loss": 3.3678, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746722765161369e-05, + "loss": 3.371, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.073835319645458e-05, + "loss": 3.3647, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.072996724894406e-05, + "loss": 3.3558, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.072158130143354e-05, + "loss": 3.384, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0713195353923017e-05, + "loss": 3.3793, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.070482578521623e-05, + "loss": 3.3653, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.069643983770571e-05, + "loss": 3.3568, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.068805389019519e-05, + "loss": 3.3688, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.067966794268467e-05, + "loss": 3.3709, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.067129837397788e-05, + "loss": 3.3823, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.066291242646736e-05, + "loss": 3.3733, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0654526478956842e-05, + "loss": 3.3785, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.064614053144632e-05, + "loss": 3.3727, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637770962739533e-05, + "loss": 3.3793, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0629385015229013e-05, + "loss": 3.3757, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0620999067718491e-05, + "loss": 3.3701, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0612613120207971e-05, + "loss": 3.381, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0604243551501184e-05, + "loss": 3.3701, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595857603990664e-05, + "loss": 3.3731, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0587471656480142e-05, + "loss": 3.3834, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0579085708969623e-05, + "loss": 3.3768, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570716140262834e-05, + "loss": 3.368, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0562330192752314e-05, + "loss": 3.3518, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0553960624045525e-05, + "loss": 3.3726, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545574676535005e-05, + "loss": 3.3749, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0537188729024487e-05, + "loss": 3.3704, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0528802781513965e-05, + "loss": 3.3731, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0520416834003445e-05, + "loss": 3.3763, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0512030886492925e-05, + "loss": 3.3685, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503644938982406e-05, + "loss": 3.3618, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0495258991471885e-05, + "loss": 3.3706, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486889422765096e-05, + "loss": 3.3767, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478503475254577e-05, + "loss": 3.3819, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0470117527744055e-05, + "loss": 3.377, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461731580233535e-05, + "loss": 3.3751, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0453362011526748e-05, + "loss": 3.367, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444976064016228e-05, + "loss": 3.3727, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436590116505706e-05, + "loss": 3.3756, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0428204168995188e-05, + "loss": 3.3722, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419834600288399e-05, + "loss": 3.3741, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0411448652777878e-05, + "loss": 3.3688, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0403062705267358e-05, + "loss": 3.3626, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394676757756838e-05, + "loss": 3.3788, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.038630718905005e-05, + "loss": 3.3553, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377921241539529e-05, + "loss": 3.3699, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369535294029009e-05, + "loss": 3.3779, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0361149346518489e-05, + "loss": 3.369, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0352779777811702e-05, + "loss": 3.3653, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.034439383030118e-05, + "loss": 3.3742, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.033600788279066e-05, + "loss": 3.3662, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0327621935280141e-05, + "loss": 3.3741, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0319252366573352e-05, + "loss": 3.373, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.031086641906283e-05, + "loss": 3.3716, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0302480471552312e-05, + "loss": 3.3748, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0294094524041792e-05, + "loss": 3.3874, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285724955335003e-05, + "loss": 3.3666, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0277339007824483e-05, + "loss": 3.3705, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0268953060313963e-05, + "loss": 3.3704, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0260567112803443e-05, + "loss": 3.3728, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0252197544096654e-05, + "loss": 3.3628, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0243811596586133e-05, + "loss": 3.368, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0235425649075613e-05, + "loss": 3.3712, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0227039701565093e-05, + "loss": 3.3814, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218670132858304e-05, + "loss": 3.3744, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0210284185347784e-05, + "loss": 3.3719, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0201898237837266e-05, + "loss": 3.3645, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0193528669130475e-05, + "loss": 3.3691, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0185142721619957e-05, + "loss": 3.3719, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176756774109436e-05, + "loss": 3.3785, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0168370826598916e-05, + "loss": 3.3821, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159984879088395e-05, + "loss": 3.3612, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0151598931577876e-05, + "loss": 3.3711, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0143212984067356e-05, + "loss": 3.3795, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134827036556835e-05, + "loss": 3.3728, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0126457467850047e-05, + "loss": 3.3672, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0118071520339527e-05, + "loss": 3.3668, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109685572829005e-05, + "loss": 3.381, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0101299625318487e-05, + "loss": 3.3817, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092930056611698e-05, + "loss": 3.3724, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084544109101178e-05, + "loss": 3.3727, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0076158161590658e-05, + "loss": 3.3687, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067772214080138e-05, + "loss": 3.3691, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0059402645373348e-05, + "loss": 3.3669, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.005101669786283e-05, + "loss": 3.3835, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042630750352308e-05, + "loss": 3.3655, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0034244802841788e-05, + "loss": 3.3775, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025875234135e-05, + "loss": 3.3656, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017489286624479e-05, + "loss": 3.3717, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.8879201412200928, + "eval_runtime": 331.7486, + "eval_samples_per_second": 1150.242, + "eval_steps_per_second": 35.946, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0009103339113959e-05, + "loss": 3.3621, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000717391603439e-05, + "loss": 3.3631, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.992347822896651e-06, + "loss": 3.3781, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.98396187538613e-06, + "loss": 3.3706, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.975575927875611e-06, + "loss": 3.3823, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.967189980365091e-06, + "loss": 3.3627, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958820411658302e-06, + "loss": 3.3759, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.950434464147782e-06, + "loss": 3.3666, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.942064895440993e-06, + "loss": 3.3709, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.933678947930473e-06, + "loss": 3.373, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.925293000419953e-06, + "loss": 3.3718, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.916907052909433e-06, + "loss": 3.3747, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.908521105398913e-06, + "loss": 3.3631, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.900135157888393e-06, + "loss": 3.3586, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891749210377872e-06, + "loss": 3.3665, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.883363262867352e-06, + "loss": 3.3559, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.874993694160565e-06, + "loss": 3.3674, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.866607746650043e-06, + "loss": 3.367, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.858221799139523e-06, + "loss": 3.3654, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.849835851629003e-06, + "loss": 3.39, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.841466282922216e-06, + "loss": 3.377, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.833080335411694e-06, + "loss": 3.3753, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.824694387901174e-06, + "loss": 3.3687, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.816308440390655e-06, + "loss": 3.3813, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.807938871683866e-06, + "loss": 3.3668, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799552924173346e-06, + "loss": 3.365, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.791166976662826e-06, + "loss": 3.3731, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782781029152306e-06, + "loss": 3.3652, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.774411460445517e-06, + "loss": 3.352, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.766025512934997e-06, + "loss": 3.3665, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757639565424477e-06, + "loss": 3.3711, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.74926999671769e-06, + "loss": 3.3768, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740884049207168e-06, + "loss": 3.3706, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732498101696648e-06, + "loss": 3.3779, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.724112154186127e-06, + "loss": 3.3602, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715726206675607e-06, + "loss": 3.364, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.707340259165087e-06, + "loss": 3.3527, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.698954311654567e-06, + "loss": 3.3736, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690568364144047e-06, + "loss": 3.3607, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.682198795437258e-06, + "loss": 