diff --git "a/checkpoint-2518560/trainer_state.json" "b/checkpoint-2518560/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2518560/trainer_state.json" @@ -0,0 +1,29803 @@ +{ + "best_metric": 3.8429176807403564, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-sent-neg/transformer/0/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2518560, + "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": 11.0791, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8058, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1753, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.962, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8072, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7008, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5926, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5211, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4455, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3903, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3407, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.2964, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2542, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1886, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1609, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1205, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.0947, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0676, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0417, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0081, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0004, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9664, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9416, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9239, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9158, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8848, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.863, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8481, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8241, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8187, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8015, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.7991, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.7703, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7636, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7531, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7421, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7259, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.6959, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.6974, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6743, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6789, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6653, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6594, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6436, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6405, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6373, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6225, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6229, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5946, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.95892359812181e-05, + "loss": 4.5872, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958085003370758e-05, + "loss": 4.5947, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957246408619706e-05, + "loss": 4.5843, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956407813868654e-05, + "loss": 4.576, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5509, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5674, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5416, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5648, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5225, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5392, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5216, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5054, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5162, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5007, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.482, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.485, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.5014, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.478, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4704, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4678, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4526, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4664, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4652, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4541, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4624, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4508, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4444, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4278, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4318, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4259, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.414, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4138, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4208, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4181, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4083, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3856, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4003, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4032, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4016, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3864, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.395, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3822, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3746, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3741, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3721, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3638, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3743, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3528, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3494, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3469, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.36, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3533, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3363, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3373, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3281, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3379, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3137, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3236, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3242, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3192, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3243, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3158, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3006, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.314, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3111, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3061, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3079, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3052, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2985, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2888, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2923, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2905, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2779, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2816, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.28, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.2874, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2697, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2748, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2647, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2734, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2601, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2765, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2628, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2579, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2572, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2587, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2638, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2633, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.2549, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2568, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883476276613099e-05, + "loss": 4.2536, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2464, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.236, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2429, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2372, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2294, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2355, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2297, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2344, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2337, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.8750952427436986e-05, + "loss": 4.2263, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.194214820861816, + "eval_runtime": 303.1282, + "eval_samples_per_second": 1258.843, + "eval_steps_per_second": 39.34, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.8742566479926466e-05, + "loss": 4.2099, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2105, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2245, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2146, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2171, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700653121177595e-05, + "loss": 4.2045, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.199, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2008, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2079, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2042, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2018, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2076, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864198424621142e-05, + "loss": 4.1786, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.86335982987009e-05, + "loss": 4.1882, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862521235119038e-05, + "loss": 4.1865, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.1738, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.1894, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.1813, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.177, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.2029, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.181, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1775, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1763, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1869, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.1677, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1671, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1692, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1639, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.163, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1582, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1757, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1628, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847433081121595e-05, + "loss": 4.16, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846594486370543e-05, + "loss": 4.1585, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1605, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1548, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1394, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1435, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.1342, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.148, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1386, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1454, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839048771491447e-05, + "loss": 4.1371, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1389, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1439, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1339, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.8356960303676126e-05, + "loss": 4.1391, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1254, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1238, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331818839948295e-05, + "loss": 4.1318, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323432892437775e-05, + "loss": 4.1289, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1326, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1063, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1288, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1075, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828153591249264e-05, + "loss": 4.136, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.105, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264780396275336e-05, + "loss": 4.1221, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256394448764816e-05, + "loss": 4.1161, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248008501254296e-05, + "loss": 4.1007, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823962255374377e-05, + "loss": 4.11, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823123660623325e-05, + "loss": 4.1085, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822285065872273e-05, + "loss": 4.0908, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821446471121221e-05, + "loss": 4.0977, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820609514250542e-05, + "loss": 4.1118, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.81977091949949e-05, + "loss": 4.1011, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818932324748438e-05, + "loss": 4.0985, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818093729997386e-05, + "loss": 4.097, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.8172567731267074e-05, + "loss": 4.085, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.8164181783756554e-05, + "loss": 4.1027, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155795836246034e-05, + "loss": 4.1019, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147409888735514e-05, + "loss": 4.1005, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813904032002872e-05, + "loss": 4.109, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.81306543725182e-05, + "loss": 4.0985, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812226842500768e-05, + "loss": 4.1001, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811389885630089e-05, + "loss": 4.0818, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810551290879037e-05, + "loss": 4.0955, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809712696127985e-05, + "loss": 4.0888, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.808874101376933e-05, + "loss": 4.0804, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808035506625881e-05, + "loss": 4.0842, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807196911874829e-05, + "loss": 4.09, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.0955, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0895, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804682765502047e-05, + "loss": 4.0704, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803844170750995e-05, + "loss": 4.0778, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0913, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0882, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.8013300243782116e-05, + "loss": 4.0804, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0857, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996544727564805e-05, + "loss": 4.0845, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988158780054285e-05, + "loss": 4.0708, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979772832543765e-05, + "loss": 4.0752, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971386885033245e-05, + "loss": 4.0812, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7963000937522725e-05, + "loss": 4.0686, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795463136881594e-05, + "loss": 4.086, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794624542130542e-05, + "loss": 4.0652, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.79378594737949e-05, + "loss": 4.0626, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792947352628438e-05, + "loss": 4.066, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792108757877386e-05, + "loss": 4.076, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.791270163126334e-05, + "loss": 4.0755, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0612, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0608, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788756016753551e-05, + "loss": 4.0549, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787917422002499e-05, + "loss": 4.0712, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.0446, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.0526, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0666, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.0567, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.055, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.057, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.7820505345058815e-05, + "loss": 4.0473, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.7812119397548295e-05, + "loss": 4.0585, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0543, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0547, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.0576, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0611, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.049, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.045, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0501, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0465, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0354, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0443, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.0395, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0508, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0338, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0432, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0269, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.0441, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0322, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0484, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0399, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0366, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0288, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0362, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.044, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0463, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602568982607675e-05, + "loss": 4.0387, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594183035097155e-05, + "loss": 4.0404, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.0327, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577411140076115e-05, + "loss": 4.0326, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.0264, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0319, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.755226967634829e-05, + "loss": 4.0274, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0164, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753549778132725e-05, + "loss": 4.0284, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752712821262046e-05, + "loss": 4.0219, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751874226510994e-05, + "loss": 4.0272, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751035631759942e-05, + "loss": 4.0249, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.75019703700889e-05, + "loss": 4.0233, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.025408744812012, + "eval_runtime": 302.9748, + "eval_samples_per_second": 1259.481, + "eval_steps_per_second": 39.36, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749358442257838e-05, + "loss": 4.0041, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748519847506786e-05, + "loss": 4.0118, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747681252755734e-05, + "loss": 4.0227, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746842658004682e-05, + "loss": 4.0198, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.74600406325363e-05, + "loss": 4.0242, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.745165468502578e-05, + "loss": 4.0031, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744326873751526e-05, + "loss": 4.0101, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.743488279000474e-05, + "loss": 4.0059, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742649684249422e-05, + "loss": 4.016, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0132, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740974132627691e-05, + "loss": 4.014, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740135537876639e-05, + "loss": 4.0124, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739296943125587e-05, + "loss": 3.9943, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738458348374535e-05, + "loss": 3.9974, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737619753623483e-05, + "loss": 4.0039, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736781158872431e-05, + "loss": 3.9938, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735944202001752e-05, + "loss": 4.0008, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7351056072507e-05, + "loss": 3.9984, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734267012499648e-05, + "loss": 3.9953, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733428417748596e-05, + "loss": 4.0248, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732591460877917e-05, + "loss": 3.999, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731752866126865e-05, + "loss": 4.0035, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730914271375813e-05, + "loss": 3.9994, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730075676624761e-05, + "loss": 4.0103, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729238719754082e-05, + "loss": 3.9903, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.72840012500303e-05, + "loss": 3.9926, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727561530251978e-05, + "loss": 3.9958, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726722935500926e-05, + "loss": 3.9947, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9844, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.99, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.724208789128143e-05, + "loss": 4.0045, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9945, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9916, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9957, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9905, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200174532532566e-05, + "loss": 3.9872, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.9735, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9847, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.971, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.984, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.9768, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149858847469446e-05, + "loss": 3.9877, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714147289995892e-05, + "loss": 3.9804, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.9761, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124717383741615e-05, + "loss": 3.984, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116331436231095e-05, + "loss": 3.9796, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.7107945488720575e-05, + "loss": 3.9829, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709959229881752e-05, + "loss": 3.9683, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9668, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 3.9788, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9744, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9756, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705766256126492e-05, + "loss": 3.9579, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.9806, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9553, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.9843, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.9513, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701574920251605e-05, + "loss": 3.9751, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700736325500553e-05, + "loss": 3.9663, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699897730749501e-05, + "loss": 3.9592, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699059135998449e-05, + "loss": 3.9603, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.69822217912777e-05, + "loss": 3.9622, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9449, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965466275060394e-05, + "loss": 3.9546, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695708032754987e-05, + "loss": 3.9638, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694869438003935e-05, + "loss": 3.9628, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694030843252883e-05, + "loss": 3.9516, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9538, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9486, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9552, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.959, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689839507377996e-05, + "loss": 3.9599, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689002550507317e-05, + "loss": 3.9697, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688163955756265e-05, + "loss": 3.9632, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687325361005213e-05, + "loss": 3.9615, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686486766254161e-05, + "loss": 3.9435, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685649809383482e-05, + "loss": 3.9569, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.68481121463243e-05, + "loss": 3.957, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683972619881378e-05, + "loss": 3.9421, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.683134025130326e-05, + "loss": 3.953, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.682295430379274e-05, + "loss": 3.9543, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681456835628222e-05, + "loss": 3.96, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.680618240877171e-05, + "loss": 3.9524, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.9344, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9471, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9552, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772654997533356e-05, + "loss": 3.9566, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764269050022836e-05, + "loss": 3.9504, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.9548, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9567, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9367, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730741638784485e-05, + "loss": 3.9487, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9479, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9393, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9592, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9402, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9303, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9403, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.951, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9468, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9388, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664691492128675e-05, + "loss": 3.9321, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663852897377623e-05, + "loss": 3.9315, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.66301430262657e-05, + "loss": 3.9487, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.921, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9329, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660500156253788e-05, + "loss": 3.9444, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659661561502736e-05, + "loss": 