diff --git "a/checkpoint-1831680/trainer_state.json" "b/checkpoint-1831680/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1831680/trainer_state.json" @@ -0,0 +1,21679 @@ +{ + "best_metric": 3.8482818603515625, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/0/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 1831680, + "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": 10.9798, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8315, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2085, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 6.0029, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8364, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7323, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6185, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5452, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4657, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4052, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3625, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3164, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2673, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2177, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.1919, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1458, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1187, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0946, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.062, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0318, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0174, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.982391148108281e-05, + "loss": 4.9839, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9684, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9416, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9354, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9031, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8876, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8579, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.851, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8285, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8212, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.811, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7942, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7832, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7702, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7545, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7525, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7217, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7116, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6904, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.693, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6795, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6804, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6593, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.963113296116324e-05, + "loss": 4.6529, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6492, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6431, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6303, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6123, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.604, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.6218, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.6102, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.5907, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5766, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5847, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5632, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5721, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5424, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5625, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5485, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5277, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5207, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5342, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4944, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5079, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5149, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4988, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4924, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4754, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4751, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4699, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4867, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.461, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4739, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4674, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4658, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4485, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4464, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.443, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4395, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4323, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4245, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4269, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4248, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.405, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4122, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4112, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4133, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.92622823011302e-05, + "loss": 4.3986, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3952, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.92455267849129e-05, + "loss": 4.3888, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923714083740238e-05, + "loss": 4.3822, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922875488989185e-05, + "loss": 4.3827, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922036894238133e-05, + "loss": 4.3874, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921198299487081e-05, + "loss": 4.3792, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920359704736029e-05, + "loss": 4.3861, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919521109984978e-05, + "loss": 4.3766, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918684153114299e-05, + "loss": 4.3595, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917845558363247e-05, + "loss": 4.3597, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917006963612195e-05, + "loss": 4.3693, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3653, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3627, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3532, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136542224883596e-05, + "loss": 4.3426, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3571, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3341, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3392, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3341, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3342, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.324, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3249, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3196, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.325, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3209, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3114, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3225, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.328, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.316, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.3028, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.3008, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2988, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.3051, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.3013, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.289, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.299, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2885, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2886, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2837, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926975431139254e-05, + "loss": 4.2848, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918589483628734e-05, + "loss": 4.2769, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910203536118214e-05, + "loss": 4.286, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890181758860769e-05, + "loss": 4.2858, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2845, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2602, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2759, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2696, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2747, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.2633, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2722, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.2612, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2783, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2473, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2663, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2505, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2497, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2518, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2365, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2413, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2486, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2377, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.202905178070068, + "eval_runtime": 309.1099, + "eval_samples_per_second": 1234.483, + "eval_steps_per_second": 38.579, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2312, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2274, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2408, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2327, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2405, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2188, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2217, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2097, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2204, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2159, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2127, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.218, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.198, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.2114, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1947, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1952, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.2004, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1946, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1972, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.2123, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1869, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1916, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1892, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1947, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1891, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1874, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1726, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1793, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1705, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1797, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1734, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1754, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.1806, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1686, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1738, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1721, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.84408033999776e-05, + "loss": 4.1595, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843241745246708e-05, + "loss": 4.1544, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1453, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.1524, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1536, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839889004122873e-05, + "loss": 4.1615, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1482, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382134525011416e-05, + "loss": 4.1471, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1524, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836536262999038e-05, + "loss": 4.1457, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1489, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1337, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.132, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1555, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1515, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831507970253472e-05, + "loss": 4.1349, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1362, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1414, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.1242, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1421, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1159, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1424, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.137, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1192, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1172, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231252985036985e-05, + "loss": 4.1309, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222867037526465e-05, + "loss": 4.0984, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214481090015945e-05, + "loss": 4.1139, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1268, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.8197725573798634e-05, + "loss": 4.1186, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189339626288114e-05, + "loss": 4.112, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.8180953678777594e-05, + "loss": 4.1011, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817260048887454e-05, + "loss": 4.1062, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.1071, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.115, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.1046, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1143, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813067075132194e-05, + "loss": 4.1168, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812228480381141e-05, + "loss": 4.113, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0988, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.1054, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809714334008359e-05, + "loss": 4.1047, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808875739257306e-05, + "loss": 4.1025, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808037144506255e-05, + "loss": 4.1008, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0943, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.8063615928845243e-05, + "loss": 4.1026, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.8055229981334717e-05, + "loss": 4.0997, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046844033824197e-05, + "loss": 4.0836, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.0898, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.8030088517606886e-05, + "loss": 4.0925, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.8021702570096366e-05, + "loss": 4.0992, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013316622585846e-05, + "loss": 4.0898, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800494705387906e-05, + "loss": 4.0844, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996561106368535e-05, + "loss": 4.0847, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988175158858015e-05, + "loss": 4.0772, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979789211347494e-05, + "loss": 4.0782, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797140326383698e-05, + "loss": 4.0899, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796301731632646e-05, + "loss": 4.0839, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.0936, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0834, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793787585259863e-05, + "loss": 4.0736, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792948990508811e-05, + "loss": 4.0739, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792110395757759e-05, + "loss": 4.0809, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791271801006707e-05, + "loss": 4.0849, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790434844136028e-05, + "loss": 4.0827, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789596249384976e-05, + "loss": 4.0757, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788757654633924e-05, + "loss": 4.0656, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.0827, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870821030121935e-05, + "loss": 4.0614, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.0701, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854065513904624e-05, + "loss": 4.0689, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845679566394104e-05, + "loss": 4.0688, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837293618883584e-05, + "loss": 4.057, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828907671373064e-05, + "loss": 4.0678, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820521723862544e-05, + "loss": 4.0582, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812135776352024e-05, + "loss": 4.0658, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803749828841504e-05, + "loss": 4.064, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779538026013471e-05, + "loss": 4.0543, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778699431262419e-05, + "loss": 4.0753, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777860836511367e-05, + "loss": 4.0753, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777023879640689e-05, + "loss": 4.066, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776185284889637e-05, + "loss": 4.0556, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775346690138585e-05, + "loss": 4.0512, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774508095387533e-05, + "loss": 4.0562, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773669500636481e-05, + "loss": 4.0545, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772830905885429e-05, + "loss": 4.0651, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.771992311134377e-05, + "loss": 4.0455, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0551, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770316759512646e-05, + "loss": 4.0575, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769478164761594e-05, + "loss": 4.0561, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768639570010542e-05, + "loss": 4.0434, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.76780097525949e-05, + "loss": 4.0517, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766962380508437e-05, + "loss": 4.0484, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766123785757386e-05, + "loss": 4.0522, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.765285191006334e-05, + "loss": 4.0566, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764448234135655e-05, + "loss": 4.0562, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.7636096393846026e-05, + "loss": 4.0365, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.7627710446335506e-05, + "loss": 4.0505, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.7619324498824986e-05, + "loss": 4.0494, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.7610954930118195e-05, + "loss": 4.049, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.0444, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.052, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.044, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757744389768358e-05, + "loss": 4.0618, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.756905795017306e-05, + "loss": 4.0364, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.756067200266254e-05, + "loss": 4.0487, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755228605515202e-05, + "loss": 4.039, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.75439001076415e-05, + "loss": 4.0348, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753551416013098e-05, + "loss": 4.0387, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0297, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751875864391367e-05, + "loss": 4.0317, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751037269640315e-05, + "loss": 4.0364, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750198674889263e-05, + "loss": 4.0318, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.0336785316467285, + "eval_runtime": 301.7288, + "eval_samples_per_second": 1264.682, + "eval_steps_per_second": 39.522, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749360080138211e-05, + "loss": 4.0274, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748521485387159e-05, + "loss": 4.022, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747682890636107e-05, + "loss": 4.0399, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746844295885055e-05, + "loss": 4.0288, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.746005701134003e-05, + "loss": 4.0442, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745167106382951e-05, + "loss": 4.0203, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744328511631899e-05, + "loss": 4.0278, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434899168808475e-05, + "loss": 4.0115, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426513221297955e-05, + "loss": 4.0269, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418127273787435e-05, + "loss": 4.0224, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740974132627691e-05, + "loss": 4.018, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.7401371757570124e-05, + "loss": 4.0306, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739300218886333e-05, + "loss": 4.0066, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738461624135281e-05, + "loss": 4.0237, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737623029384229e-05, + "loss": 4.0052, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736784434633177e-05, + "loss": 4.0077, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735945839882125e-05, + "loss": 4.007, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735107245131073e-05, + "loss": 4.0163, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734268650380021e-05, + "loss": 4.0097, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733430055628969e-05, + "loss": 4.0282, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732593098758291e-05, + "loss": 4.0078, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0134, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.73091754713656e-05, + "loss": 4.0083, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730078952385508e-05, + "loss": 4.0177, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729240357634456e-05, + "loss": 4.0046, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728401762883403e-05, + "loss": 4.0113, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727563168132351e-05, + "loss": 3.9999, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726724573381299e-05, + "loss": 4.0039, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725885978630247e-05, + "loss": 3.993, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725049021759568e-05, + "loss": 4.0076, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724210427008517e-05, + "loss": 4.0051, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.7233718322574647e-05, + "loss": 4.0056, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225332375064127e-05, + "loss": 4.0123, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 4.0008, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9987, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 4.006, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191804963825775e-05, + "loss": 3.9977, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9881, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.71750658264122e-05, + "loss": 3.9802, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9882, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.9905, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9987, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9905, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9813, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712475014134908e-05, + "loss": 3.9977, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711636419383856e-05, + "loss": 3.9876, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9842, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709962505642498e-05, + "loss": 3.9792, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709123910891446e-05, + "loss": 3.9724, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708285316140394e-05, + "loss": 3.999, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707446721389342e-05, + "loss": 3.9959, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.981, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.981, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704932575016559e-05, + "loss": 3.9901, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.7040939802655074e-05, + "loss": 3.9669, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.7032553855144554e-05, + "loss": 3.9885, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024167907634034e-05, + "loss": 3.9658, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9864, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.9937, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.9731, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699064049639568e-05, + "loss": 3.9649, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.698225454888516e-05, + "loss": 3.9838, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697386860137464e-05, + "loss": 3.9553, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9686, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9791, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9762, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9706, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693195524262577e-05, + "loss": 3.9563, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9606, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691518334760474e-05, + "loss": 3.9617, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9747, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689841145258369e-05, + "loss": 3.9621, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689002550507317e-05, + "loss": 3.9744, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9747, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9735, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9582, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685649809383482e-05, + "loss": 3.9677, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.68481121463243e-05, + "loss": 3.9682, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9617, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9657, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.9612, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814584735085956e-05, + "loss": 3.9618, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806198787575436e-05, + "loss": 3.9674, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.9478, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9587, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9551, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9666, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.956, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.9541, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747529912609254e-05, + "loss": 3.953, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739143965098734e-05, + "loss": 3.9475, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9442, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672238844888143e-05, + "loss": 3.9555, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671400250137091e-05, + "loss": 3.9654, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9604, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9526, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9462, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.947, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9506, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666370319511152e-05, + "loss": 3.9587, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655317247601e-05, + "loss": 3.9559, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664693130009048e-05, + "loss": 3.9493, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.9394, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663017578387317e-05, + "loss": 3.9608, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662178983636265e-05, + "loss": 3.9363, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661340388885213e-05, + "loss": 3.9482, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9415, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9471, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9364, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.9473, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9381, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.937, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9501, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654634906637543e-05, + "loss": 3.9308, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653796311886491e-05, + "loss": 3.9554, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652957717135439e-05, + "loss": 3.9547, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652119122384387e-05, + "loss": 3.9471, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.937, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9355, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9361, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648766381260553e-05, + "loss": 3.9369, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9455, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647089191758448e-05, + "loss": 3.9268, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9386, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9424, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9396, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9309, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9357, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9358, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9384, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.9389, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.9436, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.9228, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9368, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.938, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.935, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353537788848395e-05, + "loss": 3.932, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.9418, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9323, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9482, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.9258, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9342, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303238482589003e-05, + "loss": 3.9316, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9261, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9291, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627809701886118e-05, + "loss": 3.9241, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.9218, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9273, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9251, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9582722187042236, + "eval_runtime": 302.7231, + "eval_samples_per_second": 1260.528, + "eval_steps_per_second": 39.392, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9238, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623618366011231e-05, + "loss": 3.9151, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622779771260179e-05, + "loss": 3.9305, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9215, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9412, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.9158, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619427030136344e-05, + "loss": 3.922, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9064, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.9244, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9198, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.9129, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9219, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614398737390778e-05, + "loss": 3.9066, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613560142639726e-05, + "loss": 3.9201, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612721547888674e-05, + "loss": 3.9042, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.9035, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.9065, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.9132, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.9089, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9262, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.9094, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9171, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.9079, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9143, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.9056, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.9135, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.9048, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.9017, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009877728954384e-05, + "loss": 3.8994, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001491781443864e-05, + "loss": 3.9074, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993105833933344e-05, + "loss": 3.9107, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9075, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9179, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.9051, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959578422695e-05, + "loss": 3.9009, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.9079, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.9086, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8895, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8849, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591766506394613e-05, + "loss": 3.8913, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59092791164356e-05, + "loss": 3.9001, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.9027, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.8996, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.8872, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587575170519726e-05, + "loss": 3.9024, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586736575768674e-05, + "loss": 3.8974, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858996188979954e-05, + "loss": 3.8931, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.8863, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584222429395891e-05, + "loss": 3.8743, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583383834644839e-05, + "loss": 3.9151, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582545239893787e-05, + "loss": 3.9014, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581706645142735e-05, + "loss": 3.8927, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.580868050391683e-05, + "loss": 3.8933, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800310935210036e-05, + "loss": 3.8932, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579192498769952e-05, + "loss": 3.8783, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783539040189e-05, + "loss": 3.8969, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577515309267848e-05, + "loss": 3.8801, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8916, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575839757646117e-05, + "loss": 3.9073, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.8851, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574162568144013e-05, + "loss": 3.8726, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.8985, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.8672, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.57164842177123e-05, + "loss": 3.8744, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570809827020178e-05, + "loss": 3.8947, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.8883, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691342753984476e-05, + "loss": 3.8816, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682956806473956e-05, + "loss": 3.8747, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674570858963436e-05, + "loss": 3.8687, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8754, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8889, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649429395235605e-05, + "loss": 3.8743, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641043447725085e-05, + "loss": 3.8908, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8843, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8926, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615901983997254e-05, + "loss": 3.877, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607516036486734e-05, + "loss": 3.8786, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8844, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.875, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8875, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8751, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8768, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.881, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.8657, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554046121401004e-05, + "loss": 3.8723, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.8759, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8814, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.8718, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550693380277169e-05, + "loss": 3.8731, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549854785526117e-05, + "loss": 3.8671, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490178286554384e-05, + "loss": 3.8657, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481792339043864e-05, + "loss": 3.8636, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.5473406391533343e-05, + "loss": 3.8722, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.5465020444022823e-05, + "loss": 3.8828, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545665087531603e-05, + "loss": 3.8827, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544826492780551e-05, + "loss": 3.872, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543987898029499e-05, + "loss": 3.8635, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543149303278447e-05, + "loss": 