3.3671, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673812847926738e-06, + "loss": 3.3646, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.66542690041622e-06, + "loss": 3.3765, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.657040952905698e-06, + "loss": 3.3676, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648671384198909e-06, + "loss": 3.3638, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.64028543668839e-06, + "loss": 3.3727, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.63189948917787e-06, + "loss": 3.3615, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.623513541667349e-06, + "loss": 3.3684, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.615143972960561e-06, + "loss": 3.3519, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606758025450041e-06, + "loss": 3.3625, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.598372077939521e-06, + "loss": 3.3695, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.589986130429001e-06, + "loss": 3.3612, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.581616561722212e-06, + "loss": 3.3652, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.573230614211692e-06, + "loss": 3.3484, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.564844666701172e-06, + "loss": 3.3616, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.556458719190652e-06, + "loss": 3.3431, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.548089150483862e-06, + "loss": 3.3807, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.539703202973344e-06, + "loss": 3.3588, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.531317255462822e-06, + "loss": 3.375, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.522931307952302e-06, + "loss": 3.367, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514561739245515e-06, + "loss": 3.3539, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.506175791734993e-06, + "loss": 3.3568, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.497789844224473e-06, + "loss": 3.3612, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.489403896713955e-06, + "loss": 3.3539, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.481034328007165e-06, + "loss": 3.3466, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472648380496645e-06, + "loss": 3.3736, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.464262432986125e-06, + "loss": 3.3699, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.455892864279336e-06, + "loss": 3.3551, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447506916768816e-06, + "loss": 3.3498, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.439120969258296e-06, + "loss": 3.3554, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430735021747776e-06, + "loss": 3.3648, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.422365453040988e-06, + "loss": 3.3702, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413979505530467e-06, + "loss": 3.3638, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405593558019947e-06, + "loss": 3.3688, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.397207610509427e-06, + "loss": 3.3655, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388838041802639e-06, + "loss": 3.3704, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.380452094292117e-06, + "loss": 3.3642, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.372066146781597e-06, + "loss": 3.3623, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363680199271079e-06, + "loss": 3.3702, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.35531063056429e-06, + "loss": 3.3599, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.34692468305377e-06, + "loss": 3.3632, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.33853873554325e-06, + "loss": 3.3709, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.33015278803273e-06, + "loss": 3.37, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.32178321932594e-06, + "loss": 3.3574, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.31339727181542e-06, + "loss": 3.3452, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.3050113243049e-06, + "loss": 3.3617, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.296641755598113e-06, + "loss": 3.3657, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.288255808087591e-06, + "loss": 3.3637, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279869860577071e-06, + "loss": 3.3618, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271483913066551e-06, + "loss": 3.3657, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.263097965556031e-06, + "loss": 3.3576, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254712018045511e-06, + "loss": 3.3516, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.246326070534991e-06, + "loss": 3.3638, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.23794012302447e-06, + "loss": 3.3631, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.229570554317682e-06, + "loss": 3.3695, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.221184606807162e-06, + "loss": 3.373, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212798659296643e-06, + "loss": 3.3679, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.204412711786122e-06, + "loss": 3.3537, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.196043143079332e-06, + "loss": 3.3644, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.187657195568814e-06, + "loss": 3.3631, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.179271248058294e-06, + "loss": 3.3632, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.170885300547772e-06, + "loss": 3.3638, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162515731840985e-06, + "loss": 3.3564, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.154129784330465e-06, + "loss": 3.3541, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.145743836819945e-06, + "loss": 3.3675, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.137357889309425e-06, + "loss": 3.347, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.128988320602635e-06, + "loss": 3.3613, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120602373092115e-06, + "loss": 3.3669, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.112216425581595e-06, + "loss": 3.3562, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103830478071075e-06, + "loss": 3.3562, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095460909364286e-06, + "loss": 3.3659, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.087074961853768e-06, + "loss": 3.3554, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078689014343246e-06, + "loss": 3.368, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.070303066832726e-06, + "loss": 3.3639, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061933498125938e-06, + "loss": 3.3607, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053547550615418e-06, + "loss": 3.3629, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.045161603104897e-06, + "loss": 3.3788, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036775655594378e-06, + "loss": 3.3579, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.028406086887589e-06, + "loss": 3.3598, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.020020139377067e-06, + "loss": 3.3624, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011634191866549e-06, + "loss": 3.3607, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.00326462315976e-06, + "loss": 3.3558, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.99487867564924e-06, + "loss": 3.3538, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.98649272813872e-06, + "loss": 3.3614, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.9781067806282e-06, + "loss": 3.3706, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.96972083311768e-06, + "loss": 3.3667, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.96133488560716e-06, + "loss": 3.3612, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.95294893809664e-06, + "loss": 3.3542, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.94456299058612e-06, + "loss": 3.3566, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.936193421879332e-06, + "loss": 3.3607, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.92780747436881e-06, + "loss": 3.373, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.91942152685829e-06, + "loss": 3.3746, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.91103557934777e-06, + "loss": 3.3526, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.902666010640983e-06, + "loss": 3.3609, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.89428006313046e-06, + "loss": 3.3662, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.88589411561994e-06, + "loss": 3.3606, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877508168109422e-06, + "loss": 3.3674, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.869138599402631e-06, + "loss": 3.3564, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860752651892113e-06, + "loss": 3.3733, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.852366704381593e-06, + "loss": 3.3701, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.843980756871071e-06, + "loss": 3.3635, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835611188164284e-06, + "loss": 3.3632, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.827225240653764e-06, + "loss": 3.3625, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818839293143244e-06, + "loss": 3.358, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810469724436455e-06, + "loss": 3.3599, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.802083776925934e-06, + "loss": 3.3743, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793697829415414e-06, + "loss": 3.3551, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.785311881904894e-06, + "loss": 3.3653, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.776942313198105e-06, + "loss": 3.3606, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768556365687585e-06, + "loss": 3.3586, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8885810375213623, + "eval_runtime": 322.3119, + "eval_samples_per_second": 1183.918, + "eval_steps_per_second": 36.998, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.760170418177067e-06, + "loss": 3.3526, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.751784470666545e-06, + "loss": 3.355, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.743398523156025e-06, + "loss": 3.3701, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.735028954449237e-06, + "loss": 3.3583, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.726643006938717e-06, + "loss": 3.3744, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.718257059428196e-06, + "loss": 3.3496, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.709871111917677e-06, + "loss": 3.369, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.701501543210888e-06, + "loss": 3.3596, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.6931319745041e-06, + "loss": 3.3601, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.684746026993579e-06, + "loss": 3.3654, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.676360079483059e-06, + "loss": 3.3605, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.667974131972539e-06, + "loss": 3.3665, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.659588184462019e-06, + "loss": 3.3524, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.651202236951499e-06, + "loss": 3.3517, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.642816289440979e-06, + "loss": 3.3542, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.634430341930459e-06, + "loss": 3.3527, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.62606077322367e-06, + "loss": 3.3528, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.61767482571315e-06, + "loss": 3.3584, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.60928887820263e-06, + "loss": 3.3585, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.60090293069211e-06, + "loss": 