3.9341, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9327, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.9375, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657147415129953e-05, + "loss": 3.9301, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656308820378901e-05, + "loss": 3.9365, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655470225627849e-05, + "loss": 3.9327, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9324, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9377, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9411, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.6521174845040136e-05, + "loss": 3.9361, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9247, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650441932882283e-05, + "loss": 3.9307, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649603338131231e-05, + "loss": 3.9286, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648764743380179e-05, + "loss": 3.9193, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9317, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647089191758448e-05, + "loss": 3.9177, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.9337, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645412002256344e-05, + "loss": 3.9191, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9268, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9139, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9267, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642059261132509e-05, + "loss": 3.9178, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.641220666381457e-05, + "loss": 3.9353, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640382071630405e-05, + "loss": 3.9306, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.9231, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.9134, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9244, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370293305065705e-05, + "loss": 3.932, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.935, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353537788848395e-05, + "loss": 3.924, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.9301, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336765893827354e-05, + "loss": 3.9246, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328379946316834e-05, + "loss": 3.9252, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.9156, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9174, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303238482589003e-05, + "loss": 3.922, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629485253507848e-05, + "loss": 3.9087, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9172, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627809701886118e-05, + "loss": 3.9193, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.9138, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626132512384014e-05, + "loss": 3.9171, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9124, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.951789379119873, + "eval_runtime": 304.7819, + "eval_samples_per_second": 1252.013, + "eval_steps_per_second": 39.126, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9074, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623618366011231e-05, + "loss": 3.9038, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622779771260179e-05, + "loss": 3.9199, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9102, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9217, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.8963, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619427030136344e-05, + "loss": 3.9081, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.6185884353852924e-05, + "loss": 3.8995, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.9141, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9093, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.91, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615235694261457e-05, + "loss": 3.91, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614398737390778e-05, + "loss": 3.891, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613560142639726e-05, + "loss": 3.8982, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612721547888674e-05, + "loss": 3.9015, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611882953137622e-05, + "loss": 3.8961, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.8966, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.9017, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.8931, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9274, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.8994, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9028, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.9032, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9079, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.8914, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.9022, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.8959, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.8956, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009877728954384e-05, + "loss": 3.8851, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001491781443864e-05, + "loss": 3.8938, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993105833933344e-05, + "loss": 3.9064, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598473626522656e-05, + "loss": 3.8974, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597635031771604e-05, + "loss": 3.9011, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.8992, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959578422695e-05, + "loss": 3.8912, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.899, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.8779, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593442058016343e-05, + "loss": 3.8911, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8743, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591766506394613e-05, + "loss": 3.8909, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59092791164356e-05, + "loss": 3.885, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590089316892508e-05, + "loss": 3.895, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.8888, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.8837, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587575170519726e-05, + "loss": 3.8926, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586736575768674e-05, + "loss": 3.8881, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858996188979954e-05, + "loss": 3.888, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.8831, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584222429395891e-05, + "loss": 3.8708, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583383834644839e-05, + "loss": 3.8887, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582545239893787e-05, + "loss": 3.883, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8853, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808696882720556e-05, + "loss": 3.87, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800310935210036e-05, + "loss": 3.8935, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579192498769952e-05, + "loss": 3.8617, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8953, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.8671, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8813, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575839757646117e-05, + "loss": 3.877, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575002800775438e-05, + "loss": 3.8736, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574164206024386e-05, + "loss": 3.8695, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.8811, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.8556, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571650059651603e-05, + "loss": 3.8634, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570811464900551e-05, + "loss": 3.8802, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.875, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691342753984476e-05, + "loss": 3.869, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682956806473956e-05, + "loss": 3.8688, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.8589, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8699, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8749, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649429395235605e-05, + "loss": 3.8737, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641059826528814e-05, + "loss": 3.8856, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8762, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8784, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615901983997254e-05, + "loss": 3.8595, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8704, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8748, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.8576, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558237457275891e-05, + "loss": 3.8723, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557400500405212e-05, + "loss": 3.8674, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8729, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8696, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554884716152056e-05, + "loss": 3.855, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554047759281377e-05, + "loss": 3.8664, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.8691, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8743, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551531975028221e-05, + "loss": 3.8701, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550695018157542e-05, + "loss": 3.8703, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.54985642340649e-05, + "loss": 3.8775, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490178286554384e-05, + "loss": 3.8545, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.5481792339043864e-05, + "loss": 3.8688, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547342277033707e-05, + "loss": 3.8613, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546503682282655e-05, + "loss": 3.8617, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545666725411976e-05, + "loss": 3.8762, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544828130660924e-05, + "loss": 3.8624, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543989535909872e-05, + "loss": 3.8508, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54315094115882e-05, + "loss": 3.8601, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.869, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541473751656716e-05, + "loss": 3.8687, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540635156905664e-05, + "loss": 3.8588, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539796562154612e-05, + "loss": 3.8528, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.853, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538121010532882e-05, + "loss": 3.8687, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.53728241578183e-05, + "loss": 3.8424, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536443821030778e-05, + "loss": 3.8521, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8646, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347682694090466e-05, + "loss": 3.8592, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8503, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.8621, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8548, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314155282852115e-05, + "loss": 3.8558, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305769335341595e-05, + "loss": 3.8567, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297383387831075e-05, + "loss": 3.8534, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8668, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8582, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527224192410325e-05, + "loss": 3.8596, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526385597659273e-05, + "loss": 3.8475, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525547002908221e-05, + "loss": 3.8541, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.8541, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.52387145128649e-05, + "loss": 3.8424, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523032856535438e-05, + "loss": 3.8544, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522194261784386e-05, + "loss": 3.8456, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521355667033333e-05, + "loss": 3.8559, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520518710162655e-05, + "loss": 3.8455, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519680115411603e-05, + "loss": 3.8543, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518841520660551e-05, + "loss": 3.8339, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518002925909499e-05, + "loss": 3.8557, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171659690388204e-05, + "loss": 3.8457, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163273742877684e-05, + "loss": 3.8565, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515488779536716e-05, + "loss": 3.8528, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514650184785664e-05, + "loss": 3.854, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.5138132279149853e-05, + "loss": 3.8355, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.5129746331639333e-05, + "loss": 3.8533, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.5121360384128807e-05, + "loss": 3.8553, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112974436618287e-05, + "loss": 3.8601, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.51046048679115e-05, + "loss": 3.8516, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096218920400976e-05, + "loss": 3.8515, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508783297289046e-05, + "loss": 3.852, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8569, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507107745667316e-05, + "loss": 3.8406, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506269150916263e-05, + "loss": 3.8467, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505430556165211e-05, + "loss": 3.8476, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8386, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.50375500454348e-05, + "loss": 3.8443, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502916409792428e-05, + "loss": 3.8477, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502077815041376e-05, + "loss": 3.8407, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501239220290324e-05, + "loss": 3.8407, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.5004039013000185e-05, + "loss": 3.8483, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9111204147338867, + "eval_runtime": 302.6857, + "eval_samples_per_second": 1260.684, + "eval_steps_per_second": 39.397, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.4995653065489665e-05, + "loss": 3.8286, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987267117979145e-05, + "loss": 3.8327, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497888117046863e-05, + "loss": 3.8455, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970495222958105e-05, + "loss": 3.8419, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962109275447585e-05, + "loss": 3.8527, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953723327937065e-05, + "loss": 3.8266, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945337380426545e-05, + "loss": 3.836, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936951432916025e-05, + "loss": 3.8291, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928581864209234e-05, + "loss": 3.8435, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920195916698714e-05, + "loss": 3.8429, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491182634799192e-05, + "loss": 3.8315, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.49034404004814e-05, + "loss": 3.8473, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489505445297088e-05, + "loss": 3.8211, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488666850546037e-05, + "loss": 3.8309, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487828255794985e-05, + "loss": 3.8337, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486989661043933e-05, + "loss": 3.8247, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486151066292881e-05, + "loss": 3.8276, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485312471541829e-05, + "loss": 3.8322, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.48447551467115e-05, + "loss": 3.8269, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483636919920098e-05, + "loss": 3.8559, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482798325169046e-05, + "loss": 3.8326, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481959730417994e-05, + "loss": 3.8337, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481122773547315e-05, + "loss": 3.8378, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480284178796263e-05, + "loss": 3.8407, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479445584045211e-05, + "loss": 3.8212, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478606989294159e-05, + "loss": 3.8363, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47777003242348e-05, + "loss": 3.8282, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476931437672428e-05, + "loss": 3.8268, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476092842921376e-05, + "loss": 3.8188, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475254248170324e-05, + "loss": 3.8267, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474417291299645e-05, + "loss": 3.8416, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473580334428966e-05, + "loss": 3.8297, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472741739677914e-05, + "loss": 3.8317, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471903144926862e-05, + "loss": 3.8322, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.47106455017581e-05, + "loss": 3.8269, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470225955424758e-05, + "loss": 3.8291, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469387360673706e-05, + "loss": 3.8147, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468548765922654e-05, + "loss": 3.8228, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467711809051976e-05, + "loss": 3.8142, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466873214300924e-05, + "loss": 3.8208, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466034619549872e-05, + "loss": 3.822, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46519602479882e-05, + "loss": 3.8297, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.4643590679281406e-05, + "loss": 3.8224, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635204731770886e-05, + "loss": 3.822, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626818784260366e-05, + "loss": 3.8247, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618432836749846e-05, + "loss": 3.8211, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610063268043055e-05, + "loss": 3.8247, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601677320532535e-05, + "loss": 3.8199, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593291373022015e-05, + "loss": 3.8067, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584905425511495e-05, + "loss": 3.8263, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457653585680471e-05, + "loss": 3.8155, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456814990929419e-05, + "loss": 3.823, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455976396178367e-05, + "loss": 3.8099, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455137801427315e-05, + "loss": 3.8231, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454300844556636e-05, + "loss": 3.8012, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453462249805584e-05, + "loss": 3.8314, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452623655054532e-05, + "loss": 3.803, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.45178506030348e-05, + "loss": 3.8138, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450948103432801e-05, + "loss": 3.8186, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450109508681749e-05, + "loss": 3.8109, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449270913930697e-05, + "loss": 3.8098, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448432319179645e-05, + "loss": 3.8136, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475953623089664e-05, + "loss": 3.8016, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467567675579144e-05, + "loss": 3.7978, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459181728068624e-05, + "loss": 3.816, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450795780558104e-05, + "loss": 3.8131, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444242621185131e-05, + "loss": 3.8032, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443404026434079e-05, + "loss": 3.8107, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442565431683027e-05, + "loss": 3.7966, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441726836931975e-05, + "loss": 3.8079, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440889880061296e-05, + "loss": 3.8135, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.8102, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439212690559192e-05, + "loss": 3.8235, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.43837409580814e-05, + "loss": 3.8129, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437537138937462e-05, + "loss": 3.8222, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.7985, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435859949435358e-05, + "loss": 3.8098, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435021354684306e-05, + "loss": 3.8135, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434184397813627e-05, + "loss": 3.7937, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433345803062575e-05, + "loss": 3.8142, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432507208311523e-05, + "loss": 3.8085, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431668613560471e-05, + "loss": 3.8122, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308316566897916e-05, + "loss": 3.81, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299930619387396e-05, + "loss": 3.7944, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291544671876876e-05, + "loss": 3.8087, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283158724366356e-05, + "loss": 3.8065, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427478915565957e-05, + "loss": 3.8123, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426640320814905e-05, + "loss": 3.8096, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425801726063853e-05, + "loss": 3.8126, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249631313128005e-05, + "loss": 3.815, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424126174442122e-05, + "loss": 3.7976, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.42328757969107e-05, + "loss": 3.8093, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422448984940018e-05, + "loss": 3.8009, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216103901889654e-05, + "loss": 3.8089, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420773433318287e-05, + "loss": 3.8185, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419934838567235e-05, + "loss": 3.7995, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419096243816182e-05, + "loss": 3.7971, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418257649065131e-05, + "loss": 3.7983, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417419054314079e-05, + "loss": 3.8073, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416580459563027e-05, + "loss": 3.814, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415741864811975e-05, + "loss": 3.7973, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414903270060923e-05, + "loss": 3.7963, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414066313190244e-05, + "loss": 3.7956, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413227718439192e-05, + "loss": 3.8096, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41238912368814e-05, + "loss": 3.7863, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411550528937088e-05, + "loss": 3.7969, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410713572066409e-05, + "loss": 3.8059, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409874977315357e-05, + "loss": 3.7993, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090380204446776e-05, + "loss": 3.7937, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408199425693626e-05, + "loss": 3.8078, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407360830942574e-05, + "loss": 3.7969, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406522236191522e-05, + "loss": 3.7947, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.40568364144047e-05, + "loss": 3.803, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404845046689418e-05, + "loss": 3.8003, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404006451938366e-05, + "loss": 3.8076, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403167857187314e-05, + "loss": 3.8031, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402330900316635e-05, + "loss": 3.8, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401492305565583e-05, + "loss": 3.7901, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400653710814531e-05, + "loss": 3.7989, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399815116063479e-05, + "loss": 3.7965, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.3989781591928e-05, + "loss": 3.785, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398139564441748e-05, + "loss": 3.8001, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.397300969690696e-05, + "loss": 3.7886, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396462374939645e-05, + "loss": 3.8006, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956254180689657e-05, + "loss": 3.7933, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947868233179137e-05, + "loss": 3.797, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939482285668617e-05, + "loss": 3.7785, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931096338158096e-05, + "loss": 3.7958, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922726769451306e-05, + "loss": 3.7955, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914340821940786e-05, + "loss": 3.796, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905954874430265e-05, + "loss": 3.7971, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897568926919745e-05, + "loss": 3.8018, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889199358212955e-05, + "loss": 3.7788, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880813410702434e-05, + "loss": 3.7994, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.3872427463191914e-05, + "loss": 3.8027, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.3864041515681394e-05, + "loss": 3.8016, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385567194697461e-05, + "loss": 3.7975, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384728599946409e-05, + "loss": 3.8032, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.383890005195357e-05, + "loss": 3.7946, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383051410444305e-05, + "loss": 3.802, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382214453573626e-05, + "loss": 3.7829, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381375858822574e-05, + "loss": 3.7945, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.789, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379700307200843e-05, + "loss": 3.7874, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378861712449791e-05, + "loss": 3.7923, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378023117698739e-05, + "loss": 3.7887, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771861608280604e-05, + "loss": 3.7926, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763475660770084e-05, + "loss": 3.7826, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755089713259564e-05, + "loss": 3.7972, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8860552310943604, + "eval_runtime": 309.7483, + "eval_samples_per_second": 1231.939, + "eval_steps_per_second": 38.499, + "step": 381600 + }, + { + "epoch": 0.0, + "learning_rate": 4.3746703765749044e-05, + "loss": 3.7794, + "step": 381952 + }, + { + "epoch": 0.0, + "learning_rate": 4.3738317818238524e-05, + "loss": 3.7782, + "step": 382464 + }, + { + "epoch": 0.0, + "learning_rate": 4.3729931870728004e-05, + "loss": 3.7912, + "step": 382976 + }, + { + "epoch": 0.0, + "learning_rate": 4.3721545923217484e-05, + "loss": 3.7927, + "step": 383488 + }, + { + "epoch": 0.0, + "learning_rate": 4.371315997570696e-05, + "loss": 3.793, + "step": 384000 + }, + { + "epoch": 0.0, + "learning_rate": 4.370477402819644e-05, + "loss": 3.7784, + "step": 384512 + }, + { + "epoch": 0.0, + "learning_rate": 4.369638808068592e-05, + "loss": 3.78, + "step": 385024 + }, + { + "epoch": 0.0, + "learning_rate": 4.36880021331754e-05, + "loss": 3.7787, + "step": 385536 + }, + { + "epoch": 0.0, + "learning_rate": 4.3679632564468606e-05, + "loss": 3.7867, + "step": 386048 + }, + { + "epoch": 0.0, + "learning_rate": 4.3671246616958086e-05, + "loss": 3.7926, + "step": 386560 + }, + { + "epoch": 0.0, + "learning_rate": 4.36628770482513e-05, + "loss": 3.7781, + "step": 387072 + }, + { + "epoch": 0.0, + "learning_rate": 4.365449110074079e-05, + "loss": 3.7939, + "step": 387584 + }, + { + "epoch": 0.0, + "learning_rate": 4.364610515323026e-05, + "loss": 3.7728, + "step": 388096 + }, + { + "epoch": 0.0, + "learning_rate": 4.363771920571974e-05, + "loss": 3.7756, + "step": 388608 + }, + { + "epoch": 0.0, + "learning_rate": 4.362933325820922e-05, + "loss": 3.7817, + "step": 389120 + }, + { + "epoch": 0.0, + "learning_rate": 4.36209473106987e-05, + "loss": 3.7698, + "step": 389632 + }, + { + "epoch": 0.0, + "learning_rate": 4.361257774199191e-05, + "loss": 3.7751, + "step": 390144 + }, + { + "epoch": 0.0, + "learning_rate": 4.360419179448139e-05, + "loss": 3.7819, + "step": 390656 + }, + { + "epoch": 0.0, + "learning_rate": 4.359580584697087e-05, + "loss": 3.775, + "step": 391168 + }, + { + "epoch": 0.0, + "learning_rate": 4.358741989946035e-05, + "loss": 3.8011, + "step": 391680 + }, + { + "epoch": 0.0, + "learning_rate": 4.357903395194983e-05, + "loss": 3.7853, + "step": 392192 + }, + { + "epoch": 0.0, + "learning_rate": 4.357064800443931e-05, + "loss": 3.7836, + "step": 392704 + }, + { + "epoch": 0.0, + "learning_rate": 4.356226205692879e-05, + "loss": 3.7843, + "step": 393216 + }, + { + "epoch": 0.0, + "learning_rate": 4.3553892488222006e-05, + "loss": 3.7909, + "step": 393728 + }, + { + "epoch": 0.0, + "learning_rate": 4.3545506540711486e-05, + "loss": 3.7699, + "step": 394240 + }, + { + "epoch": 0.0, + "learning_rate": 4.3537120593200966e-05, + "loss": 3.7833, + "step": 394752 + }, + { + "epoch": 0.0, + "learning_rate": 4.3528734645690446e-05, + "loss": 3.7805, + "step": 395264 + }, + { + "epoch": 0.0, + "learning_rate": 4.3520348698179926e-05, + "loss": 3.7737, + "step": 395776 + }, + { + "epoch": 0.0, + "learning_rate": 4.3511962750669406e-05, + "loss": 3.7648, + "step": 396288 + }, + { + "epoch": 0.0, + "learning_rate": 4.3503576803158886e-05, + "loss": 3.7779, + "step": 396800 + }, + { + "epoch": 0.01, + "learning_rate": 4.3495190855648366e-05, + "loss": 3.7911, + "step": 397312 + }, + { + "epoch": 0.01, + "learning_rate": 4.3486821286941575e-05, + "loss": 3.7796, + "step": 397824 + }, + { + "epoch": 0.01, + "learning_rate": 4.3478435339431055e-05, + "loss": 3.785, + "step": 398336 + }, + { + "epoch": 0.01, + "learning_rate": 4.3470049391920535e-05, + "loss": 3.7794, + "step": 398848 + }, + { + "epoch": 0.01, + "learning_rate": 4.3461663444410015e-05, + "loss": 3.7734, + "step": 399360 + }, + { + "epoch": 0.01, + "learning_rate": 4.3453277496899495e-05, + "loss": 3.7791, + "step": 399872 + }, + { + "epoch": 0.01, + "learning_rate": 4.3444891549388975e-05, + "loss": 3.7698, + "step": 400384 + }, + { + "epoch": 0.01, + "learning_rate": 4.3436505601878455e-05, + "loss": 3.7689, + "step": 400896 + }, + { + "epoch": 0.01, + "learning_rate": 4.3428119654367935e-05, + "loss": 3.7634, + "step": 401408 + }, + { + "epoch": 0.01, + "learning_rate": 4.341975008566115e-05, + "loss": 3.7696, + "step": 401920 + }, + { + "epoch": 0.