3.8677, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.8715, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541473751656716e-05, + "loss": 3.8771, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8764, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539796562154612e-05, + "loss": 3.8712, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.8593, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538121010532882e-05, + "loss": 3.8834, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.853, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536443821030778e-05, + "loss": 3.8716, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8611, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8684, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339296746579946e-05, + "loss": 3.8585, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330910799069426e-05, + "loss": 3.8681, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8607, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8597, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8688, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8563, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289013819124284e-05, + "loss": 3.8758, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528062787161377e-05, + "loss": 3.8778, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8709, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8602, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525548640788594e-05, + "loss": 3.8606, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524710046037542e-05, + "loss": 3.8578, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.861, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8696, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522195899664759e-05, + "loss": 3.8465, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521357304913707e-05, + "loss": 3.8626, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520518710162655e-05, + "loss": 3.8634, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519680115411603e-05, + "loss": 3.8675, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518843158540924e-05, + "loss": 3.8554, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180045637898725e-05, + "loss": 3.8623, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171659690388204e-05, + "loss": 3.8544, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163273742877684e-05, + "loss": 3.8696, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154904174170894e-05, + "loss": 3.8614, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146518226660373e-05, + "loss": 3.8706, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5138132279149853e-05, + "loss": 3.8463, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129746331639333e-05, + "loss": 3.8627, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512137676293254e-05, + "loss": 3.8646, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511299081542202e-05, + "loss": 3.8557, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.51046048679115e-05, + "loss": 3.8578, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096218920400976e-05, + "loss": 3.868, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508784935169419e-05, + "loss": 3.8603, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507946340418368e-05, + "loss": 3.8755, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507107745667316e-05, + "loss": 3.8504, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506269150916263e-05, + "loss": 3.8634, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505432194045585e-05, + "loss": 3.8537, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504593599294533e-05, + "loss": 3.8549, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.50375500454348e-05, + "loss": 3.8565, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502916409792428e-05, + "loss": 3.8505, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020810908021225e-05, + "loss": 3.8494, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012424960510705e-05, + "loss": 3.8507, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004039013000185e-05, + "loss": 3.8539, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9172236919403076, + "eval_runtime": 302.6065, + "eval_samples_per_second": 1261.014, + "eval_steps_per_second": 39.408, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995653065489665e-05, + "loss": 3.8498, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987267117979145e-05, + "loss": 3.843, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497888117046863e-05, + "loss": 3.861, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970495222958105e-05, + "loss": 3.8513, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962109275447585e-05, + "loss": 3.8671, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953723327937065e-05, + "loss": 3.8502, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945337380426545e-05, + "loss": 3.8499, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936951432916025e-05, + "loss": 3.8365, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928581864209234e-05, + "loss": 3.8509, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920195916698714e-05, + "loss": 3.8471, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911809969188194e-05, + "loss": 3.8472, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903424021677674e-05, + "loss": 3.849, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489505445297088e-05, + "loss": 3.8364, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488666850546037e-05, + "loss": 3.8514, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487828255794985e-05, + "loss": 3.8345, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486989661043933e-05, + "loss": 3.8346, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486152704173254e-05, + "loss": 3.8361, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485314109422202e-05, + "loss": 3.8468, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48447551467115e-05, + "loss": 3.8373, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483636919920098e-05, + "loss": 3.856, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482799963049419e-05, + "loss": 3.8422, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481961368298367e-05, + "loss": 3.8497, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481122773547315e-05, + "loss": 3.8416, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480284178796263e-05, + "loss": 3.8441, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.4794472219255837e-05, + "loss": 3.8375, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478608627174532e-05, + "loss": 3.8477, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47777003242348e-05, + "loss": 3.8355, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476931437672428e-05, + "loss": 3.8378, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476094480801749e-05, + "loss": 3.83, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475255886050697e-05, + "loss": 3.839, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474417291299645e-05, + "loss": 3.8433, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473578696548593e-05, + "loss": 3.8415, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472741739677914e-05, + "loss": 3.8473, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.8365, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.47106455017581e-05, + "loss": 3.8354, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470225955424758e-05, + "loss": 3.8452, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469388998554079e-05, + "loss": 3.8436, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468550403803028e-05, + "loss": 3.82, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467711809051976e-05, + "loss": 3.8255, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466873214300924e-05, + "loss": 3.8248, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660362574302446e-05, + "loss": 3.8293, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651976626791926e-05, + "loss": 3.841, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643590679281406e-05, + "loss": 3.8321, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635204731770886e-05, + "loss": 3.8274, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626835163064095e-05, + "loss": 3.8358, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618449215553575e-05, + "loss": 3.8281, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610063268043055e-05, + "loss": 3.8301, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601677320532535e-05, + "loss": 3.8245, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593307751825744e-05, + "loss": 3.8052, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584921804315224e-05, + "loss": 3.8513, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457653585680471e-05, + "loss": 3.8373, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456814990929419e-05, + "loss": 3.832, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.45597803405874e-05, + "loss": 3.8269, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455141077188061e-05, + "loss": 3.8261, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454302482437009e-05, + "loss": 3.816, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453463887685957e-05, + "loss": 3.8302, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452625292934905e-05, + "loss": 3.8212, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.451786698183853e-05, + "loss": 3.8263, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450948103432801e-05, + "loss": 3.844, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450109508681749e-05, + "loss": 3.8199, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449270913930697e-05, + "loss": 3.8138, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448433957060018e-05, + "loss": 3.8356, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475953623089664e-05, + "loss": 3.8065, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467567675579144e-05, + "loss": 3.8151, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459181728068624e-05, + "loss": 3.8293, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445081215936183e-05, + "loss": 3.8253, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.8197, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443404026434079e-05, + "loss": 3.815, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425670695634e-05, + "loss": 3.8044, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441728474812348e-05, + "loss": 3.8143, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8259, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.8156, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439214328439565e-05, + "loss": 3.8248, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438375733688513e-05, + "loss": 3.8254, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8328, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.8148, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435861587315731e-05, + "loss": 3.8146, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435022992564679e-05, + "loss": 3.8242, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434184397813627e-05, + "loss": 3.8105, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433345803062575e-05, + "loss": 3.8296, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.4325088461918956e-05, + "loss": 3.8156, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.4316702514408436e-05, + "loss": 3.8161, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.8226, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.804, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291561050680605e-05, + "loss": 3.8101, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283175103170085e-05, + "loss": 3.8145, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427478915565957e-05, + "loss": 3.8229, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.8069, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425803363944226e-05, + "loss": 3.8156, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424964769193174e-05, + "loss": 3.8086, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424126174442122e-05, + "loss": 3.8114, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.8017, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422450622820391e-05, + "loss": 3.8147, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421612028069339e-05, + "loss": 3.8226, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420773433318287e-05, + "loss": 3.8213, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419934838567235e-05, + "loss": 3.8188, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419097881696556e-05, + "loss": 3.8031, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418259286945504e-05, + "loss": 3.8065, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174206921944525e-05, + "loss": 3.81, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165820974434005e-05, + "loss": 3.8196, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157451405727214e-05, + "loss": 3.8169, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4149065458216694e-05, + "loss": 3.8118, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140679510706174e-05, + "loss": 3.8052, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132293563195654e-05, + "loss": 3.8233, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412392399448886e-05, + "loss": 3.7972, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411553804697834e-05, + "loss": 3.8123, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410715209946782e-05, + "loss": 3.8038, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098766151957296e-05, + "loss": 3.8121, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409039658325051e-05, + "loss": 3.799, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408201063573999e-05, + "loss": 3.8115, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407362468822948e-05, + "loss": 3.8011, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406523874071895e-05, + "loss": 3.8063, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405686917201217e-05, + "loss": 3.8102, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404848322450165e-05, + "loss": 3.803, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404009727699113e-05, + "loss": 3.8156, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.40317113294806e-05, + "loss": 3.8216, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402334176077382e-05, + "loss": 3.8095, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149558132633e-05, + "loss": 3.8082, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400656986575277e-05, + "loss": 3.8005, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399818391824225e-05, + "loss": 3.8045, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989814349535466e-05, + "loss": 3.8022, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981428402024946e-05, + "loss": 3.8173, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3973042454514426e-05, + "loss": 3.7872, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964656507003906e-05, + "loss": 3.8055, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395628693829712e-05, + "loss": 3.8049, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.39479009907866e-05, + "loss": 3.8108, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939515043276075e-05, + "loss": 3.8, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931129095765555e-05, + "loss": 3.8049, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392275952705877e-05, + "loss": 3.7972, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914373579548244e-05, + "loss": 3.8118, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905987632037724e-05, + "loss": 3.8088, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897601684527204e-05, + "loss": 3.8114, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388923211582042e-05, + "loss": 3.7943, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.38808461683099e-05, + "loss": 3.807, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387246022079938e-05, + "loss": 3.8102, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386407427328886e-05, + "loss": 3.8009, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855704704582075e-05, + "loss": 3.8029, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384731875707155e-05, + "loss": 3.8103, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383893280956103e-05, + "loss": 3.8023, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383054686205051e-05, + "loss": 3.8239, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382217729334372e-05, + "loss": 3.796, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.38137913458332e-05, + "loss": 3.8061, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380540539832268e-05, + "loss": 3.7984, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379701945081216e-05, + "loss": 3.8009, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378864988210537e-05, + "loss": 3.8046, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378026393459485e-05, + "loss": 3.7967, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.377189436588807e-05, + "loss": 3.7996, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376350841837754e-05, + "loss": 3.7876, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375512247086702e-05, + "loss": 3.8033, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8930797576904297, + "eval_runtime": 305.8231, + "eval_samples_per_second": 1247.751, + "eval_steps_per_second": 38.993, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.37467365233565e-05, + "loss": 3.8019, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373835057584598e-05, + "loss": 3.7899, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372996462833546e-05, + "loss": 3.8041, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372157868082494e-05, + "loss": 3.8021, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371319273331442e-05, + "loss": 3.8094, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370482316460763e-05, + "loss": 3.7951, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369645359590085e-05, + "loss": 3.7964, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368806764839033e-05, + "loss": 3.7857, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367968170087981e-05, + "loss": 3.7983, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367129575336929e-05, + "loss": 3.7953, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366290980585877e-05, + "loss": 3.7972, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365452385834825e-05, + "loss": 3.791, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364613791083773e-05, + "loss": 3.7895, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363775196332721e-05, + "loss": 3.7919, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.3629382394620416e-05, + "loss": 3.7846, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.3620996447109896e-05, + "loss": 3.7798, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.3612610499599376e-05, + "loss": 3.7845, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604224552088856e-05, + "loss": 3.7926, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595854983382065e-05, + "loss": 3.7859, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587469035871545e-05, + "loss": 3.8036, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.3579083088361025e-05, + "loss": 3.7929, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357069714085051e-05, + "loss": 3.7991, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356232757214372e-05, + "loss": 3.7868, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.35539416246332e-05, + "loss": 3.7888, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354555567712268e-05, + "loss": 3.7865, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353716972961216e-05, + "loss": 3.7987, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352880016090537e-05, + "loss": 3.7867, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352041421339485e-05, + "loss": 3.7848, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351202826588433e-05, + "loss": 3.7799, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350364231837381e-05, + "loss": 3.7889, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349527274966702e-05, + "loss": 3.7901, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.34868868021565e-05, + "loss": 3.7929, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347850085464598e-05, + "loss": 3.7948, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470114907135465e-05, + "loss": 3.7906, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461745338428674e-05, + "loss": 3.785, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453359390918154e-05, + "loss": 3.7957, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444973443407634e-05, + "loss": 3.7918, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343660387470084e-05, + "loss": 3.7738, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342821792719032e-05, + "loss": 3.7748, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.34198319796798e-05, + "loss": 3.7717, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341144603216928e-05, + "loss": 3.7779, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340307646346249e-05, + "loss": 3.7903, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339469051595197e-05, + "loss": 3.7846, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338630456844145e-05, + "loss": 3.7773, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337791862093093e-05, + "loss": 3.7859, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336954905222415e-05, + "loss": 3.7776, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336116310471363e-05, + "loss": 3.7811, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335277715720311e-05, + "loss": 3.7718, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334439120969259e-05, + "loss": 3.7547, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33360216409858e-05, + "loss": 3.803, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332763569347528e-05, + "loss": 3.7848, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331924974596476e-05, + "loss": 3.7888, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331086379845424e-05, + "loss": 3.7746, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.3302494229747446e-05, + "loss": 3.7829, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294108282236926e-05, + "loss": 3.7665, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285722334726406e-05, + "loss": 3.7778, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277336387215886e-05, + "loss": 3.7771, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326895043970537e-05, + "loss": 3.7747, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326056449219485e-05, + "loss": 3.7974, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252178544684325e-05, + "loss": 3.77, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243792597173805e-05, + "loss": 3.7629, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323542302846702e-05, + "loss": 3.7898, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.32270370809565e-05, + "loss": 3.757, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218651133445974e-05, + "loss": 3.7648, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210265185935454e-05, + "loss": 3.7826, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320189561722867e-05, + "loss": 3.7802, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319350966971815e-05, + "loss": 3.7665, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185123722207623e-05, + "loss": 3.7736, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317675415350084e-05, + "loss": 3.7545, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168368205990326e-05, + "loss": 3.7694, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.31599822584798e-05, + "loss": 3.778, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315159631096928e-05, + "loss": 3.7646, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143226742262495e-05, + "loss": 3.7795, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134840794751975e-05, + "loss": 3.7771, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312645484724145e-05, + "loss": 3.7883, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311806889973093e-05, + "loss": 3.766, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109699331024144e-05, + "loss": 3.773, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310131338351362e-05, + "loss": 3.7764, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.30929274360031e-05, + "loss": 3.762, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308454148849258e-05, + "loss": 3.7781, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307617191978579e-05, + "loss": 3.7721, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306778597227527e-05, + "loss": 3.7685, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305940002476475e-05, + "loss": 3.778, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305101407725423e-05, + "loss": 3.7586, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304264450854745e-05, + "loss": 3.7582, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303425856103692e-05, + "loss": 3.7691, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.30258726135264e-05, + "loss": 3.7754, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301748666601588e-05, + "loss": 3.7642, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300911709730909e-05, + "loss": 3.7688, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300073114979857e-05, + "loss": 3.7561, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299234520228805e-05, + "loss": 3.7659, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298395925477753e-05, + "loss": 3.7578, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297558968607075e-05, + "loss": 3.7652, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967203738560227e-05, + "loss": 3.779, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958817791049707e-05, + "loss": 3.772, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950431843539186e-05, + "loss": 3.7704, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.2942062274832396e-05, + "loss": 3.7587, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.2933676327321876e-05, + "loss": 3.7602, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.2925290379811355e-05, + "loss": 3.7634, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.2916904432300835e-05, + "loss": 3.7764, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.2908534863594045e-05, + "loss": 3.7673, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.2900148916083525e-05, + "loss": 3.7728, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.2891762968573004e-05, + "loss": 3.7575, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.2883377021062484e-05, + "loss": 3.7758, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.28750074523557e-05, + "loss": 3.7536, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286662150484518e-05, + "loss": 3.7676, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285823555733466e-05, + "loss": 3.7554, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284984960982414e-05, + "loss": 3.7698, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841496419921085e-05, + "loss": 3.7544, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833110472410565e-05, + "loss": 3.7623, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282472452490004e-05, + "loss": 3.7594, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.281633857738952e-05, + "loss": 3.761, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807952629879e-05, + "loss": 3.7618, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.279956668236848e-05, + "loss": 3.7592, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.279118073485796e-05, + "loss": 3.7694, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.278279478734744e-05, + "loss": 3.7745, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774425218640654e-05, + "loss": 3.7668, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2766039271130134e-05, + "loss": 3.7676, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757653323619614e-05, + "loss": 3.7534, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749267376109094e-05, + "loss": 3.758, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.27408978074023e-05, + "loss": 3.7615, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273251185989178e-05, + "loss": 3.769, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272412591238126e-05, + "loss": 3.7442, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271573996487074e-05, + "loss": 3.7603, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270737039616395e-05, + "loss": 3.7651, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269898444865343e-05, + "loss": 3.7624, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269059850114291e-05, + "loss": 3.7569, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268221255363239e-05, + "loss": 3.7625, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267384298492561e-05, + "loss": 3.7554, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266545703741509e-05, + "loss": 3.7684, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265707108990457e-05, + "loss": 3.764, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264868514239405e-05, + "loss": 3.7677, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640315573687257e-05, + "loss": 3.749, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631929626176737e-05, + "loss": 3.7628, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623543678666216e-05, + "loss": 3.7678, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615157731155696e-05, + "loss": 3.7573, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.2606788162448906e-05, + "loss": 3.76, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.2598402214938386e-05, + "loss": 3.7652, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.2590016267427865e-05, + "loss": 3.7613, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.2581630319917345e-05, + "loss": 3.7757, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257326075121056e-05, + "loss": 3.7562, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256487480370004e-05, + "loss": 3.7611, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255648885618952e-05, + "loss": 3.7573, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548102908679e-05, + "loss": 3.7578, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253973333997221e-05, + "loss": 3.7553, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253136377126542e-05, + "loss": 3.7531, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.25229778237549e-05, + "loss": 3.7604, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251459187624438e-05, + "loss": 3.7434, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250620592873386e-05, + "loss": 3.7625, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.876544713973999, + "eval_runtime": 303.1442, + "eval_samples_per_second": 1258.777, + "eval_steps_per_second": 39.338, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249781998122334e-05, + "loss": 3.7616, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248943403371282e-05, + "loss": 3.7471, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.24810480862023e-05, + "loss": 3.7598, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247266213869178e-05, + "loss": 3.7574, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464276191181266e-05, + "loss": 3.7686, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455890243670746e-05, + "loss": 3.7544, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447520674963955e-05, + "loss": 3.7541, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2439134727453435e-05, + "loss": 3.7433, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430748779942915e-05, + "loss": 3.7539, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422362832432395e-05, + "loss": 3.7532, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413976884921875e-05, + "loss": 3.7542, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.240559093741135e-05, + "loss": 3.7482, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397221368704564e-05, + "loss": 3.7477, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388835421194044e-05, + "loss": 3.7496, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380449473683524e-05, + "loss": 3.7466, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2372063526173004e-05, + "loss": 3.738, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363677578662484e-05, + "loss": 3.7424, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355291631151963e-05, + "loss": 3.7494, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346905683641443e-05, + "loss": 3.7465, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233851973613092e-05, + "loss": 3.7578, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233015016742413e-05, + "loss": 3.7537, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232176421991361e-05, + "loss": 3.7589, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231337827240309e-05, + "loss": 3.7418, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230499232489257e-05, + "loss": 3.751, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229662275618578e-05, + "loss": 3.7455, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228823680867526e-05, + "loss": 3.7548, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227985086116474e-05, + "loss": 3.7431, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227146491365422e-05, + "loss": 3.7484, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226309534494744e-05, + "loss": 3.7398, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225470939743692e-05, + "loss": 3.7432, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.22463234499264e-05, + "loss": 3.7472, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223793750241588e-05, + "loss": 3.7566, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.2229567933709086e-05, + "loss": 3.7536, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.2221181986198566e-05, + "loss": 3.751, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212796038688046e-05, + "loss": 3.7446, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204426469981255e-05, + "loss": 3.7488, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2196040522470735e-05, + "loss": 3.7522, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187654574960215e-05, + "loss": 3.7361, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.2179268627449695e-05, + "loss": 3.7327, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217089905874291e-05, + "loss": 3.7315, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216251311123239e-05, + "loss": 3.7397, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215412716372187e-05, + "loss": 3.7456, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214574121621135e-05, + "loss": 3.7448, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213737164750456e-05, + "loss": 3.7389, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212898569999404e-05, + "loss": 3.7429, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212059975248352e-05, + "loss": 3.7397, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112213804973e-05, + "loss": 3.7412, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210384423626621e-05, + "loss": 3.7331, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209545828875569e-05, + "loss": 3.715, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208707234124517e-05, + "loss": 3.759, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207868639373465e-05, + "loss": 3.7433, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070316825027865e-05, + "loss": 3.7505, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061930877517345e-05, + "loss": 3.737, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053561308810554e-05, + "loss": 3.7385, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045175361300034e-05, + "loss": 3.727, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036789413789514e-05, + "loss": 3.7366, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028403466278993e-05, + "loss": 3.7401, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2020017518768473e-05, + "loss": 3.7327, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011631571257953e-05, + "loss": 3.7577, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200324562374743e-05, + "loss": 3.7333, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199485967623691e-05, + "loss": 3.7241, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198650648633385e-05, + "loss": 3.7485, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197812053882333e-05, + "loss": 3.7206, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196973459131281e-05, + "loss": 3.7199, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19613486438023e-05, + "loss": 3.7485, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195296269629178e-05, + "loss": 3.7424, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194457674878126e-05, + "loss": 3.7255, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193619080127074e-05, + "loss": 3.7345, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192780485376022e-05, + "loss": 3.7176, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191943528505343e-05, + "loss": 3.7309, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191104933754291e-05, + "loss": 3.7344, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190266339003239e-05, + "loss": 3.728, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189427744252187e-05, + "loss": 3.7381, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885907873815076e-05, + "loss": 3.7376, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.1877521926304556e-05, + "loss": 3.7467, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.1869135978794036e-05, + "loss": 3.7288, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.1860750031283516e-05, + "loss": 3.7325, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185238046257673e-05, + "loss": 3.7371, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184401089386994e-05, + "loss": 3.7254, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183562494635942e-05, + "loss": 3.7374, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.18272389988489e-05, + "loss": 3.7337, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181885305133838e-05, + "loss": 3.7283, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181048348263159e-05, + "loss": 3.7436, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180209753512107e-05, + "loss": 3.7179, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179371158761055e-05, + "loss": 3.7205, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178532564010003e-05, + "loss": 3.7327, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177693969258951e-05, + "loss": 3.7369, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.176855374507899e-05, + "loss": 3.7261, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760184176372206e-05, + "loss": 