3.3836, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.59253336198532e-06, + "loss": 3.3639, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.584147414474802e-06, + "loss": 3.3658, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.575761466964282e-06, + "loss": 3.3612, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.56737551945376e-06, + "loss": 3.3684, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.559005950746972e-06, + "loss": 3.3596, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.550620003236452e-06, + "loss": 3.3606, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.542234055725932e-06, + "loss": 3.3604, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.533848108215412e-06, + "loss": 3.356, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.525478539508623e-06, + "loss": 3.3394, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.517092591998103e-06, + "loss": 3.3614, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.508706644487583e-06, + "loss": 3.3598, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.500337075780794e-06, + "loss": 3.369, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.491951128270274e-06, + "loss": 3.3621, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.483565180759755e-06, + "loss": 3.3654, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.475179233249234e-06, + "loss": 3.3521, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.466793285738714e-06, + "loss": 3.3565, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.458407338228194e-06, + "loss": 3.3462, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.450021390717674e-06, + "loss": 3.3607, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.441635443207153e-06, + "loss": 3.3522, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.433265874500364e-06, + "loss": 3.3529, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.424879926989846e-06, + "loss": 3.3554, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.416493979479324e-06, + "loss": 3.3673, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.408108031968804e-06, + "loss": 3.3593, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.399738463262017e-06, + "loss": 3.3573, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.391352515751497e-06, + "loss": 3.3635, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.382966568240975e-06, + "loss": 3.3546, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.374580620730456e-06, + "loss": 3.3581, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.366194673219936e-06, + "loss": 3.3472, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.357808725709415e-06, + "loss": 3.3504, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.349422778198895e-06, + "loss": 3.3629, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.341036830688376e-06, + "loss": 3.3518, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.332667261981587e-06, + "loss": 3.356, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.324281314471067e-06, + "loss": 3.342, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.315895366960547e-06, + "loss": 3.3496, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.307509419450027e-06, + "loss": 3.3391, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.299139850743238e-06, + "loss": 3.3682, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.290753903232718e-06, + "loss": 3.3526, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.282367955722198e-06, + "loss": 3.3599, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.273982008211678e-06, + "loss": 3.3599, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.265612439504888e-06, + "loss": 3.3473, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.257226491994368e-06, + "loss": 3.344, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.248840544483848e-06, + "loss": 3.3528, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.240470975777059e-06, + "loss": 3.3441, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.232085028266539e-06, + "loss": 3.3396, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.22369908075602e-06, + "loss": 3.3616, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.2153131332455e-06, + "loss": 3.3608, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.20694356453871e-06, + "loss": 3.3469, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.198557617028191e-06, + "loss": 3.3428, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.190171669517671e-06, + "loss": 3.3448, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.18178572200715e-06, + "loss": 3.3555, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.17339977449663e-06, + "loss": 3.3561, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.165013826986111e-06, + "loss": 3.3553, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.156627879475591e-06, + "loss": 3.362, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.14824193196507e-06, + "loss": 3.357, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.139872363258282e-06, + "loss": 3.3635, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.131486415747762e-06, + "loss": 3.3499, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.12310046823724e-06, + "loss": 3.3561, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.114714520726722e-06, + "loss": 3.3616, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.106344952019933e-06, + "loss": 3.3457, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.097959004509413e-06, + "loss": 3.3604, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.089573056998893e-06, + "loss": 3.3616, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.081187109488372e-06, + "loss": 3.3638, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.072817540781583e-06, + "loss": 3.344, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.064431593271065e-06, + "loss": 3.3392, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.056062024564274e-06, + "loss": 3.3513, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.047676077053756e-06, + "loss": 3.3546, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.039290129543236e-06, + "loss": 3.3562, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.030904182032714e-06, + "loss": 3.3521, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.022518234522194e-06, + "loss": 3.3542, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.014132287011675e-06, + "loss": 3.3501, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.005762718304886e-06, + "loss": 3.3424, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.997376770794365e-06, + "loss": 3.3535, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.988990823283846e-06, + "loss": 3.3539, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.980604875773326e-06, + "loss": 3.3625, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.972218928262804e-06, + "loss": 3.3656, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.963832980752284e-06, + "loss": 3.3609, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.955447033241766e-06, + "loss": 3.3472, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.947061085731246e-06, + "loss": 3.3553, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.938691517024457e-06, + "loss": 3.348, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.930305569513937e-06, + "loss": 3.3607, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.921919622003417e-06, + "loss": 3.35, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.913533674492895e-06, + "loss": 3.3471, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.905164105786107e-06, + "loss": 3.3459, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.896778158275587e-06, + "loss": 3.3593, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.888392210765067e-06, + "loss": 3.336, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.880006263254547e-06, + "loss": 3.3553, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.871636694547758e-06, + "loss": 3.3547, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.863250747037238e-06, + "loss": 3.3462, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.85486479952672e-06, + "loss": 3.3478, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.846478852016198e-06, + "loss": 3.3602, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.83810928330941e-06, + "loss": 3.3474, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.82972333579889e-06, + "loss": 3.3537, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.821337388288369e-06, + "loss": 3.359, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.812951440777849e-06, + "loss": 3.3489, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.804581872071061e-06, + "loss": 3.3568, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.796195924560541e-06, + "loss": 3.37, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.78780997705002e-06, + "loss": 3.3482, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.779424029539501e-06, + "loss": 3.3519, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.771054460832712e-06, + "loss": 3.3516, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.762668513322192e-06, + "loss": 3.3511, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.754298944615402e-06, + "loss": 3.3454, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.745912997104882e-06, + "loss": 3.3479, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.737527049594364e-06, + "loss": 3.3491, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.729141102083842e-06, + "loss": 3.3645, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.720755154573322e-06, + "loss": 3.356, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.712369207062802e-06, + "loss": 3.3534, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.703983259552284e-06, + "loss": 3.346, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.695613690845493e-06, + "loss": 3.3471, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.687227743334973e-06, + "loss": 3.3523, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.678841795824455e-06, + "loss": 3.3649, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.670455848313933e-06, + "loss": 3.3657, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.662069900803413e-06, + "loss": 3.3423, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.653683953292893e-06, + "loss": 3.3487, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.645298005782374e-06, + "loss": 3.3604, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.636912058271853e-06, + "loss": 3.3511, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.628542489565064e-06, + "loss": 3.3587, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.620156542054545e-06, + "loss": 3.347, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.611770594544023e-06, + "loss": 3.3638, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.603384647033504e-06, + "loss": 3.3616, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.595015078326716e-06, + "loss": 3.3539, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.586629130816196e-06, + "loss": 3.3557, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.578243183305675e-06, + "loss": 3.3565, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.569857235795155e-06, + "loss": 3.3474, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.561487667088367e-06, + "loss": 3.3509, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.553101719577846e-06, + "loss": 3.3642, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.544732150871057e-06, + "loss": 3.3474, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.536346203360538e-06, + "loss": 3.356, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.527960255850018e-06, + "loss": 3.352, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.519574308339497e-06, + "loss": 3.3484, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.888969659805298, + "eval_runtime": 