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7721, + "step": 402432 + }, + { + "epoch": 0.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.7789, + "step": 402944 + }, + { + "epoch": 0.01, + "learning_rate": 4.339460862193332e-05, + "loss": 3.7717, + "step": 403456 + }, + { + "epoch": 0.01, + "learning_rate": 4.338622267442279e-05, + "loss": 3.7723, + "step": 403968 + }, + { + "epoch": 0.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.7769, + "step": 404480 + }, + { + "epoch": 0.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.7725, + "step": 404992 + }, + { + "epoch": 0.01, + "learning_rate": 4.336108121069497e-05, + "loss": 3.7756, + "step": 405504 + }, + { + "epoch": 0.01, + "learning_rate": 4.335269526318445e-05, + "loss": 3.7689, + "step": 406016 + }, + { + "epoch": 0.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.7553, + "step": 406528 + }, + { + "epoch": 0.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.7783, + "step": 407040 + }, + { + "epoch": 0.01, + "learning_rate": 4.3327553799456624e-05, + "loss": 3.7675, + "step": 407552 + }, + { + "epoch": 0.01, + "learning_rate": 4.33191678519461e-05, + "loss": 3.7757, + "step": 408064 + }, + { + "epoch": 0.01, + "learning_rate": 4.331078190443558e-05, + "loss": 3.762, + "step": 408576 + }, + { + "epoch": 0.01, + "learning_rate": 4.330239595692506e-05, + "loss": 3.772, + "step": 409088 + }, + { + "epoch": 0.01, + "learning_rate": 4.3294026388218266e-05, + "loss": 3.7519, + "step": 409600 + }, + { + "epoch": 0.01, + "learning_rate": 4.3285640440707746e-05, + "loss": 3.7799, + "step": 410112 + }, + { + "epoch": 0.01, + "learning_rate": 4.3277254493197226e-05, + "loss": 3.7565, + "step": 410624 + }, + { + "epoch": 0.01, + "learning_rate": 4.3268868545686706e-05, + "loss": 3.7686, + "step": 411136 + }, + { + "epoch": 0.01, + "learning_rate": 4.3260498976979915e-05, + "loss": 3.7716, + "step": 411648 + }, + { + "epoch": 0.01, + "learning_rate": 4.32521130294694e-05, + "loss": 3.7597, + "step": 412160 + }, + { + "epoch": 0.01, + "learning_rate": 4.324372708195888e-05, + "loss": 3.7601, + "step": 412672 + }, + { + "epoch": 0.01, + "learning_rate": 4.323534113444836e-05, + "loss": 3.7724, + "step": 413184 + }, + { + "epoch": 0.01, + "learning_rate": 4.322697156574157e-05, + "loss": 3.7497, + "step": 413696 + }, + { + "epoch": 0.01, + "learning_rate": 4.321858561823105e-05, + "loss": 3.7488, + "step": 414208 + }, + { + "epoch": 0.01, + "learning_rate": 4.321019967072053e-05, + "loss": 3.7678, + "step": 414720 + }, + { + "epoch": 0.01, + "learning_rate": 4.320181372321001e-05, + "loss": 3.7679, + "step": 415232 + }, + { + "epoch": 0.01, + "learning_rate": 4.319344415450322e-05, + "loss": 3.7536, + "step": 415744 + }, + { + "epoch": 0.01, + "learning_rate": 4.31850582069927e-05, + "loss": 3.7651, + "step": 416256 + }, + { + "epoch": 0.01, + "learning_rate": 4.317667225948218e-05, + "loss": 3.748, + "step": 416768 + }, + { + "epoch": 0.01, + "learning_rate": 4.316828631197166e-05, + "loss": 3.7572, + "step": 417280 + }, + { + "epoch": 0.01, + "learning_rate": 4.315991674326487e-05, + "loss": 3.7665, + "step": 417792 + }, + { + "epoch": 0.01, + "learning_rate": 4.3151530795754356e-05, + "loss": 3.7642, + "step": 418304 + }, + { + "epoch": 0.01, + "learning_rate": 4.3143144848243836e-05, + "loss": 3.7727, + "step": 418816 + }, + { + "epoch": 0.01, + "learning_rate": 4.3134758900733316e-05, + "loss": 3.7669, + "step": 419328 + }, + { + "epoch": 0.01, + "learning_rate": 4.3126389332026525e-05, + "loss": 3.7767, + "step": 419840 + }, + { + "epoch": 0.01, + "learning_rate": 4.3118003384516005e-05, + "loss": 3.7492, + "step": 420352 + }, + { + "epoch": 0.01, + "learning_rate": 4.3109617437005485e-05, + "loss": 3.7643, + "step": 420864 + }, + { + "epoch": 0.01, + "learning_rate": 4.3101231489494965e-05, + "loss": 3.7668, + "step": 421376 + }, + { + "epoch": 0.01, + "learning_rate": 4.3092861920788174e-05, + "loss": 3.7443, + "step": 421888 + }, + { + "epoch": 0.01, + "learning_rate": 4.3084475973277654e-05, + "loss": 3.7669, + "step": 422400 + }, + { + "epoch": 0.01, + "learning_rate": 4.3076090025767134e-05, + "loss": 3.7618, + "step": 422912 + }, + { + "epoch": 0.01, + "learning_rate": 4.3067704078256614e-05, + "loss": 3.7643, + "step": 423424 + }, + { + "epoch": 0.01, + "learning_rate": 4.305933450954982e-05, + "loss": 3.7649, + "step": 423936 + }, + { + "epoch": 0.01, + "learning_rate": 4.30509485620393e-05, + "loss": 3.753, + "step": 424448 + }, + { + "epoch": 0.01, + "learning_rate": 4.304256261452879e-05, + "loss": 3.7548, + "step": 424960 + }, + { + "epoch": 0.01, + "learning_rate": 4.303417666701827e-05, + "loss": 3.7602, + "step": 425472 + }, + { + "epoch": 0.01, + "learning_rate": 4.302580709831148e-05, + "loss": 3.7699, + "step": 425984 + }, + { + "epoch": 0.01, + "learning_rate": 4.301742115080096e-05, + "loss": 3.7588, + "step": 426496 + }, + { + "epoch": 0.01, + "learning_rate": 4.300903520329044e-05, + "loss": 3.7683, + "step": 427008 + }, + { + "epoch": 0.02, + "learning_rate": 4.300064925577992e-05, + "loss": 3.77, + "step": 427520 + }, + { + "epoch": 0.02, + "learning_rate": 4.299227968707313e-05, + "loss": 3.7531, + "step": 428032 + }, + { + "epoch": 0.02, + "learning_rate": 4.298389373956261e-05, + "loss": 3.7609, + "step": 428544 + }, + { + "epoch": 0.02, + "learning_rate": 4.297550779205209e-05, + "loss": 3.7527, + "step": 429056 + }, + { + "epoch": 0.02, + "learning_rate": 4.296712184454157e-05, + "loss": 3.7621, + "step": 429568 + }, + { + "epoch": 0.02, + "learning_rate": 4.2958752275834776e-05, + "loss": 3.7751, + "step": 430080 + }, + { + "epoch": 0.02, + "learning_rate": 4.2950366328324256e-05, + "loss": 3.7506, + "step": 430592 + }, + { + "epoch": 0.02, + "learning_rate": 4.294198038081374e-05, + "loss": 3.7541, + "step": 431104 + }, + { + "epoch": 0.02, + "learning_rate": 4.293359443330322e-05, + "loss": 3.7492, + "step": 431616 + }, + { + "epoch": 0.02, + "learning_rate": 4.29252084857927e-05, + "loss": 3.7632, + "step": 432128 + }, + { + "epoch": 0.02, + "learning_rate": 4.291682253828218e-05, + "loss": 3.7711, + "step": 432640 + }, + { + "epoch": 0.02, + "learning_rate": 4.290843659077166e-05, + "loss": 3.7537, + "step": 433152 + }, + { + "epoch": 0.02, + "learning_rate": 4.290005064326114e-05, + "loss": 3.7526, + "step": 433664 + }, + { + "epoch": 0.02, + "learning_rate": 4.289168107455435e-05, + "loss": 3.7458, + "step": 434176 + }, + { + "epoch": 0.02, + "learning_rate": 4.288329512704383e-05, + "loss": 3.7657, + "step": 434688 + }, + { + "epoch": 0.02, + "learning_rate": 4.287490917953331e-05, + "loss": 3.7389, + "step": 435200 + }, + { + "epoch": 0.02, + "learning_rate": 4.286652323202279e-05, + "loss": 3.7533, + "step": 435712 + }, + { + "epoch": 0.02, + "learning_rate": 4.2858153663316e-05, + "loss": 3.7561, + "step": 436224 + }, + { + "epoch": 0.02, + "learning_rate": 4.284976771580548e-05, + "loss": 3.7582, + "step": 436736 + }, + { + "epoch": 0.02, + "learning_rate": 4.28413981470987e-05, + "loss": 3.7491, + "step": 437248 + }, + { + "epoch": 0.02, + "learning_rate": 4.283301219958818e-05, + "loss": 3.7592, + "step": 437760 + }, + { + "epoch": 0.02, + "learning_rate": 4.282462625207766e-05, + "loss": 3.7538, + "step": 438272 + }, + { + "epoch": 0.02, + "learning_rate": 4.281624030456714e-05, + "loss": 3.7485, + "step": 438784 + }, + { + "epoch": 0.02, + "learning_rate": 4.2807854357056617e-05, + "loss": 3.7586, + "step": 439296 + }, + { + "epoch": 0.02, + "learning_rate": 4.2799468409546097e-05, + "loss": 3.7554, + "step": 439808 + }, + { + "epoch": 0.02, + "learning_rate": 4.2791082462035576e-05, + "loss": 3.7606, + "step": 440320 + }, + { + "epoch": 0.02, + "learning_rate": 4.278269651452505e-05, + "loss": 3.7618, + "step": 440832 + }, + { + "epoch": 0.02, + "learning_rate": 4.2774326945818266e-05, + "loss": 3.7544, + "step": 441344 + }, + { + "epoch": 0.02, + "learning_rate": 4.2765940998307746e-05, + "loss": 3.7475, + "step": 441856 + }, + { + "epoch": 0.02, + "learning_rate": 4.2757555050797225e-05, + "loss": 3.7522, + "step": 442368 + }, + { + "epoch": 0.02, + "learning_rate": 4.27491691032867e-05, + "loss": 3.7548, + "step": 442880 + }, + { + "epoch": 0.02, + "learning_rate": 4.2740799534579915e-05, + "loss": 3.7428, + "step": 443392 + }, + { + "epoch": 0.02, + "learning_rate": 4.2732413587069394e-05, + "loss": 3.753, + "step": 443904 + }, + { + "epoch": 0.02, + "learning_rate": 4.2724027639558874e-05, + "loss": 3.7432, + "step": 444416 + }, + { + "epoch": 0.02, + "learning_rate": 4.2715641692048354e-05, + "loss": 3.7557, + "step": 444928 + }, + { + "epoch": 0.02, + "learning_rate": 4.270727212334157e-05, + "loss": 3.7505, + "step": 445440 + }, + { + "epoch": 0.02, + "learning_rate": 4.269888617583105e-05, + "loss": 3.751, + "step": 445952 + }, + { + "epoch": 0.02, + "learning_rate": 4.2690500228320523e-05, + "loss": 3.7404, + "step": 446464 + }, + { + "epoch": 0.02, + "learning_rate": 4.268211428081e-05, + "loss": 3.7453, + "step": 446976 + }, + { + "epoch": 0.02, + "learning_rate": 4.267374471210322e-05, + "loss": 3.7519, + "step": 447488 + }, + { + "epoch": 0.02, + "learning_rate": 4.26653587645927e-05, + "loss": 3.7565, + "step": 448000 + }, + { + "epoch": 0.02, + "learning_rate": 4.265697281708217e-05, + "loss": 3.7485, + "step": 448512 + }, + { + "epoch": 0.02, + "learning_rate": 4.264860324837539e-05, + "loss": 3.7556, + "step": 449024 + }, + { + "epoch": 0.02, + "learning_rate": 4.264021730086487e-05, + "loss": 3.7407, + "step": 449536 + }, + { + "epoch": 0.02, + "learning_rate": 4.263183135335435e-05, + "loss": 3.7557, + "step": 450048 + }, + { + "epoch": 0.02, + "learning_rate": 4.262344540584383e-05, + "loss": 3.759, + "step": 450560 + }, + { + "epoch": 0.02, + "learning_rate": 4.2615075837137044e-05, + "loss": 3.7576, + "step": 451072 + }, + { + "epoch": 0.02, + "learning_rate": 4.2606689889626524e-05, + "loss": 3.7536, + "step": 451584 + }, + { + "epoch": 0.02, + "learning_rate": 4.2598303942116e-05, + "loss": 3.7617, + "step": 452096 + }, + { + "epoch": 0.02, + "learning_rate": 4.258991799460548e-05, + "loss": 3.7473, + "step": 452608 + }, + { + "epoch": 0.02, + "learning_rate": 4.258154842589869e-05, + "loss": 3.7615, + "step": 453120 + }, + { + "epoch": 0.02, + "learning_rate": 4.257316247838817e-05, + "loss": 3.74, + "step": 453632 + }, + { + "epoch": 0.02, + "learning_rate": 4.2564776530877646e-05, + "loss": 3.7503, + "step": 454144 + }, + { + "epoch": 0.02, + "learning_rate": 4.255640696217086e-05, + "loss": 3.7458, + "step": 454656 + }, + { + "epoch": 0.02, + "learning_rate": 4.254802101466034e-05, + "loss": 3.7451, + "step": 455168 + }, + { + "epoch": 0.02, + "learning_rate": 4.253963506714982e-05, + "loss": 3.7504, + "step": 455680 + }, + { + "epoch": 0.02, + "learning_rate": 4.25312491196393e-05, + "loss": 3.743, + "step": 456192 + }, + { + "epoch": 0.02, + "learning_rate": 4.252287955093252e-05, + "loss": 3.7565, + "step": 456704 + }, + { + "epoch": 0.02, + "learning_rate": 4.2514493603422e-05, + "loss": 3.7317, + "step": 457216 + }, + { + "epoch": 0.02, + "learning_rate": 4.250610765591147e-05, + "loss": 3.7587, + "step": 457728 + }, + { + "epoch": 0.03, + "eval_loss": 3.8695526123046875, + "eval_runtime": 304.277, + "eval_samples_per_second": 1254.091, + "eval_steps_per_second": 39.191, + "step": 457920 + }, + { + "epoch": 1.0, + "learning_rate": 4.249772170840095e-05, + "loss": 3.738, + "step": 458240 + }, + { + "epoch": 1.0, + "learning_rate": 4.248933576089043e-05, + "loss": 3.7356, + "step": 458752 + }, + { + "epoch": 1.0, + "learning_rate": 4.248094981337991e-05, + "loss": 3.7474, + "step": 459264 + }, + { + "epoch": 1.0, + "learning_rate": 4.247256386586939e-05, + "loss": 3.7495, + "step": 459776 + }, + { + "epoch": 1.0, + "learning_rate": 4.246417791835887e-05, + "loss": 3.7511, + "step": 460288 + }, + { + "epoch": 1.0, + "learning_rate": 4.245580834965208e-05, + "loss": 3.7376, + "step": 460800 + }, + { + "epoch": 1.0, + "learning_rate": 4.244742240214156e-05, + "loss": 3.7319, + "step": 461312 + }, + { + "epoch": 1.0, + "learning_rate": 4.243903645463104e-05, + "loss": 3.7404, + "step": 461824 + }, + { + "epoch": 1.0, + "learning_rate": 4.2430666885924255e-05, + "loss": 3.7439, + "step": 462336 + }, + { + "epoch": 1.0, + "learning_rate": 4.2422280938413735e-05, + "loss": 3.7503, + "step": 462848 + }, + { + "epoch": 1.0, + "learning_rate": 4.2413894990903215e-05, + "loss": 3.7409, + "step": 463360 + }, + { + "epoch": 1.0, + "learning_rate": 4.2405525422196424e-05, + "loss": 3.7473, + "step": 463872 + }, + { + "epoch": 1.0, + "learning_rate": 4.2397139474685904e-05, + "loss": 3.7343, + "step": 464384 + }, + { + "epoch": 1.0, + "learning_rate": 4.2388753527175384e-05, + "loss": 3.7333, + "step": 464896 + }, + { + "epoch": 1.0, + "learning_rate": 4.2380367579664864e-05, + "loss": 3.7404, + "step": 465408 + }, + { + "epoch": 1.0, + "learning_rate": 4.2371981632154344e-05, + "loss": 3.7295, + "step": 465920 + }, + { + "epoch": 1.0, + "learning_rate": 4.2363612063447553e-05, + "loss": 3.7337, + "step": 466432 + }, + { + "epoch": 1.0, + "learning_rate": 4.235522611593703e-05, + "loss": 3.741, + "step": 466944 + }, + { + "epoch": 1.0, + "learning_rate": 4.234684016842651e-05, + "loss": 3.733, + "step": 467456 + }, + { + "epoch": 1.0, + "learning_rate": 4.233845422091599e-05, + "loss": 3.7586, + "step": 467968 + }, + { + "epoch": 1.0, + "learning_rate": 4.233006827340547e-05, + "loss": 3.7477, + "step": 468480 + }, + { + "epoch": 1.0, + "learning_rate": 4.232168232589496e-05, + "loss": 3.7389, + "step": 468992 + }, + { + "epoch": 1.0, + "learning_rate": 4.231329637838444e-05, + "loss": 3.7441, + "step": 469504 + }, + { + "epoch": 1.0, + "learning_rate": 4.230491043087392e-05, + "loss": 3.751, + "step": 470016 + }, + { + "epoch": 1.0, + "learning_rate": 4.229654086216713e-05, + "loss": 3.7272, + "step": 470528 + }, + { + "epoch": 1.0, + "learning_rate": 4.228815491465661e-05, + "loss": 3.7443, + "step": 471040 + }, + { + "epoch": 1.0, + "learning_rate": 4.227976896714609e-05, + "loss": 3.7368, + "step": 471552 + }, + { + "epoch": 1.0, + "learning_rate": 4.227138301963557e-05, + "loss": 3.7342, + "step": 472064 + }, + { + "epoch": 1.0, + "learning_rate": 4.226301345092878e-05, + "loss": 3.7263, + "step": 472576 + }, + { + "epoch": 1.0, + "learning_rate": 4.225462750341826e-05, + "loss": 3.7364, + "step": 473088 + }, + { + "epoch": 1.01, + "learning_rate": 4.224624155590774e-05, + "loss": 3.7492, + "step": 473600 + }, + { + "epoch": 1.01, + "learning_rate": 4.223787198720095e-05, + "loss": 3.7378, + "step": 474112 + }, + { + "epoch": 1.01, + "learning_rate": 4.222948603969043e-05, + "loss": 3.7467, + "step": 474624 + }, + { + "epoch": 1.01, + "learning_rate": 4.2221100092179914e-05, + "loss": 3.7423, + "step": 475136 + }, + { + "epoch": 1.01, + "learning_rate": 4.2212714144669394e-05, + "loss": 3.7311, + "step": 475648 + }, + { + "epoch": 1.01, + "learning_rate": 4.2204328197158874e-05, + "loss": 3.737, + "step": 476160 + }, + { + "epoch": 1.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7317, + "step": 476672 + }, + { + "epoch": 1.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7266, + "step": 477184 + }, + { + "epoch": 1.01, + "learning_rate": 4.217917035462731e-05, + "loss": 3.7235, + "step": 477696 + }, + { + "epoch": 1.01, + "learning_rate": 4.217080078592052e-05, + "loss": 3.7269, + "step": 478208 + }, + { + "epoch": 1.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7338, + "step": 478720 + }, + { + "epoch": 1.01, + "learning_rate": 4.2154028890899476e-05, + "loss": 3.7393, + "step": 479232 + }, + { + "epoch": 1.01, + "learning_rate": 4.2145642943388956e-05, + "loss": 3.7322, + "step": 479744 + }, + { + "epoch": 1.01, + "learning_rate": 4.213727337468217e-05, + "loss": 3.7308, + "step": 480256 + }, + { + "epoch": 1.01, + "learning_rate": 4.212888742717165e-05, + "loss": 3.7366, + "step": 480768 + }, + { + "epoch": 1.01, + "learning_rate": 4.212050147966113e-05, + "loss": 3.7317, + "step": 481280 + }, + { + "epoch": 1.01, + "learning_rate": 4.211213191095435e-05, + "loss": 3.7372, + "step": 481792 + }, + { + "epoch": 1.01, + "learning_rate": 4.210374596344383e-05, + "loss": 3.7289, + "step": 482304 + }, + { + "epoch": 1.01, + "learning_rate": 4.209536001593331e-05, + "loss": 3.7135, + "step": 482816 + }, + { + "epoch": 1.01, + "learning_rate": 4.208697406842278e-05, + "loss": 3.7413, + "step": 483328 + }, + { + "epoch": 1.01, + "learning_rate": 4.2078604499715996e-05, + "loss": 3.7268, + "step": 483840 + }, + { + "epoch": 1.01, + "learning_rate": 4.2070218552205476e-05, + "loss": 3.7369, + "step": 484352 + }, + { + "epoch": 1.01, + "learning_rate": 4.206183260469495e-05, + "loss": 3.725, + "step": 484864 + }, + { + "epoch": 1.01, + "learning_rate": 4.205344665718443e-05, + "loss": 3.7275, + "step": 485376 + }, + { + "epoch": 1.01, + "learning_rate": 4.2045077088477645e-05, + "loss": 3.719, + "step": 485888 + }, + { + "epoch": 1.01, + "learning_rate": 4.2036691140967125e-05, + "loss": 3.7345, + "step": 486400 + }, + { + "epoch": 1.01, + "learning_rate": 4.2028305193456605e-05, + "loss": 3.7197, + "step": 486912 + }, + { + "epoch": 1.01, + "learning_rate": 4.2019919245946085e-05, + "loss": 3.7271, + "step": 487424 + }, + { + "epoch": 1.01, + "learning_rate": 4.20115496772393e-05, + "loss": 3.737, + "step": 487936 + }, + { + "epoch": 1.01, + "learning_rate": 4.200316372972878e-05, + "loss": 3.7156, + "step": 488448 + }, + { + "epoch": 1.01, + "learning_rate": 4.1994777782218254e-05, + "loss": 3.7171, + "step": 488960 + }, + { + "epoch": 1.01, + "learning_rate": 4.1986391834707734e-05, + "loss": 3.7376, + "step": 489472 + }, + { + "epoch": 1.01, + "learning_rate": 4.197802226600095e-05, + "loss": 3.7078, + "step": 489984 + }, + { + "epoch": 1.01, + "learning_rate": 4.196963631849042e-05, + "loss": 3.7118, + "step": 490496 + }, + { + "epoch": 1.01, + "learning_rate": 4.19612503709799e-05, + "loss": 3.7267, + "step": 491008 + }, + { + "epoch": 1.01, + "learning_rate": 4.195286442346938e-05, + "loss": 3.7275, + "step": 491520 + }, + { + "epoch": 1.01, + "learning_rate": 4.19444948547626e-05, + "loss": 3.7154, + "step": 492032 + }, + { + "epoch": 1.01, + "learning_rate": 4.193610890725207e-05, + "loss": 3.7263, + "step": 492544 + }, + { + "epoch": 1.01, + "learning_rate": 4.192772295974156e-05, + "loss": 3.7109, + "step": 493056 + }, + { + "epoch": 1.01, + "learning_rate": 4.191933701223104e-05, + "loss": 3.7165, + "step": 493568 + }, + { + "epoch": 1.01, + "learning_rate": 4.191096744352425e-05, + "loss": 3.7306, + "step": 494080 + }, + { + "epoch": 1.01, + "learning_rate": 4.190258149601373e-05, + "loss": 3.7248, + "step": 494592 + }, + { + "epoch": 1.01, + "learning_rate": 4.189419554850321e-05, + "loss": 3.7313, + "step": 495104 + }, + { + "epoch": 1.01, + "learning_rate": 4.188580960099269e-05, + "loss": 3.7289, + "step": 495616 + }, + { + "epoch": 1.01, + "learning_rate": 4.18774400322859e-05, + "loss": 3.738, + "step": 496128 + }, + { + "epoch": 1.01, + "learning_rate": 4.186905408477538e-05, + "loss": 3.7146, + "step": 496640 + }, + { + "epoch": 1.01, + "learning_rate": 4.186066813726486e-05, + "loss": 3.725, + "step": 497152 + }, + { + "epoch": 1.01, + "learning_rate": 4.185228218975434e-05, + "loss": 3.727, + "step": 497664 + }, + { + "epoch": 1.01, + "learning_rate": 4.1843912621047546e-05, + "loss": 3.7068, + "step": 498176 + }, + { + "epoch": 1.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7275, + "step": 498688 + }, + { + "epoch": 1.01, + "learning_rate": 4.182715710483024e-05, + "loss": 3.726, + "step": 499200 + }, + { + "epoch": 1.01, + "learning_rate": 4.181877115731972e-05, + "loss": 3.7282, + "step": 499712 + }, + { + "epoch": 1.01, + "learning_rate": 4.18103852098092e-05, + "loss": 3.7226, + "step": 500224 + }, + { + "epoch": 1.01, + "learning_rate": 4.180199926229868e-05, + "loss": 3.7171, + "step": 500736 + }, + { + "epoch": 1.01, + "learning_rate": 4.179361331478816e-05, + "loss": 3.715, + "step": 501248 + }, + { + "epoch": 1.01, + "learning_rate": 4.178522736727764e-05, + "loss": 3.7236, + "step": 501760 + }, + { + "epoch": 1.01, + "learning_rate": 4.177684141976712e-05, + "loss": 3.7266, + "step": 502272 + }, + { + "epoch": 1.01, + "learning_rate": 4.176847185106033e-05, + "loss": 3.7243, + "step": 502784 + }, + { + "epoch": 1.01, + "learning_rate": 4.176008590354981e-05, + "loss": 3.7283, + "step": 503296 + }, + { + "epoch": 1.02, + "learning_rate": 4.175169995603929e-05, + "loss": 3.7306, + "step": 503808 + }, + { + "epoch": 1.02, + "learning_rate": 4.174331400852877e-05, + "loss": 3.7189, + "step": 504320 + }, + { + "epoch": 1.02, + "learning_rate": 4.173494443982198e-05, + "loss": 3.7208, + "step": 504832 + }, + { + "epoch": 1.02, + "learning_rate": 4.1726558492311466e-05, + "loss": 3.7123, + "step": 505344 + }, + { + "epoch": 1.02, + "learning_rate": 4.1718172544800946e-05, + "loss": 3.7294, + "step": 505856 + }, + { + "epoch": 1.02, + "learning_rate": 4.1709802976094155e-05, + "loss": 3.7349, + "step": 506368 + }, + { + "epoch": 1.02, + "learning_rate": 4.1701417028583635e-05, + "loss": 3.717, + "step": 506880 + }, + { + "epoch": 1.02, + "learning_rate": 4.1693031081073115e-05, + "loss": 3.714, + "step": 507392 + }, + { + "epoch": 1.02, + "learning_rate": 4.1684645133562595e-05, + "loss": 3.7095, + "step": 507904 + }, + { + "epoch": 1.02, + "learning_rate": 4.1676259186052075e-05, + "loss": 3.7257, + "step": 508416 + }, + { + "epoch": 1.02, + "learning_rate": 4.1667873238541555e-05, + "loss": 3.7317, + "step": 508928 + }, + { + "epoch": 1.02, + "learning_rate": 4.1659487291031035e-05, + "loss": 3.7159, + "step": 509440 + }, + { + "epoch": 1.02, + "learning_rate": 4.1651101343520515e-05, + "loss": 3.7175, + "step": 509952 + }, + { + "epoch": 1.02, + "learning_rate": 4.1642731774813724e-05, + "loss": 3.712, + "step": 510464 + }, + { + "epoch": 1.02, + "learning_rate": 4.1634345827303204e-05, + "loss": 3.7244, + "step": 510976 + }, + { + "epoch": 1.02, + "learning_rate": 4.1625959879792684e-05, + "loss": 3.7052, + "step": 511488 + }, + { + "epoch": 1.02, + "learning_rate": 4.1617573932282164e-05, + "loss": 3.7175, + "step": 512000 + }, + { + "epoch": 1.02, + "learning_rate": 4.160920436357538e-05, + "loss": 3.7103, + "step": 512512 + }, + { + "epoch": 1.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.725, + "step": 513024 + }, + { + "epoch": 1.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7118, + "step": 513536 + }, + { + "epoch": 1.02, + "learning_rate": 4.158406289984755e-05, + "loss": 3.7213, + "step": 514048 + }, + { + "epoch": 1.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.7186, + "step": 514560 + }, + { + "epoch": 1.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.7107, + "step": 515072 + }, + { + "epoch": 1.02, + "learning_rate": 4.155890505731599e-05, + "loss": 3.7238, + "step": 515584 + }, + { + "epoch": 1.02, + "learning_rate": 4.155051910980547e-05, + "loss": 3.7177, + "step": 516096 + }, + { + "epoch": 1.02, + "learning_rate": 4.154213316229495e-05, + "loss": 3.7231, + "step": 516608 + }, + { + "epoch": 1.02, + "learning_rate": 4.153376359358816e-05, + "loss": 3.7264, + "step": 517120 + }, + { + "epoch": 1.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.7115, + "step": 517632 + }, + { + "epoch": 1.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.7172, + "step": 518144 + }, + { + "epoch": 1.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.7117, + "step": 518656 + }, + { + "epoch": 1.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.7199, + "step": 519168 + }, + { + "epoch": 1.02, + "learning_rate": 4.149183385603556e-05, + "loss": 3.7118, + "step": 519680 + }, + { + "epoch": 1.02, + "learning_rate": 4.148344790852504e-05, + "loss": 3.7136, + "step": 520192 + }, + { + "epoch": 1.02, + "learning_rate": 4.147506196101452e-05, + "loss": 3.7034, + "step": 520704 + }, + { + "epoch": 1.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7177, + "step": 521216 + }, + { + "epoch": 1.02, + "learning_rate": 4.1458306444797206e-05, + "loss": 3.7108, + "step": 521728 + }, + { + "epoch": 1.02, + "learning_rate": 4.1449920497286686e-05, + "loss": 3.7173, + "step": 522240 + }, + { + "epoch": 1.02, + "learning_rate": 4.14415509285799e-05, + "loss": 3.7029, + "step": 522752 + }, + { + "epoch": 1.