3.733, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751798228861685e-05, + "loss": 3.7148, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743412281351165e-05, + "loss": 3.7287, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1735026333840645e-05, + "loss": 3.7201, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726640386330125e-05, + "loss": 3.7299, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718254438819605e-05, + "loss": 3.7408, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170986849130908e-05, + "loss": 3.7332, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170148254379856e-05, + "loss": 3.7329, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693112975091774e-05, + "loss": 3.7213, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168472702758125e-05, + "loss": 3.7232, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167634108007073e-05, + "loss": 3.7239, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166795513256021e-05, + "loss": 3.739, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165958556385342e-05, + "loss": 3.7302, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.16511996163429e-05, + "loss": 3.7367, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164281366883238e-05, + "loss": 3.7193, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.16344441001256e-05, + "loss": 3.7355, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162605815261508e-05, + "loss": 3.7211, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161767220510455e-05, + "loss": 3.7285, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160928625759403e-05, + "loss": 3.7156, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160090031008351e-05, + "loss": 3.7323, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159253074137672e-05, + "loss": 3.7169, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.15841447938662e-05, + "loss": 3.728, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157575884635568e-05, + "loss": 3.7178, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156737289884516e-05, + "loss": 3.7299, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155898695133464e-05, + "loss": 3.7219, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155060100382413e-05, + "loss": 3.7211, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154221505631361e-05, + "loss": 3.733, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153382910880309e-05, + "loss": 3.7377, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.15254595400963e-05, + "loss": 3.732, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151707359258578e-05, + "loss": 3.7259, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150868764507526e-05, + "loss": 3.7188, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500318076368466e-05, + "loss": 3.721, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.1491932128857946e-05, + "loss": 3.7241, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.1483546181347426e-05, + "loss": 3.7277, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.1475160233836906e-05, + "loss": 3.7121, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.1466774286326386e-05, + "loss": 3.7254, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.1458388338815866e-05, + "loss": 3.7285, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.1450002391305345e-05, + "loss": 3.7258, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.1441616443794825e-05, + "loss": 3.7222, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143324687508804e-05, + "loss": 3.7227, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142487730638125e-05, + "loss": 3.7187, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141649135887073e-05, + "loss": 3.7319, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140810541136021e-05, + "loss": 3.7307, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139971946384969e-05, + "loss": 3.7298, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139133351633917e-05, + "loss": 3.7137, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138296394763238e-05, + "loss": 3.7275, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137457800012186e-05, + "loss": 3.7291, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136619205261134e-05, + "loss": 3.7217, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135780610510082e-05, + "loss": 3.726, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.13494201575903e-05, + "loss": 3.7249, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.134103421007978e-05, + "loss": 3.7246, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133264826256926e-05, + "loss": 3.741, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132426231505874e-05, + "loss": 3.7186, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315892746351955e-05, + "loss": 3.726, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307506798841435e-05, + "loss": 3.7241, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299120851330915e-05, + "loss": 3.7242, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290751282624124e-05, + "loss": 3.7173, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282365335113604e-05, + "loss": 3.7166, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273979387603084e-05, + "loss": 3.722, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126559344009256e-05, + "loss": 3.7093, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125720749258204e-05, + "loss": 3.7264, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.865278959274292, + "eval_runtime": 304.1111, + "eval_samples_per_second": 1254.775, + "eval_steps_per_second": 39.213, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124882154507152e-05, + "loss": 3.7234, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240435597561e-05, + "loss": 3.7107, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.1232049650050484e-05, + "loss": 3.7221, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122369646014743e-05, + "loss": 3.724, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121531051263691e-05, + "loss": 3.7322, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120692456512638e-05, + "loss": 3.7172, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119853861761586e-05, + "loss": 3.7242, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119015267010534e-05, + "loss": 3.7126, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118176672259482e-05, + "loss": 3.7121, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.11733807750843e-05, + "loss": 3.7246, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116499482757378e-05, + "loss": 3.7182, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115662525886699e-05, + "loss": 3.7103, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148255690160207e-05, + "loss": 3.7224, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139869742649686e-05, + "loss": 3.7078, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131483795139166e-05, + "loss": 3.7101, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123097847628646e-05, + "loss": 3.7038, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114711900118126e-05, + "loss": 3.7068, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.1106325952607606e-05, + "loss": 3.7181, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.1097940005097086e-05, + "loss": 3.7044, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.1089570436390295e-05, + "loss": 3.7286, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.1081184488879775e-05, + "loss": 3.719, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.1072798541369255e-05, + "loss": 3.7244, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.1064412593858735e-05, + "loss": 3.7104, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.1056026646348215e-05, + "loss": 3.7117, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.1047640698837695e-05, + "loss": 3.7171, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.1039254751327175e-05, + "loss": 3.7178, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.1030868803816655e-05, + "loss": 3.7089, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102249923510987e-05, + "loss": 3.7156, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101411328759935e-05, + "loss": 3.7018, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.100574371889256e-05, + "loss": 3.7111, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.099735777138204e-05, + "loss": 3.7113, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.098897182387152e-05, + "loss": 3.7207, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980585876361e-05, + "loss": 3.7184, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.097219992885048e-05, + "loss": 3.719, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.096381398133996e-05, + "loss": 3.7116, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.095544441263317e-05, + "loss": 3.7121, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.094705846512265e-05, + "loss": 3.719, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.093867251761213e-05, + "loss": 3.7027, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.093028657010161e-05, + "loss": 3.7023, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092190062259109e-05, + "loss": 3.6953, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913531053884305e-05, + "loss": 3.704, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905145106373784e-05, + "loss": 3.7076, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.0896759158863264e-05, + "loss": 3.7121, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.0888373211352744e-05, + "loss": 3.7089, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087998726384222e-05, + "loss": 3.7062, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.08716013163317e-05, + "loss": 3.7089, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086321536882118e-05, + "loss": 3.7108, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085482942131066e-05, + "loss": 3.6984, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.0846459852603867e-05, + "loss": 3.6836, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.0838073905093346e-05, + "loss": 3.7183, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.0829687957582826e-05, + "loss": 3.713, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082130201007231e-05, + "loss": 3.7178, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081293244136552e-05, + "loss": 3.7046, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080456287265874e-05, + "loss": 3.7052, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079617692514822e-05, + "loss": 3.6974, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078779097763769e-05, + "loss": 3.7018, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077940503012717e-05, + "loss": 3.7102, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077103546142039e-05, + "loss": 3.6943, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076264951390987e-05, + "loss": 3.7258, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075426356639934e-05, + "loss": 3.7055, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074587761888882e-05, + "loss": 3.6862, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.07374916713783e-05, + "loss": 3.7152, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072910572386778e-05, + "loss": 3.6898, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.0720736155160996e-05, + "loss": 3.6876, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.0712350207650476e-05, + "loss": 3.7157, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.0703964260139956e-05, + "loss": 3.7062, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.0695578312629436e-05, + "loss": 3.6944, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.0687208743922645e-05, + "loss": 3.7013, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678822796412125e-05, + "loss": 3.6862, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670436848901605e-05, + "loss": 3.6957, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662050901391085e-05, + "loss": 3.7035, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653664953880565e-05, + "loss": 3.6973, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645279006370045e-05, + "loss": 3.707, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636893058859525e-05, + "loss": 3.7005, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628507111349005e-05, + "loss": 3.7131, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620137542642214e-05, + "loss": 3.696, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.06117515951317e-05, + "loss": 3.704, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060336564762118e-05, + "loss": 3.702, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059497970011066e-05, + "loss": 3.6933, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058659375260014e-05, + "loss": 3.7084, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.703, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.6937, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056145228887231e-05, + "loss": 3.7114, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055306634136179e-05, + "loss": 3.6854, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054468039385127e-05, + "loss": 3.6852, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.7012, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.7022, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6935, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.7024, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.6858, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.6925, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.6902, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6956, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.7086, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.04608372975498e-05, + "loss": 3.6996, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045246772884301e-05, + "loss": 3.7047, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6893, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.6919, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.6926, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041892393880093e-05, + "loss": 3.7029, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041053799129041e-05, + "loss": 3.6993, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040215204377989e-05, + "loss": 3.7036, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039376609626937e-05, + "loss": 3.6897, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038541290636631e-05, + "loss": 3.6997, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6942, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036864101134527e-05, + "loss": 3.697, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6836, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035186911632423e-05, + "loss": 3.7034, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034349954761744e-05, + "loss": 3.687, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033511360010692e-05, + "loss": 3.693, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.03267276525964e-05, + "loss": 3.6859, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031834170508588e-05, + "loss": 3.6959, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030995575757536e-05, + "loss": 3.6932, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.030156981006484e-05, + "loss": 3.6896, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.029318386255432e-05, + "loss": 3.6993, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.7086, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276428346337016e-05, + "loss": 3.7057, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268042398826496e-05, + "loss": 3.6948, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259656451315976e-05, + "loss": 3.689, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.6906, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242900935098665e-05, + "loss": 3.6941, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234514987588145e-05, + "loss": 3.6951, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226129040077625e-05, + "loss": 3.681, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217743092567105e-05, + "loss": 3.6945, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.0209357145056585e-05, + "loss": 3.6997, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.0200987576349794e-05, + "loss": 3.6911, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.0192601628839274e-05, + "loss": 3.6899, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.0184215681328754e-05, + "loss": 3.6959, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.017582973381824e-05, + "loss": 3.6884, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016746016511145e-05, + "loss": 3.7009, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015907421760093e-05, + "loss": 3.6961, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015068827009041e-05, + "loss": 3.7018, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014230232257989e-05, + "loss": 3.6826, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013391637506936e-05, + "loss": 3.6956, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012553042755884e-05, + "loss": 3.6975, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011716085885206e-05, + "loss": 3.6923, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010877491134154e-05, + "loss": 3.6956, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010038896383101e-05, + "loss": 3.6919, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009200301632049e-05, + "loss": 3.695, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008361706880998e-05, + "loss": 3.7144, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007524750010319e-05, + "loss": 3.6867, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006686155259267e-05, + "loss": 3.6977, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005847560508215e-05, + "loss": 3.6939, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005008965757163e-05, + "loss": 3.6935, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004170371006111e-05, + "loss": 3.6881, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.0033334141354317e-05, + "loss": 3.6831, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.0024948193843797e-05, + "loss": 3.6923, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016562246333276e-05, + "loss": 3.6792, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.0008176298822756e-05, + "loss": 3.6966, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.858989715576172, + "eval_runtime": 303.7841, + "eval_samples_per_second": 1256.126, + "eval_steps_per_second": 39.255, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999790351312236e-05, + "loss": 3.6912, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991404403801716e-05, + "loss": 3.6835, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983018456291196e-05, + "loss": 3.6918, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974632508780676e-05, + "loss": 3.6931, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996624656127016e-05, + "loss": 3.7012, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995787699256337e-05, + "loss": 3.6887, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994949104505285e-05, + "loss": 3.6963, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994110509754233e-05, + "loss": 3.6808, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6833, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6956, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.99159636338145e-05, + "loss": 3.687, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990757768630398e-05, + "loss": 3.6802, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.694, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6763, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6801, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.98740338962619e-05, + "loss": 3.6694, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986564794875138e-05, + "loss": 3.68, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985726200124086e-05, + "loss": 3.691, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848892432534077e-05, + "loss": 3.6745, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984050648502355e-05, + "loss": 3.6951, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983212053751303e-05, + "loss": 3.6897, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.982373459000251e-05, + "loss": 3.6912, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981534864249199e-05, + "loss": 3.6829, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980696269498147e-05, + "loss": 3.6842, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979857674747095e-05, + "loss": 3.6874, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979019079996043e-05, + "loss": 3.6864, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.6775, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773451662546854e-05, + "loss": 3.6872, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765065715036334e-05, + "loss": 3.6731, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.9756679767525814e-05, + "loss": 3.6807, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.9748293820015294e-05, + "loss": 3.6831, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.9739924251308503e-05, + "loss": 3.6876, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973153830379798e-05, + "loss": 3.6906, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972315235628746e-05, + "loss": 3.6937, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971476640877694e-05, + "loss": 3.6755, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970638046126642e-05, + "loss": 3.6851, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.96979945137559e-05, + "loss": 3.6924, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968960856624538e-05, + "loss": 3.6693, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968122261873486e-05, + "loss": 3.6746, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967286942883181e-05, + "loss": 3.6701, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966448348132129e-05, + "loss": 3.6717, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965609753381077e-05, + "loss": 3.6798, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964771158630025e-05, + "loss": 3.6856, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963932563878973e-05, + "loss": 3.6784, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963093969127921e-05, + "loss": 3.6762, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962255374376869e-05, + "loss": 3.6773, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961416779625817e-05, + "loss": 3.6841, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.960579822755138e-05, + "loss": 3.6671, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6584, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589042711334066e-05, + "loss": 3.6863, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580656763823546e-05, + "loss": 3.6832, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572270816313026e-05, + "loss": 3.6887, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563884868802506e-05, + "loss": 3.6749, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955551530009572e-05, + "loss": 3.6754, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.95471293525852e-05, + "loss": 3.6706, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953874340507468e-05, + "loss": 3.6737, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953035745756416e-05, + "loss": 3.6833, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952198788885737e-05, + "loss": 3.6637, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951360194134685e-05, + "loss": 3.6992, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950521599383633e-05, + "loss": 3.6729, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.6568, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948846047761902e-05, + "loss": 3.6884, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6676, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947168858259798e-05, + "loss": 3.6567, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6844, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454933066380675e-05, + "loss": 3.678, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.6687, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438161171359635e-05, + "loss": 3.6698, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429775223849115e-05, + "loss": 3.6567, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421389276338595e-05, + "loss": 3.6669, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413003328828075e-05, + "loss": 3.6777, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.6691, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6753, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.9387861865100244e-05, + "loss": 3.6704, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.9379475917589724e-05, + "loss": 3.6865, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.6705, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936272040137241e-05, + "loss": 3.6752, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935433445386189e-05, + "loss": 3.672, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934594850635138e-05, + "loss": 3.666, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6817, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6721, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932080704262355e-05, + "loss": 3.6688, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931242109511303e-05, + "loss": 3.6818, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.93040351476025e-05, + "loss": 3.6574, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6604, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6712, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927889368387468e-05, + "loss": 3.6768, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927050773636415e-05, + "loss": 3.6612, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926213816765737e-05, + "loss": 3.6778, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6611, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.6661, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923698032512581e-05, + "loss": 3.659, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922859437761529e-05, + "loss": 3.6692, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220208430104767e-05, + "loss": 3.6796, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211838861397976e-05, + "loss": 3.6704, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203452913887456e-05, + "loss": 3.6763, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.9195066966376936e-05, + "loss": 3.6623, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.9186681018866416e-05, + "loss": 3.6655, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178295071355896e-05, + "loss": 3.6661, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169925502649105e-05, + "loss": 3.6781, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161539555138585e-05, + "loss": 3.6713, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915315360762807e-05, + "loss": 3.6721, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914476766011755e-05, + "loss": 3.6688, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913638171260703e-05, + "loss": 3.6702, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912801214390024e-05, + "loss": 3.6672, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911962619638972e-05, + "loss": 3.6659, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.91112402488792e-05, + "loss": 3.6583, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910285430136868e-05, + "loss": 3.6746, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.909448473266189e-05, + "loss": 3.6608, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.908609878515137e-05, + "loss": 3.6656, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907771283764085e-05, + "loss": 3.6639, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906932689013033e-05, + "loss": 3.6619, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906094094261981e-05, + "loss": 3.6664, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905255499510929e-05, + "loss": 3.6624, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044185426402505e-05, + "loss": 3.6758, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035799478891985e-05, + "loss": 3.6797, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027413531381465e-05, + "loss": 3.6763, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019027583870945e-05, + "loss": 3.6649, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010641636360425e-05, + "loss": 3.6657, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.9002272067653634e-05, + "loss": 3.6614, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.8993886120143114e-05, + "loss": 3.6685, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.8985500172632594e-05, + "loss": 3.6713, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977114225122074e-05, + "loss": 3.6542, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896874465641528e-05, + "loss": 3.6651, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896035870890476e-05, + "loss": 3.67, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.6681, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.6618, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.89352008663732e-05, + "loss": 3.6656, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6616, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.89184453501559e-05, + "loss": 3.6759, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6686, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890167345513486e-05, + "loss": 3.6798, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889330388642807e-05, + "loss": 3.6559, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.6664, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6735, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886814604389651e-05, + "loss": 3.6668, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885976009638599e-05, + "loss": 3.6663, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885137414887546e-05, + "loss": 3.6645, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.6666, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834618632658156e-05, + "loss": 3.6863, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882623268514764e-05, + "loss": 3.663, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817846737637116e-05, + "loss": 3.669, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880947716893033e-05, + "loss": 3.6688, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880109122141981e-05, + "loss": 3.663, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792705273909285e-05, + "loss": 3.6619, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784319326398765e-05, + "loss": 3.6593, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.6633, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6565, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759177862670934e-05, + "loss": 3.6669, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8557000160217285, + "eval_runtime": 306.0712, + "eval_samples_per_second": 1246.739, + "eval_steps_per_second": 38.962, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750791915160414e-05, + "loss": 3.6643, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742405967649894e-05, + "loss": 3.6558, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.6617, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6695, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6772, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6625, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870050898770476e-05, + "loss": 3.6634, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869212304019424e-05, + "loss": 3.6576, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.6569, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6649, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.663, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6553, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6674, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.65, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6539, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625068217717544e-05, + "loss": 3.6416, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616682270207024e-05, + "loss": 3.6585, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608296322696503e-05, + "loss": 3.6631, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599910375185983e-05, + "loss": 3.6485, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859154080647919e-05, + "loss": 3.6671, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858315485896867e-05, + "loss": 3.6641, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857476891145815e-05, + "loss": 3.6663, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856638296394763e-05, + "loss": 3.6574, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855801339524084e-05, + "loss": 3.6586, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854962744773032e-05, + "loss": 3.6585, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.85412415002198e-05, + "loss": 3.6633, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853285555270929e-05, + "loss": 3.6482, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.85244859840025e-05, + "loss": 3.6631, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851610003649198e-05, + "loss": 3.6471, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850771408898146e-05, + "loss": 3.6541, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849932814147094e-05, + "loss": 3.6602, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8490958572764146e-05, + "loss": 3.665, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482572625253626e-05, + "loss": 3.6569, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474186677743106e-05, + "loss": 3.6716, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465800730232586e-05, + "loss": 3.6512, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457414782722066e-05, + "loss": 3.6578, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6642, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6449, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.843227331899424e-05, + "loss": 3.6501, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.842388737148372e-05, + "loss": 3.6501, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.6452, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.840711547646268e-05, + "loss": 3.6522, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839872952895216e-05, + "loss": 3.6623, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839034358144164e-05, + "loss": 3.6501, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838195763393112e-05, + "loss": 3.6513, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837358806522433e-05, + "loss": 3.6514, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836520211771381e-05, + "loss": 3.6564, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835681617020329e-05, + "loss": 3.6417, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834843022269277e-05, + "loss": 3.6348, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340044275182244e-05, + "loss": 3.6622, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833167470647546e-05, + "loss": 3.6576, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832328875896494e-05, + "loss": 3.667, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831490281145442e-05, + "loss": 3.6477, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.83065168639439e-05, + "loss": 3.6504, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.8298147295237115e-05, + "loss": 3.6443, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.8289761347726595e-05, + "loss": 3.6455, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828137540021607e-05, + "loss": 3.6615, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827298945270555e-05, + "loss": 3.6341, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.8264619883998764e-05, + "loss": 3.6739, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.8256233936488244e-05, + "loss": 3.6535, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824784798897772e-05, + "loss": 3.6313, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.82394620414672e-05, + "loss": 3.6587, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823107609395668e-05, + "loss": 3.6463, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822270652524989e-05, + "loss": 3.6326, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821432057773937e-05, + "loss": 3.6554, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820593463022885e-05, + "loss": 3.6573, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819754868271833e-05, + "loss": 3.6407, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818917911401154e-05, + "loss": 3.6476, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818079316650102e-05, + "loss": 3.63, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.81724072189905e-05, + "loss": 3.6415, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816402127147998e-05, + "loss": 3.6522, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815565170277319e-05, + "loss": 3.644, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814726575526267e-05, + "loss": 3.6538, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813887980775215e-05, + "loss": 3.6405, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813049386024163e-05, + "loss": 3.6633, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812212429153485e-05, + "loss": 3.646, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811373834402433e-05, + "loss": 3.6543, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810535239651381e-05, + "loss": 3.6462, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809696644900329e-05, + "loss": 3.6423, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088596880296496e-05, + "loss": 3.654, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.8080210932785976e-05, + "loss": 3.6442, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071824985275456e-05, + "loss": 3.6484, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063439037764936e-05, + "loss": 3.6543, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055053090254416e-05, + "loss": 3.6396, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046683521547625e-05, + "loss": 3.631, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038297574037105e-05, + "loss": 3.6434, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029911626526585e-05, + "loss": 3.6545, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021525679016065e-05, + "loss": 3.637, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801315611030928e-05, + "loss": 3.6509, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.800477016279876e-05, + "loss": 3.6354, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799638421528824e-05, + "loss": 3.6409, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798799826777772e-05, + "loss": 3.6371, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.79796123202672e-05, + "loss": 