304.2467, + "eval_samples_per_second": 1254.216, + "eval_steps_per_second": 39.195, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.511188360828977e-06, + "loss": 3.3456, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.502802413318458e-06, + "loss": 3.3486, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.494416465807937e-06, + "loss": 3.3597, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.486030518297417e-06, + "loss": 3.3434, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.4776609495906286e-06, + "loss": 3.3674, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.4692750020801085e-06, + "loss": 3.3455, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.460889054569588e-06, + "loss": 3.36, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.4525031070590684e-06, + "loss": 3.3437, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.444149917156011e-06, + "loss": 3.3559, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.435763969645492e-06, + "loss": 3.3564, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.42737802213497e-06, + "loss": 3.3497, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.418992074624451e-06, + "loss": 3.3609, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.410606127113931e-06, + "loss": 3.3424, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.40222017960341e-06, + "loss": 3.3435, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.393834232092891e-06, + "loss": 3.3458, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.385448284582371e-06, + "loss": 3.3409, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.377078715875582e-06, + "loss": 3.3464, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.368709147168792e-06, + "loss": 3.3476, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.360323199658273e-06, + "loss": 3.3497, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.351937252147753e-06, + "loss": 3.3729, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.343551304637234e-06, + "loss": 3.3565, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.335165357126712e-06, + "loss": 3.3571, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.326779409616193e-06, + "loss": 3.3533, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.318393462105673e-06, + "loss": 3.3586, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.310007514595152e-06, + "loss": 3.3492, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.3016379458883635e-06, + "loss": 3.3494, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.2932519983778435e-06, + "loss": 3.3532, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.284866050867324e-06, + "loss": 3.3469, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.276480103356803e-06, + "loss": 3.3327, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.268110534650015e-06, + "loss": 3.3498, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.259724587139495e-06, + "loss": 3.3556, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.251338639628974e-06, + "loss": 3.3539, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.242952692118454e-06, + "loss": 3.3538, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.234583123411666e-06, + "loss": 3.3566, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.2261971759011465e-06, + "loss": 3.3427, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.2178112283906256e-06, + "loss": 3.3457, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.2094252808801055e-06, + "loss": 3.3406, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.201055712173317e-06, + "loss": 3.3483, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.192669764662797e-06, + "loss": 3.3431, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.184283817152276e-06, + "loss": 3.3442, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.175897869641757e-06, + "loss": 3.3484, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.167528300934969e-06, + "loss": 3.3581, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.159142353424447e-06, + "loss": 3.3483, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.150756405913928e-06, + "loss": 3.3473, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.142370458403408e-06, + "loss": 3.3548, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.134000889696619e-06, + "loss": 3.3405, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.1256149421860984e-06, + "loss": 3.3478, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.117228994675578e-06, + "loss": 3.343, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.108843047165059e-06, + "loss": 3.3359, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.100473478458271e-06, + "loss": 3.3509, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.09208753094775e-06, + "loss": 3.3445, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.08370158343723e-06, + "loss": 3.3432, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.0753320147304415e-06, + "loss": 3.3373, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.066946067219921e-06, + "loss": 3.3414, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.058560119709401e-06, + "loss": 3.328, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.050174172198881e-06, + "loss": 3.3539, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.041804603492093e-06, + "loss": 3.3453, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.033418655981572e-06, + "loss": 3.3517, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.025032708471052e-06, + "loss": 3.3516, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.016646760960532e-06, + "loss": 3.3399, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.008277192253744e-06, + "loss": 3.3331, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.999891244743223e-06, + "loss": 3.3501, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.991505297232704e-06, + "loss": 3.3333, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.9831193497221836e-06, + "loss": 3.3316, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.9747497810153935e-06, + "loss": 3.352, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.966363833504874e-06, + "loss": 3.3524, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.957977885994354e-06, + "loss": 3.3366, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.949591938483833e-06, + "loss": 3.3345, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.941222369777045e-06, + "loss": 3.336, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.932836422266526e-06, + "loss": 3.3434, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.924450474756006e-06, + "loss": 3.3494, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.916064527245485e-06, + "loss": 3.3453, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.9076949585386965e-06, + "loss": 3.3557, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.8993090110281765e-06, + "loss": 3.3442, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.890923063517657e-06, + "loss": 3.3561, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.8825371160071355e-06, + "loss": 3.344, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.874167547300347e-06, + "loss": 3.3469, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.865781599789828e-06, + "loss": 3.3517, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.857395652279307e-06, + "loss": 3.3356, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.849009704768787e-06, + "loss": 3.3498, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.840640136061999e-06, + "loss": 3.357, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.832254188551479e-06, + "loss": 3.3532, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.823868241040958e-06, + "loss": 3.335, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.8154822935304385e-06, + "loss": 3.3287, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.80711272482365e-06, + "loss": 3.3425, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.798743156116862e-06, + "loss": 3.3421, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.79035720860634e-06, + "loss": 3.3517, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.781971261095821e-06, + "loss": 3.3432, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.773585313585301e-06, + "loss": 3.3489, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.76519936607478e-06, + "loss": 3.3403, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.756813418564261e-06, + "loss": 3.3323, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.748427471053741e-06, + "loss": 3.346, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.740057902346952e-06, + "loss": 3.3412, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.7316719548364315e-06, + "loss": 3.3569, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.723286007325911e-06, + "loss": 3.3571, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.714900059815392e-06, + "loss": 3.35, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.706530491108604e-06, + "loss": 3.3358, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.698144543598082e-06, + "loss": 3.3489, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.689758596087563e-06, + "loss": 3.3393, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.681372648577043e-06, + "loss": 3.3511, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.673003079870254e-06, + "loss": 3.3397, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.664617132359734e-06, + "loss": 3.3428, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.6562311848492136e-06, + "loss": 3.3343, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.647845237338694e-06, + "loss": 3.3491, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.639475668631904e-06, + "loss": 3.3259, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.631089721121385e-06, + "loss": 3.3483, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.622703773610865e-06, + "loss": 3.3395, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.614317826100344e-06, + "loss": 3.3426, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.605948257393556e-06, + "loss": 3.3389, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.597562309883036e-06, + "loss": 3.3499, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.589176362372517e-06, + "loss": 3.3429, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.580790414861996e-06, + "loss": 3.3421, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.572420846155207e-06, + "loss": 3.3516, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.564034898644687e-06, + "loss": 3.3357, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.555648951134167e-06, + "loss": 3.3527, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.547263003623646e-06, + "loss": 3.3634, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.538893434916858e-06, + "loss": 3.3396, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.530507487406339e-06, + "loss": 3.3417, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.522121539895817e-06, + "loss": 3.3418, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.513735592385298e-06, + "loss": 3.3424, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.50538240248224e-06, + "loss": 3.338, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.496996454971721e-06, + "loss": 3.3389, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.4886105074612e-06, + "loss": 3.3395, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.48022455995068e-06, + "loss": 3.3528, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.471838612440161e-06, + "loss": 3.3461, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.463452664929641e-06, + "loss": 3.345, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.45506671741912e-06, + "loss": 3.335, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.446697148712332e-06, + "loss": 