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.7139, + "step": 523264 + }, + { + "epoch": 1.02, + "learning_rate": 4.1424779033558855e-05, + "loss": 3.7113, + "step": 523776 + }, + { + "epoch": 1.02, + "learning_rate": 4.1416393086048335e-05, + "loss": 3.7232, + "step": 524288 + }, + { + "epoch": 1.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7125, + "step": 524800 + }, + { + "epoch": 1.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7202, + "step": 525312 + }, + { + "epoch": 1.02, + "learning_rate": 4.139125162232051e-05, + "loss": 3.702, + "step": 525824 + }, + { + "epoch": 1.02, + "learning_rate": 4.138286567480999e-05, + "loss": 3.7222, + "step": 526336 + }, + { + "epoch": 1.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.7209, + "step": 526848 + }, + { + "epoch": 1.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7207, + "step": 527360 + }, + { + "epoch": 1.02, + "learning_rate": 4.135772421108216e-05, + "loss": 3.7182, + "step": 527872 + }, + { + "epoch": 1.02, + "learning_rate": 4.134933826357164e-05, + "loss": 3.725, + "step": 528384 + }, + { + "epoch": 1.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7116, + "step": 528896 + }, + { + "epoch": 1.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7265, + "step": 529408 + }, + { + "epoch": 1.02, + "learning_rate": 4.132419679984381e-05, + "loss": 3.7042, + "step": 529920 + }, + { + "epoch": 1.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.7147, + "step": 530432 + }, + { + "epoch": 1.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7104, + "step": 530944 + }, + { + "epoch": 1.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7117, + "step": 531456 + }, + { + "epoch": 1.02, + "learning_rate": 4.1290669388605465e-05, + "loss": 3.7105, + "step": 531968 + }, + { + "epoch": 1.02, + "learning_rate": 4.1282283441094945e-05, + "loss": 3.7051, + "step": 532480 + }, + { + "epoch": 1.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7194, + "step": 532992 + }, + { + "epoch": 1.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.6986, + "step": 533504 + }, + { + "epoch": 1.02, + "learning_rate": 4.1257141977367114e-05, + "loss": 3.7257, + "step": 534016 + }, + { + "epoch": 1.03, + "eval_loss": 3.8601512908935547, + "eval_runtime": 302.4726, + "eval_samples_per_second": 1261.572, + "eval_steps_per_second": 39.425, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.7048, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.6975, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.1231984134835553e-05, + "loss": 3.711, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.1223598187325033e-05, + "loss": 3.7143, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.1215212239814513e-05, + "loss": 3.7118, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120682629230399e-05, + "loss": 3.7079, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119845672359721e-05, + "loss": 3.7016, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119007077608669e-05, + "loss": 3.7035, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118168482857617e-05, + "loss": 3.7097, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117329888106565e-05, + "loss": 3.7162, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.116491293355513e-05, + "loss": 3.7072, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.115654336484834e-05, + "loss": 3.708, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.114815741733782e-05, + "loss": 3.7041, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.11397714698273e-05, + "loss": 3.6989, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.113138552231678e-05, + "loss": 3.7021, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.112299957480626e-05, + "loss": 3.6946, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111463000609947e-05, + "loss": 3.7012, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110624405858895e-05, + "loss": 3.7055, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109785811107843e-05, + "loss": 3.6973, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108947216356791e-05, + "loss": 3.7205, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.1081086216057394e-05, + "loss": 3.7153, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.10727166473506e-05, + "loss": 3.7041, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106433069984008e-05, + "loss": 3.709, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105594475232956e-05, + "loss": 3.7159, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104755880481904e-05, + "loss": 3.6938, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.1039172857308516e-05, + "loss": 3.7113, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.1030786909797996e-05, + "loss": 3.705, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.1022400962287476e-05, + "loss": 3.7012, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.1014015014776956e-05, + "loss": 3.6913, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.1005645446070165e-05, + "loss": 3.7046, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.0997259498559645e-05, + "loss": 3.7109, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098888992985286e-05, + "loss": 3.7076, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098050398234234e-05, + "loss": 3.7135, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097211803483182e-05, + "loss": 3.7028, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.09637320873213e-05, + "loss": 3.697, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095534613981078e-05, + "loss": 3.7046, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094696019230026e-05, + "loss": 3.7, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093857424478974e-05, + "loss": 3.6894, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.093020467608295e-05, + "loss": 3.6902, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.092181872857243e-05, + "loss": 3.695, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.091343278106191e-05, + "loss": 3.6982, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.090504683355139e-05, + "loss": 3.7049, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.08966772648446e-05, + "loss": 3.6999, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888291317334085e-05, + "loss": 3.6968, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879905369823565e-05, + "loss": 3.7041, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871519422313045e-05, + "loss": 3.7019, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863149853606254e-05, + "loss": 3.7023, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.0854763906095734e-05, + "loss": 3.6972, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.0846377958585214e-05, + "loss": 3.6733, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.0837992011074694e-05, + "loss": 3.712, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.08296224423679e-05, + "loss": 3.693, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082123649485738e-05, + "loss": 3.7069, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081285054734686e-05, + "loss": 3.689, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080448097864007e-05, + "loss": 3.6947, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079609503112955e-05, + "loss": 3.684, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078770908361904e-05, + "loss": 3.7006, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077932313610852e-05, + "loss": 3.6876, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.0770937188598e-05, + "loss": 3.6932, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076255124108748e-05, + "loss": 3.7048, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075416529357696e-05, + "loss": 3.6865, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.074579572487017e-05, + "loss": 3.6831, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.073740977735965e-05, + "loss": 3.7026, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.072904020865286e-05, + "loss": 3.6784, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.072065426114234e-05, + "loss": 3.6773, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.071226831363182e-05, + "loss": 3.6921, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.07038823661213e-05, + "loss": 3.6943, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.0695496418610777e-05, + "loss": 3.6861, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.0687110471100257e-05, + "loss": 3.6944, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.0678724523589736e-05, + "loss": 3.6757, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.067033857607922e-05, + "loss": 3.6874, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.066196900737243e-05, + "loss": 3.697, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065358305986191e-05, + "loss": 3.6916, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064519711235139e-05, + "loss": 3.7022, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063681116484087e-05, + "loss": 3.6945, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062844159613408e-05, + "loss": 3.7041, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.062005564862356e-05, + "loss": 3.6805, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061166970111304e-05, + "loss": 3.6945, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060328375360252e-05, + "loss": 3.6921, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059491418489573e-05, + "loss": 3.6774, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058652823738521e-05, + "loss": 3.6934, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.0578158668678426e-05, + "loss": 3.6944, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.0569772721167906e-05, + "loss": 3.6942, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.0561386773657386e-05, + "loss": 3.6971, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.0553000826146866e-05, + "loss": 3.6816, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.0544614878636346e-05, + "loss": 3.6823, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.053622893112582e-05, + "loss": 3.6927, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.05278429836153e-05, + "loss": 3.695, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0519473414908515e-05, + "loss": 3.6941, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511087467397995e-05, + "loss": 3.6936, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.050270151988747e-05, + "loss": 3.6983, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.049431557237695e-05, + "loss": 3.6916, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0485946003670164e-05, + "loss": 3.6858, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.047757643496338e-05, + "loss": 3.683, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.046919048745286e-05, + "loss": 3.6948, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.046082091874607e-05, + "loss": 3.7001, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.045243497123555e-05, + "loss": 3.6885, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.044404902372503e-05, + "loss": 3.6824, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.043566307621451e-05, + "loss": 3.6793, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042727712870399e-05, + "loss": 3.6908, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041889118119347e-05, + "loss": 3.7043, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041050523368294e-05, + "loss": 3.6827, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040211928617242e-05, + "loss": 3.6875, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.03937333386619e-05, + "loss": 3.6837, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038534739115138e-05, + "loss": 3.6882, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037696144364087e-05, + "loss": 3.6776, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036857549613035e-05, + "loss": 3.6878, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036020592742356e-05, + "loss": 3.676, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.0351836358716766e-05, + "loss": 3.6938, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.0343450411206246e-05, + "loss": 3.6848, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.0335064463695726e-05, + "loss": 3.687, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326678516185206e-05, + "loss": 3.6874, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318308947478415e-05, + "loss": 3.6858, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.0309922999967895e-05, + "loss": 3.6868, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301537052457375e-05, + "loss": 3.6883, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293151104946855e-05, + "loss": 3.6899, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.028478153624007e-05, + "loss": 3.6979, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027639558872955e-05, + "loss": 3.6809, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026800964121903e-05, + "loss": 3.6868, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025962369370851e-05, + "loss": 3.6821, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.025125412500172e-05, + "loss": 3.6854, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.02428681774912e-05, + "loss": 3.6831, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023448222998068e-05, + "loss": 3.6837, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022609628247016e-05, + "loss": 3.674, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021771033495964e-05, + "loss": 3.6823, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020932438744912e-05, + "loss": 3.6857, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.02009384399386e-05, + "loss": 3.6849, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019255249242808e-05, + "loss": 3.6693, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.018418292372129e-05, + "loss": 3.6869, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017579697621077e-05, + "loss": 3.681, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.0167411028700256e-05, + "loss": 3.692, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.0159025081189736e-05, + "loss": 3.6831, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.0150655512482945e-05, + "loss": 3.6906, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.0142269564972425e-05, + "loss": 3.6731, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133883617461905e-05, + "loss": 3.6926, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125497669951385e-05, + "loss": 3.6899, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.0117128101244594e-05, + "loss": 3.6897, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0108742153734074e-05, + "loss": 3.6893, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0100356206223554e-05, + "loss": 3.6906, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091970258713034e-05, + "loss": 3.6833, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.008360069000624e-05, + "loss": 3.6945, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.007521474249572e-05, + "loss": 3.6757, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.006682879498521e-05, + "loss": 3.6856, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.005845922627842e-05, + "loss": 3.6778, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.00500732787679e-05, + "loss": 3.6838, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004168733125738e-05, + "loss": 3.6762, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003330138374686e-05, + "loss": 3.6745, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002493181504007e-05, + "loss": 3.6846, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001654586752955e-05, + "loss": 3.672, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000815992001903e-05, + "loss": 3.6965, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.852959156036377, + "eval_runtime": 304.2764, + "eval_samples_per_second": 1254.093, + "eval_steps_per_second": 39.191, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.999977397250851e-05, + "loss": 3.6717, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999138802499799e-05, + "loss": 3.6721, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998300207748747e-05, + "loss": 3.6779, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997461612997695e-05, + "loss": 3.6828, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996623018246643e-05, + "loss": 3.6853, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995786061375964e-05, + "loss": 3.6733, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994949104505285e-05, + "loss": 3.6781, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994110509754233e-05, + "loss": 3.6745, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993271915003181e-05, + "loss": 3.6751, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992433320252129e-05, + "loss": 3.6875, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991594725501077e-05, + "loss": 3.6753, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.990757768630398e-05, + "loss": 3.679, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989919173879346e-05, + "loss": 3.6753, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989080579128294e-05, + "loss": 3.6675, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.988241984377242e-05, + "loss": 3.6771, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.98740338962619e-05, + "loss": 3.6644, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.986566432755512e-05, + "loss": 3.6718, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.9857278380044597e-05, + "loss": 3.6784, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.9848892432534077e-05, + "loss": 3.6663, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984050648502355e-05, + "loss": 3.6885, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.9832136916316766e-05, + "loss": 3.6895, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9823750968806246e-05, + "loss": 3.6779, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.9815365021295726e-05, + "loss": 3.6753, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.98069790737852e-05, + "loss": 3.6851, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.979859312627468e-05, + "loss": 3.6711, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.979020717876416e-05, + "loss": 3.6743, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978182123125364e-05, + "loss": 3.6776, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.977343528374312e-05, + "loss": 3.6724, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.9765065715036334e-05, + "loss": 3.6674, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.9756679767525814e-05, + "loss": 3.6698, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.9748310198819023e-05, + "loss": 3.679, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.9739924251308503e-05, + "loss": 3.6826, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973153830379798e-05, + "loss": 3.683, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972315235628746e-05, + "loss": 3.6728, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971476640877694e-05, + "loss": 3.6669, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970638046126642e-05, + "loss": 3.6767, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.96979945137559e-05, + "loss": 3.672, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.968962494504911e-05, + "loss": 3.663, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.968123899753859e-05, + "loss": 3.6641, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.967285305002807e-05, + "loss": 3.6619, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.966446710251755e-05, + "loss": 3.6684, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.965609753381077e-05, + "loss": 3.6722, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.964771158630025e-05, + "loss": 3.6763, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.963932563878973e-05, + "loss": 3.6707, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.963093969127921e-05, + "loss": 3.6695, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.962257012257242e-05, + "loss": 3.6738, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.96141841750619e-05, + "loss": 3.6706, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.960579822755138e-05, + "loss": 3.6727, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959741228004086e-05, + "loss": 3.6444, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.9589042711334066e-05, + "loss": 3.6822, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.9580656763823546e-05, + "loss": 3.6635, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.9572270816313026e-05, + "loss": 3.6793, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.9563884868802506e-05, + "loss": 3.6604, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955551530009572e-05, + "loss": 3.6647, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.95471293525852e-05, + "loss": 3.6567, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953874340507468e-05, + "loss": 3.6724, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953035745756416e-05, + "loss": 3.6626, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952197151005364e-05, + "loss": 3.6631, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951360194134685e-05, + "loss": 3.6748, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950521599383633e-05, + "loss": 3.6623, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949683004632581e-05, + "loss": 3.6533, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.948844409881529e-05, + "loss": 3.6767, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6517, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.947168858259798e-05, + "loss": 3.6476, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6671, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945491668757694e-05, + "loss": 3.6669, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.9446530740066426e-05, + "loss": 3.6603, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.9438144792555906e-05, + "loss": 3.6639, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.9429758845045386e-05, + "loss": 3.6474, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.942137289753486e-05, + "loss": 3.6589, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.9413003328828075e-05, + "loss": 3.6691, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.6597, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6764, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.9387861865100244e-05, + "loss": 3.6627, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.9379475917589724e-05, + "loss": 3.6777, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.9371089970079204e-05, + "loss": 3.6527, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.936270402256868e-05, + "loss": 3.669, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.9354318075058164e-05, + "loss": 3.6595, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.9345932127547644e-05, + "loss": 3.6519, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933756255884086e-05, + "loss": 3.6656, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6697, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932080704262355e-05, + "loss": 3.6633, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931242109511303e-05, + "loss": 3.6717, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.93040351476025e-05, + "loss": 3.6504, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.929564920009198e-05, + "loss": 3.6527, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928726325258146e-05, + "loss": 3.6675, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.927887730507094e-05, + "loss": 3.6676, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.927050773636415e-05, + "loss": 3.6665, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.926212178885363e-05, + "loss": 3.6686, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.925373584134312e-05, + "loss": 3.6649, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.92453498938326e-05, + "loss": 3.6653, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.923698032512581e-05, + "loss": 3.6608, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6558, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.6699, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.921185524020171e-05, + "loss": 3.6677, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.920346929269119e-05, + "loss": 3.6653, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6563, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6517, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.9178311450159625e-05, + "loss": 3.66, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.9169925502649105e-05, + "loss": 3.6744, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.9161539555138585e-05, + "loss": 3.6581, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915315360762807e-05, + "loss": 3.6607, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914476766011755e-05, + "loss": 3.6551, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.913638171260703e-05, + "loss": 3.6585, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912799576509651e-05, + "loss": 3.6562, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911960981758599e-05, + "loss": 3.6554, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.91112402488792e-05, + "loss": 3.6509, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910287068017241e-05, + "loss": 3.6691, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909448473266189e-05, + "loss": 3.6581, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908609878515137e-05, + "loss": 3.6579, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.907771283764085e-05, + "loss": 3.6549, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906934326893406e-05, + "loss": 3.6626, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.906095732142354e-05, + "loss": 3.6616, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.9052571373913025e-05, + "loss": 3.6603, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.9044185426402505e-05, + "loss": 3.6632, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.9035815857695714e-05, + "loss": 3.6688, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.9027429910185194e-05, + "loss": 3.6557, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.9019043962674674e-05, + "loss": 3.6631, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.9010658015164154e-05, + "loss": 3.6508, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.900228844645736e-05, + "loss": 3.6605, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.899390249894684e-05, + "loss": 3.655, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.898551655143632e-05, + "loss": 3.651, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.89771306039258e-05, + "loss": 3.6514, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.896874465641528e-05, + "loss": 3.6575, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.896035870890476e-05, + "loss": 3.6592, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.658, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.644, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893521724517694e-05, + "loss": 3.6569, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6532, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.89184453501559e-05, + "loss": 3.6645, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.891005940264538e-05, + "loss": 3.6591, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890168983393859e-05, + "loss": 3.6591, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889330388642807e-05, + "loss": 3.6464, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8884934317721277e-05, + "loss": 3.6652, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.8876548370210757e-05, + "loss": 3.6635, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.8868162422700236e-05, + "loss": 3.6642, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.8859776475189716e-05, + "loss": 3.6625, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885140690648293e-05, + "loss": 3.6646, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.884302095897241e-05, + "loss": 3.6572, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883463501146189e-05, + "loss": 3.6684, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882624906395137e-05, + "loss": 3.649, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.6592, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880949354773406e-05, + "loss": 3.6548, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880110760022354e-05, + "loss": 