3.6449, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797122637275668e-05, + "loss": 3.6539, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796285680404989e-05, + "loss": 3.6473, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795447085653937e-05, + "loss": 3.6516, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794608490902885e-05, + "loss": 3.6399, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793769896151833e-05, + "loss": 3.6395, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792932939281154e-05, + "loss": 3.6419, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792094344530102e-05, + "loss": 3.6518, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912557497790505e-05, + "loss": 3.6485, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904171550279985e-05, + "loss": 3.6514, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895801981573194e-05, + "loss": 3.6431, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.7887416034062674e-05, + "loss": 3.6417, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.7879030086552154e-05, + "loss": 3.6487, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.7870644139041634e-05, + "loss": 3.6409, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786227457033484e-05, + "loss": 3.6369, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785388862282432e-05, + "loss": 3.6486, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.78455026753138e-05, + "loss": 3.637, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783711672780328e-05, + "loss": 3.6397, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782874715909649e-05, + "loss": 3.6373, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782036121158597e-05, + "loss": 3.638, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781197526407546e-05, + "loss": 3.6459, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780358931656494e-05, + "loss": 3.6388, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779520336905442e-05, + "loss": 3.649, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778683380034763e-05, + "loss": 3.6537, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.777844785283711e-05, + "loss": 3.6549, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777006190532659e-05, + "loss": 3.6436, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776167595781607e-05, + "loss": 3.6431, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775330638910928e-05, + "loss": 3.6343, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7744920441598757e-05, + "loss": 3.6483, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.7736534494088237e-05, + "loss": 3.6434, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.7728148546577716e-05, + "loss": 3.6307, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719778977870926e-05, + "loss": 3.6403, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771139303036041e-05, + "loss": 3.6428, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770300708284989e-05, + "loss": 3.6471, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769462113533937e-05, + "loss": 3.6376, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768623518782885e-05, + "loss": 3.6417, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767786561912206e-05, + "loss": 3.6346, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766947967161154e-05, + "loss": 3.6523, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766109372410102e-05, + "loss": 3.644, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652707776590494e-05, + "loss": 3.6531, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644321829079974e-05, + "loss": 3.6335, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763595226037319e-05, + "loss": 3.6432, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.762756631286267e-05, + "loss": 3.651, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761918036535215e-05, + "loss": 3.6394, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.761079441784163e-05, + "loss": 3.6434, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760240847033111e-05, + "loss": 3.6387, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7594038901624326e-05, + "loss": 3.649, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.75856529541138e-05, + "loss": 3.6567, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757726700660328e-05, + "loss": 3.6439, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756888105909276e-05, + "loss": 3.6434, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756051149038597e-05, + "loss": 3.6478, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755212554287545e-05, + "loss": 3.6391, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754373959536493e-05, + "loss": 3.6404, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753535364785441e-05, + "loss": 3.6352, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752696770034389e-05, + "loss": 3.6388, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.7518598131637104e-05, + "loss": 3.6338, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.7510212184126584e-05, + "loss": 3.6421, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8520336151123047, + "eval_runtime": 303.5111, + "eval_samples_per_second": 1257.256, + "eval_steps_per_second": 39.29, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.7501826236616064e-05, + "loss": 3.6431, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493440289105544e-05, + "loss": 3.6324, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485054341595024e-05, + "loss": 3.6387, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476668394084504e-05, + "loss": 3.6454, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746829882537771e-05, + "loss": 3.6535, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745991287786719e-05, + "loss": 3.6377, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745152693035667e-05, + "loss": 3.6446, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744314098284615e-05, + "loss": 3.6338, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743475503533563e-05, + "loss": 3.6326, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742638546662884e-05, + "loss": 3.6397, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741799951911832e-05, + "loss": 3.6435, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.74096135716078e-05, + "loss": 3.6328, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740122762409728e-05, + "loss": 3.6411, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.73928580553905e-05, + "loss": 3.6278, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738447210787998e-05, + "loss": 3.6312, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737608616036946e-05, + "loss": 3.6156, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736770021285894e-05, + "loss": 3.6364, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.7359330644152146e-05, + "loss": 3.639, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.7350944696641626e-05, + "loss": 3.6272, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.7342558749131106e-05, + "loss": 3.6421, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.7334172801620586e-05, + "loss": 3.6453, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.7325786854110066e-05, + "loss": 3.6427, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.7317417285403275e-05, + "loss": 3.6351, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.7309031337892755e-05, + "loss": 3.6347, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.7300645390382235e-05, + "loss": 3.6398, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729225944287172e-05, + "loss": 3.6412, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728388987416493e-05, + "loss": 3.6239, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727550392665441e-05, + "loss": 3.6401, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726711797914389e-05, + "loss": 3.6273, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725873203163337e-05, + "loss": 3.6269, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725034608412285e-05, + "loss": 3.6365, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724197651541606e-05, + "loss": 3.6413, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723359056790554e-05, + "loss": 3.6367, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722520462039502e-05, + "loss": 3.6466, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.72168186728845e-05, + "loss": 3.6308, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.720844910417771e-05, + "loss": 3.6377, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720006315666719e-05, + "loss": 3.6441, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191677209156676e-05, + "loss": 3.6201, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183291261646155e-05, + "loss": 3.6236, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174921692939365e-05, + "loss": 3.6276, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166535745428845e-05, + "loss": 3.6187, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.7158149797918324e-05, + "loss": 3.6307, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149763850407804e-05, + "loss": 3.6431, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714137790289728e-05, + "loss": 3.6269, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133008334190493e-05, + "loss": 3.6284, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.7124622386679973e-05, + "loss": 3.6327, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.7116236439169453e-05, + "loss": 3.6321, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107850491658927e-05, + "loss": 3.6187, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709946454414841e-05, + "loss": 3.6101, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709107859663789e-05, + "loss": 3.6369, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.70827090279311e-05, + "loss": 3.6361, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707432308042058e-05, + "loss": 3.6461, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706593713291006e-05, + "loss": 3.6253, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705755118539954e-05, + "loss": 3.6253, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704918161669275e-05, + "loss": 3.6236, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704079566918223e-05, + "loss": 3.6248, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703240972167171e-05, + "loss": 3.6393, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702402377416119e-05, + "loss": 3.6098, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701563782665067e-05, + "loss": 3.6529, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700726825794388e-05, + "loss": 3.6321, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699888231043337e-05, + "loss": 3.6101, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699049636292285e-05, + "loss": 3.6359, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698211041541233e-05, + "loss": 3.6223, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973740846705536e-05, + "loss": 3.6106, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.6965354899195016e-05, + "loss": 3.6346, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.6956968951684496e-05, + "loss": 3.6345, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.6948583004173976e-05, + "loss": 3.6175, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.6940213435467185e-05, + "loss": 3.6314, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931827487956665e-05, + "loss": 3.6069, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923441540446145e-05, + "loss": 3.6206, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915055592935625e-05, + "loss": 3.6236, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906686024228834e-05, + "loss": 3.6261, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689830007671832e-05, + "loss": 3.6293, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.68899141292078e-05, + "loss": 3.6217, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688152818169728e-05, + "loss": 3.6426, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687315861299049e-05, + "loss": 3.6243, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686477266547997e-05, + "loss": 3.633, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685638671796945e-05, + "loss": 3.6223, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.684800077045893e-05, + "loss": 3.6194, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683963120175214e-05, + "loss": 3.6325, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683124525424162e-05, + "loss": 3.6227, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.68228593067311e-05, + "loss": 3.6251, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681447335922058e-05, + "loss": 3.6359, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680608741171006e-05, + "loss": 3.6176, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797717843003274e-05, + "loss": 3.6079, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789331895492754e-05, + "loss": 3.6204, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780945947982234e-05, + "loss": 3.6334, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772560000471714e-05, + "loss": 3.6136, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676419043176492e-05, + "loss": 3.6297, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.67558044842544e-05, + "loss": 3.6188, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674741853674388e-05, + "loss": 3.6132, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673903258923336e-05, + "loss": 3.6164, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673064664172284e-05, + "loss": 3.621, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672227707301605e-05, + "loss": 3.6351, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671389112550553e-05, + "loss": 3.6255, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670550517799501e-05, + "loss": 3.6284, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669711923048449e-05, + "loss": 3.6194, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668874966177771e-05, + "loss": 3.6166, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668036371426719e-05, + "loss": 3.6187, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667197776675667e-05, + "loss": 3.6308, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666359181924615e-05, + "loss": 3.6271, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.665522225053936e-05, + "loss": 3.6273, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664683630302884e-05, + "loss": 3.6238, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663845035551832e-05, + "loss": 3.6165, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.66300644080078e-05, + "loss": 3.6291, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662167846049728e-05, + "loss": 3.6205, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613308891790486e-05, + "loss": 3.6141, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604922944279966e-05, + "loss": 3.6231, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596536996769446e-05, + "loss": 3.6189, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588151049258926e-05, + "loss": 3.6186, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657978148055214e-05, + "loss": 3.6162, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657139553304162e-05, + "loss": 3.6141, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.65630095855311e-05, + "loss": 3.6217, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655462363802058e-05, + "loss": 3.6223, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654625406931379e-05, + "loss": 3.6222, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653786812180327e-05, + "loss": 3.6317, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652948217429275e-05, + "loss": 3.6357, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652109622678223e-05, + "loss": 3.6192, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.6512710279271704e-05, + "loss": 3.6207, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650434071056492e-05, + "loss": 3.6139, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64959547630544e-05, + "loss": 3.6236, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648756881554388e-05, + "loss": 3.6202, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647918286803336e-05, + "loss": 3.6115, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470813299326575e-05, + "loss": 3.6157, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462427351816055e-05, + "loss": 3.625, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454041404305535e-05, + "loss": 3.6267, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644565545679501e-05, + "loss": 3.6134, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643726950928449e-05, + "loss": 3.6208, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428899940577704e-05, + "loss": 3.6182, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642051399306718e-05, + "loss": 3.6276, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641212804555666e-05, + "loss": 3.6239, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640374209804614e-05, + "loss": 3.6329, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639535615053562e-05, + "loss": 3.6123, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638698658182883e-05, + "loss": 3.6236, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637860063431831e-05, + "loss": 3.6275, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637021468680779e-05, + "loss": 3.6151, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636182873929727e-05, + "loss": 3.6231, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635344279178675e-05, + "loss": 3.6211, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634507322307996e-05, + "loss": 3.6301, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633668727556944e-05, + "loss": 3.633, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632830132805892e-05, + "loss": 3.6218, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.63199153805484e-05, + "loss": 3.6213, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631154581184161e-05, + "loss": 3.6268, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630315986433109e-05, + "loss": 3.618, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629477391682057e-05, + "loss": 3.618, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628638796931005e-05, + "loss": 3.6171, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627801840060327e-05, + "loss": 3.612, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269632453092747e-05, + "loss": 3.6177, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261246505582227e-05, + "loss": 3.6162, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8501782417297363, + "eval_runtime": 303.0344, + "eval_samples_per_second": 1259.233, + "eval_steps_per_second": 39.352, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252860558071707e-05, + "loss": 3.6184, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244474610561186e-05, + "loss": 3.6127, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236088663050666e-05, + "loss": 3.6191, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227719094343876e-05, + "loss": 3.6215, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219333146833355e-05, + "loss": 3.6308, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210947199322835e-05, + "loss": 3.6192, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202561251812315e-05, + "loss": 3.625, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194191683105524e-05, + "loss": 3.6155, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185805735595004e-05, + "loss": 3.6083, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617741978808449e-05, + "loss": 3.6144, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616903384057397e-05, + "loss": 3.6266, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616064789306345e-05, + "loss": 3.6072, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615227832435666e-05, + "loss": 3.6235, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614389237684614e-05, + "loss": 3.6047, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613550642933562e-05, + "loss": 3.6092, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.61271204818251e-05, + "loss": 3.5972, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611875091311831e-05, + "loss": 3.6168, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611036496560779e-05, + "loss": 3.6151, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610197901809727e-05, + "loss": 3.6111, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609359307058675e-05, + "loss": 3.6131, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608520712307623e-05, + "loss": 3.6284, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.6076837554369445e-05, + "loss": 3.6186, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068451606858925e-05, + "loss": 3.6151, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060065659348405e-05, + "loss": 3.6116, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051679711837885e-05, + "loss": 3.6216, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043310143131094e-05, + "loss": 3.6148, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034924195620574e-05, + "loss": 3.6082, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026538248110054e-05, + "loss": 3.6188, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018152300599534e-05, + "loss": 3.6059, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600978273189274e-05, + "loss": 3.6041, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600139678438222e-05, + "loss": 3.6166, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.59930108368717e-05, + "loss": 3.615, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598462488936118e-05, + "loss": 3.6198, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597623894185066e-05, + "loss": 3.6226, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596786937314388e-05, + "loss": 3.6083, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595948342563336e-05, + "loss": 3.6177, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595109747812284e-05, + "loss": 3.6194, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594271153061231e-05, + "loss": 3.6046, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593432558310179e-05, + "loss": 3.6068, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592595601439501e-05, + "loss": 3.6021, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591757006688449e-05, + "loss": 3.601, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590918411937396e-05, + "loss": 3.612, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590079817186344e-05, + "loss": 3.6236, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892428603156656e-05, + "loss": 3.6076, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884042655646136e-05, + "loss": 3.605, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875656708135616e-05, + "loss": 3.613, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867270760625096e-05, + "loss": 3.6112, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858884813114576e-05, + "loss": 3.5994, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850515244407785e-05, + "loss": 3.5922, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842129296897265e-05, + "loss": 3.6157, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833743349386745e-05, + "loss": 3.6182, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825357401876225e-05, + "loss": 3.6216, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816987833169434e-05, + "loss": 3.6064, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808601885658914e-05, + "loss": 3.6034, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800215938148394e-05, + "loss": 3.6028, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791829990637874e-05, + "loss": 3.6021, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783444043127354e-05, + "loss": 3.6206, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577507447442057e-05, + "loss": 3.5921, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576668852691005e-05, + "loss": 3.6283, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575830257939953e-05, + "loss": 3.6132, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574991663188901e-05, + "loss": 3.5947, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574153068437849e-05, + "loss": 3.6108, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.57331611156717e-05, + "loss": 3.6019, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572477516816118e-05, + "loss": 3.5917, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571638922065066e-05, + "loss": 3.6099, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570800327314014e-05, + "loss": 3.615, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569963370443335e-05, + "loss": 3.598, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569124775692283e-05, + "loss": 3.6115, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568286180941231e-05, + "loss": 3.5881, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567447586190179e-05, + "loss": 3.601, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666106293195004e-05, + "loss": 3.6047, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657720345684483e-05, + "loss": 3.6062, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649334398173963e-05, + "loss": 3.6046, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640948450663443e-05, + "loss": 3.6065, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563257888195665e-05, + "loss": 3.6198, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562419293444613e-05, + "loss": 3.608, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561580698693561e-05, + "loss": 3.612, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560742103942509e-05, + "loss": 3.603, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.55990514707183e-05, + "loss": 3.5997, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559066552320778e-05, + "loss": 3.6139, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558227957569726e-05, + "loss": 3.6052, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557389362818674e-05, + "loss": 3.6051, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556552405947996e-05, + "loss": 3.6139, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555713811196944e-05, + "loss": 3.6025, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554875216445892e-05, + "loss": 3.5858, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.55403662169484e-05, + "loss": 3.6022, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.5531996648241606e-05, + "loss": 3.608, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523610700731086e-05, + "loss": 3.5964, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515224753220566e-05, + "loss": 3.6057, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.5506838805710046e-05, + "loss": 3.6019, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.5498452858199526e-05, + "loss": 3.5921, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490083289492735e-05, + "loss": 3.5983, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481697341982215e-05, + "loss": 3.5989, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473311394471695e-05, + "loss": 3.6112, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464925446961175e-05, + "loss": 3.6087, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545655587825439e-05, + "loss": 3.6098, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544816993074387e-05, + "loss": 3.5958, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.543978398323335e-05, + "loss": 3.5975, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543139803572283e-05, + "loss": 3.6021, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542301208821231e-05, + "loss": 3.6088, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541464251950552e-05, + "loss": 3.6085, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406256571995e-05, + "loss": 3.6076, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539787062448448e-05, + "loss": 3.6005, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538948467697396e-05, + "loss": 3.5982, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538109872946344e-05, + "loss": 3.6114, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537272916075665e-05, + "loss": 3.5975, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536434321324613e-05, + "loss": 3.601, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535595726573561e-05, + "loss": 3.6027, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347571318225095e-05, + "loss": 3.5986, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.5339201749518304e-05, + "loss": 3.6, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330815802007784e-05, + "loss": 3.5946, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322429854497264e-05, + "loss": 3.594, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5314043906986744e-05, + "loss": 3.6054, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530567433827995e-05, + "loss": 3.6026, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529728839076943e-05, + "loss": 3.5996, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528890244325891e-05, + "loss": 3.6103, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280516495748386e-05, + "loss": 3.619, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272130548237866e-05, + "loss": 3.5991, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526376097953108e-05, + "loss": 3.5989, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525537503202056e-05, + "loss": 3.5973, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524698908451004e-05, + "loss": 3.6028, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523860313699952e-05, + "loss": 3.601, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230217189489e-05, + "loss": 3.5954, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522184762078222e-05, + "loss": 3.5958, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521346167327169e-05, + "loss": 3.6048, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520507572576117e-05, + "loss": 3.6012, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519668977825065e-05, + "loss": 3.5974, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518832020954386e-05, + "loss": 3.6039, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517993426203334e-05, + "loss": 3.6008, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517154831452282e-05, + "loss": 3.6017, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.51631623670123e-05, + "loss": 3.6083, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515477641950179e-05, + "loss": 3.6113, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146406850794996e-05, + "loss": 3.5949, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5138020903284476e-05, + "loss": 3.6025, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129634955773956e-05, + "loss": 3.6061, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121249008263436e-05, + "loss": 3.597, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5112879439556645e-05, + "loss": 3.5989, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104493492046125e-05, + "loss": 3.5997, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096107544535605e-05, + "loss": 3.6112, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.5087721597025085e-05, + "loss": 3.6129, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.5079352028318294e-05, + "loss": 3.6043, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.5070966080807774e-05, + "loss": 3.6001, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.5062580133297254e-05, + "loss": 3.6052, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505419418578674e-05, + "loss": 3.6014, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504582461707995e-05, + "loss": 3.5966, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503743866956943e-05, + "loss": 3.6039, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502905272205891e-05, + "loss": 3.5908, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502066677454839e-05, + "loss": 3.6002, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.50122972058416e-05, + "loss": 3.5966, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.849426746368408, + "eval_runtime": 310.3948, + "eval_samples_per_second": 1229.373, + "eval_steps_per_second": 38.419, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500391125833108e-05, + "loss": 3.6114, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499552531082056e-05, + "loss": 3.5893, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.498713936331004e-05, + "loss": 3.5986, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497875341579952e-05, + "loss": 3.6078, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970367468289e-05, + "loss": 3.605, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.496199789958221e-05, + "loss": 3.6065, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953611952071694e-05, + "loss": 3.6032, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945226004561174e-05, + "loss": 3.5948, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936840057050654e-05, + "loss": 3.5885, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492847048834386e-05, + "loss": 3.6014, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492008454083334e-05, + "loss": 3.598, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.491169859332282e-05, + "loss": 3.5941, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.49033126458123e-05, + "loss": 3.6015, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489494307710551e-05, + "loss": 3.5843, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488655712959499e-05, + "loss": 3.5913, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487817118208447e-05, + "loss": 3.5764, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486978523457395e-05, + "loss": 3.6006, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486141566586716e-05, + "loss": 3.5917, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485302971835665e-05, + "loss": 3.5947, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484464377084613e-05, + "loss": 3.5948, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483625782333561e-05, + "loss": 3.6051, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482787187582509e-05, + "loss": 3.6004, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48195023071183e-05, + "loss": 3.5955, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481111635960778e-05, + "loss": 3.5937, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.480273041209726e-05, + "loss": 3.6057, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794344464586737e-05, + "loss": 3.5953, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4785974895879946e-05, + "loss": 3.5864, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777588948369426e-05, + "loss": 3.6004, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769203000858906e-05, + "loss": 3.5818, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760817053348386e-05, + "loss": 3.5914, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.47524474846416e-05, + "loss": 3.6007, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.474406153713108e-05, + "loss": 3.5964, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.473567558962056e-05, + "loss": 3.5978, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.472728964211004e-05, + "loss": 3.6049, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.471892007340325e-05, + "loss": 3.5925, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471053412589273e-05, + "loss": 3.6005, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470214817838221e-05, + "loss": 3.6026, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469376223087169e-05, + "loss": 3.5834, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.46853926621649e-05, + "loss": 3.5895, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467700671465438e-05, + "loss": 3.5827, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466862076714386e-05, + "loss": 3.5838, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466023481963334e-05, + "loss": 3.5918, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465184887212282e-05, + "loss": 3.602, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.4643479303416035e-05, + "loss": 3.5879, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.4635093355905515e-05, + "loss": 3.5876, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.4626707408394995e-05, + "loss": 3.5938, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461832146088447e-05, + "loss": 3.5935, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609951892177684e-05, + "loss": 3.5827, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601565944667164e-05, + "loss": 3.571, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593179997156644e-05, + "loss": 3.5927, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458479404964612e-05, + "loss": 3.6043, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.45764081021356e-05, + "loss": 3.6022, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456803853342881e-05, + "loss": 3.5842, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455965258591829e-05, + "loss": 3.587, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455126663840777e-05, + "loss": 3.5863, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454288069089725e-05, + "loss": 3.5787, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453451112219047e-05, + "loss": 3.6087, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.452612517467994e-05, + "loss": 3.5731, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451773922716942e-05, + "loss": 3.6085, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.45093532796589e-05, + "loss": 3.5943, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450098371095212e-05, + "loss": 3.5771, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449259776344159e-05, + "loss": 3.5921, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448421181593107e-05, + "loss": 3.5865, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447582586842055e-05, + "loss": 3.573, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446743992091003e-05, + "loss": 3.592, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459070352203247e-05, + "loss": 3.5963, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4450684404692727e-05, + "loss": 3.5803, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442298457182206e-05, + "loss": 3.5903, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4433912509671686e-05, + "loss": 3.567, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425542940964896e-05, + "loss": 3.5834, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417156993454375e-05, + "loss": 3.584, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4408771045943855e-05, + "loss": 3.5904, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.4400385098433335e-05, + "loss": 3.584, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.4392015529726544e-05, + "loss": 3.5872, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.4383629582216024e-05, + "loss": 3.6002, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.4375243634705504e-05, + "loss": 