3.3404, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.438311201201812e-06, + "loss": 3.3388, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.429925253691291e-06, + "loss": 3.3582, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.421539306180771e-06, + "loss": 3.3573, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.4131533586702515e-06, + "loss": 3.3396, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.4047674111597315e-06, + "loss": 3.3379, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.396381463649211e-06, + "loss": 3.3518, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.3879955161386905e-06, + "loss": 3.3411, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.379625947431902e-06, + "loss": 3.3524, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.371239999921381e-06, + "loss": 3.3354, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.362854052410862e-06, + "loss": 3.3561, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.354468104900342e-06, + "loss": 3.3474, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.346098536193554e-06, + "loss": 3.3488, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.337712588683033e-06, + "loss": 3.3469, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.329326641172513e-06, + "loss": 3.346, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.3209406936619936e-06, + "loss": 3.3384, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.3125711249552035e-06, + "loss": 3.3449, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.304185177444684e-06, + "loss": 3.3527, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.295799229934164e-06, + "loss": 3.3436, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.287413282423644e-06, + "loss": 3.3437, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.279043713716855e-06, + "loss": 3.342, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.270657766206335e-06, + "loss": 3.34, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.889561176300049, + "eval_runtime": 304.7477, + "eval_samples_per_second": 1252.154, + "eval_steps_per_second": 39.131, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.262271818695816e-06, + "loss": 3.3351, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.253885871185294e-06, + "loss": 3.3381, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.245499923674775e-06, + "loss": 3.3522, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.237113976164255e-06, + "loss": 3.3357, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.2287444074574656e-06, + "loss": 3.3633, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.220358459946946e-06, + "loss": 3.3324, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.2119725124364255e-06, + "loss": 3.3529, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.203586564925906e-06, + "loss": 3.3388, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.195233375022849e-06, + "loss": 3.3443, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.186847427512329e-06, + "loss": 3.3453, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.178461480001809e-06, + "loss": 3.3383, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.170075532491289e-06, + "loss": 3.3487, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.161689584980769e-06, + "loss": 3.3358, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.153303637470248e-06, + "loss": 3.3335, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.1449176899597285e-06, + "loss": 3.3405, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.136531742449208e-06, + "loss": 3.331, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.128162173742419e-06, + "loss": 3.3367, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.119792605035631e-06, + "loss": 3.338, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.111406657525111e-06, + "loss": 3.338, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.103020710014591e-06, + "loss": 3.3628, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.094634762504071e-06, + "loss": 3.3489, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.086248814993551e-06, + "loss": 3.3508, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.07786286748303e-06, + "loss": 3.3414, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.069476919972511e-06, + "loss": 3.3489, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.06109097246199e-06, + "loss": 3.3408, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.052721403755201e-06, + "loss": 3.3432, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.044335456244681e-06, + "loss": 3.3455, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.035949508734161e-06, + "loss": 3.3359, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.027563561223641e-06, + "loss": 3.3297, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.019193992516852e-06, + "loss": 3.3356, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.010808045006333e-06, + "loss": 3.3477, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.002438476299544e-06, + "loss": 3.3443, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.9940525287890236e-06, + "loss": 3.348, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.9856665812785035e-06, + "loss": 3.349, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.9772806337679835e-06, + "loss": 3.3294, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.9688946862574634e-06, + "loss": 3.3367, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.9605087387469425e-06, + "loss": 3.3339, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.952122791236423e-06, + "loss": 3.3353, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.9437368437259024e-06, + "loss": 3.3364, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.935367275019114e-06, + "loss": 3.3335, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.926981327508594e-06, + "loss": 3.3412, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.918595379998074e-06, + "loss": 3.3467, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.910209432487554e-06, + "loss": 3.3432, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.901839863780766e-06, + "loss": 3.3355, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.8934539162702455e-06, + "loss": 3.3458, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.885067968759725e-06, + "loss": 3.3346, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.8766820212492055e-06, + "loss": 3.3386, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.8682960737386846e-06, + "loss": 3.334, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.859910126228165e-06, + "loss": 3.3252, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.8515241787176445e-06, + "loss": 3.3454, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.8431382312071244e-06, + "loss": 3.335, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.834768662500336e-06, + "loss": 3.337, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.826382714989816e-06, + "loss": 3.3275, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.817996767479296e-06, + "loss": 3.3309, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.809610819968776e-06, + "loss": 3.3195, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.8012412512619876e-06, + "loss": 3.342, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.792855303751467e-06, + "loss": 3.3394, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.7844693562409475e-06, + "loss": 3.34, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.776083408730427e-06, + "loss": 3.3433, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.767713840023638e-06, + "loss": 3.3318, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.759327892513118e-06, + "loss": 3.3234, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.750941945002597e-06, + "loss": 3.3404, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.742555997492078e-06, + "loss": 3.3239, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.734186428785289e-06, + "loss": 3.3242, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.725800481274769e-06, + "loss": 3.3419, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.717414533764249e-06, + "loss": 3.3425, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.70902858625373e-06, + "loss": 3.33, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.70065901754694e-06, + "loss": 3.3264, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.69227307003642e-06, + "loss": 3.3245, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.6838871225259e-06, + "loss": 3.3283, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.675517553819112e-06, + "loss": 3.341, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.667131606308591e-06, + "loss": 3.3386, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.658745658798071e-06, + "loss": 3.3459, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.650359711287551e-06, + "loss": 3.3335, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.641990142580763e-06, + "loss": 3.3514, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.6336041950702426e-06, + "loss": 3.3325, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.6252182475597225e-06, + "loss": 3.342, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.6168323000492025e-06, + "loss": 3.3398, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.608462731342413e-06, + "loss": 3.3236, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.600076783831894e-06, + "loss": 3.3459, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.591690836321373e-06, + "loss": 3.3464, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.583304888810853e-06, + "loss": 3.34, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.574935320104065e-06, + "loss": 3.3296, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.566549372593544e-06, + "loss": 3.3224, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.558163425083025e-06, + "loss": 3.3351, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.5497938563762355e-06, + "loss": 3.3342, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.541407908865716e-06, + "loss": 3.3424, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.533021961355195e-06, + "loss": 3.3292, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.524636013844676e-06, + "loss": 3.3418, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.516250066334155e-06, + "loss": 3.3334, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.507864118823635e-06, + "loss": 3.3293, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.499478171313115e-06, + "loss": 3.332, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.491108602606326e-06, + "loss": 3.3306, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.482722655095807e-06, + "loss": 3.3504, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.474336707585286e-06, + "loss": 3.3458, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.465950760074767e-06, + "loss": 3.3434, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.4575811913679775e-06, + "loss": 3.324, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.4491952438574574e-06, + "loss": 3.3415, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.440809296346937e-06, + "loss": 3.3316, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.432423348836417e-06, + "loss": 3.3394, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.424053780129629e-06, + "loss": 3.3293, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.415667832619108e-06, + "loss": 3.3323, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.407281885108589e-06, + "loss": 3.3276, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.398895937598068e-06, + "loss": 3.3413, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.39052636889128e-06, + "loss": 3.3188, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.38214042138076e-06, + "loss": 3.3363, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.3737544738702396e-06, + "loss": 