3.6566, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879272165271302e-05, + "loss": 3.6486, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.87843357052025e-05, + "loss": 3.6494, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.877596613649571e-05, + "loss": 3.66, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876758018898519e-05, + "loss": 3.651, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875919424147467e-05, + "loss": 3.6672, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.84900164604187, + "eval_runtime": 305.2259, + "eval_samples_per_second": 1250.192, + "eval_steps_per_second": 39.069, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875080829396415e-05, + "loss": 3.6433, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874242234645363e-05, + "loss": 3.6447, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.6481, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6633, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6589, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6465, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870049260890103e-05, + "loss": 3.6534, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869210666139051e-05, + "loss": 3.6473, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.8683753471487455e-05, + "loss": 3.648, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.8675367523976935e-05, + "loss": 3.6644, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.6459, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6496, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.865020968144537e-05, + "loss": 3.6593, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864182373393485e-05, + "loss": 3.6352, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.8633437786424334e-05, + "loss": 3.6493, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.8625051838913814e-05, + "loss": 3.6394, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861669864901076e-05, + "loss": 3.6486, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.860831270150023e-05, + "loss": 3.6495, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859992675398971e-05, + "loss": 3.6396, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.859154080647919e-05, + "loss": 3.6611, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.858315485896867e-05, + "loss": 3.6612, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.857478529026188e-05, + "loss": 3.6573, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.856639934275136e-05, + "loss": 3.6516, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.855801339524084e-05, + "loss": 3.6534, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.854962744773032e-05, + "loss": 3.6481, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.85412415002198e-05, + "loss": 3.6458, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.853285555270929e-05, + "loss": 3.6545, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852446960519877e-05, + "loss": 3.65, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851610003649198e-05, + "loss": 3.6393, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850771408898146e-05, + "loss": 3.6449, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.849932814147094e-05, + "loss": 3.6527, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8490958572764146e-05, + "loss": 3.6599, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.8482572625253626e-05, + "loss": 3.6563, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.8474186677743106e-05, + "loss": 3.6499, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.8465800730232586e-05, + "loss": 3.6419, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.8457414782722066e-05, + "loss": 3.6461, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.8449028835211546e-05, + "loss": 3.6502, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.8440642887701026e-05, + "loss": 3.6392, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.843227331899424e-05, + "loss": 3.6371, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842388737148372e-05, + "loss": 3.6366, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.84155014239732e-05, + "loss": 3.6447, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840711547646268e-05, + "loss": 3.6443, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839874590775589e-05, + "loss": 3.65, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839035996024537e-05, + "loss": 3.6479, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838197401273485e-05, + "loss": 3.6467, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837358806522433e-05, + "loss": 3.6476, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.836521849651754e-05, + "loss": 3.6433, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835683254900702e-05, + "loss": 3.6522, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.83484466014965e-05, + "loss": 3.6165, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.834006065398598e-05, + "loss": 3.6537, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.8331691085279195e-05, + "loss": 3.639, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323305137768675e-05, + "loss": 3.6567, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314919190258155e-05, + "loss": 3.6386, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306549621551364e-05, + "loss": 3.6399, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.8298163674040844e-05, + "loss": 3.6293, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.8289777726530324e-05, + "loss": 3.6461, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.8281391779019804e-05, + "loss": 3.6431, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.8273005831509284e-05, + "loss": 3.6353, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8264619883998764e-05, + "loss": 3.6509, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8256233936488244e-05, + "loss": 3.6394, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824784798897772e-05, + "loss": 3.6226, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.823947842027093e-05, + "loss": 3.6522, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823110885156415e-05, + "loss": 3.6292, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822272290405363e-05, + "loss": 3.6226, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821433695654311e-05, + "loss": 3.6421, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820595100903259e-05, + "loss": 3.6402, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819756506152207e-05, + "loss": 3.6281, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818917911401154e-05, + "loss": 3.6444, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818079316650102e-05, + "loss": 3.6258, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.81724072189905e-05, + "loss": 3.6311, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816403765028371e-05, + "loss": 3.646, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.815566808157693e-05, + "loss": 3.6378, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814728213406641e-05, + "loss": 3.6526, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813889618655589e-05, + "loss": 3.6362, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813051023904537e-05, + "loss": 3.6517, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.812212429153485e-05, + "loss": 3.6315, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.811373834402433e-05, + "loss": 3.6484, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.810536877531754e-05, + "loss": 3.6301, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096982827807016e-05, + "loss": 3.632, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8088596880296496e-05, + "loss": 3.6391, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8080210932785976e-05, + "loss": 3.6436, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071824985275456e-05, + "loss": 3.6393, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8063455416568665e-05, + "loss": 3.6486, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8055069469058145e-05, + "loss": 3.6258, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046683521547625e-05, + "loss": 3.6276, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038297574037105e-05, + "loss": 3.6426, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.8029911626526585e-05, + "loss": 3.6453, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.8021525679016065e-05, + "loss": 3.6388, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801313973150555e-05, + "loss": 3.6454, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800477016279876e-05, + "loss": 3.6387, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799638421528824e-05, + "loss": 3.6435, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798799826777772e-05, + "loss": 3.639, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.79796123202672e-05, + "loss": 3.631, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797124275156041e-05, + "loss": 3.6439, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796285680404989e-05, + "loss": 3.6459, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.795447085653937e-05, + "loss": 3.6381, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794608490902885e-05, + "loss": 3.6363, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793769896151833e-05, + "loss": 3.6222, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792931301400781e-05, + "loss": 3.6374, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792094344530102e-05, + "loss": 3.6481, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.7912557497790505e-05, + "loss": 3.6339, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.7904171550279985e-05, + "loss": 3.6375, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.7895785602769465e-05, + "loss": 3.6311, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.7887399655258945e-05, + "loss": 3.6313, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.7879013707748425e-05, + "loss": 3.6337, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.7870627760237905e-05, + "loss": 3.6289, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.7862258191531114e-05, + "loss": 3.6273, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.7853872244020594e-05, + "loss": 3.6443, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.7845486296510074e-05, + "loss": 3.6384, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783710034899955e-05, + "loss": 3.6291, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782871440148903e-05, + "loss": 3.6332, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782034483278224e-05, + "loss": 3.6322, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781195888527172e-05, + "loss": 3.6416, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.78035729377612e-05, + "loss": 3.6339, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779518699025068e-05, + "loss": 3.6431, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.77868174215439e-05, + "loss": 3.645, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777843147403338e-05, + "loss": 3.6281, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.777004552652285e-05, + "loss": 3.6383, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776165957901233e-05, + "loss": 3.6299, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775329001030555e-05, + "loss": 3.6345, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774490406279502e-05, + "loss": 3.6356, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.77365181152845e-05, + "loss": 3.627, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772813216777398e-05, + "loss": 3.624, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771974622026346e-05, + "loss": 3.634, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7711376651556676e-05, + "loss": 3.6365, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.7702990704046156e-05, + "loss": 3.6322, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7694604756535636e-05, + "loss": 3.6214, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.7686218809025116e-05, + "loss": 3.6292, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7677832861514596e-05, + "loss": 3.6295, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7669446914004076e-05, + "loss": 3.6404, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7661060966493556e-05, + "loss": 3.6368, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.7652675018983036e-05, + "loss": 3.6381, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7644305450276245e-05, + "loss": 3.6207, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.7635935881569454e-05, + "loss": 3.6477, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.7627549934058934e-05, + "loss": 3.6359, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.7619163986548414e-05, + "loss": 3.6431, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.7610778039037894e-05, + "loss": 3.6343, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760239209152738e-05, + "loss": 3.6397, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759400614401686e-05, + "loss": 3.6346, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758562019650634e-05, + "loss": 3.6487, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757723424899582e-05, + "loss": 3.622, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756886468028903e-05, + "loss": 3.6363, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756049511158224e-05, + "loss": 3.6298, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755210916407172e-05, + "loss": 3.6315, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.75437232165612e-05, + "loss": 3.6287, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753533726905068e-05, + "loss": 3.6259, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752696770034389e-05, + "loss": 3.6338, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.751858175283337e-05, + "loss": 3.6292, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.751019580532285e-05, + "loss": 3.6399, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.8468878269195557, + "eval_runtime": 627.8259, + "eval_samples_per_second": 607.797, + "eval_steps_per_second": 18.994, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750180985781233e-05, + "loss": 3.6244, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.7493423910301815e-05, + "loss": 3.6239, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.7485037962791294e-05, + "loss": 3.6216, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.7476652015280774e-05, + "loss": 3.6383, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.7468266067770254e-05, + "loss": 3.6392, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.7459896499063463e-05, + "loss": 3.6225, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.745152693035667e-05, + "loss": 3.6288, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744314098284615e-05, + "loss": 3.6245, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743475503533563e-05, + "loss": 3.6288, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742636908782511e-05, + "loss": 3.6383, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741799951911832e-05, + "loss": 3.6241, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.74096135716078e-05, + "loss": 3.6271, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.740122762409728e-05, + "loss": 3.6339, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.739284167658677e-05, + "loss": 3.6145, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.738445572907625e-05, + "loss": 3.6245, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.737606978156573e-05, + "loss": 3.615, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.736770021285894e-05, + "loss": 3.6247, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.735931426534842e-05, + "loss": 3.6265, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.73509283178379e-05, + "loss": 3.6164, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.734254237032738e-05, + "loss": 3.6357, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.733415642281686e-05, + "loss": 3.642, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7325786854110066e-05, + "loss": 3.6309, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317400906599546e-05, + "loss": 3.6284, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7309014959089026e-05, + "loss": 3.6302, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300629011578506e-05, + "loss": 3.6301, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7292243064067986e-05, + "loss": 3.6226, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.7283857116557466e-05, + "loss": 3.6267, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7275471169046946e-05, + "loss": 3.6316, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7267101600340155e-05, + "loss": 3.6158, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.7258715652829635e-05, + "loss": 3.6227, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.7250329705319115e-05, + "loss": 3.6314, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724196013661233e-05, + "loss": 3.6296, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.7233574189101804e-05, + "loss": 3.6377, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.7225188241591284e-05, + "loss": 3.6289, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.7216802294080764e-05, + "loss": 3.6193, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.7208416346570244e-05, + "loss": 3.6252, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.7200030399059724e-05, + "loss": 3.6296, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719166083035294e-05, + "loss": 3.6147, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718327488284242e-05, + "loss": 3.6143, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.71748889353319e-05, + "loss": 3.6172, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716650298782138e-05, + "loss": 3.6178, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715811704031086e-05, + "loss": 3.6263, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.714973109280034e-05, + "loss": 3.6253, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714136152409355e-05, + "loss": 3.6262, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713297557658303e-05, + "loss": 3.6188, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712458962907251e-05, + "loss": 3.6292, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.711620368156199e-05, + "loss": 3.6206, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.710781773405147e-05, + "loss": 3.6296, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.709944816534468e-05, + "loss": 3.597, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.709106221783416e-05, + "loss": 3.6271, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.7082676270323644e-05, + "loss": 3.6194, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.7074290322813124e-05, + "loss": 3.6336, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.7065904375302604e-05, + "loss": 3.6145, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705753480659581e-05, + "loss": 3.6171, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704914885908529e-05, + "loss": 3.6114, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704076291157477e-05, + "loss": 3.6178, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703237696406425e-05, + "loss": 3.626, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702399101655373e-05, + "loss": 3.6078, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701562144784694e-05, + "loss": 3.6318, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700723550033642e-05, + "loss": 3.6191, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.69988495528259e-05, + "loss": 3.5964, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699046360531538e-05, + "loss": 3.6288, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698207765780486e-05, + "loss": 3.6103, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.697369171029434e-05, + "loss": 3.5983, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.696530576278382e-05, + "loss": 3.6212, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.695693619407704e-05, + "loss": 3.6179, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.694855024656652e-05, + "loss": 3.6043, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.694016429905599e-05, + "loss": 3.6257, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.693177835154547e-05, + "loss": 3.6005, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.692339240403495e-05, + "loss": 3.6091, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.691500645652443e-05, + "loss": 3.6219, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.690663688781764e-05, + "loss": 3.6162, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.689825094030712e-05, + "loss": 3.6279, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.68898649927966e-05, + "loss": 3.6167, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.688147904528608e-05, + "loss": 3.6296, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.687309309777556e-05, + "loss": 3.6102, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6864723529068775e-05, + "loss": 3.6247, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6856337581558255e-05, + "loss": 3.6056, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847951634047735e-05, + "loss": 3.6096, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.6839565686537215e-05, + "loss": 3.6184, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.6831196117830424e-05, + "loss": 3.6158, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.6822810170319904e-05, + "loss": 3.6223, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.6814424222809384e-05, + "loss": 3.6234, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.6806038275298864e-05, + "loss": 3.6094, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.6797652327788344e-05, + "loss": 3.605, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.6789266380277824e-05, + "loss": 3.6164, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678089681157103e-05, + "loss": 3.6261, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677251086406051e-05, + "loss": 3.6137, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676412491655e-05, + "loss": 3.623, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675573896903948e-05, + "loss": 3.6207, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674735302152896e-05, + "loss": 3.6195, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673898345282217e-05, + "loss": 3.617, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673059750531165e-05, + "loss": 3.6113, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672221155780113e-05, + "loss": 3.6205, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671382561029061e-05, + "loss": 3.6218, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.670543966278009e-05, + "loss": 3.6208, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.669705371526957e-05, + "loss": 3.6113, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.668868414656278e-05, + "loss": 3.6021, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.668029819905226e-05, + "loss": 3.6153, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.667191225154174e-05, + "loss": 3.626, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666352630403122e-05, + "loss": 3.6155, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.6655156735324434e-05, + "loss": 3.6167, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.6646770787813914e-05, + "loss": 3.6113, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.6638384840303393e-05, + "loss": 3.6087, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.6629998892792873e-05, + "loss": 3.6166, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662161294528235e-05, + "loss": 3.6039, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.6613226997771827e-05, + "loss": 3.6092, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.6604841050261307e-05, + "loss": 3.6185, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659647148155452e-05, + "loss": 3.6179, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.6588085534044e-05, + "loss": 3.611, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.6579699586533476e-05, + "loss": 3.6113, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.6571313639022955e-05, + "loss": 3.6076, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656294407031617e-05, + "loss": 3.6219, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.655455812280565e-05, + "loss": 3.6113, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.654617217529513e-05, + "loss": 3.6241, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.653778622778461e-05, + "loss": 3.6185, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.652941665907783e-05, + "loss": 3.6132, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.65210307115673e-05, + "loss": 3.6129, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.651264476405678e-05, + "loss": 3.6108, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.650425881654626e-05, + "loss": 3.6116, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.649587286903574e-05, + "loss": 3.6178, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.648750330032895e-05, + "loss": 3.6024, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647911735281843e-05, + "loss": 3.6045, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647073140530791e-05, + "loss": 3.6114, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646234545779739e-05, + "loss": 3.6156, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.6453975889090605e-05, + "loss": 3.6096, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.6445589941580085e-05, + "loss": 3.6039, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.6437203994069565e-05, + "loss": 3.6098, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.6428818046559045e-05, + "loss": 3.6036, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.6420432099048525e-05, + "loss": 3.622, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.6412062530341734e-05, + "loss": 3.6127, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.6403676582831214e-05, + "loss": 3.618, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.6395290635320694e-05, + "loss": 3.6004, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.6386904687810174e-05, + "loss": 3.623, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.6378518740299654e-05, + "loss": 3.6117, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.637014917159286e-05, + "loss": 3.62, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.636176322408234e-05, + "loss": 3.62, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635337727657183e-05, + "loss": 3.616, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.634499132906131e-05, + "loss": 3.6117, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633660538155079e-05, + "loss": 3.6273, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632821943404027e-05, + "loss": 3.6008, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.631984986533348e-05, + "loss": 3.6148, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.631146391782296e-05, + "loss": 3.6095, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.630307797031244e-05, + "loss": 3.6103, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.629469202280192e-05, + "loss": 3.6057, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.62863060752914e-05, + "loss": 3.6055, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.627793650658461e-05, + "loss": 3.607, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.626955055907409e-05, + "loss": 3.6141, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.626116461156357e-05, + "loss": 3.615, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.8435890674591064, + "eval_runtime": 631.6437, + "eval_samples_per_second": 604.124, + "eval_steps_per_second": 18.879, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.625277866405305e-05, + "loss": 3.605, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624439271654253e-05, + "loss": 3.5988, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.623600676903201e-05, + "loss": 3.6027, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622762082152149e-05, + "loss": 3.6171, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621923487401097e-05, + "loss": 3.6171, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621084892650045e-05, + "loss": 3.6016, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620247935779366e-05, + "loss": 