3.5864, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366857687194984e-05, + "loss": 3.592, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358471739684464e-05, + "loss": 3.5863, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435010217097768e-05, + "loss": 3.5829, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434171622346716e-05, + "loss": 3.5937, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433333027595664e-05, + "loss": 3.584, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432494432844612e-05, + "loss": 3.5905, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431657475973933e-05, + "loss": 3.5922, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430818881222881e-05, + "loss": 3.5876, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429980286471829e-05, + "loss": 3.5647, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429141691720777e-05, + "loss": 3.5868, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428304734850098e-05, + "loss": 3.5877, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427466140099046e-05, + "loss": 3.5798, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426627545347994e-05, + "loss": 3.5874, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.425788950596942e-05, + "loss": 3.5828, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.42495035584589e-05, + "loss": 3.5769, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424111761094838e-05, + "loss": 3.5786, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.4232748042241594e-05, + "loss": 3.5844, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224362094731074e-05, + "loss": 3.589, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215976147220554e-05, + "loss": 3.5905, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207590199710034e-05, + "loss": 3.5904, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419922063100324e-05, + "loss": 3.5813, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419083468349272e-05, + "loss": 3.5793, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.41824487359822e-05, + "loss": 3.5832, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417406278847168e-05, + "loss": 3.5916, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416569321976489e-05, + "loss": 3.5877, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415730727225437e-05, + "loss": 3.5886, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414892132474385e-05, + "loss": 3.5834, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414053537723333e-05, + "loss": 3.5794, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413214942972282e-05, + "loss": 3.5904, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412377986101603e-05, + "loss": 3.5804, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411539391350551e-05, + "loss": 3.5827, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410700796599499e-05, + "loss": 3.584, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409862201848447e-05, + "loss": 3.5806, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.4090252449777676e-05, + "loss": 3.5804, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.4081866502267156e-05, + "loss": 3.5798, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073480554756636e-05, + "loss": 3.5725, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065094607246116e-05, + "loss": 3.5864, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4056725038539325e-05, + "loss": 3.5913, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048339091028805e-05, + "loss": 3.5782, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4039953143518285e-05, + "loss": 3.5923, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403156719600777e-05, + "loss": 3.6001, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402319762730098e-05, + "loss": 3.5828, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401481167979046e-05, + "loss": 3.5819, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400642573227994e-05, + "loss": 3.5836, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399803978476942e-05, + "loss": 3.5834, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.39896538372589e-05, + "loss": 3.5811, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398128426855211e-05, + "loss": 3.579, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397289832104159e-05, + "loss": 3.5792, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396451237353107e-05, + "loss": 3.5862, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395612642602054e-05, + "loss": 3.5839, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394775685731376e-05, + "loss": 3.5842, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393937090980324e-05, + "loss": 3.583, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930984962292726e-05, + "loss": 3.5834, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.39225990147822e-05, + "loss": 3.5792, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914229446075415e-05, + "loss": 3.595, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905843498564895e-05, + "loss": 3.591, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897457551054375e-05, + "loss": 3.5794, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388907160354385e-05, + "loss": 3.5798, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880702034837064e-05, + "loss": 3.5914, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872316087326544e-05, + "loss": 3.5756, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386393013981602e-05, + "loss": 3.5872, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.38555441923055e-05, + "loss": 3.5829, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384717462359871e-05, + "loss": 3.5938, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383878867608819e-05, + "loss": 3.5915, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383040272857767e-05, + "loss": 3.5918, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382201678106715e-05, + "loss": 3.5809, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381363083355663e-05, + "loss": 3.5914, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380526126484985e-05, + "loss": 3.5807, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379687531733932e-05, + "loss": 3.5767, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.37884893698288e-05, + "loss": 3.5849, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378010342231828e-05, + "loss": 3.5713, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377173385361149e-05, + "loss": 3.5845, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376334790610097e-05, + "loss": 3.5791, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.8482818603515625, + "eval_runtime": 303.0798, + "eval_samples_per_second": 1259.045, + "eval_steps_per_second": 39.346, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375496195859045e-05, + "loss": 3.5846, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374657601107993e-05, + "loss": 3.5742, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738206442373146e-05, + "loss": 3.5795, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729820494862626e-05, + "loss": 3.5902, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721434547352106e-05, + "loss": 3.5854, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713048599841586e-05, + "loss": 3.5936, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3704679031134795e-05, + "loss": 3.5803, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696293083624275e-05, + "loss": 3.5785, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3687907136113755e-05, + "loss": 3.5682, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.3679521188603235e-05, + "loss": 3.5836, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.3671151619896444e-05, + "loss": 3.5819, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.3662765672385924e-05, + "loss": 3.577, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.3654379724875404e-05, + "loss": 3.5895, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.3645993777364884e-05, + "loss": 3.5637, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.36376242086581e-05, + "loss": 3.5713, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362923826114758e-05, + "loss": 3.5672, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362085231363706e-05, + "loss": 3.5762, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361246636612654e-05, + "loss": 3.5777, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360409679741975e-05, + "loss": 3.5753, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359571084990923e-05, + "loss": 3.5795, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358732490239871e-05, + "loss": 3.585, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357893895488819e-05, + "loss": 3.5834, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.35705693861814e-05, + "loss": 3.5801, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356218343867088e-05, + "loss": 3.5752, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355379749116036e-05, + "loss": 3.591, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354541154364984e-05, + "loss": 3.5759, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3537041974943054e-05, + "loss": 3.5732, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528656027432534e-05, + "loss": 3.5822, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520270079922013e-05, + "loss": 3.5645, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3511884132411493e-05, + "loss": 3.5721, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.35035145637047e-05, + "loss": 3.5792, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349512861619418e-05, + "loss": 3.5774, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348674266868366e-05, + "loss": 3.5825, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347835672117314e-05, + "loss": 3.586, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.346997077366262e-05, + "loss": 3.5753, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346160120495583e-05, + "loss": 3.5809, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345321525744531e-05, + "loss": 3.585, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344482930993479e-05, + "loss": 3.5671, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343644336242427e-05, + "loss": 3.5726, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342807379371749e-05, + "loss": 3.5624, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341968784620697e-05, + "loss": 3.5704, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341130189869645e-05, + "loss": 3.5695, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340291595118593e-05, + "loss": 3.59, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394546382479136e-05, + "loss": 3.5687, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.3386160434968616e-05, + "loss": 3.5704, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.3377774487458096e-05, + "loss": 3.574, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.3369388539947576e-05, + "loss": 3.5741, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3361018971240785e-05, + "loss": 3.5688, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352633023730265e-05, + "loss": 3.5551, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344247076219745e-05, + "loss": 3.5782, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335861128709225e-05, + "loss": 3.5837, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332747518119871e-05, + "loss": 3.581, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331910561249192e-05, + "loss": 3.5724, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.33107196649814e-05, + "loss": 3.5656, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330233371747088e-05, + "loss": 3.5732, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329394776996036e-05, + "loss": 3.5596, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328557820125357e-05, + "loss": 3.5891, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327719225374305e-05, + "loss": 3.5577, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326880630623253e-05, + "loss": 3.5887, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326042035872201e-05, + "loss": 3.5769, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325205079001522e-05, + "loss": 3.5562, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.32436648425047e-05, + "loss": 3.5737, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323527889499418e-05, + "loss": 3.5702, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.3226892947483665e-05, + "loss": 3.5577, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.3218523378776874e-05, + "loss": 3.5658, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.3210137431266354e-05, + "loss": 3.5852, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.3201751483755834e-05, + "loss": 3.5659, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.3193365536245314e-05, + "loss": 3.5692, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.3184995967538523e-05, + "loss": 3.5549, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176610020028e-05, + "loss": 3.5684, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316822407251748e-05, + "loss": 3.5658, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.315983812500696e-05, + "loss": 3.5735, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315146855630017e-05, + "loss": 3.5675, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314308260878965e-05, + "loss": 3.5724, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313469666127913e-05, + "loss": 3.5785, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312631071376862e-05, + "loss": 3.569, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311794114506183e-05, + "loss": 3.5746, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.310955519755131e-05, + "loss": 3.5705, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.310116925004079e-05, + "loss": 3.568, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309278330253027e-05, + "loss": 3.5748, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308441373382348e-05, + "loss": 3.5684, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307602778631296e-05, + "loss": 3.5717, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306764183880244e-05, + "loss": 3.5762, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305925589129192e-05, + "loss": 3.5687, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.3050886322585126e-05, + "loss": 3.5518, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042500375074606e-05, + "loss": 3.5689, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034114427564086e-05, + "loss": 3.5661, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302572848005357e-05, + "loss": 3.5671, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301735891134678e-05, + "loss": 3.5656, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300897296383626e-05, + "loss": 3.5705, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300058701632574e-05, + "loss": 3.5552, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299220106881522e-05, + "loss": 3.5628, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298383150010843e-05, + "loss": 3.5649, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297544555259791e-05, + "loss": 3.5751, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296705960508739e-05, + "loss": 3.5702, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2958673657576864e-05, + "loss": 3.5764, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295030408887008e-05, + "loss": 3.5577, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294191814135956e-05, + "loss": 3.5662, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293353219384904e-05, + "loss": 3.5664, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292514624633852e-05, + "loss": 3.5752, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916776677631735e-05, + "loss": 3.5708, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908390730121215e-05, + "loss": 3.5744, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2900004782610695e-05, + "loss": 3.567, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289161883510017e-05, + "loss": 3.5625, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883249266393384e-05, + "loss": 3.5768, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2874863318882864e-05, + "loss": 3.5601, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286647737137234e-05, + "loss": 3.565, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285809142386182e-05, + "loss": 3.5664, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.2849721855155033e-05, + "loss": 3.5637, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284133590764451e-05, + "loss": 3.5628, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283294996013399e-05, + "loss": 3.5657, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282456401262347e-05, + "loss": 3.5557, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281619444391669e-05, + "loss": 3.5696, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280780849640617e-05, + "loss": 3.5729, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279942254889564e-05, + "loss": 3.5611, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279103660138512e-05, + "loss": 3.5742, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278266703267834e-05, + "loss": 3.5813, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277428108516781e-05, + "loss": 3.5649, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.276589513765729e-05, + "loss": 3.5658, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.275750919014677e-05, + "loss": 3.5643, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.274913962143999e-05, + "loss": 3.5656, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274075367392947e-05, + "loss": 3.5628, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273236772641895e-05, + "loss": 3.5631, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272398177890843e-05, + "loss": 3.5607, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271559583139791e-05, + "loss": 3.5695, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707226262691116e-05, + "loss": 3.5689, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2698840315180596e-05, + "loss": 3.5636, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.2690454367670076e-05, + "loss": 3.5651, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.2682068420159556e-05, + "loss": 3.566, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.2673698851452765e-05, + "loss": 3.5616, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.2665312903942245e-05, + "loss": 3.5783, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.2656926956431725e-05, + "loss": 3.5768, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.2648541008921205e-05, + "loss": 3.5665, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264017144021442e-05, + "loss": 3.5623, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.26317854927039e-05, + "loss": 3.5696, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262339954519338e-05, + "loss": 3.5642, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261501359768286e-05, + "loss": 3.5698, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260664402897607e-05, + "loss": 3.5652, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259825808146555e-05, + "loss": 3.5835, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258987213395503e-05, + "loss": 3.5662, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258148618644451e-05, + "loss": 3.5762, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257311661773772e-05, + "loss": 3.5638, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.25647306702272e-05, + "loss": 3.5759, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255634472271668e-05, + "loss": 3.564, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254795877520616e-05, + "loss": 3.5591, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.2539589206499374e-05, + "loss": 3.5705, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531203258988854e-05, + "loss": 3.5562, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.2522817311478334e-05, + "loss": 3.57, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.2514431363967814e-05, + "loss": 3.5578, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.849764108657837, + "eval_runtime": 302.8026, + "eval_samples_per_second": 1260.197, + "eval_steps_per_second": 39.382, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250606179526102e-05, + "loss": 3.5619, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.24976758477505e-05, + "loss": 3.5634, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248928990023998e-05, + "loss": 3.5596, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248090395272946e-05, + "loss": 3.575, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247251800521894e-05, + "loss": 3.5685, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246414843651215e-05, + "loss": 3.577, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245576248900163e-05, + "loss": 3.5633, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244737654149111e-05, + "loss": 3.5608, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243899059398059e-05, + "loss": 3.5559, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243062102527381e-05, + "loss": 3.5671, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242223507776329e-05, + "loss": 3.5627, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241384913025277e-05, + "loss": 3.5613, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240546318274225e-05, + "loss": 3.5715, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239709361403546e-05, + "loss": 3.5496, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238870766652494e-05, + "loss": 3.5504, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238032171901442e-05, + "loss": 3.5513, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.23719357715039e-05, + "loss": 3.5586, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363566202797106e-05, + "loss": 3.5602, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2355180255286586e-05, + "loss": 3.5618, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346794307776066e-05, + "loss": 3.5612, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338408360265546e-05, + "loss": 3.572, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233003879155876e-05, + "loss": 3.5614, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232165284404824e-05, + "loss": 3.5654, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231326689653772e-05, + "loss": 3.5566, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.23048809490272e-05, + "loss": 3.5744, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229651138032041e-05, + "loss": 3.5597, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228812543280989e-05, + "loss": 3.5599, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227973948529937e-05, + "loss": 3.5602, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227135353778885e-05, + "loss": 3.551, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226298396908206e-05, + "loss": 3.5568, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225459802157154e-05, + "loss": 3.5611, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224621207406102e-05, + "loss": 3.5618, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.22378261265505e-05, + "loss": 3.5664, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222944017903998e-05, + "loss": 3.5711, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221070610333195e-05, + "loss": 3.5585, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2212684662822675e-05, + "loss": 3.5668, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2204298715312155e-05, + "loss": 3.5648, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2195912767801635e-05, + "loss": 3.5529, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187526820291115e-05, + "loss": 3.5571, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2179157251584324e-05, + "loss": 3.5474, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.2170771304073804e-05, + "loss": 3.5556, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.2162385356563284e-05, + "loss": 3.5547, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153999409052764e-05, + "loss": 3.5728, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214562984034597e-05, + "loss": 3.5507, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213724389283545e-05, + "loss": 3.5549, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212885794532493e-05, + "loss": 3.559, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212047199781442e-05, + "loss": 3.5598, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211210242910763e-05, + "loss": 3.5563, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210371648159711e-05, + "loss": 3.535, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209533053408659e-05, + "loss": 3.5585, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208694458657607e-05, + "loss": 3.5675, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207857501786928e-05, + "loss": 3.5683, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207018907035876e-05, + "loss": 3.5524, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206180312284824e-05, + "loss": 3.5498, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205341717533772e-05, + "loss": 3.5587, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204503122782719e-05, + "loss": 3.5465, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203666165912041e-05, + "loss": 3.5717, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202827571160989e-05, + "loss": 3.5414, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201988976409937e-05, + "loss": 3.5733, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201152019539258e-05, + "loss": 3.5622, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200313424788206e-05, + "loss": 3.5413, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199474830037154e-05, + "loss": 3.5551, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.1986362352861016e-05, + "loss": 3.5593, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.1977976405350496e-05, + "loss": 3.5419, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196960683664371e-05, + "loss": 3.5483, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196122088913319e-05, + "loss": 3.5689, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.1952834941622665e-05, + "loss": 3.5525, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944448994112145e-05, + "loss": 3.5529, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193607942540536e-05, + "loss": 3.5366, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192769347789484e-05, + "loss": 3.5514, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191930753038432e-05, + "loss": 3.5494, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.19109215828738e-05, + "loss": 3.561, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902552014167016e-05, + "loss": 3.5478, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189416606665649e-05, + "loss": 3.5584, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188578011914597e-05, + "loss": 3.5604, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187739417163545e-05, + "loss": 3.5574, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1869024602928665e-05, + "loss": 3.5556, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186063865541814e-05, + "loss": 3.5528, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185225270790762e-05, + "loss": 3.5574, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.18438667603971e-05, + "loss": 3.5581, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835497191690314e-05, + "loss": 3.5541, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1827111244179794e-05, + "loss": 3.5547, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.1818725296669274e-05, + "loss": 3.5553, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.1810339349158754e-05, + "loss": 3.5525, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.1801953401648234e-05, + "loss": 3.538, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179358383294144e-05, + "loss": 3.5522, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178519788543092e-05, + "loss": 3.5513, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.17768119379204e-05, + "loss": 3.5516, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176842599040988e-05, + "loss": 3.552, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176005642170309e-05, + "loss": 3.5547, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175167047419257e-05, + "loss": 3.5422, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174328452668205e-05, + "loss": 3.5429, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173489857917153e-05, + "loss": 3.5481, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172652901046475e-05, + "loss": 3.5591, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171814306295423e-05, + "loss": 3.5532, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170975711544371e-05, + "loss": 3.5591, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170137116793319e-05, + "loss": 3.547, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.16930015992264e-05, + "loss": 3.5516, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168461565171588e-05, + "loss": 3.5472, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676229704205357e-05, + "loss": 3.5619, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667843756694837e-05, + "loss": 3.5526, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659474187988046e-05, + "loss": 3.5583, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1651088240477526e-05, + "loss": 3.5511, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642702292967006e-05, + "loss": 3.5453, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634316345456486e-05, + "loss": 3.5643, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.16259467767497e-05, + "loss": 3.5402, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161756082923918e-05, + "loss": 3.5468, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160917488172866e-05, + "loss": 3.5539, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160078893421814e-05, + "loss": 3.5459, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159241936551135e-05, + "loss": 3.5468, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158403341800083e-05, + "loss": 3.5499, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157564747049031e-05, + "loss": 3.5409, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156726152297979e-05, + "loss": 3.5551, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155887557546927e-05, + "loss": 3.5538, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155050600676248e-05, + "loss": 3.5505, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154212005925196e-05, + "loss": 3.5603, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153373411174144e-05, + "loss": 3.5652, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152534816423092e-05, + "loss": 3.5542, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516978595524135e-05, + "loss": 3.5511, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508592648013615e-05, + "loss": 3.546, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500206700503095e-05, + "loss": 3.5515, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491820752992575e-05, + "loss": 3.5467, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483434805482055e-05, + "loss": 3.5512, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.1475065236775264e-05, + "loss": 3.541, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466679289264744e-05, + "loss": 3.5559, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458293341754224e-05, + "loss": 3.5517, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449907394243704e-05, + "loss": 3.5524, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144153782553691e-05, + "loss": 3.5501, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143315187802639e-05, + "loss": 3.5492, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142476593051587e-05, + "loss": 3.5459, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141637998300536e-05, + "loss": 3.562, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140801041429857e-05, + "loss": 3.5589, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139962446678805e-05, + "loss": 3.5536, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139123851927753e-05, + "loss": 3.5428, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138285257176701e-05, + "loss": 3.5536, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137446662425649e-05, + "loss": 3.5502, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.13660970555497e-05, + "loss": 3.5537, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135771110803918e-05, + "loss": 3.5531, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134932516052866e-05, + "loss": 3.5649, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134093921301814e-05, + "loss": 3.5516, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332569644311347e-05, + "loss": 3.5636, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1324183696800826e-05, + "loss": 3.5496, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131579774929031e-05, + "loss": 3.5582, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130741180177979e-05, + "loss": 3.543, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1299042233073e-05, + "loss": 3.5479, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129065628556248e-05, + "loss": 3.5548, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128227033805196e-05, + "loss": 3.5379, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127388439054144e-05, + "loss": 3.5525, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126551482183465e-05, + "loss": 3.5447, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.85017466545105, + "eval_runtime": 305.0961, + "eval_samples_per_second": 1250.724, + "eval_steps_per_second": 39.086, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125712887432413e-05, + "loss": 3.5521, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124874292681361e-05, + "loss": 3.5487, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124035697930309e-05, + "loss": 3.5429, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.12319874105963e-05, + "loss": 3.5582, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122360146308578e-05, + "loss": 3.5539, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121521551557526e-05, + "loss": 3.5624, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120682956806475e-05, + "loss": 3.5465, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1198459999357956e-05, + "loss": 3.547, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1190074051847436e-05, + "loss": 3.5394, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1181688104336916e-05, + "loss": 3.555, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117330215682639e-05, + "loss": 3.5486, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1164932588119605e-05, + "loss": 3.5464, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156546640609085e-05, + "loss": 3.5509, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.1148160693098565e-05, + "loss": 3.5393, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113977474558804e-05, + "loss": 3.5392, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.1131405176881254e-05, + "loss": 3.5396, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.1123019229370734e-05, + "loss": 3.5378, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.1114633281860214e-05, + "loss": 3.5446, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.1106247334349694e-05, + "loss": 3.5478, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109787776564291e-05, + "loss": 3.5445, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108949181813239e-05, + "loss": 3.558, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108110587062186e-05, + "loss": 3.5476, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107271992311134e-05, + "loss": 3.549, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106435035440456e-05, + "loss": 3.544, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105596440689404e-05, + "loss": 3.5591, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104757845938351e-05, + "loss": 3.5404, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103919251187299e-05, + "loss": 3.5464, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103082294316621e-05, + "loss": 3.5412, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102243699565569e-05, + "loss": 3.5427, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101405104814517e-05, + "loss": 3.5414, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100566510063465e-05, + "loss": 3.5439, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099729553192786e-05, + "loss": 3.5505, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0988909584417336e-05, + "loss": 3.5531, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980523636906816e-05, + "loss": 3.5524, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0972137689396296e-05, + "loss": 3.5476, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096376812068951e-05, + "loss": 3.5507, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955382173178985e-05, + "loss": 3.5509, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946996225668465e-05, + "loss": 3.5339, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938610278157945e-05, + "loss": 3.5439, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093024070945116e-05, + "loss": 3.5296, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092185476194064e-05, + "loss": 3.5409, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091346881443012e-05, + "loss": 3.5379, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.09050828669196e-05, + "loss": 3.5556, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089669691940908e-05, + "loss": 3.5428, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088832735070229e-05, + "loss": 3.5363, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087994140319177e-05, + "loss": 3.545, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087155545568125e-05, + "loss": 3.5479, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086316950817073e-05, + "loss": 3.5386, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085479993946394e-05, + "loss": 3.5216, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084641399195342e-05, + "loss": 3.5392, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.08380280444429e-05, + "loss": 3.5536, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082964209693238e-05, + "loss": 3.5506, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.0821272528225595e-05, + "loss": 3.5435, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.0812886580715075e-05, + "loss": 3.5333, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804500633204555e-05, + "loss": 3.545, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0796114685694035e-05, + "loss": 3.5292, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787745116987244e-05, + "loss": 3.5555, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779359169476724e-05, + "loss": 