3.3303, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.3653685263597195e-06, + "loss": 3.3327, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.35699895765293e-06, + "loss": 3.33, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.348613010142411e-06, + "loss": 3.3429, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.34022706263189e-06, + "loss": 3.3311, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.331841115121371e-06, + "loss": 3.3328, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.323471546414582e-06, + "loss": 3.3441, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.315085598904062e-06, + "loss": 3.3318, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.306699651393542e-06, + "loss": 3.3399, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.298313703883021e-06, + "loss": 3.35, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.2899441351762325e-06, + "loss": 3.3329, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.2815581876657124e-06, + "loss": 3.3353, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.273172240155192e-06, + "loss": 3.3311, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.264786292644672e-06, + "loss": 3.333, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.256416723937884e-06, + "loss": 3.331, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.248030776427364e-06, + "loss": 3.3346, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.239644828916844e-06, + "loss": 3.3248, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.231275260210055e-06, + "loss": 3.3428, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.2228893126995355e-06, + "loss": 3.3418, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.214503365189015e-06, + "loss": 3.3366, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.2061174176784945e-06, + "loss": 3.3249, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.1977314701679745e-06, + "loss": 3.3341, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.189361901461186e-06, + "loss": 3.3319, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.180975953950666e-06, + "loss": 3.3435, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.172590006440146e-06, + "loss": 3.3507, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.164204058929626e-06, + "loss": 3.3347, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.155818111419106e-06, + "loss": 3.3242, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.147432163908585e-06, + "loss": 3.3415, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.139046216398066e-06, + "loss": 3.3287, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.130676647691277e-06, + "loss": 3.3434, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.122290700180757e-06, + "loss": 3.3275, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.113904752670237e-06, + "loss": 3.344, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.1055188051597165e-06, + "loss": 3.3408, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.097149236452927e-06, + "loss": 3.3441, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.088763288942408e-06, + "loss": 3.3385, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.080377341431888e-06, + "loss": 3.335, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.071991393921367e-06, + "loss": 3.3298, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.063621825214579e-06, + "loss": 3.3336, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.055235877704059e-06, + "loss": 3.3414, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.046849930193539e-06, + "loss": 3.3381, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.038463982683019e-06, + "loss": 3.3327, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.03009441397623e-06, + "loss": 3.3372, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.0217084664657094e-06, + "loss": 3.3287, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.888798475265503, + "eval_runtime": 308.3869, + "eval_samples_per_second": 1237.378, + "eval_steps_per_second": 38.669, + "step": 2747520 + }, + { + "epoch": 1.0, + "learning_rate": 5.01332251895519e-06, + "loss": 3.3301, + "step": 2747904 + }, + { + "epoch": 1.0, + "learning_rate": 5.004936571444669e-06, + "loss": 3.3313, + "step": 2748416 + }, + { + "epoch": 1.0, + "learning_rate": 4.996567002737881e-06, + "loss": 3.3405, + "step": 2748928 + }, + { + "epoch": 1.0, + "learning_rate": 4.988181055227361e-06, + "loss": 3.3324, + "step": 2749440 + }, + { + "epoch": 1.0, + "learning_rate": 4.979795107716841e-06, + "loss": 3.3492, + "step": 2749952 + }, + { + "epoch": 1.0, + "learning_rate": 4.971409160206321e-06, + "loss": 3.3305, + "step": 2750464 + }, + { + "epoch": 1.0, + "learning_rate": 4.963039591499532e-06, + "loss": 3.3379, + "step": 2750976 + }, + { + "epoch": 1.0, + "learning_rate": 4.9546536439890125e-06, + "loss": 3.3319, + "step": 2751488 + }, + { + "epoch": 1.0, + "learning_rate": 4.946284075282223e-06, + "loss": 3.3356, + "step": 2752000 + }, + { + "epoch": 1.0, + "learning_rate": 4.937898127771703e-06, + "loss": 3.3365, + "step": 2752512 + }, + { + "epoch": 1.0, + "learning_rate": 4.929512180261183e-06, + "loss": 3.3324, + "step": 2753024 + }, + { + "epoch": 1.0, + "learning_rate": 4.921126232750663e-06, + "loss": 3.3397, + "step": 2753536 + }, + { + "epoch": 1.0, + "learning_rate": 4.912740285240143e-06, + "loss": 3.3286, + "step": 2754048 + }, + { + "epoch": 1.0, + "learning_rate": 4.904354337729623e-06, + "loss": 3.3246, + "step": 2754560 + }, + { + "epoch": 1.0, + "learning_rate": 4.895968390219103e-06, + "loss": 3.3314, + "step": 2755072 + }, + { + "epoch": 1.0, + "learning_rate": 4.887582442708583e-06, + "loss": 3.3235, + "step": 2755584 + }, + { + "epoch": 1.0, + "learning_rate": 4.8792128740017946e-06, + "loss": 3.329, + "step": 2756096 + }, + { + "epoch": 1.0, + "learning_rate": 4.870843305295005e-06, + "loss": 3.3311, + "step": 2756608 + }, + { + "epoch": 1.0, + "learning_rate": 4.862457357784485e-06, + "loss": 3.3294, + "step": 2757120 + }, + { + "epoch": 1.0, + "learning_rate": 4.854071410273965e-06, + "loss": 3.3529, + "step": 2757632 + }, + { + "epoch": 1.0, + "learning_rate": 4.845685462763445e-06, + "loss": 3.3397, + "step": 2758144 + }, + { + "epoch": 1.0, + "learning_rate": 4.837299515252925e-06, + "loss": 3.3419, + "step": 2758656 + }, + { + "epoch": 1.0, + "learning_rate": 4.828913567742404e-06, + "loss": 3.3356, + "step": 2759168 + }, + { + "epoch": 1.0, + "learning_rate": 4.820527620231885e-06, + "loss": 3.3404, + "step": 2759680 + }, + { + "epoch": 1.0, + "learning_rate": 4.812141672721364e-06, + "loss": 3.3308, + "step": 2760192 + }, + { + "epoch": 1.0, + "learning_rate": 4.803772104014576e-06, + "loss": 3.3389, + "step": 2760704 + }, + { + "epoch": 1.0, + "learning_rate": 4.795386156504056e-06, + "loss": 3.3335, + "step": 2761216 + }, + { + "epoch": 1.0, + "learning_rate": 4.787000208993537e-06, + "loss": 3.3293, + "step": 2761728 + }, + { + "epoch": 1.0, + "learning_rate": 4.778614261483016e-06, + "loss": 3.3254, + "step": 2762240 + }, + { + "epoch": 1.0, + "learning_rate": 4.770244692776227e-06, + "loss": 3.3286, + "step": 2762752 + }, + { + "epoch": 1.01, + "learning_rate": 4.761858745265707e-06, + "loss": 3.3342, + "step": 2763264 + }, + { + "epoch": 1.01, + "learning_rate": 4.753489176558919e-06, + "loss": 3.3363, + "step": 2763776 + }, + { + "epoch": 1.01, + "learning_rate": 4.745103229048398e-06, + "loss": 3.3363, + "step": 2764288 + }, + { + "epoch": 1.01, + "learning_rate": 4.736717281537878e-06, + "loss": 3.341, + "step": 2764800 + }, + { + "epoch": 1.01, + "learning_rate": 4.728331334027358e-06, + "loss": 3.3198, + "step": 2765312 + }, + { + "epoch": 1.01, + "learning_rate": 4.719945386516838e-06, + "loss": 3.3302, + "step": 2765824 + }, + { + "epoch": 1.01, + "learning_rate": 4.711559439006318e-06, + "loss": 3.3279, + "step": 2766336 + }, + { + "epoch": 1.01, + "learning_rate": 4.703173491495798e-06, + "loss": 3.3264, + "step": 2766848 + }, + { + "epoch": 1.01, + "learning_rate": 4.694787543985278e-06, + "loss": 3.3301, + "step": 2767360 + }, + { + "epoch": 1.01, + "learning_rate": 4.686417975278489e-06, + "loss": 3.3236, + "step": 2767872 + }, + { + "epoch": 1.01, + "learning_rate": 4.6780320277679685e-06, + "loss": 3.3367, + "step": 2768384 + }, + { + "epoch": 1.01, + "learning_rate": 4.669646080257449e-06, + "loss": 3.3371, + "step": 2768896 + }, + { + "epoch": 1.01, + "learning_rate": 4.6612601327469284e-06, + "loss": 3.3342, + "step": 2769408 + }, + { + "epoch": 1.01, + "learning_rate": 4.65289056404014e-06, + "loss": 3.326, + "step": 2769920 + }, + { + "epoch": 1.01, + "learning_rate": 4.64450461652962e-06, + "loss": 3.3403, + "step": 2770432 + }, + { + "epoch": 1.01, + "learning_rate": 4.636118669019099e-06, + "loss": 3.3235, + "step": 2770944 + }, + { + "epoch": 1.01, + "learning_rate": 4.62773272150858e-06, + "loss": 3.334, + "step": 2771456 + }, + { + "epoch": 1.01, + "learning_rate": 4.619363152801791e-06, + "loss": 3.3267, + "step": 2771968 + }, + { + "epoch": 1.01, + "learning_rate": 4.6109772052912715e-06, + "loss": 3.3131, + "step": 2772480 + }, + { + "epoch": 1.01, + "learning_rate": 4.602591257780751e-06, + "loss": 3.3396, + "step": 2772992 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942053102702314e-06, + "loss": 3.3266, + "step": 2773504 + }, + { + "epoch": 1.01, + "learning_rate": 4.585835741563442e-06, + "loss": 3.3275, + "step": 2774016 + }, + { + "epoch": 1.01, + "learning_rate": 4.577449794052922e-06, + "loss": 3.3211, + "step": 2774528 + }, + { + "epoch": 1.01, + "learning_rate": 4.569063846542402e-06, + "loss": 3.3194, + "step": 2775040 + }, + { + "epoch": 1.01, + "learning_rate": 4.560677899031881e-06, + "loss": 3.3151, + "step": 2775552 + }, + { + "epoch": 1.01, + "learning_rate": 4.552308330325093e-06, + "loss": 3.3307, + "step": 2776064 + }, + { + "epoch": 1.01, + "learning_rate": 4.543922382814573e-06, + "loss": 3.3345, + "step": 2776576 + }, + { + "epoch": 1.01, + "learning_rate": 4.535536435304053e-06, + "loss": 3.3315, + "step": 2777088 + }, + { + "epoch": 1.01, + "learning_rate": 4.527150487793533e-06, + "loss": 3.3347, + "step": 2777600 + }, + { + "epoch": 1.01, + "learning_rate": 4.518780919086744e-06, + "loss": 3.3272, + "step": 2778112 + }, + { + "epoch": 1.01, + "learning_rate": 4.510394971576224e-06, + "loss": 3.3114, + "step": 2778624 + }, + { + "epoch": 1.01, + "learning_rate": 4.502009024065704e-06, + "loss": 3.3377, + "step": 2779136 + }, + { + "epoch": 1.01, + "learning_rate": 4.493623076555184e-06, + "loss": 3.3139, + "step": 2779648 + }, + { + "epoch": 1.01, + "learning_rate": 4.485253507848396e-06, + "loss": 3.3101, + "step": 2780160 + }, + { + "epoch": 1.01, + "learning_rate": 4.476867560337875e-06, + "loss": 3.3377, + "step": 2780672 + }, + { + "epoch": 1.01, + "learning_rate": 4.468481612827355e-06, + "loss": 3.3318, + "step": 2781184 + }, + { + "epoch": 1.01, + "learning_rate": 4.460095665316835e-06, + "loss": 3.322, + "step": 2781696 + }, + { + "epoch": 1.01, + "learning_rate": 4.4517260966100466e-06, + "loss": 3.3199, + "step": 2782208 + }, + { + "epoch": 1.01, + "learning_rate": 4.4433401490995265e-06, + "loss": 3.315, + "step": 2782720 + }, + { + "epoch": 1.01, + "learning_rate": 4.4349542015890065e-06, + "loss": 3.32, + "step": 2783232 + }, + { + "epoch": 1.01, + "learning_rate": 4.4265682540784864e-06, + "loss": 3.3357, + "step": 2783744 + }, + { + "epoch": 1.01, + "learning_rate": 4.418198685371697e-06, + "loss": 3.3284, + "step": 2784256 + }, + { + "epoch": 1.01, + "learning_rate": 4.409812737861178e-06, + "loss": 3.3372, + "step": 2784768 + }, + { + "epoch": 1.01, + "learning_rate": 4.401426790350657e-06, + "loss": 3.3254, + "step": 2785280 + }, + { + "epoch": 1.01, + "learning_rate": 4.393040842840137e-06, + "loss": 3.3451, + "step": 2785792 + }, + { + "epoch": 1.01, + "learning_rate": 4.384671274133349e-06, + "loss": 