3.6082, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.6194093410283136e-05, + "loss": 3.606, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.6185707462772616e-05, + "loss": 3.6061, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.6177321515262096e-05, + "loss": 3.6117, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.6168951946555305e-05, + "loss": 3.6097, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.6160565999044785e-05, + "loss": 3.6061, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.6152180051534265e-05, + "loss": 3.615, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.6143794104023745e-05, + "loss": 3.5931, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.613540815651323e-05, + "loss": 3.6046, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.612703858780644e-05, + "loss": 3.5935, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.611865264029592e-05, + "loss": 3.6067, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.61102666927854e-05, + "loss": 3.6104, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.610188074527488e-05, + "loss": 3.5909, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.609349479776436e-05, + "loss": 3.613, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608512522905757e-05, + "loss": 3.6211, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.607673928154705e-05, + "loss": 3.6101, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.606835333403653e-05, + "loss": 3.6111, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.605996738652601e-05, + "loss": 3.611, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605159781781922e-05, + "loss": 3.6075, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.60432118703087e-05, + "loss": 3.6018, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034825922798185e-05, + "loss": 3.6049, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.6026439975287665e-05, + "loss": 3.6072, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.6018054027777145e-05, + "loss": 3.5972, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.6009668080266625e-05, + "loss": 3.6009, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.6001298511559834e-05, + "loss": 3.6107, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.5992912564049314e-05, + "loss": 3.6125, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.5984526616538794e-05, + "loss": 3.6095, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.5976140669028274e-05, + "loss": 3.6137, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.5967754721517754e-05, + "loss": 3.5961, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595938515281096e-05, + "loss": 3.6053, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595099920530044e-05, + "loss": 3.6097, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594261325778992e-05, + "loss": 3.5897, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.59342273102794e-05, + "loss": 3.5972, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592585774157262e-05, + "loss": 3.599, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.59174717940621e-05, + "loss": 3.5966, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.590908584655158e-05, + "loss": 3.6026, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.590069989904106e-05, + "loss": 3.6082, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.589233033033427e-05, + "loss": 3.6046, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.588394438282375e-05, + "loss": 3.6008, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.587555843531323e-05, + "loss": 3.6062, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.586717248780271e-05, + "loss": 3.5978, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.585878654029219e-05, + "loss": 3.6077, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.58504169715854e-05, + "loss": 3.581, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.584203102407488e-05, + "loss": 3.6068, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.583364507656436e-05, + "loss": 3.5955, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582525912905384e-05, + "loss": 3.6126, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581688956034705e-05, + "loss": 3.5953, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580850361283653e-05, + "loss": 3.5951, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.580011766532601e-05, + "loss": 3.5909, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579173171781549e-05, + "loss": 3.6006, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578334577030497e-05, + "loss": 3.607, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.5774959822794446e-05, + "loss": 3.5859, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.5766573875283926e-05, + "loss": 3.6114, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.5758187927773405e-05, + "loss": 3.6011, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574983473787035e-05, + "loss": 3.5745, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574144879035983e-05, + "loss": 3.6081, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573306284284931e-05, + "loss": 3.5899, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572467689533879e-05, + "loss": 3.5807, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5716307326632006e-05, + "loss": 3.596, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5707921379121486e-05, + "loss": 3.5984, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5699535431610966e-05, + "loss": 3.5884, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.569114948410044e-05, + "loss": 3.6052, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.568276353658992e-05, + "loss": 3.5772, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.56743775890794e-05, + "loss": 3.5885, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566599164156888e-05, + "loss": 3.6033, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565762207286209e-05, + "loss": 3.5996, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564923612535157e-05, + "loss": 3.6035, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.564085017784105e-05, + "loss": 3.5996, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.563246423033053e-05, + "loss": 3.6048, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.5624094661623744e-05, + "loss": 3.593, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.5615708714113224e-05, + "loss": 3.6059, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.5607322766602704e-05, + "loss": 3.5897, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.5598936819092184e-05, + "loss": 3.5873, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.5590550871581664e-05, + "loss": 3.5928, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558218130287487e-05, + "loss": 3.5995, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557379535536435e-05, + "loss": 3.6004, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556540940785383e-05, + "loss": 3.6054, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555702346034331e-05, + "loss": 3.5914, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554865389163652e-05, + "loss": 3.5827, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.5540267944126e-05, + "loss": 3.5957, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553188199661548e-05, + "loss": 3.6075, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552349604910496e-05, + "loss": 3.5932, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551511010159445e-05, + "loss": 3.6021, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550674053288766e-05, + "loss": 3.6035, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.549835458537714e-05, + "loss": 3.5993, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.548996863786662e-05, + "loss": 3.5961, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.54815826903561e-05, + "loss": 3.5907, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5473213121649307e-05, + "loss": 3.6014, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464827174138787e-05, + "loss": 3.603, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456441226628266e-05, + "loss": 3.5979, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5448055279117746e-05, + "loss": 3.5942, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5439685710410956e-05, + "loss": 3.5814, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5431299762900436e-05, + "loss": 3.5941, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.5422913815389915e-05, + "loss": 3.6075, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.54145278678794e-05, + "loss": 3.5934, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540614192036888e-05, + "loss": 3.5969, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539777235166209e-05, + "loss": 3.5914, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538938640415157e-05, + "loss": 3.5906, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538100045664105e-05, + "loss": 3.5949, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537261450913053e-05, + "loss": 3.5884, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536422856162001e-05, + "loss": 3.5877, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535585899291322e-05, + "loss": 3.5972, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.53474730454027e-05, + "loss": 3.5963, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533908709789218e-05, + "loss": 3.5917, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533070115038166e-05, + "loss": 3.5952, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.532233158167487e-05, + "loss": 3.5864, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5313945634164356e-05, + "loss": 3.6037, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.5305559686653836e-05, + "loss": 3.5925, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5297173739143316e-05, + "loss": 3.6009, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5288804170436525e-05, + "loss": 3.6008, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.5280418222926005e-05, + "loss": 3.5923, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.5272032275415485e-05, + "loss": 3.5943, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.5263646327904965e-05, + "loss": 3.5937, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.5255276759198174e-05, + "loss": 3.5899, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.5246890811687654e-05, + "loss": 3.5969, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.5238504864177134e-05, + "loss": 3.5848, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.5230118916666614e-05, + "loss": 3.5856, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.5221732969156094e-05, + "loss": 3.5921, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521336340044931e-05, + "loss": 3.594, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520497745293879e-05, + "loss": 3.5895, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519659150542827e-05, + "loss": 3.5845, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518820555791775e-05, + "loss": 3.5862, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517981961040722e-05, + "loss": 3.5879, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.51714336628967e-05, + "loss": 3.6024, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.516306409418992e-05, + "loss": 3.5928, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.51546781466794e-05, + "loss": 3.6025, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.514629219916887e-05, + "loss": 3.5804, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.513790625165835e-05, + "loss": 3.5986, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.512952030414783e-05, + "loss": 3.5947, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.512115073544105e-05, + "loss": 3.5995, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.511276478793053e-05, + "loss": 3.6009, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.510437884042001e-05, + "loss": 3.5955, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.509599289290949e-05, + "loss": 3.5964, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.5087623324202696e-05, + "loss": 3.603, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.5079237376692176e-05, + "loss": 3.588, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070851429181656e-05, + "loss": 3.5948, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062465481671136e-05, + "loss": 3.5899, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.5054079534160616e-05, + "loss": 3.5899, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.5045709965453825e-05, + "loss": 3.5865, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.5037324017943305e-05, + "loss": 3.5895, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.5028938070432785e-05, + "loss": 3.5874, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.5020552122922265e-05, + "loss": 3.5896, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.501218255421548e-05, + "loss": 3.5962, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8437225818634033, + "eval_runtime": 304.6749, + "eval_samples_per_second": 1252.453, + "eval_steps_per_second": 39.14, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500379660670496e-05, + "loss": 3.5931, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.499541065919444e-05, + "loss": 3.576, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498702471168392e-05, + "loss": 3.5847, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497865514297713e-05, + "loss": 3.5969, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497026919546661e-05, + "loss": 3.5932, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496188324795609e-05, + "loss": 3.5852, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495349730044557e-05, + "loss": 3.5924, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494511135293505e-05, + "loss": 3.5846, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493674178422826e-05, + "loss": 3.5849, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.492835583671774e-05, + "loss": 3.59, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.491996988920722e-05, + "loss": 3.5945, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.49115839416967e-05, + "loss": 3.5844, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490319799418618e-05, + "loss": 3.5981, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.4894828425479395e-05, + "loss": 3.5702, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.4886442477968874e-05, + "loss": 3.5845, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.4878056530458354e-05, + "loss": 3.575, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.4869670582947834e-05, + "loss": 3.5879, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.4861284635437314e-05, + "loss": 3.5886, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.4852915066730523e-05, + "loss": 3.5749, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.4844529119220003e-05, + "loss": 3.5921, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483614317170948e-05, + "loss": 3.6019, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482775722419896e-05, + "loss": 3.5891, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.481937127668844e-05, + "loss": 3.5926, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481100170798165e-05, + "loss": 3.5911, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480261576047113e-05, + "loss": 3.5922, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479422981296062e-05, + "loss": 3.584, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.47858438654501e-05, + "loss": 3.583, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477745791793958e-05, + "loss": 3.5917, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476907197042906e-05, + "loss": 3.5783, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.476070240172227e-05, + "loss": 3.5807, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475231645421175e-05, + "loss": 3.5952, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.474393050670123e-05, + "loss": 3.592, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.473554455919071e-05, + "loss": 3.5867, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.472717499048392e-05, + "loss": 3.5972, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.47187890429734e-05, + "loss": 3.5793, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.471040309546288e-05, + "loss": 3.5871, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.470201714795236e-05, + "loss": 3.5858, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.469364757924557e-05, + "loss": 3.572, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.468526163173505e-05, + "loss": 3.5809, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467687568422453e-05, + "loss": 3.58, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.4668489736714006e-05, + "loss": 3.5755, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.4660103789203486e-05, + "loss": 3.5823, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.46517342204967e-05, + "loss": 3.5915, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.464334827298618e-05, + "loss": 3.5875, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.4634962325475655e-05, + "loss": 3.581, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.4626576377965135e-05, + "loss": 3.5891, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.4618190430454615e-05, + "loss": 3.5784, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.4609820861747824e-05, + "loss": 3.5885, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460143491423731e-05, + "loss": 3.568, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459304896672679e-05, + "loss": 3.5847, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458466301921627e-05, + "loss": 3.578, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457629345050948e-05, + "loss": 3.5937, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456790750299896e-05, + "loss": 3.5793, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.455952155548844e-05, + "loss": 3.5734, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455113560797792e-05, + "loss": 3.5742, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454276603927113e-05, + "loss": 3.5815, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.453438009176061e-05, + "loss": 3.5903, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452599414425009e-05, + "loss": 3.5652, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.451760819673957e-05, + "loss": 3.5947, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.450922224922905e-05, + "loss": 3.5832, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.4500852680522264e-05, + "loss": 3.5607, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.4492466733011744e-05, + "loss": 3.5885, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.4484080785501224e-05, + "loss": 3.5704, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.4475694837990704e-05, + "loss": 3.5634, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446732526928391e-05, + "loss": 3.5744, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445893932177339e-05, + "loss": 3.5835, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445055337426287e-05, + "loss": 3.5727, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444216742675235e-05, + "loss": 3.5777, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443379785804556e-05, + "loss": 3.5634, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442541191053504e-05, + "loss": 3.5678, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441702596302452e-05, + "loss": 3.5818, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.4408640015514e-05, + "loss": 3.5843, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.440027044680722e-05, + "loss": 3.5854, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.43918844992967e-05, + "loss": 3.5783, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438349855178618e-05, + "loss": 3.5896, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.437511260427566e-05, + "loss": 3.5748, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.436674303556887e-05, + "loss": 3.5846, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.435835708805835e-05, + "loss": 3.5726, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.434997114054783e-05, + "loss": 3.5721, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.434158519303731e-05, + "loss": 3.5783, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.433319924552679e-05, + "loss": 3.5732, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.4324813298016267e-05, + "loss": 3.5852, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4316443729309476e-05, + "loss": 3.5867, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.4308057781798956e-05, + "loss": 3.5768, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.4299671834288436e-05, + "loss": 3.5585, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291285886777916e-05, + "loss": 3.5795, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428291631807113e-05, + "loss": 3.5849, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427453037056061e-05, + "loss": 3.5767, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426614442305009e-05, + "loss": 3.5821, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425775847553957e-05, + "loss": 3.5863, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424938890683278e-05, + "loss": 3.5771, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424100295932226e-05, + "loss": 3.5787, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423261701181174e-05, + "loss": 3.5732, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422423106430122e-05, + "loss": 3.5846, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421586149559443e-05, + "loss": 3.5836, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420747554808391e-05, + "loss": 3.5818, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419908960057339e-05, + "loss": 3.5745, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.419070365306287e-05, + "loss": 3.5625, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.4182334084356085e-05, + "loss": 3.5761, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.4173948136845565e-05, + "loss": 3.5912, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.4165562189335045e-05, + "loss": 3.5769, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.4157176241824525e-05, + "loss": 3.5735, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.4148806673117734e-05, + "loss": 3.5756, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.4140420725607214e-05, + "loss": 3.5728, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.4132034778096694e-05, + "loss": 3.5768, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.4123648830586174e-05, + "loss": 3.5734, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.4115262883075654e-05, + "loss": 3.5692, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4106876935565134e-05, + "loss": 3.5781, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409850736685834e-05, + "loss": 3.5793, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.409012141934782e-05, + "loss": 3.5744, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.40817354718373e-05, + "loss": 3.5741, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407334952432679e-05, + "loss": 3.57, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406497995562e-05, + "loss": 3.5845, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.405659400810948e-05, + "loss": 3.5767, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404820806059896e-05, + "loss": 3.5779, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403982211308843e-05, + "loss": 3.5817, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403145254438165e-05, + "loss": 3.5789, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402306659687113e-05, + "loss": 3.5766, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401468064936061e-05, + "loss": 3.5733, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400629470185008e-05, + "loss": 3.5754, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399790875433956e-05, + "loss": 3.5773, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.3989539185632777e-05, + "loss": 3.5662, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.3981153238122257e-05, + "loss": 3.5733, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3972767290611736e-05, + "loss": 3.5686, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.3964381343101216e-05, + "loss": 3.5766, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.395601177439443e-05, + "loss": 3.5753, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.3947625826883905e-05, + "loss": 3.5669, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.3939239879373385e-05, + "loss": 3.5639, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3930853931862865e-05, + "loss": 3.571, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.3922467984352345e-05, + "loss": 3.5836, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.3914098415645554e-05, + "loss": 3.5749, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.3905712468135034e-05, + "loss": 3.5822, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.3897326520624514e-05, + "loss": 3.5658, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.3888940573113994e-05, + "loss": 3.5792, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388057100440721e-05, + "loss": 3.5788, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387218505689669e-05, + "loss": 3.5781, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.386379910938617e-05, + "loss": 3.5819, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.385541316187565e-05, + "loss": 3.5761, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384704359316886e-05, + "loss": 3.5831, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383865764565834e-05, + "loss": 3.5842, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383027169814782e-05, + "loss": 3.5671, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.38218857506373e-05, + "loss": 3.577, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381349980312678e-05, + "loss": 3.57, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380513023441999e-05, + "loss": 3.5733, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.379674428690947e-05, + "loss": 3.5685, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378835833939895e-05, + "loss": 3.573, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.3779972391888435e-05, + "loss": 3.5685, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.3771602823181644e-05, + "loss": 3.5737, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.3763216875671124e-05, + "loss": 3.5761, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8429176807403564, + "eval_runtime": 304.2484, + "eval_samples_per_second": 1254.209, + "eval_steps_per_second": 39.195, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.3754830928160604e-05, + "loss": 3.5854, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.3746444980650084e-05, + "loss": 3.56, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.3738059033139564e-05, + "loss": 3.568, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.3729673085629044e-05, + "loss": 3.5805, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.3721287138118524e-05, + "loss": 3.5743, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371291756941173e-05, + "loss": 3.5699, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370453162190121e-05, + "loss": 3.5736, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369614567439069e-05, + "loss": 3.5662, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.368775972688017e-05, + "loss": 3.5674, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367939015817339e-05, + "loss": 3.5754, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367100421066287e-05, + "loss": 3.574, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366261826315235e-05, + "loss": 3.5723, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.365423231564183e-05, + "loss": 3.5812, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.364586274693504e-05, + "loss": 3.5511, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.363747679942452e-05, + "loss": 3.5678, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3629090851914e-05, + "loss": 3.5562, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.362070490440348e-05, + "loss": 3.5721, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.3612335335696686e-05, + "loss": 3.5697, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.3603949388186166e-05, + "loss": 