3.5273, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770973221966204e-05, + "loss": 3.5558, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762587274455684e-05, + "loss": 3.5499, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075421770574889e-05, + "loss": 3.528, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074583175823837e-05, + "loss": 3.5407, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073744581072785e-05, + "loss": 3.5468, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072905986321733e-05, + "loss": 3.5221, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072069029451055e-05, + "loss": 3.5331, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071230434700003e-05, + "loss": 3.5558, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.070391839948951e-05, + "loss": 3.5371, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069553245197899e-05, + "loss": 3.5362, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.06871628832722e-05, + "loss": 3.5269, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067877693576168e-05, + "loss": 3.5357, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067039098825116e-05, + "loss": 3.5299, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066200504074064e-05, + "loss": 3.5494, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.0653635472033846e-05, + "loss": 3.531, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0645249524523326e-05, + "loss": 3.5445, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636863577012806e-05, + "loss": 3.5441, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628477629502286e-05, + "loss": 3.5391, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.06201080607955e-05, + "loss": 3.5408, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061172211328498e-05, + "loss": 3.5374, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060333616577446e-05, + "loss": 3.5437, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059495021826394e-05, + "loss": 3.5416, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058658064955715e-05, + "loss": 3.5396, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057819470204663e-05, + "loss": 3.5403, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056980875453611e-05, + "loss": 3.5419, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056142280702559e-05, + "loss": 3.539, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.05530532383188e-05, + "loss": 3.5244, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.054466729080828e-05, + "loss": 3.5348, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053628134329776e-05, + "loss": 3.5364, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052789539578724e-05, + "loss": 3.5364, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051950944827672e-05, + "loss": 3.5383, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511139879569932e-05, + "loss": 3.5381, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502753932059412e-05, + "loss": 3.5301, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494367984548892e-05, + "loss": 3.5261, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485982037038376e-05, + "loss": 3.5336, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477612468331585e-05, + "loss": 3.5442, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469226520821065e-05, + "loss": 3.5394, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460840573310545e-05, + "loss": 3.5448, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452454625800025e-05, + "loss": 3.5349, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444085057093237e-05, + "loss": 3.5351, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435699109582717e-05, + "loss": 3.5307, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427313162072197e-05, + "loss": 3.5456, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418927214561677e-05, + "loss": 3.5381, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.0410557645854886e-05, + "loss": 3.5453, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0402171698344366e-05, + "loss": 3.5343, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393785750833846e-05, + "loss": 3.5296, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038539980332333e-05, + "loss": 3.5504, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.037703023461654e-05, + "loss": 3.5308, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036864428710602e-05, + "loss": 3.5317, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.03602583395955e-05, + "loss": 3.537, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351872392084978e-05, + "loss": 3.5393, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034350282337819e-05, + "loss": 3.5278, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.033511687586767e-05, + "loss": 3.5349, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.032673092835715e-05, + "loss": 3.5274, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.031834498084663e-05, + "loss": 3.5377, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.030997541213984e-05, + "loss": 3.5387, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030158946462932e-05, + "loss": 3.5353, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.02932035171188e-05, + "loss": 3.5413, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284817569608283e-05, + "loss": 3.5537, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276448000901492e-05, + "loss": 3.5413, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268062053390972e-05, + "loss": 3.5337, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259676105880452e-05, + "loss": 3.5303, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251290158369932e-05, + "loss": 3.5343, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242920589663144e-05, + "loss": 3.5329, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234534642152624e-05, + "loss": 3.5319, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226148694642104e-05, + "loss": 3.5301, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217762747131584e-05, + "loss": 3.5394, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209393178424793e-05, + "loss": 3.5391, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201007230914273e-05, + "loss": 3.5388, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192621283403753e-05, + "loss": 3.534, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0184235335893237e-05, + "loss": 3.5343, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175865767186446e-05, + "loss": 3.528, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167479819675926e-05, + "loss": 3.5475, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159093872165406e-05, + "loss": 3.5477, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150707924654886e-05, + "loss": 3.5404, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142338355948098e-05, + "loss": 3.5284, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133952408437578e-05, + "loss": 3.5351, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125566460927058e-05, + "loss": 3.539, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0117180513416538e-05, + "loss": 3.5386, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108810944709747e-05, + "loss": 3.5373, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0100424997199227e-05, + "loss": 3.5473, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092039049688707e-05, + "loss": 3.5348, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083653102178184e-05, + "loss": 3.5515, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.00752835334714e-05, + "loss": 3.5331, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.006689758596088e-05, + "loss": 3.5419, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005851163845036e-05, + "loss": 3.5349, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050125690939836e-05, + "loss": 3.5289, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041756122233052e-05, + "loss": 3.5439, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033370174722532e-05, + "loss": 3.5278, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.002498422721201e-05, + "loss": 3.5351, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016598279701485e-05, + "loss": 3.5319, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.00082287109947e-05, + "loss": 3.5354, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.851316452026367, + "eval_runtime": 305.47, + "eval_samples_per_second": 1249.193, + "eval_steps_per_second": 39.038, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.999984276348418e-05, + "loss": 3.531, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991456815973657e-05, + "loss": 3.5329, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9983070868463137e-05, + "loss": 3.5422, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974684920952617e-05, + "loss": 3.5405, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966315352245833e-05, + "loss": 3.5511, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957929404735306e-05, + "loss": 3.5311, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994954345722479e-05, + "loss": 3.5286, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994115750971427e-05, + "loss": 3.5309, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932787941007485e-05, + "loss": 3.5383, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992440199349696e-05, + "loss": 3.5315, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991601604598644e-05, + "loss": 3.5341, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990763009847592e-05, + "loss": 3.533, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989926052976913e-05, + "loss": 3.5259, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989087458225861e-05, + "loss": 3.5301, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988248863474809e-05, + "loss": 3.5242, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987410268723757e-05, + "loss": 3.5204, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986573311853078e-05, + "loss": 3.5303, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985734717102026e-05, + "loss": 3.5345, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848961223509743e-05, + "loss": 3.5289, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840575275999223e-05, + "loss": 3.5465, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832205707292432e-05, + "loss": 3.5299, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823819759781912e-05, + "loss": 3.5364, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815433812271392e-05, + "loss": 3.5295, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807047864760872e-05, + "loss": 3.5423, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798678296054085e-05, + "loss": 3.5289, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790292348543565e-05, + "loss": 3.5338, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781906401033045e-05, + "loss": 3.5268, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773520453522524e-05, + "loss": 3.5345, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765150884815734e-05, + "loss": 3.5203, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756764937305214e-05, + "loss": 3.5302, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748378989794693e-05, + "loss": 3.5375, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739993042284177e-05, + "loss": 3.5328, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731623473577386e-05, + "loss": 3.5376, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723237526066866e-05, + "loss": 3.5361, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714851578556346e-05, + "loss": 3.5289, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706465631045826e-05, + "loss": 3.5401, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698096062339038e-05, + "loss": 3.5236, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689710114828518e-05, + "loss": 3.5259, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681324167317998e-05, + "loss": 3.5187, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672938219807478e-05, + "loss": 3.5245, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664568651100687e-05, + "loss": 3.5218, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656182703590167e-05, + "loss": 3.5387, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647796756079647e-05, + "loss": 3.5274, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963941080856913e-05, + "loss": 3.5246, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963104123986234e-05, + "loss": 3.5314, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962265529235182e-05, + "loss": 3.5323, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.96142693448413e-05, + "loss": 3.5218, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.960588339733078e-05, + "loss": 3.5127, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597513828623992e-05, + "loss": 3.5198, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589127881113472e-05, + "loss": 3.5406, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580741933602952e-05, + "loss": 3.5387, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572355986092432e-05, + "loss": 3.5246, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956398641738564e-05, + "loss": 3.5205, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955560046987512e-05, + "loss": 3.5319, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.95472145223646e-05, + "loss": 3.5154, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538828574854084e-05, + "loss": 3.5364, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530442627343564e-05, + "loss": 3.5135, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522073058636773e-05, + "loss": 3.541, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513687111126253e-05, + "loss": 3.5353, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505301163615733e-05, + "loss": 3.5196, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496915216105213e-05, + "loss": 3.5205, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488545647398426e-05, + "loss": 3.5343, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480159699887906e-05, + "loss": 3.5103, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471773752377385e-05, + "loss": 3.5157, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463387804866865e-05, + "loss": 3.5378, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455018236160075e-05, + "loss": 3.5251, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446632288649554e-05, + "loss": 3.5228, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438246341139038e-05, + "loss": 3.5135, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429860393628518e-05, + "loss": 3.5179, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421490824921727e-05, + "loss": 3.5171, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413104877411207e-05, + "loss": 3.5363, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404718929900687e-05, + "loss": 3.5166, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9396332982390167e-05, + "loss": 3.5297, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938796341368338e-05, + "loss": 3.5269, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937957746617286e-05, + "loss": 3.5325, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937119151866234e-05, + "loss": 3.5234, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936280557115182e-05, + "loss": 3.5256, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354436002445028e-05, + "loss": 3.5276, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9346050054934508e-05, + "loss": 3.5284, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933766410742399e-05, + "loss": 3.526, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.932927815991347e-05, + "loss": 3.523, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.932090859120668e-05, + "loss": 3.5268, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.931252264369616e-05, + "loss": 3.5233, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930413669618564e-05, + "loss": 3.516, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929575074867512e-05, + "loss": 3.5176, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287381179968333e-05, + "loss": 3.5254, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278995232457813e-05, + "loss": 3.5275, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270609284947293e-05, + "loss": 3.5204, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262223337436773e-05, + "loss": 3.5232, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253853768729982e-05, + "loss": 3.5151, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245467821219462e-05, + "loss": 3.512, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237081873708945e-05, + "loss": 3.5183, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228695926198425e-05, + "loss": 3.5261, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220326357491634e-05, + "loss": 3.5251, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211940409981114e-05, + "loss": 3.5302, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203554462470594e-05, + "loss": 3.5256, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195168514960074e-05, + "loss": 3.5177, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186798946253287e-05, + "loss": 3.5171, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178412998742767e-05, + "loss": 3.5279, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170027051232246e-05, + "loss": 3.5287, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161641103721726e-05, + "loss": 3.5301, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153271535014936e-05, + "loss": 3.5191, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144885587504415e-05, + "loss": 3.5163, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.91364996399939e-05, + "loss": 3.5361, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912811369248338e-05, + "loss": 3.5146, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119744123776588e-05, + "loss": 3.5228, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111358176266068e-05, + "loss": 3.5206, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102972228755548e-05, + "loss": 3.526, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094586281245028e-05, + "loss": 3.512, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908621671253824e-05, + "loss": 3.5189, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907783076502772e-05, + "loss": 3.5142, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.90694448175172e-05, + "loss": 3.5246, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906105887000668e-05, + "loss": 3.525, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905268930129989e-05, + "loss": 3.5177, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904430335378937e-05, + "loss": 3.5301, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035917406278853e-05, + "loss": 3.5398, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027531458768332e-05, + "loss": 3.5289, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901916189006154e-05, + "loss": 3.5184, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901077594255102e-05, + "loss": 3.5192, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.90023899950405e-05, + "loss": 3.5185, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8994004047529978e-05, + "loss": 3.5229, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985634478823194e-05, + "loss": 3.5225, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977248531312674e-05, + "loss": 3.5153, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968862583802154e-05, + "loss": 3.5216, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960476636291627e-05, + "loss": 3.5264, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8952107067584843e-05, + "loss": 3.5234, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943721120074323e-05, + "loss": 3.518, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935335172563803e-05, + "loss": 3.5196, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892694922505328e-05, + "loss": 3.5181, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918579656346495e-05, + "loss": 3.5307, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910193708835975e-05, + "loss": 3.5314, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8901807761325452e-05, + "loss": 3.5294, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893421813814932e-05, + "loss": 3.5121, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885052245108148e-05, + "loss": 3.5244, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876666297597628e-05, + "loss": 3.5221, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.88682803500871e-05, + "loss": 3.5242, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.885989440257658e-05, + "loss": 3.5181, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885150845506606e-05, + "loss": 3.5344, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843138886359276e-05, + "loss": 3.519, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834752938848753e-05, + "loss": 3.5415, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826366991338233e-05, + "loss": 3.5189, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.881799742263145e-05, + "loss": 3.531, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809611475120922e-05, + "loss": 3.5186, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801225527610402e-05, + "loss": 3.5189, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792839580099885e-05, + "loss": 3.5281, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.87844700113931e-05, + "loss": 3.5151, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776084063882574e-05, + "loss": 3.5193, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767698116372054e-05, + "loss": 3.5168, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759312168861534e-05, + "loss": 3.5188, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.852893352508545, + "eval_runtime": 307.4616, + "eval_samples_per_second": 1241.101, + "eval_steps_per_second": 38.785, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750926221351014e-05, + "loss": 3.5177, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742540273840494e-05, + "loss": 3.5182, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734154326329978e-05, + "loss": 3.5309, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725768378819458e-05, + "loss": 3.5241, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717398810112667e-05, + "loss": 3.5363, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8709012862602147e-05, + "loss": 3.5194, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700626915091627e-05, + "loss": 3.5162, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692240967581107e-05, + "loss": 3.5163, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.868387139887432e-05, + "loss": 3.5265, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.86754854513638e-05, + "loss": 3.5184, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.866709950385328e-05, + "loss": 3.5183, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.865871355634276e-05, + "loss": 3.5235, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650343987635968e-05, + "loss": 3.5077, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.8641958040125448e-05, + "loss": 3.5185, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863357209261493e-05, + "loss": 3.5091, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862518614510441e-05, + "loss": 3.5108, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.861681657639762e-05, + "loss": 3.5151, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.86084306288871e-05, + "loss": 3.5168, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.860004468137658e-05, + "loss": 3.5139, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.859165873386606e-05, + "loss": 3.5363, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583289165159273e-05, + "loss": 3.5176, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.8574903217648753e-05, + "loss": 3.52, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.8566517270138233e-05, + "loss": 3.5182, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.8558131322627713e-05, + "loss": 3.5233, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.854976175392092e-05, + "loss": 3.5202, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.85413758064104e-05, + "loss": 3.5236, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532989858899885e-05, + "loss": 3.5106, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524603911389365e-05, + "loss": 3.5188, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516234342682574e-05, + "loss": 3.5036, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507848395172054e-05, + "loss": 3.5225, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499462447661534e-05, + "loss": 3.5187, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8491076500151014e-05, + "loss": 3.5202, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482706931444226e-05, + "loss": 3.5287, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474320983933706e-05, + "loss": 3.5206, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465935036423186e-05, + "loss": 3.519, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457549088912666e-05, + "loss": 3.5227, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449179520205875e-05, + "loss": 3.5127, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440793572695355e-05, + "loss": 3.5105, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.843240762518484e-05, + "loss": 3.5045, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.842402167767432e-05, + "loss": 3.5122, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415652108967528e-05, + "loss": 3.5113, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407266161457008e-05, + "loss": 3.5263, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398880213946488e-05, + "loss": 3.5148, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.8390494266435968e-05, + "loss": 3.5103, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.838212469772918e-05, + "loss": 3.5191, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837373875021866e-05, + "loss": 3.5161, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836535280270814e-05, + "loss": 3.512, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.835696685519762e-05, + "loss": 3.5017, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.834859728649083e-05, + "loss": 3.5041, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.834021133898031e-05, + "loss": 3.5276, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.8331825391469792e-05, + "loss": 3.525, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.8323439443959272e-05, + "loss": 3.5091, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831506987525248e-05, + "loss": 3.5101, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830668392774196e-05, + "loss": 3.5163, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829829798023144e-05, + "loss": 3.5023, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.828991203272092e-05, + "loss": 3.5245, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281542464014134e-05, + "loss": 3.5026, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273156516503614e-05, + "loss": 3.5258, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264770568993094e-05, + "loss": 3.5217, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256384621482574e-05, + "loss": 3.5085, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.8248015052775783e-05, + "loss": 3.5069, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.8239629105265263e-05, + "loss": 3.5204, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231243157754746e-05, + "loss": 3.4926, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222857210244226e-05, + "loss": 3.5058, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214487641537435e-05, + "loss": 3.5228, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8206101694026915e-05, + "loss": 3.5153, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197715746516395e-05, + "loss": 3.5072, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189329799005875e-05, + "loss": 3.501, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180960230299087e-05, + "loss": 3.5066, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172574282788567e-05, + "loss": 3.5062, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164188335278047e-05, + "loss": 3.517, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155802387767527e-05, + "loss": 3.5052, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147432819060736e-05, + "loss": 3.5162, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8139046871550216e-05, + "loss": 3.5172, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.8130660924039696e-05, + "loss": 3.5185, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.812227497652918e-05, + "loss": 3.5085, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.811390540782239e-05, + "loss": 3.5133, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.810551946031187e-05, + "loss": 3.5152, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.809713351280135e-05, + "loss": 3.5119, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808874756529083e-05, + "loss": 3.5148, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808037799658404e-05, + "loss": 3.5102, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.807199204907352e-05, + "loss": 3.5173, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.8063606101563e-05, + "loss": 3.5094, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.8055220154052474e-05, + "loss": 3.4988, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.804685058534569e-05, + "loss": 3.5022, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803846463783517e-05, + "loss": 3.5111, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.803007869032465e-05, + "loss": 3.5171, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.8021692742814126e-05, + "loss": 3.5081, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.8013323174107342e-05, + "loss": 3.5091, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.8004937226596822e-05, + "loss": 3.5012, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.7996551279086302e-05, + "loss": 3.4994, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.798816533157578e-05, + "loss": 3.5029, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979795762868995e-05, + "loss": 3.5155, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971409815358475e-05, + "loss": 3.5138, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7963023867847948e-05, + "loss": 3.5167, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954637920337428e-05, + "loss": 3.5142, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946268351630644e-05, + "loss": 3.5063, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937882404120124e-05, + "loss": 3.508, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.79294964566096e-05, + "loss": 3.512, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.792111050909908e-05, + "loss": 3.5177, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912740940392296e-05, + "loss": 3.517, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.790435499288177e-05, + "loss": 3.508, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789596904537125e-05, + "loss": 3.501, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887583097860732e-05, + "loss": 3.5208, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.787921352915395e-05, + "loss": 3.5007, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.787082758164342e-05, + "loss": 3.5103, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.78624416341329e-05, + "loss": 3.5101, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.785405568662238e-05, + "loss": 3.5108, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845686117915597e-05, + "loss": 3.4994, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837300170405074e-05, + "loss": 3.5097, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828914222894554e-05, + "loss": 3.5015, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.7820528275384034e-05, + "loss": 3.5093, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.7812158706677243e-05, + "loss": 3.513, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803772759166723e-05, + "loss": 3.5025, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795386811656203e-05, + "loss": 3.521, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.7787000864145686e-05, + "loss": 3.5254, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.7778631295438895e-05, + "loss": 3.5151, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770245347928375e-05, + "loss": 3.5069, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761859400417855e-05, + "loss": 3.5027, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.7753473452907335e-05, + "loss": 3.5107, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.7745103884200548e-05, + "loss": 3.5024, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736717936690028e-05, + "loss": 3.5148, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728331989179507e-05, + "loss": 3.4997, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719946041668987e-05, + "loss": 3.506, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711576472962197e-05, + "loss": 3.5143, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703190525451676e-05, + "loss": 3.5161, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.7694804577941156e-05, + "loss": 3.5024, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768641863043064e-05, + "loss": 3.5069, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.767804906172385e-05, + "loss": 3.5106, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.766966311421333e-05, + "loss": 3.5133, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.766127716670281e-05, + "loss": 3.5201, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.765289121919229e-05, + "loss": 3.5172, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.76445216504855e-05, + "loss": 3.5, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.763613570297498e-05, + "loss": 3.512, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762774975546446e-05, + "loss": 3.5118, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.761936380795394e-05, + "loss": 3.5092, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761099423924715e-05, + "loss": 3.5082, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760260829173663e-05, + "loss": 3.5187, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759422234422611e-05, + "loss": 3.5097, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.7585836396715593e-05, + "loss": 3.5282, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.7577466828008803e-05, + "loss": 3.507, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.7569080880498283e-05, + "loss": 3.5153, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560694932987762e-05, + "loss": 3.5078, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552308985477242e-05, + "loss": 3.5064, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543939416770455e-05, + "loss": 3.5119, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535553469259935e-05, + "loss": 3.5073, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527167521749415e-05, + "loss": 3.5066, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518781574238895e-05, + "loss": 3.5016, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510412005532104e-05, + "loss": 3.5059, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.8540518283843994, + "eval_runtime": 303.6096, + "eval_samples_per_second": 1256.848, + "eval_steps_per_second": 39.277, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7502026058021584e-05, + "loss": 3.5081, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493640110511064e-05, + "loss": 3.5043, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485254163000547e-05, + "loss": 3.5161, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476868215490027e-05, + "loss": 3.5081, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468498646783236e-05, + "loss": 3.5276, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7460112699272716e-05, + "loss": 3.5024, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451726751762196e-05, + "loss": 3.5068, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443340804251676e-05, + "loss": 3.4977, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.743497123554489e-05, + "loss": 3.5127, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742658528803437e-05, + "loss": 3.5063, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.741819934052385e-05, + "loss": 3.5007, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409829771817058e-05, + "loss": 3.5167, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401443824306537e-05, + "loss": 3.4943, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7393057876796017e-05, + "loss": 3.5077, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.73846719292855e-05, + "loss": 3.4938, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.737630236057871e-05, + "loss": 3.4994, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736791641306819e-05, + "loss": 3.4952, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735953046555767e-05, + "loss": 3.509, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735114451804715e-05, + "loss": 3.5025, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.7342774949340362e-05, + "loss": 3.5209, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.7334389001829842e-05, + "loss": 3.5056, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7326003054319322e-05, + "loss": 3.5069, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317617106808802e-05, + "loss": 3.5054, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.730924753810201e-05, + "loss": 3.513, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.730086159059149e-05, + "loss": 3.5036, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729247564308097e-05, + "loss": 3.5129, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.7284089695570454e-05, + "loss": 3.498, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275720126863664e-05, + "loss": 3.5048, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267334179353144e-05, + "loss": 3.4898, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258948231842623e-05, + "loss": 3.5091, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250562284332103e-05, + "loss": 3.5095, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242192715625316e-05, + "loss": 3.5052, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233806768114796e-05, + "loss": 3.5174, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225420820604276e-05, + "loss": 3.5062, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7217034873093756e-05, + "loss": 3.5007, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208665304386965e-05, + "loss": 3.5124, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200279356876445e-05, + "loss": 3.502, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191893409365925e-05, + "loss": 3.4978, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183507461855405e-05, + "loss": 