3.3239, + "step": 2786304 + }, + { + "epoch": 1.01, + "learning_rate": 4.376285326622828e-06, + "loss": 3.3346, + "step": 2786816 + }, + { + "epoch": 1.01, + "learning_rate": 4.367899379112309e-06, + "loss": 3.3327, + "step": 2787328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3595298104055194e-06, + "loss": 3.3115, + "step": 2787840 + }, + { + "epoch": 1.01, + "learning_rate": 4.351143862894999e-06, + "loss": 3.3403, + "step": 2788352 + }, + { + "epoch": 1.01, + "learning_rate": 4.342757915384479e-06, + "loss": 3.3357, + "step": 2788864 + }, + { + "epoch": 1.01, + "learning_rate": 4.334371967873959e-06, + "loss": 3.3322, + "step": 2789376 + }, + { + "epoch": 1.01, + "learning_rate": 4.326002399167171e-06, + "loss": 3.3236, + "step": 2789888 + }, + { + "epoch": 1.01, + "learning_rate": 4.317616451656651e-06, + "loss": 3.3132, + "step": 2790400 + }, + { + "epoch": 1.01, + "learning_rate": 4.309230504146131e-06, + "loss": 3.3247, + "step": 2790912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3008609354393425e-06, + "loss": 3.3245, + "step": 2791424 + }, + { + "epoch": 1.01, + "learning_rate": 4.292474987928822e-06, + "loss": 3.3342, + "step": 2791936 + }, + { + "epoch": 1.01, + "learning_rate": 4.2840890404183015e-06, + "loss": 3.3233, + "step": 2792448 + }, + { + "epoch": 1.01, + "learning_rate": 4.2757030929077815e-06, + "loss": 3.3317, + "step": 2792960 + }, + { + "epoch": 1.02, + "learning_rate": 4.2673171453972615e-06, + "loss": 3.3204, + "step": 2793472 + }, + { + "epoch": 1.02, + "learning_rate": 4.258931197886741e-06, + "loss": 3.3254, + "step": 2793984 + }, + { + "epoch": 1.02, + "learning_rate": 4.250545250376221e-06, + "loss": 3.3232, + "step": 2794496 + }, + { + "epoch": 1.02, + "learning_rate": 4.242175681669433e-06, + "loss": 3.3223, + "step": 2795008 + }, + { + "epoch": 1.02, + "learning_rate": 4.233789734158913e-06, + "loss": 3.3387, + "step": 2795520 + }, + { + "epoch": 1.02, + "learning_rate": 4.225403786648392e-06, + "loss": 3.3382, + "step": 2796032 + }, + { + "epoch": 1.02, + "learning_rate": 4.217017839137873e-06, + "loss": 3.3391, + "step": 2796544 + }, + { + "epoch": 1.02, + "learning_rate": 4.208648270431084e-06, + "loss": 3.3157, + "step": 2797056 + }, + { + "epoch": 1.02, + "learning_rate": 4.200262322920564e-06, + "loss": 3.3317, + "step": 2797568 + }, + { + "epoch": 1.02, + "learning_rate": 4.1918763754100436e-06, + "loss": 3.3224, + "step": 2798080 + }, + { + "epoch": 1.02, + "learning_rate": 4.1834904278995235e-06, + "loss": 3.3315, + "step": 2798592 + }, + { + "epoch": 1.02, + "learning_rate": 4.175120859192734e-06, + "loss": 3.3249, + "step": 2799104 + }, + { + "epoch": 1.02, + "learning_rate": 4.166734911682215e-06, + "loss": 3.3232, + "step": 2799616 + }, + { + "epoch": 1.02, + "learning_rate": 4.158348964171695e-06, + "loss": 3.3226, + "step": 2800128 + }, + { + "epoch": 1.02, + "learning_rate": 4.149963016661174e-06, + "loss": 3.3312, + "step": 2800640 + }, + { + "epoch": 1.02, + "learning_rate": 4.141593447954386e-06, + "loss": 3.3131, + "step": 2801152 + }, + { + "epoch": 1.02, + "learning_rate": 4.133207500443866e-06, + "loss": 3.3265, + "step": 2801664 + }, + { + "epoch": 1.02, + "learning_rate": 4.124821552933346e-06, + "loss": 3.3203, + "step": 2802176 + }, + { + "epoch": 1.02, + "learning_rate": 4.116435605422826e-06, + "loss": 3.3291, + "step": 2802688 + }, + { + "epoch": 1.02, + "learning_rate": 4.108066036716037e-06, + "loss": 3.3207, + "step": 2803200 + }, + { + "epoch": 1.02, + "learning_rate": 4.0996800892055164e-06, + "loss": 3.3323, + "step": 2803712 + }, + { + "epoch": 1.02, + "learning_rate": 4.091294141694996e-06, + "loss": 3.3249, + "step": 2804224 + }, + { + "epoch": 1.02, + "learning_rate": 4.082908194184476e-06, + "loss": 3.3245, + "step": 2804736 + }, + { + "epoch": 1.02, + "learning_rate": 4.074538625477688e-06, + "loss": 3.3336, + "step": 2805248 + }, + { + "epoch": 1.02, + "learning_rate": 4.066152677967168e-06, + "loss": 3.3231, + "step": 2805760 + }, + { + "epoch": 1.02, + "learning_rate": 4.057766730456648e-06, + "loss": 3.332, + "step": 2806272 + }, + { + "epoch": 1.02, + "learning_rate": 4.049380782946128e-06, + "loss": 3.3403, + "step": 2806784 + }, + { + "epoch": 1.02, + "learning_rate": 4.041011214239339e-06, + "loss": 3.3239, + "step": 2807296 + }, + { + "epoch": 1.02, + "learning_rate": 4.0326252667288194e-06, + "loss": 3.3242, + "step": 2807808 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242393192182986e-06, + "loss": 3.3261, + "step": 2808320 + }, + { + "epoch": 1.02, + "learning_rate": 4.0158533717077785e-06, + "loss": 3.3234, + "step": 2808832 + }, + { + "epoch": 1.02, + "learning_rate": 4.007500181804722e-06, + "loss": 3.325, + "step": 2809344 + }, + { + "epoch": 1.02, + "learning_rate": 3.999114234294202e-06, + "loss": 3.3241, + "step": 2809856 + }, + { + "epoch": 1.02, + "learning_rate": 3.990728286783682e-06, + "loss": 3.3216, + "step": 2810368 + }, + { + "epoch": 1.02, + "learning_rate": 3.982342339273161e-06, + "loss": 3.3357, + "step": 2810880 + }, + { + "epoch": 1.02, + "learning_rate": 3.973956391762642e-06, + "loss": 3.3301, + "step": 2811392 + }, + { + "epoch": 1.02, + "learning_rate": 3.965570444252121e-06, + "loss": 3.3314, + "step": 2811904 + }, + { + "epoch": 1.02, + "learning_rate": 3.9571844967416016e-06, + "loss": 3.317, + "step": 2812416 + }, + { + "epoch": 1.02, + "learning_rate": 3.948798549231081e-06, + "loss": 3.3208, + "step": 2812928 + }, + { + "epoch": 1.02, + "learning_rate": 3.940428980524292e-06, + "loss": 3.3254, + "step": 2813440 + }, + { + "epoch": 1.02, + "learning_rate": 3.932043033013772e-06, + "loss": 3.3313, + "step": 2813952 + }, + { + "epoch": 1.02, + "learning_rate": 3.923657085503251e-06, + "loss": 3.3371, + "step": 2814464 + }, + { + "epoch": 1.02, + "learning_rate": 3.915271137992732e-06, + "loss": 3.3302, + "step": 2814976 + }, + { + "epoch": 1.02, + "learning_rate": 3.906901569285943e-06, + "loss": 3.3171, + "step": 2815488 + }, + { + "epoch": 1.02, + "learning_rate": 3.898515621775423e-06, + "loss": 3.335, + "step": 2816000 + }, + { + "epoch": 1.02, + "learning_rate": 3.890129674264903e-06, + "loss": 3.3198, + "step": 2816512 + }, + { + "epoch": 1.02, + "learning_rate": 3.881743726754383e-06, + "loss": 3.3356, + "step": 2817024 + }, + { + "epoch": 1.02, + "learning_rate": 3.8733741580475945e-06, + "loss": 3.3188, + "step": 2817536 + }, + { + "epoch": 1.02, + "learning_rate": 3.8649882105370744e-06, + "loss": 3.3372, + "step": 2818048 + }, + { + "epoch": 1.02, + "learning_rate": 3.856602263026554e-06, + "loss": 3.3317, + "step": 2818560 + }, + { + "epoch": 1.02, + "learning_rate": 3.8482163155160335e-06, + "loss": 3.3366, + "step": 2819072 + }, + { + "epoch": 1.02, + "learning_rate": 3.839846746809245e-06, + "loss": 3.3275, + "step": 2819584 + }, + { + "epoch": 1.02, + "learning_rate": 3.831460799298725e-06, + "loss": 3.3265, + "step": 2820096 + }, + { + "epoch": 1.02, + "learning_rate": 3.823074851788205e-06, + "loss": 3.3227, + "step": 2820608 + }, + { + "epoch": 1.02, + "learning_rate": 3.814688904277685e-06, + "loss": 3.3282, + "step": 2821120 + }, + { + "epoch": 1.02, + "learning_rate": 3.8063193355708966e-06, + "loss": 3.3308, + "step": 2821632 + }, + { + "epoch": 1.02, + "learning_rate": 3.797933388060376e-06, + "loss": 3.3316, + "step": 2822144 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895474405498565e-06, + "loss": 3.3261, + "step": 2822656 + }, + { + "epoch": 1.02, + "learning_rate": 3.781161493039336e-06, + "loss": 3.3247, + "step": 2823168 + }, + { + "epoch": 1.02, + "learning_rate": 3.7727919243325477e-06, + "loss": 3.3257, + "step": 2823680 + }, + { + "epoch": 1.03, + "eval_loss": 3.8884074687957764, + "eval_runtime": 311.059, + "eval_samples_per_second": 1226.748, + "eval_steps_per_second": 38.337, + "step": 2823840 + }, + { + "epoch": 0.0, + "learning_rate": 3.7644059768220272e-06, + "loss": 3.3224, + "step": 2824192 + }, + { + "epoch": 0.0, + "learning_rate": 3.756020029311507e-06, + "loss": 3.3195, + "step": 2824704 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476340818009876e-06, + "loss": 3.332, + "step": 2825216 + }, + { + "epoch": 0.0, + "learning_rate": 3.739248134290467e-06, + "loss": 3.322, + "step": 2825728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7308785655836788e-06, + "loss": 3.3397, + "step": 2826240 + }, + { + "epoch": 0.0, + "learning_rate": 3.7224926180731583e-06, + "loss": 3.3239, + "step": 2826752 + }, + { + "epoch": 0.0, + "learning_rate": 3.7141066705626387e-06, + "loss": 3.3258, + "step": 2827264 + }, + { + "epoch": 0.0, + "learning_rate": 3.705720723052118e-06, + "loss": 3.3291, + "step": 2827776 + }, + { + "epoch": 0.0, + "learning_rate": 3.697367533149061e-06, + "loss": 3.3249, + "step": 2828288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6889815856385406e-06, + "loss": 3.3267, + "step": 2828800 + }, + { + "epoch": 0.0, + "learning_rate": 3.680595638128021e-06, + "loss": 3.3283, + "step": 2829312 + }, + { + "epoch": 0.0, + "learning_rate": 3.672209690617501e-06, + "loss": 3.3287, + "step": 2829824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6638237431069805e-06, + "loss": 3.3205, + "step": 2830336 + }, + { + "epoch": 0.0, + "learning_rate": 3.655437795596461e-06, + "loss": 3.3156, + "step": 2830848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6470518480859404e-06, + "loss": 3.3267, + "step": 2831360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6386659005754208e-06, + "loss": 3.31, + "step": 2831872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6302963318686316e-06, + "loss": 3.3191, + "step": 2832384 + }, + { + "epoch": 0.0, + "learning_rate": 3.621910384358112e-06, + "loss": 3.3208, + "step": 2832896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135244368475915e-06, + "loss": 3.3206, + "step": 2833408 + }, + { + "epoch": 0.0, + "learning_rate": 3.605138489337071e-06, + "loss": 3.3442, + "step": 2833920 + }, + { + "epoch": 0.0, + "learning_rate": 3.5967689206302827e-06, + "loss": 3.3346, + "step": 2834432 + }, + { + "epoch": 0.0, + "learning_rate": 3.5883829731197626e-06, + "loss": 3.3344, + "step": 2834944 + }, + { + "epoch": 0.0, + "learning_rate": 3.5799970256092426e-06, + "loss": 3.3249, + "step": 2835456 + }, + { + "epoch": 0.0, + "learning_rate": 3.5716110780987225e-06, + "loss": 3.3295, + "step": 2835968 + }, + { + "epoch": 0.0, + "learning_rate": 3.563241509391934e-06, + "loss": 3.326, + "step": 2836480 + }, + { + "epoch": 0.0, + "learning_rate": 3.5548555618814137e-06, + "loss": 3.3298, + "step": 2836992 + }, + { + "epoch": 0.0, + "learning_rate": 3.546469614370894e-06, + "loss": 3.3221, + "step": 2837504 + }, + { + "epoch": 0.0, + "learning_rate": 3.5380836668603736e-06, + "loss": 3.3223, + "step": 2838016 + }, + { + "epoch": 0.0, + "learning_rate": 3.5297140981535852e-06, + "loss": 3.3173, + "step": 2838528 + }, + { + "epoch": 0.0, + "learning_rate": 3.5213281506430648e-06, + "loss": 3.3184, + "step": 2839040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5129422031325443e-06, + "loss": 3.3214, + "step": 2839552 + }, + { + "epoch": 0.01, + "learning_rate": 3.5045562556220247e-06, + "loss": 3.3312, + "step": 2840064 + }, + { + "epoch": 0.01, + "learning_rate": 3.496186686915236e-06, + "loss": 3.329, + "step": 2840576 + }, + { + "epoch": 0.01, + "learning_rate": 3.4878171182084475e-06, + "loss": 3.333, + "step": 2841088 + }, + { + "epoch": 0.01, + "learning_rate": 3.479431170697927e-06, + "loss": 3.3131, + "step": 2841600 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710452231874074e-06, + "loss": 3.3239, + "step": 2842112 + }, + { + "epoch": 0.01, + "learning_rate": 3.462659275676887e-06, + "loss": 3.3184, + "step": 2842624 + }, + { + "epoch": 0.01, + "learning_rate": 3.4542733281663674e-06, + "loss": 3.3156, + "step": 2843136 + }, + { + "epoch": 0.01, + "learning_rate": 3.445887380655847e-06, + "loss": 3.3257, + "step": 