3.4914, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7175137893148617e-05, + "loss": 3.4978, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166751945638097e-05, + "loss": 3.4998, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158365998127577e-05, + "loss": 3.5115, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149980050617057e-05, + "loss": 3.505, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.714161048191027e-05, + "loss": 3.4953, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.713322453439975e-05, + "loss": 3.5102, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712483858688923e-05, + "loss": 3.5028, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711645263937871e-05, + "loss": 3.4966, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.710808307067192e-05, + "loss": 3.492, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.70996971231614e-05, + "loss": 3.4893, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709131117565088e-05, + "loss": 3.5152, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708292522814036e-05, + "loss": 3.5133, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.707455565943357e-05, + "loss": 3.4974, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.706616971192305e-05, + "loss": 3.4964, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705778376441253e-05, + "loss": 3.5072, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.704939781690201e-05, + "loss": 3.4874, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704102824819522e-05, + "loss": 3.5103, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.7032642300684703e-05, + "loss": 3.4921, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024256353174183e-05, + "loss": 3.5062, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7015870405663663e-05, + "loss": 3.5166, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007500836956872e-05, + "loss": 3.4963, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6999114889446352e-05, + "loss": 3.4882, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990728941935832e-05, + "loss": 3.5082, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.6982342994425312e-05, + "loss": 3.4825, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973973425718525e-05, + "loss": 3.4957, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965587478208005e-05, + "loss": 3.5088, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957201530697484e-05, + "loss": 3.5043, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948815583186964e-05, + "loss": 3.4966, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940446014480174e-05, + "loss": 3.4872, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6932060066969657e-05, + "loss": 3.4896, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.6923674119459137e-05, + "loss": 3.4926, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.6915288171948617e-05, + "loss": 3.5042, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906918603241826e-05, + "loss": 3.4909, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898532655731306e-05, + "loss": 3.5051, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890146708220786e-05, + "loss": 3.5032, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881760760710266e-05, + "loss": 3.5066, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873391192003478e-05, + "loss": 3.4959, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.6865005244492958e-05, + "loss": 3.4987, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.6856619296982438e-05, + "loss": 3.5073, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.6848233349471918e-05, + "loss": 3.4967, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.6839863780765127e-05, + "loss": 3.5057, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683147783325461e-05, + "loss": 3.5003, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.682309188574409e-05, + "loss": 3.5015, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681470593823357e-05, + "loss": 3.4994, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.680633636952678e-05, + "loss": 3.4854, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.679795042201626e-05, + "loss": 3.4955, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.678956447450574e-05, + "loss": 3.4946, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781178526995216e-05, + "loss": 3.5046, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772808958288432e-05, + "loss": 3.495, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764423010777912e-05, + "loss": 3.497, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6756037063267392e-05, + "loss": 3.4888, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747651115756865e-05, + "loss": 3.4885, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.673928154705008e-05, + "loss": 3.4866, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730895599539564e-05, + "loss": 3.4987, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722509652029044e-05, + "loss": 3.5085, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6714123704518517e-05, + "loss": 3.5039, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705754135811733e-05, + "loss": 3.498, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697368188301213e-05, + "loss": 3.4938, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.668898224079069e-05, + "loss": 3.4961, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.668059629328017e-05, + "loss": 3.4959, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.6672226724573386e-05, + "loss": 3.5059, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.6663840777062866e-05, + "loss": 3.5029, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665545482955234e-05, + "loss": 3.4962, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664706888204182e-05, + "loss": 3.4896, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.6638699313335035e-05, + "loss": 3.5089, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.6630313365824518e-05, + "loss": 3.4881, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.662192741831399e-05, + "loss": 3.4997, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661354147080347e-05, + "loss": 3.491, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.6605171902096687e-05, + "loss": 3.4987, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.6596785954586163e-05, + "loss": 3.4887, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.6588400007075643e-05, + "loss": 3.5001, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6580014059565123e-05, + "loss": 3.4914, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.657164449085834e-05, + "loss": 3.4902, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563258543347812e-05, + "loss": 3.5047, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554872595837292e-05, + "loss": 3.488, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546486648326772e-05, + "loss": 3.5073, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6538117079619985e-05, + "loss": 3.5118, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529731132109465e-05, + "loss": 3.5014, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521345184598945e-05, + "loss": 3.4951, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6512959237088425e-05, + "loss": 3.4925, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504589668381634e-05, + "loss": 3.4938, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496203720871117e-05, + "loss": 3.4923, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487817773360597e-05, + "loss": 3.5006, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479431825850077e-05, + "loss": 3.4854, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6471062257143286e-05, + "loss": 3.4953, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462676309632766e-05, + "loss": 3.5042, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454290362122246e-05, + "loss": 3.5035, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445904414611726e-05, + "loss": 3.4907, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643753484590494e-05, + "loss": 3.493, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642914889839442e-05, + "loss": 3.4991, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.64207629508839e-05, + "loss": 3.4988, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412393382177107e-05, + "loss": 3.5032, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6404007434666587e-05, + "loss": 3.5071, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.639562148715607e-05, + "loss": 3.4877, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.638723553964555e-05, + "loss": 3.4996, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.637884959213503e-05, + "loss": 3.5006, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.637048002342824e-05, + "loss": 3.4958, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636209407591772e-05, + "loss": 3.4952, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.63537081284072e-05, + "loss": 3.5075, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.6345338559700412e-05, + "loss": 3.4963, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6336952612189892e-05, + "loss": 3.5152, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328566664679372e-05, + "loss": 3.4939, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320180717168852e-05, + "loss": 3.499, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.631181114846206e-05, + "loss": 3.4975, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630342520095154e-05, + "loss": 3.4947, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.6295039253441024e-05, + "loss": 3.4968, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.6286653305930504e-05, + "loss": 3.4975, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278283737223713e-05, + "loss": 3.492, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269897789713193e-05, + "loss": 3.4895, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261511842202673e-05, + "loss": 3.4959, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.8551788330078125, + "eval_runtime": 303.5428, + "eval_samples_per_second": 1257.124, + "eval_steps_per_second": 39.286, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6253125894692153e-05, + "loss": 3.4951, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244739947181633e-05, + "loss": 3.4917, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236353999671113e-05, + "loss": 3.5017, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.6227968052160597e-05, + "loss": 3.497, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219598483453806e-05, + "loss": 3.5176, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211212535943286e-05, + "loss": 3.4934, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.6202826588432766e-05, + "loss": 3.4951, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.6194440640922246e-05, + "loss": 3.4831, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6186071072215458e-05, + "loss": 3.5012, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177685124704938e-05, + "loss": 3.4953, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169299177194418e-05, + "loss": 3.4889, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160913229683898e-05, + "loss": 3.4983, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152543660977107e-05, + "loss": 3.4856, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144157713466587e-05, + "loss": 3.4955, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.6135771765956067e-05, + "loss": 3.4832, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.612740219724928e-05, + "loss": 3.4865, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611901624973876e-05, + "loss": 3.4851, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611063030222824e-05, + "loss": 3.4947, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610224435471772e-05, + "loss": 3.4883, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609387478601093e-05, + "loss": 3.508, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.6085488838500412e-05, + "loss": 3.4936, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.607710289098989e-05, + "loss": 3.5002, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.606871694347937e-05, + "loss": 3.4894, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.606034737477258e-05, + "loss": 3.4983, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.605196142726206e-05, + "loss": 3.4908, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.604357547975154e-05, + "loss": 3.5017, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.603518953224102e-05, + "loss": 3.4893, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026819963534233e-05, + "loss": 3.4888, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018434016023713e-05, + "loss": 3.4808, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6010048068513193e-05, + "loss": 3.4941, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001662121002673e-05, + "loss": 3.5011, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993292552295882e-05, + "loss": 3.4921, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.5984906604785365e-05, + "loss": 3.5078, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.5976520657274845e-05, + "loss": 3.4944, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.5968134709764325e-05, + "loss": 3.4873, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.5959765141057534e-05, + "loss": 3.4951, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.5951379193547014e-05, + "loss": 3.4976, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.5942993246036494e-05, + "loss": 3.4799, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934607298525974e-05, + "loss": 3.4804, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926237729819187e-05, + "loss": 3.484, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.5917851782308667e-05, + "loss": 3.4925, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.5909465834798147e-05, + "loss": 3.4946, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.5901079887287627e-05, + "loss": 3.4954, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.5892710318580836e-05, + "loss": 3.4798, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.588432437107032e-05, + "loss": 3.4958, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.58759384235598e-05, + "loss": 3.4919, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.586755247604928e-05, + "loss": 3.485, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859182907342488e-05, + "loss": 3.4785, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850796959831968e-05, + "loss": 3.4712, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842411012321448e-05, + "loss": 3.5095, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5834025064810928e-05, + "loss": 3.4993, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.582565549610414e-05, + "loss": 3.4873, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.581726954859362e-05, + "loss": 3.4881, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.58088836010831e-05, + "loss": 3.4881, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.580049765357258e-05, + "loss": 3.4759, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.579212808486579e-05, + "loss": 3.4945, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783742137355273e-05, + "loss": 3.4835, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775356189844753e-05, + "loss": 3.4913, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766970242334233e-05, + "loss": 3.5049, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758600673627442e-05, + "loss": 3.4872, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.575023110492065e-05, + "loss": 3.4756, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741845157410134e-05, + "loss": 3.5012, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733459209899614e-05, + "loss": 3.4722, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5725073262389094e-05, + "loss": 3.4775, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.5716687314878574e-05, + "loss": 3.5004, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.5708301367368054e-05, + "loss": 3.4902, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.5699915419857534e-05, + "loss": 3.4859, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.569152947234701e-05, + "loss": 3.4806, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5683159903640226e-05, + "loss": 3.4735, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674773956129706e-05, + "loss": 3.4802, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666388008619186e-05, + "loss": 3.4939, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565800206110866e-05, + "loss": 3.4753, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.5649632492401875e-05, + "loss": 3.4954, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.5641246544891355e-05, + "loss": 3.4901, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.5632860597380835e-05, + "loss": 3.499, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.5624474649870312e-05, + "loss": 3.4865, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5616105081163528e-05, + "loss": 3.4836, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607719133653008e-05, + "loss": 3.4927, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.559933318614248e-05, + "loss": 3.48, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.5590947238631964e-05, + "loss": 3.4972, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558257766992518e-05, + "loss": 3.488, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557419172241466e-05, + "loss": 3.4869, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.556582215370787e-05, + "loss": 3.4878, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.555743620619735e-05, + "loss": 3.4737, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.554905025868683e-05, + "loss": 3.4814, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.554066431117631e-05, + "loss": 3.4854, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532278363665786e-05, + "loss": 3.4918, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523892416155266e-05, + "loss": 3.4813, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515506468644745e-05, + "loss": 3.4862, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5507120521134225e-05, + "loss": 3.4784, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498750952427435e-05, + "loss": 3.4753, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490365004916918e-05, + "loss": 3.4765, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481979057406398e-05, + "loss": 3.4852, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473593109895878e-05, + "loss": 3.496, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465223541189087e-05, + "loss": 3.496, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456837593678567e-05, + "loss": 3.4871, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448451646168047e-05, + "loss": 3.4788, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5440065698657527e-05, + "loss": 3.4835, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.543167975114701e-05, + "loss": 3.4856, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.542331018244022e-05, + "loss": 3.4917, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.54149242349297e-05, + "loss": 3.4913, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.540653828741918e-05, + "loss": 3.4867, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.5398168718712388e-05, + "loss": 3.4776, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538978277120187e-05, + "loss": 3.4994, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538139682369135e-05, + "loss": 3.4714, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537301087618083e-05, + "loss": 3.4907, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536462492867031e-05, + "loss": 3.4774, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535625535996352e-05, + "loss": 3.4869, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.5347869412453e-05, + "loss": 3.4761, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.533948346494248e-05, + "loss": 3.4865, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.5331113896235693e-05, + "loss": 3.4806, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322727948725173e-05, + "loss": 3.4815, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314342001214653e-05, + "loss": 3.4875, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305956053704133e-05, + "loss": 3.4804, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297586484997342e-05, + "loss": 3.4922, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289200537486825e-05, + "loss": 3.5001, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280814589976305e-05, + "loss": 3.492, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272428642465785e-05, + "loss": 3.4822, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5264042694955265e-05, + "loss": 3.4836, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255673126248474e-05, + "loss": 3.4811, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247287178737954e-05, + "loss": 3.48, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238901231227434e-05, + "loss": 3.4912, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230531662520647e-05, + "loss": 3.4691, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5222145715010127e-05, + "loss": 3.4856, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213759767499606e-05, + "loss": 3.4876, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205373819989086e-05, + "loss": 3.4936, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5197004251282296e-05, + "loss": 3.4778, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188618303771775e-05, + "loss": 3.4825, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.518023235626126e-05, + "loss": 3.4821, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.517184640875074e-05, + "loss": 3.4935, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163476840043948e-05, + "loss": 3.4878, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5155090892533428e-05, + "loss": 3.495, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146704945022908e-05, + "loss": 3.4736, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138318997512388e-05, + "loss": 3.4889, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.51299494288056e-05, + "loss": 3.4906, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512156348129508e-05, + "loss": 3.481, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.511317753378456e-05, + "loss": 3.4818, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.510479158627404e-05, + "loss": 3.4968, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.509642201756725e-05, + "loss": 3.4876, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.508803607005673e-05, + "loss": 3.5032, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079650122546212e-05, + "loss": 3.4775, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071264175035692e-05, + "loss": 3.4885, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.50628946063289e-05, + "loss": 3.4828, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.505450865881838e-05, + "loss": 3.4851, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.504612271130786e-05, + "loss": 3.484, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.503773676379734e-05, + "loss": 3.4842, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029367195090554e-05, + "loss": 3.4831, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020981247580034e-05, + "loss": 3.4726, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012595300069514e-05, + "loss": 3.482, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.8570358753204346, + "eval_runtime": 302.4551, + "eval_samples_per_second": 1261.645, + "eval_steps_per_second": 39.427, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5004209352558994e-05, + "loss": 3.4822, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4995839783852203e-05, + "loss": 3.4795, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4987453836341683e-05, + "loss": 3.4888, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4979067888831166e-05, + "loss": 3.4846, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970681941320646e-05, + "loss": 3.5015, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962295993810123e-05, + "loss": 3.4859, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953910046299603e-05, + "loss": 3.4805, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945524098789083e-05, + "loss": 3.4728, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4937138151278563e-05, + "loss": 3.4872, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928768582571775e-05, + "loss": 3.482, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920382635061255e-05, + "loss": 3.4832, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911996687550735e-05, + "loss": 3.4825, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903627118843944e-05, + "loss": 3.4738, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895241171333424e-05, + "loss": 3.4828, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886855223822904e-05, + "loss": 3.4725, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878469276312384e-05, + "loss": 3.4735, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4870099707605596e-05, + "loss": 3.4714, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861713760095076e-05, + "loss": 3.4865, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4853327812584556e-05, + "loss": 3.4751, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844941865074036e-05, + "loss": 3.4953, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836572296367245e-05, + "loss": 3.4826, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482818634885673e-05, + "loss": 3.4894, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481980040134621e-05, + "loss": 3.48, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481141445383569e-05, + "loss": 3.4833, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4803044885128898e-05, + "loss": 3.4778, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794658937618378e-05, + "loss": 3.489, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786272990107858e-05, + "loss": 3.477, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777887042597338e-05, + "loss": 3.4805, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476951747389055e-05, + "loss": 3.4679, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476113152638003e-05, + "loss": 3.4795, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.475274557886951e-05, + "loss": 3.4885, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474435963135899e-05, + "loss": 3.4833, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.47359900626522e-05, + "loss": 3.4906, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727604115141682e-05, + "loss": 3.4789, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719218167631162e-05, + "loss": 3.4794, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710832220120642e-05, + "loss": 3.4859, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.470246265141385e-05, + "loss": 3.4867, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469407670390333e-05, + "loss": 3.4645, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468569075639281e-05, + "loss": 3.4726, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467730480888229e-05, + "loss": 3.4718, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668935240175504e-05, + "loss": 3.4761, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660549292664984e-05, + "loss": 3.4866, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652163345154464e-05, + "loss": 3.4812, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643777397643944e-05, + "loss": 3.4732, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635407828937153e-05, + "loss": 3.483, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4627021881426636e-05, + "loss": 3.4737, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618635933916116e-05, + "loss": 3.4768, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610249986405596e-05, + "loss": 3.471, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601880417698805e-05, + "loss": 3.4524, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593494470188285e-05, + "loss": 3.4963, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4585108522677765e-05, + "loss": 3.487, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576722575167245e-05, + "loss": 3.4811, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568353006460457e-05, + "loss": 3.4725, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559967058949937e-05, + "loss": 3.4759, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551581111439417e-05, + "loss": 3.4643, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543195163928894e-05, + "loss": 3.481, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534825595222106e-05, + "loss": 3.4749, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452643964771159e-05, + "loss": 3.4772, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451805370020107e-05, + "loss": 3.4948, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509667752690546e-05, + "loss": 3.4742, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450129818398376e-05, + "loss": 3.4661, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449291223647324e-05, + "loss": 3.4886, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448452628896272e-05, + "loss": 3.4616, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.44761403414522e-05, + "loss": 3.4694, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446775439394168e-05, + "loss": 3.484, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445936844643116e-05, + "loss": 3.4789, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445098249892064e-05, + "loss": 3.4726, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444259655141012e-05, + "loss": 3.4706, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434226982703327e-05, + "loss": 3.4596, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425841035192807e-05, + "loss": 3.4686, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441745508768229e-05, + "loss": 3.4799, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440906914017177e-05, + "loss": 3.4688, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440069957146498e-05, + "loss": 3.4807, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439231362395446e-05, + "loss": 3.4776, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438392767644394e-05, + "loss": 3.489, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.437554172893342e-05, + "loss": 3.4732, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367172160226632e-05, + "loss": 3.4696, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358786212716112e-05, + "loss": 3.4808, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350400265205592e-05, + "loss": 3.4678, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4342014317695072e-05, + "loss": 3.487, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.433364474898828e-05, + "loss": 3.4763, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.432525880147776e-05, + "loss": 3.474, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316872853967244e-05, + "loss": 3.4794, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308486906456724e-05, + "loss": 3.4605, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300117337749934e-05, + "loss": 3.4674, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291731390239413e-05, + "loss": 3.4741, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283345442728893e-05, + "loss": 3.4803, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274959495218373e-05, + "loss": 3.4662, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266589926511586e-05, + "loss": 3.4753, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258203979001066e-05, + "loss": 3.4686, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249818031490546e-05, + "loss": 3.4687, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241432083980022e-05, + "loss": 3.4613, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4233062515273235e-05, + "loss": 3.4773, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224676567762715e-05, + "loss": 3.4831, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4216290620252198e-05, + "loss": 3.4822, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207904672741675e-05, + "loss": 3.4797, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199535104034887e-05, + "loss": 3.4677, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191149156524367e-05, + "loss": 3.4702, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182763209013847e-05, + "loss": 3.4726, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417439364030706e-05, + "loss": 3.4828, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416600769279654e-05, + "loss": 3.477, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415762174528602e-05, + "loss": 3.4743, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149235797775496e-05, + "loss": 3.4699, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.414086622906871e-05, + "loss": 3.4852, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413248028155819e-05, + "loss": 3.4629, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412409433404767e-05, + "loss": 3.4754, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411570838653715e-05, + "loss": 3.467, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410733881783036e-05, + "loss": 3.4754, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409895287031984e-05, + "loss": 3.464, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409056692280932e-05, + "loss": 3.4771, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082180975298797e-05, + "loss": 3.4682, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073811406592013e-05, + "loss": 3.472, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065425459081493e-05, + "loss": 3.4741, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405703951157097e-05, + "loss": 3.4699, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404865356406045e-05, + "loss": 3.4811, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040283995353662e-05, + "loss": 3.4876, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031898047843142e-05, + "loss": 3.4752, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023512100332622e-05, + "loss": 3.4738, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015126152822102e-05, + "loss": 3.4673, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006756584115315e-05, + "loss": 3.4735, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399837063660479e-05, + "loss": 3.4682, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398998468909427e-05, + "loss": 3.4808, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.398159874158375e-05, + "loss": 3.4544, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973229172876967e-05, + "loss": 3.4724, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964843225366443e-05, + "loss": 3.4739, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956457277855923e-05, + "loss": 3.4824, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948071330345403e-05, + "loss": 3.4703, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939701761638616e-05, + "loss": 3.472, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931315814128092e-05, + "loss": 3.4695, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922929866617576e-05, + "loss": 3.481, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914543919107056e-05, + "loss": 3.4787, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906174350400265e-05, + "loss": 3.4825, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897788402889745e-05, + "loss": 3.4638, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889402455379225e-05, + "loss": 3.4769, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881016507868705e-05, + "loss": 3.4801, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872646939161917e-05, + "loss": 3.4707, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3864260991651397e-05, + "loss": 3.4713, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855875044140877e-05, + "loss": 3.4817, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847489096630357e-05, + "loss": 3.472, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839119527923566e-05, + "loss": 3.4967, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830733580413046e-05, + "loss": 3.4686, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382234763290253e-05, + "loss": 3.475, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381396168539201e-05, + "loss": 3.4697, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380559211668522e-05, + "loss": 3.4704, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.37972061691747e-05, + "loss": 3.4777, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378882022166418e-05, + "loss": 3.4713, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378043427415366e-05, + "loss": 3.474, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377206470544687e-05, + "loss": 3.4559, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376367875793635e-05, + "loss": 3.4744, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.85760498046875, + "eval_runtime": 314.2885, + "eval_samples_per_second": 1214.142, + "eval_steps_per_second": 37.943, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375529281042583e-05, + "loss": 3.4732, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.374692324171904e-05, + "loss": 3.4691, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373853729420852e-05, + "loss": 3.4771, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3730151346698e-05, + "loss": 3.4762, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721765399187483e-05, + "loss": 3.4873, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713379451676963e-05, + "loss": 3.4734, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3704993504166443e-05, + "loss": 3.4715, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369660755665592e-05, + "loss": 3.4626, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.36882216091454e-05, + "loss": 3.4739, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679852040438612e-05, + "loss": 3.4685, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671466092928092e-05, + "loss": 3.474, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3663080145417572e-05, + "loss": 3.4674, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654694197907052e-05, + "loss": 3.4694, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646324629200264e-05, + "loss": 3.4643, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637938681689744e-05, + "loss": 3.4644, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.362955273417922e-05, + "loss": 3.4572, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621183165472437e-05, + "loss": 3.4632, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612797217961917e-05, + "loss": 3.4737, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604411270451393e-05, + "loss": 3.4641, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596025322940873e-05, + "loss": 