2843648 + }, + { + "epoch": 0.01, + "learning_rate": 3.4375014331453264e-06, + "loss": 3.3094, + "step": 2844160 + }, + { + "epoch": 0.01, + "learning_rate": 3.429115485634807e-06, + "loss": 3.3252, + "step": 2844672 + }, + { + "epoch": 0.01, + "learning_rate": 3.4207459169280176e-06, + "loss": 3.3266, + "step": 2845184 + }, + { + "epoch": 0.01, + "learning_rate": 3.412359969417498e-06, + "loss": 3.3282, + "step": 2845696 + }, + { + "epoch": 0.01, + "learning_rate": 3.4039740219069775e-06, + "loss": 3.3195, + "step": 2846208 + }, + { + "epoch": 0.01, + "learning_rate": 3.3955880743964575e-06, + "loss": 3.3324, + "step": 2846720 + }, + { + "epoch": 0.01, + "learning_rate": 3.387218505689669e-06, + "loss": 3.3128, + "step": 2847232 + }, + { + "epoch": 0.01, + "learning_rate": 3.3788325581791486e-06, + "loss": 3.3276, + "step": 2847744 + }, + { + "epoch": 0.01, + "learning_rate": 3.370446610668629e-06, + "loss": 3.3167, + "step": 2848256 + }, + { + "epoch": 0.01, + "learning_rate": 3.3620606631581085e-06, + "loss": 3.3001, + "step": 2848768 + }, + { + "epoch": 0.01, + "learning_rate": 3.35369109445132e-06, + "loss": 3.3352, + "step": 2849280 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453051469407997e-06, + "loss": 3.3156, + "step": 2849792 + }, + { + "epoch": 0.01, + "learning_rate": 3.33691919943028e-06, + "loss": 3.3261, + "step": 2850304 + }, + { + "epoch": 0.01, + "learning_rate": 3.3285332519197596e-06, + "loss": 3.3111, + "step": 2850816 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201636832129713e-06, + "loss": 3.312, + "step": 2851328 + }, + { + "epoch": 0.01, + "learning_rate": 3.311777735702451e-06, + "loss": 3.3101, + "step": 2851840 + }, + { + "epoch": 0.01, + "learning_rate": 3.3033917881919307e-06, + "loss": 3.3167, + "step": 2852352 + }, + { + "epoch": 0.01, + "learning_rate": 3.2950058406814107e-06, + "loss": 3.3281, + "step": 2852864 + }, + { + "epoch": 0.01, + "learning_rate": 3.286636271974622e-06, + "loss": 3.3203, + "step": 2853376 + }, + { + "epoch": 0.01, + "learning_rate": 3.2782503244641023e-06, + "loss": 3.3307, + "step": 2853888 + }, + { + "epoch": 0.01, + "learning_rate": 3.269864376953582e-06, + "loss": 3.3173, + "step": 2854400 + }, + { + "epoch": 0.01, + "learning_rate": 3.261478429443062e-06, + "loss": 3.3069, + "step": 2854912 + }, + { + "epoch": 0.01, + "learning_rate": 3.253108860736273e-06, + "loss": 3.328, + "step": 2855424 + }, + { + "epoch": 0.01, + "learning_rate": 3.2447229132257534e-06, + "loss": 3.3021, + "step": 2855936 + }, + { + "epoch": 0.01, + "learning_rate": 3.236336965715233e-06, + "loss": 3.3043, + "step": 2856448 + }, + { + "epoch": 0.01, + "learning_rate": 3.2279510182047124e-06, + "loss": 3.3294, + "step": 2856960 + }, + { + "epoch": 0.01, + "learning_rate": 3.219581449497924e-06, + "loss": 3.3234, + "step": 2857472 + }, + { + "epoch": 0.01, + "learning_rate": 3.211195501987404e-06, + "loss": 3.3135, + "step": 2857984 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028095544768844e-06, + "loss": 3.3125, + "step": 2858496 + }, + { + "epoch": 0.01, + "learning_rate": 3.194423606966364e-06, + "loss": 3.3075, + "step": 2859008 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860540382595756e-06, + "loss": 3.3119, + "step": 2859520 + }, + { + "epoch": 0.01, + "learning_rate": 3.177668090749055e-06, + "loss": 3.3287, + "step": 2860032 + }, + { + "epoch": 0.01, + "learning_rate": 3.1692821432385355e-06, + "loss": 3.3194, + "step": 2860544 + }, + { + "epoch": 0.01, + "learning_rate": 3.160896195728015e-06, + "loss": 3.3275, + "step": 2861056 + }, + { + "epoch": 0.01, + "learning_rate": 3.1525266270212267e-06, + "loss": 3.3208, + "step": 2861568 + }, + { + "epoch": 0.01, + "learning_rate": 3.144140679510706e-06, + "loss": 3.3355, + "step": 2862080 + }, + { + "epoch": 0.01, + "learning_rate": 3.1357547320001857e-06, + "loss": 3.3165, + "step": 2862592 + }, + { + "epoch": 0.01, + "learning_rate": 3.127368784489666e-06, + "loss": 3.3257, + "step": 2863104 + }, + { + "epoch": 0.01, + "learning_rate": 3.1189992157828777e-06, + "loss": 3.322, + "step": 2863616 + }, + { + "epoch": 0.01, + "learning_rate": 3.1106132682723577e-06, + "loss": 3.3049, + "step": 2864128 + }, + { + "epoch": 0.01, + "learning_rate": 3.1022273207618372e-06, + "loss": 3.33, + "step": 2864640 + }, + { + "epoch": 0.01, + "learning_rate": 3.093857752055049e-06, + "loss": 3.3287, + "step": 2865152 + }, + { + "epoch": 0.01, + "learning_rate": 3.0854718045445284e-06, + "loss": 3.322, + "step": 2865664 + }, + { + "epoch": 0.01, + "learning_rate": 3.0770858570340084e-06, + "loss": 3.3184, + "step": 2866176 + }, + { + "epoch": 0.01, + "learning_rate": 3.0686999095234883e-06, + "loss": 3.3088, + "step": 2866688 + }, + { + "epoch": 0.01, + "learning_rate": 3.0603303408166995e-06, + "loss": 3.3118, + "step": 2867200 + }, + { + "epoch": 0.01, + "learning_rate": 3.051960772109911e-06, + "loss": 3.3175, + "step": 2867712 + }, + { + "epoch": 0.01, + "learning_rate": 3.043574824599391e-06, + "loss": 3.3251, + "step": 2868224 + }, + { + "epoch": 0.01, + "learning_rate": 3.035188877088871e-06, + "loss": 3.3128, + "step": 2868736 + }, + { + "epoch": 0.01, + "learning_rate": 3.026802929578351e-06, + "loss": 3.3223, + "step": 2869248 + }, + { + "epoch": 0.02, + "learning_rate": 3.018416982067831e-06, + "loss": 3.313, + "step": 2869760 + }, + { + "epoch": 0.02, + "learning_rate": 3.010047413361042e-06, + "loss": 3.3203, + "step": 2870272 + }, + { + "epoch": 0.02, + "learning_rate": 3.001661465850522e-06, + "loss": 3.3145, + "step": 2870784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9932755183400017e-06, + "loss": 3.316, + "step": 2871296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9848895708294816e-06, + "loss": 3.3291, + "step": 2871808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9765036233189616e-06, + "loss": 3.3287, + "step": 2872320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9681176758084416e-06, + "loss": 3.3317, + "step": 2872832 + }, + { + "epoch": 0.02, + "learning_rate": 2.959731728297921e-06, + "loss": 3.3042, + "step": 2873344 + }, + { + "epoch": 0.02, + "learning_rate": 2.951345780787401e-06, + "loss": 3.327, + "step": 2873856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9429762120806127e-06, + "loss": 3.3117, + "step": 2874368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9345902645700926e-06, + "loss": 3.3268, + "step": 2874880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9262043170595726e-06, + "loss": 3.3139, + "step": 2875392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178183695490526e-06, + "loss": 3.3188, + "step": 2875904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094488008422638e-06, + "loss": 3.3121, + "step": 2876416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010628533317437e-06, + "loss": 3.3211, + "step": 2876928 + }, + { + "epoch": 0.02, + "learning_rate": 2.8926769058212237e-06, + "loss": 3.3051, + "step": 2877440 + }, + { + "epoch": 0.02, + "learning_rate": 2.884290958310703e-06, + "loss": 3.322, + "step": 2877952 + }, + { + "epoch": 0.02, + "learning_rate": 2.875921389603915e-06, + "loss": 3.3098, + "step": 2878464 + }, + { + "epoch": 0.02, + "learning_rate": 2.8675354420933944e-06, + "loss": 3.3246, + "step": 2878976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8591494945828743e-06, + "loss": 3.3177, + "step": 2879488 + }, + { + "epoch": 0.02, + "learning_rate": 2.8507635470723543e-06, + "loss": 3.3191, + "step": 2880000 + }, + { + "epoch": 0.02, + "learning_rate": 2.842393978365566e-06, + "loss": 3.3178, + "step": 2880512 + }, + { + "epoch": 0.02, + "learning_rate": 2.834008030855046e-06, + "loss": 3.3231, + "step": 2881024 + }, + { + "epoch": 0.02, + "learning_rate": 2.825622083344526e-06, + "loss": 3.3236, + "step": 2881536 + }, + { + "epoch": 0.02, + "learning_rate": 2.817236135834006e-06, + "loss": 3.3184, + "step": 2882048 + }, + { + "epoch": 0.02, + "learning_rate": 2.808866567127217e-06, + "loss": 3.3206, + "step": 2882560 + }, + { + "epoch": 0.02, + "learning_rate": 2.800480619616697e-06, + "loss": 3.336, + "step": 2883072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7920946721061765e-06, + "loss": 3.3177, + "step": 2883584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837087245956565e-06, + "loss": 3.3135, + "step": 2884096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753391558888677e-06, + "loss": 3.3201, + "step": 2884608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669532083783476e-06, + "loss": 3.3177, + "step": 2885120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585836396715593e-06, + "loss": 3.3096, + "step": 2885632 + }, + { + "epoch": 0.02, + "learning_rate": 2.7501976921610392e-06, + "loss": 3.3199, + "step": 2886144 + }, + { + "epoch": 0.02, + "learning_rate": 2.741811744650519e-06, + "loss": 3.3125, + "step": 2886656 + }, + { + "epoch": 0.02, + "learning_rate": 2.733425797139999e-06, + "loss": 3.3257, + "step": 2887168 + }, + { + "epoch": 0.02, + "learning_rate": 2.725039849629479e-06, + "loss": 3.3252, + "step": 2887680 + }, + { + "epoch": 0.02, + "learning_rate": 2.7166539021189586e-06, + "loss": 3.3196, + "step": 2888192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7082679546084386e-06, + "loss": 3.3118, + "step": 2888704 + }, + { + "epoch": 0.02, + "learning_rate": 2.6998820070979185e-06, + "loss": 3.3132, + "step": 2889216 + }, + { + "epoch": 0.02, + "learning_rate": 2.6915124383911297e-06, + "loss": 3.3206, + "step": 2889728 + }, + { + "epoch": 0.02, + "learning_rate": 2.6831264908806097e-06, + "loss": 3.3258, + "step": 2890240 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747405433700897e-06, + "loss": 3.3247, + "step": 2890752 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663545958595696e-06, + "loss": 3.3257, + "step": 2891264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579850271527812e-06, + "loss": 3.3062, + "step": 2891776 + }, + { + "epoch": 0.02, + "learning_rate": 2.649599079642261e-06, + "loss": 3.3274, + "step": 2892288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6412131321317407e-06, + "loss": 3.3141, + "step": 2892800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328271846212207e-06, + "loss": 3.3279, + "step": 2893312 + }, + { + "epoch": 0.02, + "learning_rate": 2.624457615914432e-06, + "loss": 3.3117, + "step": 2893824 + }, + { + "epoch": 0.02, + "learning_rate": 2.616071668403912e-06, + "loss": 3.3299, + "step": 2894336 + }, + { + "epoch": 0.02, + "learning_rate": 2.607685720893392e-06, + "loss": 3.3203, + "step": 2894848 + }, + { + "epoch": 0.02, + "learning_rate": 2.5992997733828718e-06, + "loss": 3.3308, + "step": 2895360 + }, + { + "epoch": 0.02, + "learning_rate": 2.590930204676083e-06, + "loss": 3.3146, + "step": 2895872 + }, + { + "epoch": 0.02, + "learning_rate": 2.582544257165563e-06, + "loss": 3.3262, + "step": 2896384 + }, + { + "epoch": 0.02, + "learning_rate": 2.574158309655043e-06, + "loss": 3.3074, + "step": 2896896 + }, + { + "epoch": 0.02, + "learning_rate": 2.565772362144523e-06, + "loss": 3.3232, + "step": 2897408 + }, + { + "epoch": 0.02, + "learning_rate": 2.557402793437734e-06, + "loss": 3.325, + "step": 2897920 + }, + { + "epoch": 0.02, + "learning_rate": 2.549016845927214e-06, + "loss": 3.3202, + "step": 2898432 + }, + { + "epoch": 0.02, + "learning_rate": 2.540630898416694e-06, + "loss": 3.3228, + "step": 2898944 + }, + { + "epoch": 0.02, + "learning_rate": 2.532244950906174e-06, + "loss": 3.3142, + "step": 2899456 + }, + { + "epoch": 0.02, + "learning_rate": 2.523875382199385e-06, + "loss": 3.3182, + "step": 2899968 + }, + { + "epoch": 0.03, + "eval_loss": 3.88747501373291, + "eval_runtime": 312.6059, + "eval_samples_per_second": 1220.677, + "eval_steps_per_second": 38.147, + "step": 2900160 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 2.007469859420713e+18, + "trial_name": null, + "trial_params": null +}