3.4837, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.3587655754234086e-05, + "loss": 3.4733, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.3579269806723566e-05, + "loss": 3.4805, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570883859213046e-05, + "loss": 3.4658, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562497911702526e-05, + "loss": 3.4698, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554128342995738e-05, + "loss": 3.4678, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545742395485218e-05, + "loss": 3.4819, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537356447974695e-05, + "loss": 3.4676, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3528970500464175e-05, + "loss": 3.4648, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.352060093175739e-05, + "loss": 3.4593, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.3512214984246867e-05, + "loss": 3.4694, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503829036736347e-05, + "loss": 3.4735, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495443089225827e-05, + "loss": 3.4741, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.348707352051904e-05, + "loss": 3.4763, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478687573008516e-05, + "loss": 3.475, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470301625498e-05, + "loss": 3.4664, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.346191567798748e-05, + "loss": 3.476, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345352973047696e-05, + "loss": 3.4742, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344514378296644e-05, + "loss": 3.4593, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343675783545592e-05, + "loss": 3.4605, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.34283718879454e-05, + "loss": 3.458, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420002319238608e-05, + "loss": 3.4625, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.341161637172809e-05, + "loss": 3.4757, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340323042421757e-05, + "loss": 3.472, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394844476707048e-05, + "loss": 3.4632, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338647490800026e-05, + "loss": 3.4706, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337808896048974e-05, + "loss": 3.4659, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336970301297922e-05, + "loss": 3.4661, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361333444272433e-05, + "loss": 3.4575, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352947496761913e-05, + "loss": 3.4422, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344561549251393e-05, + "loss": 3.4871, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333617560174087e-05, + "loss": 3.4718, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327806033034082e-05, + "loss": 3.4727, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319420085523562e-05, + "loss": 3.4587, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311034138013045e-05, + "loss": 3.468, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302648190502522e-05, + "loss": 3.454, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294278621795734e-05, + "loss": 3.4671, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285892674285214e-05, + "loss": 3.4674, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277506726774694e-05, + "loss": 3.4648, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269120779264174e-05, + "loss": 3.4847, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260751210557387e-05, + "loss": 3.4619, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252381641850596e-05, + "loss": 3.4538, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243995694340076e-05, + "loss": 3.4785, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235609746829556e-05, + "loss": 3.4489, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.3227223799319036e-05, + "loss": 3.4535, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.3218837851808516e-05, + "loss": 3.4727, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210451904297995e-05, + "loss": 3.47, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202065956787475e-05, + "loss": 3.4564, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193680009276955e-05, + "loss": 3.4658, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185310440570168e-05, + "loss": 3.4475, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3176924493059644e-05, + "loss": 3.4597, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168538545549124e-05, + "loss": 3.4681, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160152598038608e-05, + "loss": 3.4531, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.3151783029331817e-05, + "loss": 3.4703, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.3143397081821297e-05, + "loss": 3.4657, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135011134310777e-05, + "loss": 3.4791, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126625186800257e-05, + "loss": 3.4584, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.311825561809347e-05, + "loss": 3.465, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.310986967058295e-05, + "loss": 3.4672, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.310148372307243e-05, + "loss": 3.4554, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309309777556191e-05, + "loss": 3.471, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084728206855118e-05, + "loss": 3.4682, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076342259344598e-05, + "loss": 3.462, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067956311834078e-05, + "loss": 3.4703, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.305958674312729e-05, + "loss": 3.4524, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.305120079561677e-05, + "loss": 3.454, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304281484810625e-05, + "loss": 3.4624, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303442890059573e-05, + "loss": 3.4693, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302604295308521e-05, + "loss": 3.4573, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.301765700557469e-05, + "loss": 3.4641, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.300927105806417e-05, + "loss": 3.4477, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.300088511055365e-05, + "loss": 3.4595, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992515541846863e-05, + "loss": 3.453, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984129594336343e-05, + "loss": 3.4607, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975743646825823e-05, + "loss": 3.4745, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967374078119032e-05, + "loss": 3.4671, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958988130608515e-05, + "loss": 3.4672, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950602183097995e-05, + "loss": 3.4564, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.294221623558747e-05, + "loss": 3.4604, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933846666880684e-05, + "loss": 3.4616, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925460719370164e-05, + "loss": 3.4713, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2917074771859644e-05, + "loss": 3.4619, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.2908688824349124e-05, + "loss": 3.4683, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.2900319255642336e-05, + "loss": 3.4557, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.2891933308131816e-05, + "loss": 3.4714, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883547360621296e-05, + "loss": 3.453, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875161413110773e-05, + "loss": 3.4647, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866791844403985e-05, + "loss": 3.4529, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285840589689347e-05, + "loss": 3.4676, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2850019949382945e-05, + "loss": 3.4546, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841634001872425e-05, + "loss": 3.4608, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833264433165638e-05, + "loss": 3.4573, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824878485655118e-05, + "loss": 3.4625, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816492538144598e-05, + "loss": 3.4612, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808106590634078e-05, + "loss": 3.4613, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279973702192729e-05, + "loss": 3.4655, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279135107441677e-05, + "loss": 3.4764, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782965126906247e-05, + "loss": 3.4676, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774579179395727e-05, + "loss": 3.4664, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.276620961068894e-05, + "loss": 3.4547, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.275782366317842e-05, + "loss": 3.4616, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.27494377156679e-05, + "loss": 3.4612, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.274105176815738e-05, + "loss": 3.4688, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273268219945059e-05, + "loss": 3.4436, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724296251940068e-05, + "loss": 3.4623, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715910304429548e-05, + "loss": 3.4633, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.270752435691903e-05, + "loss": 3.4677, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.269915478821224e-05, + "loss": 3.4598, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.269076884070172e-05, + "loss": 3.4619, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.26823828931912e-05, + "loss": 3.4587, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.267399694568068e-05, + "loss": 3.4696, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665627376973893e-05, + "loss": 3.4676, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657241429463373e-05, + "loss": 3.4711, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648855481952853e-05, + "loss": 3.4514, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640469534442333e-05, + "loss": 3.4669, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2632099965735542e-05, + "loss": 3.4692, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262371401822502e-05, + "loss": 3.4588, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.26153280707145e-05, + "loss": 3.4624, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606942123203985e-05, + "loss": 3.4679, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598572554497194e-05, + "loss": 3.464, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590186606986674e-05, + "loss": 3.4816, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581800659476154e-05, + "loss": 3.4598, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573414711965634e-05, + "loss": 3.4626, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.2565045143258846e-05, + "loss": 3.4601, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.2556659195748326e-05, + "loss": 3.4609, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548273248237806e-05, + "loss": 3.46, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539887300727286e-05, + "loss": 3.4606, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531517732020495e-05, + "loss": 3.465, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523131784509975e-05, + "loss": 3.4433, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514745836999455e-05, + "loss": 3.4665, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.859339714050293, + "eval_runtime": 308.1224, + "eval_samples_per_second": 1238.44, + "eval_steps_per_second": 38.702, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250635988948894e-05, + "loss": 3.4659, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249797394197842e-05, + "loss": 3.4594, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489587994467895e-05, + "loss": 3.4639, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481202046957375e-05, + "loss": 3.4646, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472832478250588e-05, + "loss": 3.4776, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464446530740068e-05, + "loss": 3.4614, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2456060583229547e-05, + "loss": 3.4608, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2447674635719027e-05, + "loss": 3.4512, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243930506701224e-05, + "loss": 3.4643, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243091911950172e-05, + "loss": 3.4581, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422533171991196e-05, + "loss": 3.4584, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2414147224480676e-05, + "loss": 3.4548, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405777655773892e-05, + "loss": 3.4563, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.239739170826337e-05, + "loss": 3.4547, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238900576075285e-05, + "loss": 3.4586, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.238061981324233e-05, + "loss": 3.4466, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237225024453554e-05, + "loss": 3.4512, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363864297025018e-05, + "loss": 3.4609, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.23554783495145e-05, + "loss": 3.4549, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234709240200398e-05, + "loss": 3.4689, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338722833297194e-05, + "loss": 3.4636, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.233033688578667e-05, + "loss": 3.4694, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232195093827615e-05, + "loss": 3.4511, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313581369569363e-05, + "loss": 3.4618, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2305195422058843e-05, + "loss": 3.4569, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296809474548323e-05, + "loss": 3.4696, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288423527037802e-05, + "loss": 3.4552, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2280053958331015e-05, + "loss": 3.459, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227166801082049e-05, + "loss": 3.4495, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226328206330997e-05, + "loss": 3.4547, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254896115799455e-05, + "loss": 3.458, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246526547092667e-05, + "loss": 3.4669, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2238140599582144e-05, + "loss": 3.466, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229754652071624e-05, + "loss": 3.4629, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221368704561104e-05, + "loss": 3.4538, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212999135854316e-05, + "loss": 3.4592, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204613188343796e-05, + "loss": 3.466, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196227240833276e-05, + "loss": 3.4495, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187841293322756e-05, + "loss": 3.4478, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179471724615965e-05, + "loss": 3.4458, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2171085777105445e-05, + "loss": 3.4551, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162699829594925e-05, + "loss": 3.4602, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215431388208441e-05, + "loss": 3.4592, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145944313377618e-05, + "loss": 3.4547, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137558365867098e-05, + "loss": 3.4566, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129172418356578e-05, + "loss": 3.4568, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120786470846057e-05, + "loss": 3.4555, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211241690213927e-05, + "loss": 3.4463, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210403095462875e-05, + "loss": 3.4307, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209564500711823e-05, + "loss": 3.4722, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208725905960771e-05, + "loss": 3.458, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207888949090092e-05, + "loss": 3.4624, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.20705035433904e-05, + "loss": 3.4507, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.206211759587988e-05, + "loss": 3.4549, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053731648369362e-05, + "loss": 3.4425, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204536207966257e-05, + "loss": 3.4537, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203697613215205e-05, + "loss": 3.4594, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202859018464153e-05, + "loss": 3.4509, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202020423713101e-05, + "loss": 3.4737, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011834668424224e-05, + "loss": 3.4509, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003465099717436e-05, + "loss": 3.4442, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1995079152206913e-05, + "loss": 3.4646, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986693204696393e-05, + "loss": 3.4412, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978307257185873e-05, + "loss": 3.4356, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969921309675353e-05, + "loss": 3.4674, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961535362164832e-05, + "loss": 3.4593, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1953149414654316e-05, + "loss": 3.4441, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944763467143792e-05, + "loss": 3.4551, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936393898437005e-05, + "loss": 3.4355, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1928007950926485e-05, + "loss": 3.4485, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919622003415965e-05, + "loss": 3.4548, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191123605590544e-05, + "loss": 3.4464, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902866487198657e-05, + "loss": 3.4554, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894480539688137e-05, + "loss": 3.4537, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1886094592177617e-05, + "loss": 3.4646, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877708644667094e-05, + "loss": 3.4492, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869339075960306e-05, + "loss": 3.4534, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860953128449786e-05, + "loss": 3.4552, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852567180939266e-05, + "loss": 3.4443, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844181233428746e-05, + "loss": 3.4587, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183581166472196e-05, + "loss": 3.4574, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.182742571721144e-05, + "loss": 3.4489, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1819056148504648e-05, + "loss": 3.463, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181067020099413e-05, + "loss": 3.4384, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180228425348361e-05, + "loss": 3.4411, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179389830597309e-05, + "loss": 3.4539, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785512358462567e-05, + "loss": 3.4576, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1777126410952047e-05, + "loss": 3.4458, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768740463441527e-05, + "loss": 3.4557, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760354515931007e-05, + "loss": 3.4357, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175198494722422e-05, + "loss": 3.4489, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.17435989997137e-05, + "loss": 3.4427, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173521305220318e-05, + "loss": 3.453, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172682710469266e-05, + "loss": 3.4632, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171845753598587e-05, + "loss": 3.4536, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.171007158847535e-05, + "loss": 3.4569, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701685640964832e-05, + "loss": 3.4468, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693299693454312e-05, + "loss": 3.4498, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168493012474752e-05, + "loss": 3.4497, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1676544177237e-05, + "loss": 3.4618, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166815822972648e-05, + "loss": 3.4524, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165977228221596e-05, + "loss": 3.4616, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651402713509173e-05, + "loss": 3.4426, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1643016765998653e-05, + "loss": 3.4595, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634630818488133e-05, + "loss": 3.4463, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626244870977613e-05, + "loss": 3.4519, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617875302270822e-05, + "loss": 3.4405, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609489354760302e-05, + "loss": 3.4576, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1601103407249786e-05, + "loss": 3.4411, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592717459739266e-05, + "loss": 3.4529, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584347891032475e-05, + "loss": 3.4412, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575961943521955e-05, + "loss": 3.4556, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567575996011435e-05, + "loss": 3.4473, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1559190048500915e-05, + "loss": 3.4474, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550820479794127e-05, + "loss": 3.4588, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542434532283607e-05, + "loss": 3.4646, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1534048584773087e-05, + "loss": 3.4578, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525662637262567e-05, + "loss": 3.4518, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517293068555776e-05, + "loss": 3.4482, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508907121045256e-05, + "loss": 3.4462, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150052117353474e-05, + "loss": 3.4518, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149213522602422e-05, + "loss": 3.4555, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.148376565731743e-05, + "loss": 3.4376, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.147537970980691e-05, + "loss": 3.4518, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146699376229639e-05, + "loss": 3.453, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458607814785865e-05, + "loss": 3.4542, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.145023824607908e-05, + "loss": 3.4497, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144185229856856e-05, + "loss": 3.4481, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.143346635105804e-05, + "loss": 3.4481, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1425080403547517e-05, + "loss": 3.4606, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141671083484073e-05, + "loss": 3.457, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140832488733021e-05, + "loss": 3.4575, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139993893981969e-05, + "loss": 3.4443, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139155299230917e-05, + "loss": 3.4564, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1383183423602382e-05, + "loss": 3.4535, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374797476091862e-05, + "loss": 3.4495, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136641152858134e-05, + "loss": 3.4533, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1358041959874554e-05, + "loss": 3.4528, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349656012364034e-05, + "loss": 3.4528, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1341270064853514e-05, + "loss": 3.4712, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133288411734299e-05, + "loss": 3.4478, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324514548636203e-05, + "loss": 3.4535, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1316128601125683e-05, + "loss": 3.4549, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307742653615163e-05, + "loss": 3.4509, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299356706104643e-05, + "loss": 3.4439, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290987137397856e-05, + "loss": 3.4479, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282601189887336e-05, + "loss": 3.4518, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1274215242376812e-05, + "loss": 3.435, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265829294866292e-05, + "loss": 3.4556, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.861457586288452, + "eval_runtime": 305.6976, + "eval_samples_per_second": 1248.263, + "eval_steps_per_second": 39.009, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257443347355772e-05, + "loss": 3.4558, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1249073778648988e-05, + "loss": 3.4467, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240687831138465e-05, + "loss": 3.4511, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232301883627945e-05, + "loss": 3.4549, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223915936117425e-05, + "loss": 3.4639, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215529988606905e-05, + "loss": 3.4508, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207144041096384e-05, + "loss": 3.4547, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198758093585864e-05, + "loss": 3.4421, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190372146075344e-05, + "loss": 3.4465, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1182002577368557e-05, + "loss": 3.4546, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173616629858037e-05, + "loss": 3.4478, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165230682347517e-05, + "loss": 3.4413, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156844734836993e-05, + "loss": 3.4554, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114847516613021e-05, + "loss": 3.439, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.114008921861969e-05, + "loss": 3.443, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.113170327110917e-05, + "loss": 3.4369, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123317323598646e-05, + "loss": 3.4399, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114947754891858e-05, + "loss": 3.4501, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106561807381338e-05, + "loss": 3.4371, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098175859870818e-05, + "loss": 3.4602, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089789912360298e-05, + "loss": 3.4537, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.108142034365351e-05, + "loss": 3.4587, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.107303439614299e-05, + "loss": 3.4436, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064648448632467e-05, + "loss": 3.4459, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.105627887992568e-05, + "loss": 3.451, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047892932415163e-05, + "loss": 3.4546, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039506984904643e-05, + "loss": 3.4431, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.103112103739412e-05, + "loss": 3.4503, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022751468687332e-05, + "loss": 3.4354, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014365521176812e-05, + "loss": 3.4432, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100597957366629e-05, + "loss": 3.4471, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997593626155772e-05, + "loss": 3.4554, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989224057448984e-05, + "loss": 3.4539, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980838109938464e-05, + "loss": 3.4541, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.097245216242794e-05, + "loss": 3.4443, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.096406621491742e-05, + "loss": 3.4474, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.0955696646210633e-05, + "loss": 3.4543, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.0947310698700117e-05, + "loss": 3.4386, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.0938924751189593e-05, + "loss": 3.4369, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.0930538803679073e-05, + "loss": 3.4346, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922169234972286e-05, + "loss": 3.4435, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913783287461762e-05, + "loss": 3.4424, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.0905397339951242e-05, + "loss": 3.4517, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.0897011392440725e-05, + "loss": 3.4464, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888641823733938e-05, + "loss": 3.4434, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880255876223415e-05, + "loss": 3.4463, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871869928712894e-05, + "loss": 3.4489, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863483981202374e-05, + "loss": 3.4336, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0855114412495587e-05, + "loss": 3.4206, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.0846728464985067e-05, + "loss": 3.4566, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838342517474547e-05, + "loss": 3.4502, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829956569964027e-05, + "loss": 3.4555, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821587001257236e-05, + "loss": 3.4394, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813201053746716e-05, + "loss": 3.4434, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804815106236196e-05, + "loss": 3.4333, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.079642915872568e-05, + "loss": 3.4392, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0788059590018888e-05, + "loss": 3.4521, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779673642508368e-05, + "loss": 3.4363, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771287694997848e-05, + "loss": 3.4637, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762901747487328e-05, + "loss": 3.4453, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754548557584273e-05, + "loss": 3.4275, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0746162610073753e-05, + "loss": 3.4562, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737776662563233e-05, + "loss": 3.4305, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072939071505271e-05, + "loss": 3.4256, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.072100476754219e-05, + "loss": 3.4563, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.071261882003167e-05, + "loss": 3.4465, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.070423287252115e-05, + "loss": 3.4358, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695846925010633e-05, + "loss": 3.4407, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687477356303842e-05, + "loss": 3.428, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679091408793322e-05, + "loss": 3.4363, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670705461282802e-05, + "loss": 3.4472, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662319513772282e-05, + "loss": 3.437, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653949945065494e-05, + "loss": 3.4473, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645563997554974e-05, + "loss": 3.4401, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637178050044454e-05, + "loss": 3.4531, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628792102533934e-05, + "loss": 3.4393, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620422533827143e-05, + "loss": 3.4453, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0612036586316623e-05, + "loss": 3.4412, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603650638806103e-05, + "loss": 3.434, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595264691295586e-05, + "loss": 3.4511, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586895122588796e-05, + "loss": 3.4473, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578509175078276e-05, + "loss": 3.435, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570123227567755e-05, + "loss": 3.4541, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561737280057235e-05, + "loss": 3.4265, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553367711350448e-05, + "loss": 3.428, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544981763839928e-05, + "loss": 3.4448, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536595816329408e-05, + "loss": 3.446, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528209868818888e-05, + "loss": 3.436, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519840300112097e-05, + "loss": 3.4464, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511454352601577e-05, + "loss": 3.4263, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0503068405091057e-05, + "loss": 3.4354, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049468245758054e-05, + "loss": 3.4337, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.048631288887375e-05, + "loss": 3.4398, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.047792694136323e-05, + "loss": 3.4533, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.046954099385271e-05, + "loss": 3.4428, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461155046342186e-05, + "loss": 3.4472, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.04527854776354e-05, + "loss": 3.4339, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.044439953012488e-05, + "loss": 3.4392, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.043601358261436e-05, + "loss": 3.4371, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427627635103838e-05, + "loss": 3.4481, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.041925806639705e-05, + "loss": 3.4421, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.041087211888653e-05, + "loss": 3.4491, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.040248617137601e-05, + "loss": 3.4353, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.039410022386549e-05, + "loss": 3.4431, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385730655158703e-05, + "loss": 3.44, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.0377344707648183e-05, + "loss": 3.4402, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036895876013766e-05, + "loss": 3.4284, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036057281262714e-05, + "loss": 3.4493, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.0352203243920355e-05, + "loss": 3.4311, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.0343817296409835e-05, + "loss": 3.4395, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.0335431348899312e-05, + "loss": 3.4311, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.0327045401388792e-05, + "loss": 3.443, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.0318675832682004e-05, + "loss": 3.4382, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.0310289885171484e-05, + "loss": 3.4361, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.0301903937660964e-05, + "loss": 3.4447, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.0293517990150444e-05, + "loss": 3.4532, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285148421443657e-05, + "loss": 3.4521, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276762473933133e-05, + "loss": 3.4402, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268392905226346e-05, + "loss": 3.435, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0260006957715826e-05, + "loss": 3.4367, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025162101020531e-05, + "loss": 3.4401, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243235062694785e-05, + "loss": 3.4419, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234849115184265e-05, + "loss": 3.4287, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226463167673745e-05, + "loss": 3.4393, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0218077220163225e-05, + "loss": 3.4465, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209691272652705e-05, + "loss": 3.4409, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201321703945918e-05, + "loss": 3.4382, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192935756435398e-05, + "loss": 3.4401, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184549808924878e-05, + "loss": 3.4359, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176163861414358e-05, + "loss": 3.4473, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167794292707567e-05, + "loss": 3.4447, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159408345197047e-05, + "loss": 3.4489, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0151022397686527e-05, + "loss": 3.4323, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.014263645017601e-05, + "loss": 3.4438, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.013426688146922e-05, + "loss": 3.4433, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.01258809339587e-05, + "loss": 3.4415, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.011749498644818e-05, + "loss": 3.4422, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.010910903893766e-05, + "loss": 3.4403, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.010073947023087e-05, + "loss": 3.4418, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.009235352272035e-05, + "loss": 3.4619, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.008396757520983e-05, + "loss": 3.4346, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007558162769931e-05, + "loss": 3.4437, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.006721205899252e-05, + "loss": 3.4425, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058826111482e-05, + "loss": 3.4395, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.005044016397148e-05, + "loss": 3.4358, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0042054216460964e-05, + "loss": 3.436, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033684647754173e-05, + "loss": 3.4442, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025298700243653e-05, + "loss": 3.4247, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.0016912752733133e-05, + "loss": 3.4438, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.862182378768921, + "eval_runtime": 305.6011, + "eval_samples_per_second": 1248.657, + "eval_steps_per_second": 39.021, + "step": 1831680 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.2508123704670863e+18, + "trial_name": null, + "trial_params": null +}