3.5602, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.3595563440675646e-05, + "loss": 3.5681, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.3587177493165126e-05, + "loss": 3.5871, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.357880792445834e-05, + "loss": 3.5715, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.357042197694782e-05, + "loss": 3.5744, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.35620360294373e-05, + "loss": 3.5752, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.355365008192678e-05, + "loss": 3.5762, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.354528051321999e-05, + "loss": 3.5635, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.353689456570947e-05, + "loss": 3.5653, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.352850861819895e-05, + "loss": 3.5736, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.352012267068843e-05, + "loss": 3.5619, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.351173672317791e-05, + "loss": 3.5646, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.350336715447112e-05, + "loss": 3.5749, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.34949812069606e-05, + "loss": 3.5753, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348659525945008e-05, + "loss": 3.5723, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347820931193956e-05, + "loss": 3.5765, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346982336442904e-05, + "loss": 3.5623, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.3461453795722256e-05, + "loss": 3.5716, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.3453067848211736e-05, + "loss": 3.5706, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.3444681900701216e-05, + "loss": 3.5529, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343629595319069e-05, + "loss": 3.5669, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.3427926384483905e-05, + "loss": 3.5617, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.3419540436973385e-05, + "loss": 3.5564, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.3411154489462864e-05, + "loss": 3.5648, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340276854195234e-05, + "loss": 3.5792, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.3394398973245554e-05, + "loss": 3.564, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3386013025735033e-05, + "loss": 3.5647, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377627078224513e-05, + "loss": 3.569, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3369241130713993e-05, + "loss": 3.5618, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.336085518320347e-05, + "loss": 3.5712, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335248561449669e-05, + "loss": 3.551, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334409966698616e-05, + "loss": 3.5644, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333571371947564e-05, + "loss": 3.5625, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332732777196512e-05, + "loss": 3.5761, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.33189418244546e-05, + "loss": 3.5646, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331057225574781e-05, + "loss": 3.5559, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330218630823729e-05, + "loss": 3.5561, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329380036072677e-05, + "loss": 3.5607, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328541441321625e-05, + "loss": 3.5728, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327704484450947e-05, + "loss": 3.5504, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326865889699895e-05, + "loss": 3.5719, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326027294948843e-05, + "loss": 3.5641, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325188700197791e-05, + "loss": 3.5485, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.3243517433271116e-05, + "loss": 3.5703, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3235131485760596e-05, + "loss": 3.5554, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226745538250076e-05, + "loss": 3.5478, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218359590739556e-05, + "loss": 3.5535, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3209990022032765e-05, + "loss": 3.5647, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201604074522245e-05, + "loss": 3.5608, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3193218127011725e-05, + "loss": 3.5545, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184832179501205e-05, + "loss": 3.553, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176446231990685e-05, + "loss": 3.5522, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.31680766632839e-05, + "loss": 3.5608, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.315969071577338e-05, + "loss": 3.5654, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.315130476826286e-05, + "loss": 3.5671, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314291882075234e-05, + "loss": 3.5667, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313454925204555e-05, + "loss": 3.5689, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312616330453503e-05, + "loss": 3.5587, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311777735702451e-05, + "loss": 3.5654, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310939140951399e-05, + "loss": 3.5585, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.31010218408072e-05, + "loss": 3.5568, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309263589329668e-05, + "loss": 3.5557, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308424994578616e-05, + "loss": 3.5616, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307586399827564e-05, + "loss": 3.5683, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.3067494429568854e-05, + "loss": 3.5686, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.3059108482058334e-05, + "loss": 3.5626, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.3050722534547814e-05, + "loss": 3.5439, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042336587037294e-05, + "loss": 3.5606, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.30339670183305e-05, + "loss": 3.5684, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302558107081998e-05, + "loss": 3.5637, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301719512330946e-05, + "loss": 3.5608, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300880917579894e-05, + "loss": 3.5722, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.300043960709215e-05, + "loss": 3.5598, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.299205365958163e-05, + "loss": 3.5619, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.298366771207111e-05, + "loss": 3.5583, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.297528176456059e-05, + "loss": 3.5666, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.296691219585381e-05, + "loss": 3.5664, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.295852624834329e-05, + "loss": 3.5679, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.295014030083277e-05, + "loss": 3.5539, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294175435332225e-05, + "loss": 3.5512, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293338478461546e-05, + "loss": 3.5557, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.292499883710494e-05, + "loss": 3.5704, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291661288959442e-05, + "loss": 3.5606, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.29082269420839e-05, + "loss": 3.559, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289984099457338e-05, + "loss": 3.5582, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.2891471425866586e-05, + "loss": 3.5569, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.2883085478356066e-05, + "loss": 3.5588, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.2874699530845546e-05, + "loss": 3.5545, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.2866313583335026e-05, + "loss": 3.5545, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.285794401462824e-05, + "loss": 3.5629, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.284955806711772e-05, + "loss": 3.5623, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.28411721196072e-05, + "loss": 3.5547, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.283278617209668e-05, + "loss": 3.558, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.282441660338989e-05, + "loss": 3.5535, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.281603065587937e-05, + "loss": 3.5683, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.280764470836885e-05, + "loss": 3.5614, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.279925876085833e-05, + "loss": 3.5625, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.279088919215154e-05, + "loss": 3.5618, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.278250324464102e-05, + "loss": 3.565, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.27741172971305e-05, + "loss": 3.5596, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.276573134961998e-05, + "loss": 3.5538, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.2757361780913195e-05, + "loss": 3.5599, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.2748975833402675e-05, + "loss": 3.5586, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.2740589885892155e-05, + "loss": 3.5494, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.2732203938381635e-05, + "loss": 3.5534, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.2723817990871115e-05, + "loss": 3.5542, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.2715448422164324e-05, + "loss": 3.5598, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.2707062474653804e-05, + "loss": 3.5535, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.2698676527143284e-05, + "loss": 3.5548, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.2690290579632764e-05, + "loss": 3.55, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268192101092597e-05, + "loss": 3.554, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267353506341545e-05, + "loss": 3.5673, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.266514911590493e-05, + "loss": 3.5598, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265676316839441e-05, + "loss": 3.5667, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264839359968763e-05, + "loss": 3.5468, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.264000765217711e-05, + "loss": 3.5635, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.263162170466659e-05, + "loss": 3.563, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262323575715606e-05, + "loss": 3.5656, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261486618844928e-05, + "loss": 3.5605, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260648024093876e-05, + "loss": 3.5609, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259809429342824e-05, + "loss": 3.5692, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.258970834591771e-05, + "loss": 3.5656, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258133877721093e-05, + "loss": 3.5528, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257295282970041e-05, + "loss": 3.5594, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256456688218989e-05, + "loss": 3.5581, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.255618093467937e-05, + "loss": 3.5597, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254781136597258e-05, + "loss": 3.551, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253942541846206e-05, + "loss": 3.5599, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.2531039470951536e-05, + "loss": 3.5497, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.2522653523441016e-05, + "loss": 3.5632, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.251428395473423e-05, + "loss": 3.5519, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.843665361404419, + "eval_runtime": 303.1809, + "eval_samples_per_second": 1258.625, + "eval_steps_per_second": 39.333, + "step": 1068480 + }, + { + "epoch": 1.0, + "learning_rate": 3.250589800722371e-05, + "loss": 3.5629, + "step": 1068544 + }, + { + "epoch": 1.0, + "learning_rate": 3.2497512059713185e-05, + "loss": 3.5455, + "step": 1069056 + }, + { + "epoch": 1.0, + "learning_rate": 3.2489126112202665e-05, + "loss": 3.5495, + "step": 1069568 + }, + { + "epoch": 1.0, + "learning_rate": 3.248075654349588e-05, + "loss": 3.5633, + "step": 1070080 + }, + { + "epoch": 1.0, + "learning_rate": 3.247237059598536e-05, + "loss": 3.5593, + "step": 1070592 + }, + { + "epoch": 1.0, + "learning_rate": 3.246398464847484e-05, + "loss": 3.5565, + "step": 1071104 + }, + { + "epoch": 1.0, + "learning_rate": 3.245559870096432e-05, + "loss": 3.5523, + "step": 1071616 + }, + { + "epoch": 1.0, + "learning_rate": 3.2447229132257536e-05, + "loss": 3.5466, + "step": 1072128 + }, + { + "epoch": 1.0, + "learning_rate": 3.243884318474701e-05, + "loss": 3.5515, + "step": 1072640 + }, + { + "epoch": 1.0, + "learning_rate": 3.243045723723649e-05, + "loss": 3.5603, + "step": 1073152 + }, + { + "epoch": 1.0, + "learning_rate": 3.242207128972597e-05, + "loss": 3.5575, + "step": 1073664 + }, + { + "epoch": 1.0, + "learning_rate": 3.2413701721019185e-05, + "loss": 3.5579, + "step": 1074176 + }, + { + "epoch": 1.0, + "learning_rate": 3.240531577350866e-05, + "loss": 3.5625, + "step": 1074688 + }, + { + "epoch": 1.0, + "learning_rate": 3.239692982599814e-05, + "loss": 3.5394, + "step": 1075200 + }, + { + "epoch": 1.0, + "learning_rate": 3.238854387848762e-05, + "loss": 3.5512, + "step": 1075712 + }, + { + "epoch": 1.0, + "learning_rate": 3.238017430978083e-05, + "loss": 3.5415, + "step": 1076224 + }, + { + "epoch": 1.0, + "learning_rate": 3.2371788362270314e-05, + "loss": 3.5549, + "step": 1076736 + }, + { + "epoch": 1.0, + "learning_rate": 3.2363402414759794e-05, + "loss": 3.548, + "step": 1077248 + }, + { + "epoch": 1.0, + "learning_rate": 3.2355016467249274e-05, + "loss": 3.549, + "step": 1077760 + }, + { + "epoch": 1.0, + "learning_rate": 3.234664689854248e-05, + "loss": 3.5525, + "step": 1078272 + }, + { + "epoch": 1.0, + "learning_rate": 3.233826095103196e-05, + "loss": 3.5697, + "step": 1078784 + }, + { + "epoch": 1.0, + "learning_rate": 3.232987500352144e-05, + "loss": 3.5581, + "step": 1079296 + }, + { + "epoch": 1.0, + "learning_rate": 3.232148905601092e-05, + "loss": 3.5553, + "step": 1079808 + }, + { + "epoch": 1.0, + "learning_rate": 3.23131031085004e-05, + "loss": 3.5571, + "step": 1080320 + }, + { + "epoch": 1.0, + "learning_rate": 3.230473353979361e-05, + "loss": 3.5678, + "step": 1080832 + }, + { + "epoch": 1.0, + "learning_rate": 3.229634759228309e-05, + "loss": 3.5411, + "step": 1081344 + }, + { + "epoch": 1.0, + "learning_rate": 3.228796164477257e-05, + "loss": 3.5517, + "step": 1081856 + }, + { + "epoch": 1.0, + "learning_rate": 3.227957569726205e-05, + "loss": 3.5591, + "step": 1082368 + }, + { + "epoch": 1.0, + "learning_rate": 3.227120612855527e-05, + "loss": 3.5409, + "step": 1082880 + }, + { + "epoch": 1.0, + "learning_rate": 3.226282018104475e-05, + "loss": 3.5483, + "step": 1083392 + }, + { + "epoch": 1.01, + "learning_rate": 3.225443423353423e-05, + "loss": 3.5564, + "step": 1083904 + }, + { + "epoch": 1.01, + "learning_rate": 3.224604828602371e-05, + "loss": 3.5605, + "step": 1084416 + }, + { + "epoch": 1.01, + "learning_rate": 3.223767871731692e-05, + "loss": 3.5562, + "step": 1084928 + }, + { + "epoch": 1.01, + "learning_rate": 3.22292927698064e-05, + "loss": 3.561, + "step": 1085440 + }, + { + "epoch": 1.01, + "learning_rate": 3.222090682229588e-05, + "loss": 3.5473, + "step": 1085952 + }, + { + "epoch": 1.01, + "learning_rate": 3.221252087478536e-05, + "loss": 3.5589, + "step": 1086464 + }, + { + "epoch": 1.01, + "learning_rate": 3.2204151306078566e-05, + "loss": 3.5512, + "step": 1086976 + }, + { + "epoch": 1.01, + "learning_rate": 3.2195765358568046e-05, + "loss": 3.5391, + "step": 1087488 + }, + { + "epoch": 1.01, + "learning_rate": 3.2187379411057526e-05, + "loss": 3.5532, + "step": 1088000 + }, + { + "epoch": 1.01, + "learning_rate": 3.2179009842350735e-05, + "loss": 3.5417, + "step": 1088512 + }, + { + "epoch": 1.01, + "learning_rate": 3.217062389484022e-05, + "loss": 3.542, + "step": 1089024 + }, + { + "epoch": 1.01, + "learning_rate": 3.21622379473297e-05, + "loss": 3.5496, + "step": 1089536 + }, + { + "epoch": 1.01, + "learning_rate": 3.215385199981918e-05, + "loss": 3.5623, + "step": 1090048 + }, + { + "epoch": 1.01, + "learning_rate": 3.214546605230866e-05, + "loss": 3.5451, + "step": 1090560 + }, + { + "epoch": 1.01, + "learning_rate": 3.213709648360187e-05, + "loss": 3.5554, + "step": 1091072 + }, + { + "epoch": 1.01, + "learning_rate": 3.212871053609135e-05, + "loss": 3.5529, + "step": 1091584 + }, + { + "epoch": 1.01, + "learning_rate": 3.212032458858083e-05, + "loss": 3.5516, + "step": 1092096 + }, + { + "epoch": 1.01, + "learning_rate": 3.211193864107031e-05, + "loss": 3.5543, + "step": 1092608 + }, + { + "epoch": 1.01, + "learning_rate": 3.210356907236352e-05, + "loss": 3.5358, + "step": 1093120 + }, + { + "epoch": 1.01, + "learning_rate": 3.2095183124853e-05, + "loss": 3.5499, + "step": 1093632 + }, + { + "epoch": 1.01, + "learning_rate": 3.208679717734248e-05, + "loss": 3.5487, + "step": 1094144 + }, + { + "epoch": 1.01, + "learning_rate": 3.207841122983196e-05, + "loss": 3.5562, + "step": 1094656 + }, + { + "epoch": 1.01, + "learning_rate": 3.2070041661125175e-05, + "loss": 3.5496, + "step": 1095168 + }, + { + "epoch": 1.01, + "learning_rate": 3.2061655713614655e-05, + "loss": 3.5373, + "step": 1095680 + }, + { + "epoch": 1.01, + "learning_rate": 3.2053269766104135e-05, + "loss": 3.5399, + "step": 1096192 + }, + { + "epoch": 1.01, + "learning_rate": 3.2044883818593615e-05, + "loss": 3.5438, + "step": 1096704 + }, + { + "epoch": 1.01, + "learning_rate": 3.2036514249886824e-05, + "loss": 3.5616, + "step": 1097216 + }, + { + "epoch": 1.01, + "learning_rate": 3.2028128302376304e-05, + "loss": 3.5343, + "step": 1097728 + }, + { + "epoch": 1.01, + "learning_rate": 3.2019742354865784e-05, + "loss": 3.555, + "step": 1098240 + }, + { + "epoch": 1.01, + "learning_rate": 3.2011356407355264e-05, + "loss": 3.5497, + "step": 1098752 + }, + { + "epoch": 1.01, + "learning_rate": 3.200298683864847e-05, + "loss": 3.5307, + "step": 1099264 + }, + { + "epoch": 1.01, + "learning_rate": 3.199460089113795e-05, + "loss": 3.5505, + "step": 1099776 + }, + { + "epoch": 1.01, + "learning_rate": 3.198621494362743e-05, + "loss": 3.5432, + "step": 1100288 + }, + { + "epoch": 1.01, + "learning_rate": 3.197782899611691e-05, + "loss": 3.5312, + "step": 1100800 + }, + { + "epoch": 1.01, + "learning_rate": 3.196945942741013e-05, + "loss": 3.5342, + "step": 1101312 + }, + { + "epoch": 1.01, + "learning_rate": 3.196107347989961e-05, + "loss": 3.5544, + "step": 1101824 + }, + { + "epoch": 1.01, + "learning_rate": 3.195268753238909e-05, + "loss": 3.5415, + "step": 1102336 + }, + { + "epoch": 1.01, + "learning_rate": 3.194430158487857e-05, + "loss": 3.5372, + "step": 1102848 + }, + { + "epoch": 1.01, + "learning_rate": 3.193593201617178e-05, + "loss": 3.5357, + "step": 1103360 + }, + { + "epoch": 1.01, + "learning_rate": 3.192754606866126e-05, + "loss": 3.5388, + "step": 1103872 + }, + { + "epoch": 1.01, + "learning_rate": 3.191916012115074e-05, + "loss": 3.5461, + "step": 1104384 + }, + { + "epoch": 1.01, + "learning_rate": 3.191077417364022e-05, + "loss": 3.5491, + "step": 1104896 + }, + { + "epoch": 1.01, + "learning_rate": 3.190240460493343e-05, + "loss": 3.5496, + "step": 1105408 + }, + { + "epoch": 1.01, + "learning_rate": 3.189401865742291e-05, + "loss": 3.5519, + "step": 1105920 + }, + { + "epoch": 1.01, + "learning_rate": 3.188563270991239e-05, + "loss": 3.5514, + "step": 1106432 + }, + { + "epoch": 1.01, + "learning_rate": 3.187724676240187e-05, + "loss": 3.5513, + "step": 1106944 + }, + { + "epoch": 1.01, + "learning_rate": 3.186887719369508e-05, + "loss": 3.5462, + "step": 1107456 + }, + { + "epoch": 1.01, + "learning_rate": 3.186049124618456e-05, + "loss": 3.5375, + "step": 1107968 + }, + { + "epoch": 1.01, + "learning_rate": 3.185210529867404e-05, + "loss": 3.5412, + "step": 1108480 + }, + { + "epoch": 1.01, + "learning_rate": 3.184371935116352e-05, + "loss": 3.5424, + "step": 1108992 + }, + { + "epoch": 1.01, + "learning_rate": 3.183534978245673e-05, + "loss": 3.5456, + "step": 1109504 + }, + { + "epoch": 1.01, + "learning_rate": 3.182696383494621e-05, + "loss": 3.549, + "step": 1110016 + }, + { + "epoch": 1.01, + "learning_rate": 3.181857788743569e-05, + "loss": 3.5555, + "step": 1110528 + }, + { + "epoch": 1.01, + "learning_rate": 3.181019193992517e-05, + "loss": 3.5456, + "step": 1111040 + }, + { + "epoch": 1.01, + "learning_rate": 3.180182237121838e-05, + "loss": 3.5282, + "step": 1111552 + }, + { + "epoch": 1.01, + "learning_rate": 3.179343642370786e-05, + "loss": 3.5437, + "step": 1112064 + }, + { + "epoch": 1.01, + "learning_rate": 3.178505047619734e-05, + "loss": 3.5501, + "step": 1112576 + }, + { + "epoch": 1.01, + "learning_rate": 3.177666452868682e-05, + "loss": 3.5516, + "step": 1113088 + }, + { + "epoch": 1.01, + "learning_rate": 3.176829495998003e-05, + "loss": 3.5417, + "step": 1113600 + }, + { + "epoch": 1.01, + "learning_rate": 3.1759909012469516e-05, + "loss": 3.5549, + "step": 1114112 + }, + { + "epoch": 1.02, + "learning_rate": 3.1751523064958996e-05, + "loss": 3.547, + "step": 1114624 + }, + { + "epoch": 1.02, + "learning_rate": 3.1743137117448476e-05, + "loss": 3.5443, + "step": 1115136 + }, + { + "epoch": 1.02, + "learning_rate": 3.1734767548741685e-05, + "loss": 3.543, + "step": 1115648 + }, + { + "epoch": 1.02, + "learning_rate": 3.1726381601231165e-05, + "loss": 3.5533, + "step": 1116160 + }, + { + "epoch": 1.02, + "learning_rate": 3.1717995653720645e-05, + "loss": 3.5484, + "step": 1116672 + }, + { + "epoch": 1.02, + "learning_rate": 3.1709609706210125e-05, + "loss": 3.5518, + "step": 1117184 + }, + { + "epoch": 1.02, + "learning_rate": 3.1701240137503334e-05, + "loss": 3.5404, + "step": 1117696 + }, + { + "epoch": 1.02, + "learning_rate": 3.1692854189992814e-05, + "loss": 3.5357, + "step": 1118208 + }, + { + "epoch": 1.02, + "learning_rate": 3.1684468242482294e-05, + "loss": 3.5409, + "step": 1118720 + }, + { + "epoch": 1.02, + "learning_rate": 3.1676082294971774e-05, + "loss": 3.5547, + "step": 1119232 + }, + { + "epoch": 1.02, + "learning_rate": 3.166771272626498e-05, + "loss": 3.5462, + "step": 1119744 + }, + { + "epoch": 1.02, + "learning_rate": 3.165932677875447e-05, + "loss": 3.5434, + "step": 1120256 + }, + { + "epoch": 1.02, + "learning_rate": 3.165094083124395e-05, + "loss": 3.5386, + "step": 1120768 + }, + { + "epoch": 1.02, + "learning_rate": 3.164255488373343e-05, + "loss": 3.5414, + "step": 1121280 + }, + { + "epoch": 1.02, + "learning_rate": 3.163416893622291e-05, + "loss": 3.5479, + "step": 1121792 + }, + { + "epoch": 1.02, + "learning_rate": 3.162579936751612e-05, + "loss": 3.5369, + "step": 1122304 + }, + { + "epoch": 1.02, + "learning_rate": 3.16174134200056e-05, + "loss": 3.5377, + "step": 1122816 + }, + { + "epoch": 1.02, + "learning_rate": 3.160902747249508e-05, + "loss": 3.5472, + "step": 1123328 + }, + { + "epoch": 1.02, + "learning_rate": 3.160064152498456e-05, + "loss": 3.5444, + "step": 1123840 + }, + { + "epoch": 1.02, + "learning_rate": 3.159227195627777e-05, + "loss": 3.5423, + "step": 1124352 + }, + { + "epoch": 1.02, + "learning_rate": 3.158388600876725e-05, + "loss": 3.5456, + "step": 1124864 + }, + { + "epoch": 1.02, + "learning_rate": 3.157550006125673e-05, + "loss": 3.5349, + "step": 1125376 + }, + { + "epoch": 1.02, + "learning_rate": 3.156713049254994e-05, + "loss": 3.5512, + "step": 1125888 + }, + { + "epoch": 1.02, + "learning_rate": 3.1558744545039423e-05, + "loss": 3.5473, + "step": 1126400 + }, + { + "epoch": 1.02, + "learning_rate": 3.1550358597528903e-05, + "loss": 3.5416, + "step": 1126912 + }, + { + "epoch": 1.02, + "learning_rate": 3.1541972650018383e-05, + "loss": 3.5509, + "step": 1127424 + }, + { + "epoch": 1.02, + "learning_rate": 3.1533586702507857e-05, + "loss": 3.5482, + "step": 1127936 + }, + { + "epoch": 1.02, + "learning_rate": 3.152521713380107e-05, + "loss": 3.5415, + "step": 1128448 + }, + { + "epoch": 1.02, + "learning_rate": 3.151683118629055e-05, + "loss": 3.5405, + "step": 1128960 + }, + { + "epoch": 1.02, + "learning_rate": 3.150844523878003e-05, + "loss": 3.546, + "step": 1129472 + }, + { + "epoch": 1.02, + "learning_rate": 3.1500059291269506e-05, + "loss": 3.5405, + "step": 1129984 + }, + { + "epoch": 1.02, + "learning_rate": 3.149168972256272e-05, + "loss": 3.5335, + "step": 1130496 + }, + { + "epoch": 1.02, + "learning_rate": 3.14833037750522e-05, + "loss": 3.5415, + "step": 1131008 + }, + { + "epoch": 1.02, + "learning_rate": 3.147491782754168e-05, + "loss": 3.5384, + "step": 1131520 + }, + { + "epoch": 1.02, + "learning_rate": 3.146653188003116e-05, + "loss": 3.5466, + "step": 1132032 + }, + { + "epoch": 1.02, + "learning_rate": 3.145816231132438e-05, + "loss": 3.5336, + "step": 1132544 + }, + { + "epoch": 1.02, + "learning_rate": 3.144977636381386e-05, + "loss": 3.5444, + "step": 1133056 + }, + { + "epoch": 1.02, + "learning_rate": 3.144139041630333e-05, + "loss": 3.5377, + "step": 1133568 + }, + { + "epoch": 1.02, + "learning_rate": 3.143300446879281e-05, + "loss": 3.5385, + "step": 1134080 + }, + { + "epoch": 1.02, + "learning_rate": 3.1424634900086026e-05, + "loss": 3.5475, + "step": 1134592 + }, + { + "epoch": 1.02, + "learning_rate": 3.1416248952575506e-05, + "loss": 3.5473, + "step": 1135104 + }, + { + "epoch": 1.02, + "learning_rate": 3.140786300506498e-05, + "loss": 3.5455, + "step": 1135616 + }, + { + "epoch": 1.02, + "learning_rate": 3.139947705755446e-05, + "loss": 3.5325, + "step": 1136128 + }, + { + "epoch": 1.02, + "learning_rate": 3.1391107488847675e-05, + "loss": 3.5489, + "step": 1136640 + }, + { + "epoch": 1.02, + "learning_rate": 3.1382721541337155e-05, + "loss": 3.5481, + "step": 1137152 + }, + { + "epoch": 1.02, + "learning_rate": 3.137433559382663e-05, + "loss": 3.545, + "step": 1137664 + }, + { + "epoch": 1.02, + "learning_rate": 3.1365949646316115e-05, + "loss": 3.5475, + "step": 1138176 + }, + { + "epoch": 1.02, + "learning_rate": 3.135758007760933e-05, + "loss": 3.5453, + "step": 1138688 + }, + { + "epoch": 1.02, + "learning_rate": 3.1349194130098804e-05, + "loss": 3.5552, + "step": 1139200 + }, + { + "epoch": 1.02, + "learning_rate": 3.1340808182588284e-05, + "loss": 3.5487, + "step": 1139712 + }, + { + "epoch": 1.02, + "learning_rate": 3.1332422235077764e-05, + "loss": 3.5378, + "step": 1140224 + }, + { + "epoch": 1.02, + "learning_rate": 3.132405266637098e-05, + "loss": 3.5423, + "step": 1140736 + }, + { + "epoch": 1.02, + "learning_rate": 3.131566671886045e-05, + "loss": 3.5398, + "step": 1141248 + }, + { + "epoch": 1.02, + "learning_rate": 3.130728077134993e-05, + "loss": 3.5406, + "step": 1141760 + }, + { + "epoch": 1.02, + "learning_rate": 3.129889482383941e-05, + "loss": 3.5385, + "step": 1142272 + }, + { + "epoch": 1.02, + "learning_rate": 3.129052525513262e-05, + "loss": 3.5435, + "step": 1142784 + }, + { + "epoch": 1.02, + "learning_rate": 3.12821393076221e-05, + "loss": 3.5364, + "step": 1143296 + }, + { + "epoch": 1.02, + "learning_rate": 3.127375336011158e-05, + "loss": 3.5486, + "step": 1143808 + }, + { + "epoch": 1.02, + "learning_rate": 3.126536741260107e-05, + "loss": 3.5385, + "step": 1144320 + }, + { + "epoch": 1.03, + "eval_loss": 3.844938039779663, + "eval_runtime": 303.3897, + "eval_samples_per_second": 1257.759, + "eval_steps_per_second": 39.306, + "step": 1144800 + }, + { + "epoch": 0.0, + "learning_rate": 3.125699784389428e-05, + "loss": 3.5079, + "step": 1144832 + }, + { + "epoch": 0.0, + "learning_rate": 3.124861189638376e-05, + "loss": 3.5383, + "step": 1145344 + }, + { + "epoch": 0.0, + "learning_rate": 3.124022594887324e-05, + "loss": 3.5321, + "step": 1145856 + }, + { + "epoch": 0.0, + "learning_rate": 3.123184000136272e-05, + "loss": 3.5473, + "step": 1146368 + }, + { + "epoch": 0.0, + "learning_rate": 3.12234540538522e-05, + "loss": 3.5436, + "step": 1146880 + }, + { + "epoch": 0.0, + "learning_rate": 3.121508448514541e-05, + "loss": 3.5422, + "step": 1147392 + }, + { + "epoch": 0.0, + "learning_rate": 3.1206698537634887e-05, + "loss": 3.5342, + "step": 1147904 + }, + { + "epoch": 0.0, + "learning_rate": 3.1198312590124367e-05, + "loss": 3.5325, + "step": 1148416 + }, + { + "epoch": 0.0, + "learning_rate": 3.1189943021417576e-05, + "loss": 3.5403, + "step": 1148928 + }, + { + "epoch": 0.0, + "learning_rate": 3.1181557073907056e-05, + "loss": 3.5407, + "step": 1149440 + }, + { + "epoch": 0.0, + "learning_rate": 3.1173171126396536e-05, + "loss": 3.5426, + "step": 1149952 + }, + { + "epoch": 0.0, + "learning_rate": 3.116478517888602e-05, + "loss": 3.5404, + "step": 1150464 + }, + { + "epoch": 0.0, + "learning_rate": 3.11563992313755e-05, + "loss": 3.5487, + "step": 1150976 + }, + { + "epoch": 0.0, + "learning_rate": 3.114802966266871e-05, + "loss": 3.5217, + "step": 1151488 + }, + { + "epoch": 0.0, + "learning_rate": 3.113964371515819e-05, + "loss": 3.5367, + "step": 1152000 + }, + { + "epoch": 0.0, + "learning_rate": 3.113125776764767e-05, + "loss": 3.5283, + "step": 1152512 + }, + { + "epoch": 0.0, + "learning_rate": 3.112287182013715e-05, + "loss": 3.5356, + "step": 1153024 + }, + { + "epoch": 0.0, + "learning_rate": 3.111450225143036e-05, + "loss": 3.5353, + "step": 1153536 + }, + { + "epoch": 0.0, + "learning_rate": 3.110611630391984e-05, + "loss": 3.5347, + "step": 1154048 + }, + { + "epoch": 0.0, + "learning_rate": 3.109773035640932e-05, + "loss": 3.5343, + "step": 1154560 + }, + { + "epoch": 0.0, + "learning_rate": 3.10893444088988e-05, + "loss": 3.5552, + "step": 1155072 + }, + { + "epoch": 0.0, + "learning_rate": 3.108097484019201e-05, + "loss": 3.5425, + "step": 1155584 + }, + { + "epoch": 0.0, + "learning_rate": 3.107258889268149e-05, + "loss": 3.5365, + "step": 1156096 + }, + { + "epoch": 0.0, + "learning_rate": 3.1064202945170976e-05, + "loss": 3.5451, + "step": 1156608 + }, + { + "epoch": 0.0, + "learning_rate": 3.1055816997660456e-05, + "loss": 3.5514, + "step": 1157120 + }, + { + "epoch": 0.0, + "learning_rate": 3.1047447428953665e-05, + "loss": 3.5306, + "step": 1157632 + }, + { + "epoch": 0.0, + "learning_rate": 3.1039061481443145e-05, + "loss": 3.5339, + "step": 1158144 + }, + { + "epoch": 0.0, + "learning_rate": 3.1030675533932625e-05, + "loss": 3.5449, + "step": 1158656 + }, + { + "epoch": 0.0, + "learning_rate": 3.1022289586422105e-05, + "loss": 3.5279, + "step": 1159168 + }, + { + "epoch": 0.0, + "learning_rate": 3.1013920017715314e-05, + "loss": 3.5348, + "step": 1159680 + }, + { + "epoch": 0.01, + "learning_rate": 3.1005534070204794e-05, + "loss": 3.537, + "step": 1160192 + }, + { + "epoch": 0.01, + "learning_rate": 3.0997148122694274e-05, + "loss": 3.5475, + "step": 1160704 + }, + { + "epoch": 0.01, + "learning_rate": 3.0988762175183754e-05, + "loss": 3.5396, + "step": 1161216 + }, + { + "epoch": 0.01, + "learning_rate": 3.098039260647696e-05, + "loss": 3.5418, + "step": 1161728 + }, + { + "epoch": 0.01, + "learning_rate": 3.097200665896644e-05, + "loss": 3.5347, + "step": 1162240 + }, + { + "epoch": 0.01, + "learning_rate": 3.096362071145593e-05, + "loss": 3.5428, + "step": 1162752 + }, + { + "epoch": 0.01, + "learning_rate": 3.095523476394541e-05, + "loss": 3.5384, + "step": 1163264 + }, + { + "epoch": 0.01, + "learning_rate": 3.094686519523862e-05, + "loss": 3.5218, + "step": 1163776 + }, + { + "epoch": 0.01, + "learning_rate": 3.09384792477281e-05, + "loss": 3.5374, + "step": 1164288 + }, + { + "epoch": 0.01, + "learning_rate": 3.093009330021758e-05, + "loss": 3.5253, + "step": 1164800 + }, + { + "epoch": 0.01, + "learning_rate": 3.092170735270706e-05, + "loss": 3.5315, + "step": 1165312 + }, + { + "epoch": 0.01, + "learning_rate": 3.091333778400027e-05, + "loss": 3.5318, + "step": 1165824 + }, + { + "epoch": 0.01, + "learning_rate": 3.090495183648975e-05, + "loss": 3.5445, + "step": 1166336 + }, + { + "epoch": 0.01, + "learning_rate": 3.089656588897923e-05, + "loss": 3.5343, + "step": 1166848 + }, + { + "epoch": 0.01, + "learning_rate": 3.088817994146871e-05, + "loss": 3.5342, + "step": 1167360 + }, + { + "epoch": 0.01, + "learning_rate": 3.0879810372761917e-05, + "loss": 3.541, + "step": 1167872 + }, + { + "epoch": 0.01, + "learning_rate": 3.0871424425251397e-05, + "loss": 3.5295, + "step": 1168384 + }, + { + "epoch": 0.01, + "learning_rate": 3.0863038477740877e-05, + "loss": 3.5431, + "step": 1168896 + }, + { + "epoch": 0.01, + "learning_rate": 3.085465253023036e-05, + "loss": 3.5211, + "step": 1169408 + }, + { + "epoch": 0.01, + "learning_rate": 3.084628296152357e-05, + "loss": 3.5296, + "step": 1169920 + }, + { + "epoch": 0.01, + "learning_rate": 3.083789701401305e-05, + "loss": 3.5354, + "step": 1170432 + }, + { + "epoch": 0.01, + "learning_rate": 3.082951106650253e-05, + "loss": 3.5387, + "step": 1170944 + }, + { + "epoch": 0.01, + "learning_rate": 3.082112511899201e-05, + "loss": 3.5393, + "step": 1171456 + }, + { + "epoch": 0.01, + "learning_rate": 3.081275555028522e-05, + "loss": 3.5198, + "step": 1171968 + }, + { + "epoch": 0.01, + "learning_rate": 3.08043696027747e-05, + "loss": 3.5279, + "step": 1172480 + }, + { + "epoch": 0.01, + "learning_rate": 3.079598365526418e-05, + "loss": 3.5259, + "step": 1172992 + }, + { + "epoch": 0.01, + "learning_rate": 3.078759770775366e-05, + "loss": 3.549, + "step": 1173504 + }, + { + "epoch": 0.01, + "learning_rate": 3.077922813904687e-05, + "loss": 3.5174, + "step": 1174016 + }, + { + "epoch": 0.01, + "learning_rate": 3.077084219153635e-05, + "loss": 3.539, + "step": 1174528 + }, + { + "epoch": 0.01, + "learning_rate": 3.076245624402583e-05, + "loss": 3.535, + "step": 1175040 + }, + { + "epoch": 0.01, + "learning_rate": 3.075407029651532e-05, + "loss": 3.5172, + "step": 1175552 + }, + { + "epoch": 0.01, + "learning_rate": 3.0745700727808526e-05, + "loss": 3.5366, + "step": 1176064 + }, + { + "epoch": 0.01, + "learning_rate": 3.0737314780298006e-05, + "loss": 3.53, + "step": 1176576 + }, + { + "epoch": 0.01, + "learning_rate": 3.0728928832787486e-05, + "loss": 3.5157, + "step": 1177088 + }, + { + "epoch": 0.01, + "learning_rate": 3.0720542885276966e-05, + "loss": 3.5204, + "step": 1177600 + }, + { + "epoch": 0.01, + "learning_rate": 3.0712173316570175e-05, + "loss": 3.5401, + "step": 1178112 + }, + { + "epoch": 0.01, + "learning_rate": 3.0703787369059655e-05, + "loss": 3.5266, + "step": 1178624 + }, + { + "epoch": 0.01, + "learning_rate": 3.0695401421549135e-05, + "loss": 3.5246, + "step": 1179136 + }, + { + "epoch": 0.01, + "learning_rate": 3.0687015474038615e-05, + "loss": 3.5208, + "step": 1179648 + }, + { + "epoch": 0.01, + "learning_rate": 3.0678645905331824e-05, + "loss": 3.5236, + "step": 1180160 + }, + { + "epoch": 0.01, + "learning_rate": 3.0670259957821304e-05, + "loss": 3.5317, + "step": 1180672 + }, + { + "epoch": 0.01, + "learning_rate": 3.0661874010310784e-05, + "loss": 3.5344, + "step": 1181184 + }, + { + "epoch": 0.01, + "learning_rate": 3.065348806280027e-05, + "loss": 3.5329, + "step": 1181696 + }, + { + "epoch": 0.01, + "learning_rate": 3.064511849409348e-05, + "loss": 3.5394, + "step": 1182208 + }, + { + "epoch": 0.01, + "learning_rate": 3.063673254658296e-05, + "loss": 3.5361, + "step": 1182720 + }, + { + "epoch": 0.01, + "learning_rate": 3.062834659907244e-05, + "loss": 3.5334, + "step": 1183232 + }, + { + "epoch": 0.01, + "learning_rate": 3.061996065156192e-05, + "loss": 3.5317, + "step": 1183744 + }, + { + "epoch": 0.01, + "learning_rate": 3.061159108285513e-05, + "loss": 3.5254, + "step": 1184256 + }, + { + "epoch": 0.01, + "learning_rate": 3.060320513534461e-05, + "loss": 3.5273, + "step": 1184768 + }, + { + "epoch": 0.01, + "learning_rate": 3.059481918783409e-05, + "loss": 3.5297, + "step": 1185280 + }, + { + "epoch": 0.01, + "learning_rate": 3.058643324032357e-05, + "loss": 3.5273, + "step": 1185792 + }, + { + "epoch": 0.01, + "learning_rate": 3.057806367161678e-05, + "loss": 3.5363, + "step": 1186304 + }, + { + "epoch": 0.01, + "learning_rate": 3.056967772410626e-05, + "loss": 3.5332, + "step": 1186816 + }, + { + "epoch": 0.01, + "learning_rate": 3.056129177659574e-05, + "loss": 3.5329, + "step": 1187328 + }, + { + "epoch": 0.01, + "learning_rate": 3.0552905829085224e-05, + "loss": 3.5166, + "step": 1187840 + }, + { + "epoch": 0.01, + "learning_rate": 3.054453626037843e-05, + "loss": 3.5241, + "step": 1188352 + }, + { + "epoch": 0.01, + "learning_rate": 3.053615031286791e-05, + "loss": 3.542, + "step": 1188864 + }, + { + "epoch": 0.01, + "learning_rate": 3.052776436535739e-05, + "loss": 3.5341, + "step": 1189376 + }, + { + "epoch": 0.01, + "learning_rate": 3.051937841784687e-05, + "loss": 3.5305, + "step": 1189888 + }, + { + "epoch": 0.01, + "learning_rate": 3.0511008849140082e-05, + "loss": 3.5415, + "step": 1190400 + }, + { + "epoch": 0.02, + "learning_rate": 3.0502622901629562e-05, + "loss": 3.5309, + "step": 1190912 + }, + { + "epoch": 0.02, + "learning_rate": 3.0494236954119042e-05, + "loss": 3.5305, + "step": 1191424 + }, + { + "epoch": 0.02, + "learning_rate": 3.0485851006608522e-05, + "loss": 3.5288, + "step": 1191936 + }, + { + "epoch": 0.02, + "learning_rate": 3.0477481437901735e-05, + "loss": 3.5367, + "step": 1192448 + }, + { + "epoch": 0.02, + "learning_rate": 3.0469095490391215e-05, + "loss": 3.53, + "step": 1192960 + }, + { + "epoch": 0.02, + "learning_rate": 3.0460709542880695e-05, + "loss": 3.5422, + "step": 1193472 + }, + { + "epoch": 0.02, + "learning_rate": 3.0452323595370175e-05, + "loss": 3.5202, + "step": 1193984 + }, + { + "epoch": 0.02, + "learning_rate": 3.0443954026663384e-05, + "loss": 3.528, + "step": 1194496 + }, + { + "epoch": 0.02, + "learning_rate": 3.0435568079152864e-05, + "loss": 3.5236, + "step": 1195008 + }, + { + "epoch": 0.02, + "learning_rate": 3.0427182131642347e-05, + "loss": 3.5381, + "step": 1195520 + }, + { + "epoch": 0.02, + "learning_rate": 3.0418796184131827e-05, + "loss": 3.5378, + "step": 1196032 + }, + { + "epoch": 0.02, + "learning_rate": 3.0410426615425036e-05, + "loss": 3.5251, + "step": 1196544 + }, + { + "epoch": 0.02, + "learning_rate": 3.0402040667914516e-05, + "loss": 3.5277, + "step": 1197056 + }, + { + "epoch": 0.02, + "learning_rate": 3.0393654720403996e-05, + "loss": 3.5269, + "step": 1197568 + }, + { + "epoch": 0.02, + "learning_rate": 3.0385268772893476e-05, + "loss": 3.5326, + "step": 1198080 + }, + { + "epoch": 0.02, + "learning_rate": 3.037689920418669e-05, + "loss": 3.5173, + "step": 1198592 + }, + { + "epoch": 0.02, + "learning_rate": 3.0368513256676168e-05, + "loss": 3.5269, + "step": 1199104 + }, + { + "epoch": 0.02, + "learning_rate": 3.0360127309165648e-05, + "loss": 3.5317, + "step": 1199616 + }, + { + "epoch": 0.02, + "learning_rate": 3.035174136165512e-05, + "loss": 3.5291, + "step": 1200128 + }, + { + "epoch": 0.02, + "learning_rate": 3.0343371792948337e-05, + "loss": 3.5304, + "step": 1200640 + }, + { + "epoch": 0.02, + "learning_rate": 3.0334985845437817e-05, + "loss": 3.5316, + "step": 1201152 + }, + { + "epoch": 0.02, + "learning_rate": 3.03265998979273e-05, + "loss": 3.5178, + "step": 1201664 + }, + { + "epoch": 0.02, + "learning_rate": 3.0318213950416774e-05, + "loss": 3.538, + "step": 1202176 + }, + { + "epoch": 0.02, + "learning_rate": 3.030984438170999e-05, + "loss": 3.5317, + "step": 1202688 + }, + { + "epoch": 0.02, + "learning_rate": 3.030145843419947e-05, + "loss": 3.5274, + "step": 1203200 + }, + { + "epoch": 0.02, + "learning_rate": 3.029307248668895e-05, + "loss": 3.5367, + "step": 1203712 + }, + { + "epoch": 0.02, + "learning_rate": 3.0284686539178426e-05, + "loss": 3.535, + "step": 1204224 + }, + { + "epoch": 0.02, + "learning_rate": 3.0276316970471642e-05, + "loss": 3.525, + "step": 1204736 + }, + { + "epoch": 0.02, + "learning_rate": 3.0267931022961122e-05, + "loss": 3.5238, + "step": 1205248 + }, + { + "epoch": 0.02, + "learning_rate": 3.0259545075450595e-05, + "loss": 3.5293, + "step": 1205760 + }, + { + "epoch": 0.02, + "learning_rate": 3.0251159127940075e-05, + "loss": 3.526, + "step": 1206272 + }, + { + "epoch": 0.02, + "learning_rate": 3.024278955923329e-05, + "loss": 3.5207, + "step": 1206784 + }, + { + "epoch": 0.02, + "learning_rate": 3.023440361172277e-05, + "loss": 3.5249, + "step": 1207296 + }, + { + "epoch": 0.02, + "learning_rate": 3.0226017664212247e-05, + "loss": 3.5247, + "step": 1207808 + }, + { + "epoch": 0.02, + "learning_rate": 3.0217631716701727e-05, + "loss": 3.5302, + "step": 1208320 + }, + { + "epoch": 0.02, + "learning_rate": 3.0209262147994943e-05, + "loss": 3.5226, + "step": 1208832 + }, + { + "epoch": 0.02, + "learning_rate": 3.0200876200484423e-05, + "loss": 3.5274, + "step": 1209344 + }, + { + "epoch": 0.02, + "learning_rate": 3.01924902529739e-05, + "loss": 3.5217, + "step": 1209856 + }, + { + "epoch": 0.02, + "learning_rate": 3.018410430546338e-05, + "loss": 3.5258, + "step": 1210368 + }, + { + "epoch": 0.02, + "learning_rate": 3.0175734736756596e-05, + "loss": 3.5279, + "step": 1210880 + }, + { + "epoch": 0.02, + "learning_rate": 3.016734878924607e-05, + "loss": 3.5311, + "step": 1211392 + }, + { + "epoch": 0.02, + "learning_rate": 3.015896284173555e-05, + "loss": 3.5337, + "step": 1211904 + }, + { + "epoch": 0.02, + "learning_rate": 3.015057689422503e-05, + "loss": 3.5204, + "step": 1212416 + }, + { + "epoch": 0.02, + "learning_rate": 3.014219094671451e-05, + "loss": 3.5281, + "step": 1212928 + }, + { + "epoch": 0.02, + "learning_rate": 3.013382137800772e-05, + "loss": 3.5339, + "step": 1213440 + }, + { + "epoch": 0.02, + "learning_rate": 3.01254354304972e-05, + "loss": 3.5332, + "step": 1213952 + }, + { + "epoch": 0.02, + "learning_rate": 3.011704948298668e-05, + "loss": 3.534, + "step": 1214464 + }, + { + "epoch": 0.02, + "learning_rate": 3.010866353547616e-05, + "loss": 3.5311, + "step": 1214976 + }, + { + "epoch": 0.02, + "learning_rate": 3.010029396676937e-05, + "loss": 3.5422, + "step": 1215488 + }, + { + "epoch": 0.02, + "learning_rate": 3.0091908019258853e-05, + "loss": 3.5309, + "step": 1216000 + }, + { + "epoch": 0.02, + "learning_rate": 3.0083522071748333e-05, + "loss": 3.5281, + "step": 1216512 + }, + { + "epoch": 0.02, + "learning_rate": 3.0075136124237813e-05, + "loss": 3.527, + "step": 1217024 + }, + { + "epoch": 0.02, + "learning_rate": 3.0066766555531023e-05, + "loss": 3.5231, + "step": 1217536 + }, + { + "epoch": 0.02, + "learning_rate": 3.0058380608020502e-05, + "loss": 3.5249, + "step": 1218048 + }, + { + "epoch": 0.02, + "learning_rate": 3.0049994660509982e-05, + "loss": 3.5205, + "step": 1218560 + }, + { + "epoch": 0.02, + "learning_rate": 3.0041608712999462e-05, + "loss": 3.5335, + "step": 1219072 + }, + { + "epoch": 0.02, + "learning_rate": 3.0033239144292675e-05, + "loss": 3.5204, + "step": 1219584 + }, + { + "epoch": 0.02, + "learning_rate": 3.0024853196782155e-05, + "loss": 3.5335, + "step": 1220096 + }, + { + "epoch": 0.02, + "learning_rate": 3.0016467249271635e-05, + "loss": 3.5255, + "step": 1220608 + }, + { + "epoch": 0.03, + "learning_rate": 3.0008081301761115e-05, + "loss": 3.5289, + "step": 1221120 + }, + { + "epoch": 0.03, + "eval_loss": 3.847226619720459, + "eval_runtime": 305.4752, + "eval_samples_per_second": 1249.172, + "eval_steps_per_second": 39.038, + "step": 1221120 + }, + { + "epoch": 1.0, + "learning_rate": 2.9999711733054324e-05, + "loss": 3.52, + "step": 1221632 + }, + { + "epoch": 1.0, + "learning_rate": 2.9991325785543807e-05, + "loss": 3.5172, + "step": 1222144 + }, + { + "epoch": 1.0, + "learning_rate": 2.9982939838033287e-05, + "loss": 3.5302, + "step": 1222656 + }, + { + "epoch": 1.0, + "learning_rate": 2.9974553890522767e-05, + "loss": 3.5324, + "step": 1223168 + }, + { + "epoch": 1.0, + "learning_rate": 2.9966184321815976e-05, + "loss": 3.5304, + "step": 1223680 + }, + { + "epoch": 1.0, + "learning_rate": 2.9957798374305456e-05, + "loss": 3.5197, + "step": 1224192 + }, + { + "epoch": 1.0, + "learning_rate": 2.9949412426794936e-05, + "loss": 3.5184, + "step": 1224704 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941026479284416e-05, + "loss": 3.5209, + "step": 1225216 + }, + { + "epoch": 1.0, + "learning_rate": 2.993265691057763e-05, + "loss": 3.5305, + "step": 1225728 + }, + { + "epoch": 1.0, + "learning_rate": 2.992427096306711e-05, + "loss": 3.5239, + "step": 1226240 + }, + { + "epoch": 1.0, + "learning_rate": 2.991588501555659e-05, + "loss": 3.5303, + "step": 1226752 + }, + { + "epoch": 1.0, + "learning_rate": 2.990749906804607e-05, + "loss": 3.5359, + "step": 1227264 + }, + { + "epoch": 1.0, + "learning_rate": 2.9899129499339277e-05, + "loss": 3.5113, + "step": 1227776 + }, + { + "epoch": 1.0, + "learning_rate": 2.989074355182876e-05, + "loss": 3.5157, + "step": 1228288 + }, + { + "epoch": 1.0, + "learning_rate": 2.988235760431824e-05, + "loss": 3.5134, + "step": 1228800 + }, + { + "epoch": 1.0, + "learning_rate": 2.987398803561145e-05, + "loss": 3.5212, + "step": 1229312 + }, + { + "epoch": 1.0, + "learning_rate": 2.986560208810093e-05, + "loss": 3.5224, + "step": 1229824 + }, + { + "epoch": 1.0, + "learning_rate": 2.985721614059041e-05, + "loss": 3.5267, + "step": 1230336 + }, + { + "epoch": 1.0, + "learning_rate": 2.984883019307989e-05, + "loss": 3.5183, + "step": 1230848 + }, + { + "epoch": 1.0, + "learning_rate": 2.9840460624373102e-05, + "loss": 3.5405, + "step": 1231360 + }, + { + "epoch": 1.0, + "learning_rate": 2.9832074676862582e-05, + "loss": 3.5272, + "step": 1231872 + }, + { + "epoch": 1.0, + "learning_rate": 2.9823688729352062e-05, + "loss": 3.5254, + "step": 1232384 + }, + { + "epoch": 1.0, + "learning_rate": 2.9815302781841542e-05, + "loss": 3.5258, + "step": 1232896 + }, + { + "epoch": 1.0, + "learning_rate": 2.9806916834331022e-05, + "loss": 3.5394, + "step": 1233408 + }, + { + "epoch": 1.0, + "learning_rate": 2.979854726562423e-05, + "loss": 3.5154, + "step": 1233920 + }, + { + "epoch": 1.0, + "learning_rate": 2.9790161318113714e-05, + "loss": 3.5211, + "step": 1234432 + }, + { + "epoch": 1.0, + "learning_rate": 2.9781775370603194e-05, + "loss": 3.5277, + "step": 1234944 + }, + { + "epoch": 1.0, + "learning_rate": 2.9773389423092674e-05, + "loss": 3.5149, + "step": 1235456 + }, + { + "epoch": 1.0, + "learning_rate": 2.9765019854385884e-05, + "loss": 3.5194, + "step": 1235968 + }, + { + "epoch": 1.01, + "learning_rate": 2.9756633906875363e-05, + "loss": 3.5211, + "step": 1236480 + }, + { + "epoch": 1.01, + "learning_rate": 2.9748247959364843e-05, + "loss": 3.5373, + "step": 1236992 + }, + { + "epoch": 1.01, + "learning_rate": 2.9739862011854323e-05, + "loss": 3.5226, + "step": 1237504 + }, + { + "epoch": 1.01, + "learning_rate": 2.9731492443147536e-05, + "loss": 3.5285, + "step": 1238016 + }, + { + "epoch": 1.01, + "learning_rate": 2.9723106495637016e-05, + "loss": 3.5239, + "step": 1238528 + }, + { + "epoch": 1.01, + "learning_rate": 2.9714720548126496e-05, + "loss": 3.5251, + "step": 1239040 + }, + { + "epoch": 1.01, + "learning_rate": 2.9706334600615976e-05, + "loss": 3.5243, + "step": 1239552 + }, + { + "epoch": 1.01, + "learning_rate": 2.9697965031909185e-05, + "loss": 3.5107, + "step": 1240064 + }, + { + "epoch": 1.01, + "learning_rate": 2.9689579084398668e-05, + "loss": 3.5215, + "step": 1240576 + }, + { + "epoch": 1.01, + "learning_rate": 2.9681193136888148e-05, + "loss": 3.5098, + "step": 1241088 + }, + { + "epoch": 1.01, + "learning_rate": 2.9672807189377628e-05, + "loss": 3.5201, + "step": 1241600 + }, + { + "epoch": 1.01, + "learning_rate": 2.9664437620670837e-05, + "loss": 3.515, + "step": 1242112 + }, + { + "epoch": 1.01, + "learning_rate": 2.9656051673160317e-05, + "loss": 3.5302, + "step": 1242624 + }, + { + "epoch": 1.01, + "learning_rate": 2.9647665725649797e-05, + "loss": 3.5215, + "step": 1243136 + }, + { + "epoch": 1.01, + "learning_rate": 2.9639279778139277e-05, + "loss": 3.5211, + "step": 1243648 + }, + { + "epoch": 1.01, + "learning_rate": 2.963091020943249e-05, + "loss": 3.5261, + "step": 1244160 + }, + { + "epoch": 1.01, + "learning_rate": 2.962252426192197e-05, + "loss": 3.5178, + "step": 1244672 + }, + { + "epoch": 1.01, + "learning_rate": 2.961413831441145e-05, + "loss": 3.5298, + "step": 1245184 + }, + { + "epoch": 1.01, + "learning_rate": 2.960575236690093e-05, + "loss": 3.5039, + "step": 1245696 + }, + { + "epoch": 1.01, + "learning_rate": 2.959738279819414e-05, + "loss": 3.5176, + "step": 1246208 + }, + { + "epoch": 1.01, + "learning_rate": 2.9588996850683622e-05, + "loss": 3.5244, + "step": 1246720 + }, + { + "epoch": 1.01, + "learning_rate": 2.9580610903173102e-05, + "loss": 3.5262, + "step": 1247232 + }, + { + "epoch": 1.01, + "learning_rate": 2.9572224955662582e-05, + "loss": 3.522, + "step": 1247744 + }, + { + "epoch": 1.01, + "learning_rate": 2.956385538695579e-05, + "loss": 3.5038, + "step": 1248256 + }, + { + "epoch": 1.01, + "learning_rate": 2.955546943944527e-05, + "loss": 3.5201, + "step": 1248768 + }, + { + "epoch": 1.01, + "learning_rate": 2.954708349193475e-05, + "loss": 3.5081, + "step": 1249280 + }, + { + "epoch": 1.01, + "learning_rate": 2.953869754442423e-05, + "loss": 3.5334, + "step": 1249792 + }, + { + "epoch": 1.01, + "learning_rate": 2.9530327975717443e-05, + "loss": 3.5094, + "step": 1250304 + }, + { + "epoch": 1.01, + "learning_rate": 2.9521942028206923e-05, + "loss": 3.5269, + "step": 1250816 + }, + { + "epoch": 1.01, + "learning_rate": 2.9513556080696403e-05, + "loss": 3.5164, + "step": 1251328 + }, + { + "epoch": 1.01, + "learning_rate": 2.9505170133185883e-05, + "loss": 3.504, + "step": 1251840 + }, + { + "epoch": 1.01, + "learning_rate": 2.9496800564479092e-05, + "loss": 3.5218, + "step": 1252352 + }, + { + "epoch": 1.01, + "learning_rate": 2.9488414616968572e-05, + "loss": 3.5155, + "step": 1252864 + }, + { + "epoch": 1.01, + "learning_rate": 2.9480028669458055e-05, + "loss": 3.4982, + "step": 1253376 + }, + { + "epoch": 1.01, + "learning_rate": 2.9471642721947535e-05, + "loss": 3.5058, + "step": 1253888 + }, + { + "epoch": 1.01, + "learning_rate": 2.9463273153240745e-05, + "loss": 3.5249, + "step": 1254400 + }, + { + "epoch": 1.01, + "learning_rate": 2.9454887205730224e-05, + "loss": 3.5132, + "step": 1254912 + }, + { + "epoch": 1.01, + "learning_rate": 2.9446501258219704e-05, + "loss": 3.5074, + "step": 1255424 + }, + { + "epoch": 1.01, + "learning_rate": 2.9438115310709184e-05, + "loss": 3.5089, + "step": 1255936 + }, + { + "epoch": 1.01, + "learning_rate": 2.9429745742002397e-05, + "loss": 3.5065, + "step": 1256448 + }, + { + "epoch": 1.01, + "learning_rate": 2.9421359794491877e-05, + "loss": 3.5137, + "step": 1256960 + }, + { + "epoch": 1.01, + "learning_rate": 2.9412973846981357e-05, + "loss": 3.5224, + "step": 1257472 + }, + { + "epoch": 1.01, + "learning_rate": 2.9404587899470837e-05, + "loss": 3.518, + "step": 1257984 + }, + { + "epoch": 1.01, + "learning_rate": 2.9396218330764046e-05, + "loss": 3.5296, + "step": 1258496 + }, + { + "epoch": 1.01, + "learning_rate": 2.9387832383253526e-05, + "loss": 3.5178, + "step": 1259008 + }, + { + "epoch": 1.01, + "learning_rate": 2.937944643574301e-05, + "loss": 3.5236, + "step": 1259520 + }, + { + "epoch": 1.01, + "learning_rate": 2.9371076867036218e-05, + "loss": 3.5137, + "step": 1260032 + }, + { + "epoch": 1.01, + "learning_rate": 2.9362690919525698e-05, + "loss": 3.5149, + "step": 1260544 + }, + { + "epoch": 1.01, + "learning_rate": 2.9354304972015178e-05, + "loss": 3.5162, + "step": 1261056 + }, + { + "epoch": 1.01, + "learning_rate": 2.9345919024504658e-05, + "loss": 3.5089, + "step": 1261568 + }, + { + "epoch": 1.01, + "learning_rate": 2.9337533076994138e-05, + "loss": 3.5142, + "step": 1262080 + }, + { + "epoch": 1.01, + "learning_rate": 2.932916350828735e-05, + "loss": 3.5225, + "step": 1262592 + }, + { + "epoch": 1.01, + "learning_rate": 2.932077756077683e-05, + "loss": 3.5241, + "step": 1263104 + }, + { + "epoch": 1.01, + "learning_rate": 2.931239161326631e-05, + "loss": 3.5147, + "step": 1263616 + }, + { + "epoch": 1.01, + "learning_rate": 2.930400566575579e-05, + "loss": 3.5017, + "step": 1264128 + }, + { + "epoch": 1.01, + "learning_rate": 2.9295636097049e-05, + "loss": 3.5139, + "step": 1264640 + }, + { + "epoch": 1.01, + "learning_rate": 2.928725014953848e-05, + "loss": 3.5273, + "step": 1265152 + }, + { + "epoch": 1.01, + "learning_rate": 2.9278864202027963e-05, + "loss": 3.522, + "step": 1265664 + }, + { + "epoch": 1.01, + "learning_rate": 2.9270494633321172e-05, + "loss": 3.5139, + "step": 1266176 + }, + { + "epoch": 1.01, + "learning_rate": 2.9262108685810652e-05, + "loss": 3.5279, + "step": 1266688 + }, + { + "epoch": 1.02, + "learning_rate": 2.9253722738300132e-05, + "loss": 3.5174, + "step": 1267200 + }, + { + "epoch": 1.02, + "learning_rate": 2.9245336790789612e-05, + "loss": 3.5121, + "step": 1267712 + }, + { + "epoch": 1.02, + "learning_rate": 2.9236967222082824e-05, + "loss": 3.5162, + "step": 1268224 + }, + { + "epoch": 1.02, + "learning_rate": 2.9228581274572304e-05, + "loss": 3.5214, + "step": 1268736 + }, + { + "epoch": 1.02, + "learning_rate": 2.9220195327061784e-05, + "loss": 3.5162, + "step": 1269248 + }, + { + "epoch": 1.02, + "learning_rate": 2.9211809379551264e-05, + "loss": 3.5286, + "step": 1269760 + }, + { + "epoch": 1.02, + "learning_rate": 2.9203439810844473e-05, + "loss": 3.5085, + "step": 1270272 + }, + { + "epoch": 1.02, + "learning_rate": 2.9195053863333953e-05, + "loss": 3.5103, + "step": 1270784 + }, + { + "epoch": 1.02, + "learning_rate": 2.9186667915823433e-05, + "loss": 3.5107, + "step": 1271296 + }, + { + "epoch": 1.02, + "learning_rate": 2.9178281968312916e-05, + "loss": 3.5245, + "step": 1271808 + }, + { + "epoch": 1.02, + "learning_rate": 2.9169912399606126e-05, + "loss": 3.5193, + "step": 1272320 + }, + { + "epoch": 1.02, + "learning_rate": 2.9161526452095606e-05, + "loss": 3.5151, + "step": 1272832 + }, + { + "epoch": 1.02, + "learning_rate": 2.9153140504585085e-05, + "loss": 3.5104, + "step": 1273344 + }, + { + "epoch": 1.02, + "learning_rate": 2.9144754557074565e-05, + "loss": 3.5136, + "step": 1273856 + }, + { + "epoch": 1.02, + "learning_rate": 2.9136384988367778e-05, + "loss": 3.5218, + "step": 1274368 + }, + { + "epoch": 1.02, + "learning_rate": 2.9127999040857258e-05, + "loss": 3.4995, + "step": 1274880 + }, + { + "epoch": 1.02, + "learning_rate": 2.9119613093346738e-05, + "loss": 3.5152, + "step": 1275392 + }, + { + "epoch": 1.02, + "learning_rate": 2.9111227145836218e-05, + "loss": 3.5225, + "step": 1275904 + }, + { + "epoch": 1.02, + "learning_rate": 2.9102857577129427e-05, + "loss": 3.5126, + "step": 1276416 + }, + { + "epoch": 1.02, + "learning_rate": 2.9094471629618907e-05, + "loss": 3.5138, + "step": 1276928 + }, + { + "epoch": 1.02, + "learning_rate": 2.9086085682108387e-05, + "loss": 3.5189, + "step": 1277440 + }, + { + "epoch": 1.02, + "learning_rate": 2.9077699734597863e-05, + "loss": 3.5038, + "step": 1277952 + }, + { + "epoch": 1.02, + "learning_rate": 2.906933016589108e-05, + "loss": 3.5194, + "step": 1278464 + }, + { + "epoch": 1.02, + "learning_rate": 2.906094421838056e-05, + "loss": 3.5202, + "step": 1278976 + }, + { + "epoch": 1.02, + "learning_rate": 2.905255827087004e-05, + "loss": 3.5155, + "step": 1279488 + }, + { + "epoch": 1.02, + "learning_rate": 2.9044172323359516e-05, + "loss": 3.5198, + "step": 1280000 + }, + { + "epoch": 1.02, + "learning_rate": 2.903580275465273e-05, + "loss": 3.5203, + "step": 1280512 + }, + { + "epoch": 1.02, + "learning_rate": 2.902741680714221e-05, + "loss": 3.5139, + "step": 1281024 + }, + { + "epoch": 1.02, + "learning_rate": 2.901903085963169e-05, + "loss": 3.5125, + "step": 1281536 + }, + { + "epoch": 1.02, + "learning_rate": 2.9010644912121165e-05, + "loss": 3.5139, + "step": 1282048 + }, + { + "epoch": 1.02, + "learning_rate": 2.900227534341438e-05, + "loss": 3.5134, + "step": 1282560 + }, + { + "epoch": 1.02, + "learning_rate": 2.899388939590386e-05, + "loss": 3.5054, + "step": 1283072 + }, + { + "epoch": 1.02, + "learning_rate": 2.8985503448393337e-05, + "loss": 3.5103, + "step": 1283584 + }, + { + "epoch": 1.02, + "learning_rate": 2.8977117500882817e-05, + "loss": 3.5104, + "step": 1284096 + }, + { + "epoch": 1.02, + "learning_rate": 2.8968747932176033e-05, + "loss": 3.5205, + "step": 1284608 + }, + { + "epoch": 1.02, + "learning_rate": 2.8960361984665513e-05, + "loss": 3.5071, + "step": 1285120 + }, + { + "epoch": 1.02, + "learning_rate": 2.8951976037154986e-05, + "loss": 3.5138, + "step": 1285632 + }, + { + "epoch": 1.02, + "learning_rate": 2.894359008964447e-05, + "loss": 3.5077, + "step": 1286144 + }, + { + "epoch": 1.02, + "learning_rate": 2.8935220520937685e-05, + "loss": 3.5138, + "step": 1286656 + }, + { + "epoch": 1.02, + "learning_rate": 2.8926834573427165e-05, + "loss": 3.5095, + "step": 1287168 + }, + { + "epoch": 1.02, + "learning_rate": 2.891844862591664e-05, + "loss": 3.5242, + "step": 1287680 + }, + { + "epoch": 1.02, + "learning_rate": 2.891006267840612e-05, + "loss": 3.5188, + "step": 1288192 + }, + { + "epoch": 1.02, + "learning_rate": 2.8901693109699334e-05, + "loss": 3.5101, + "step": 1288704 + }, + { + "epoch": 1.02, + "learning_rate": 2.889330716218881e-05, + "loss": 3.5118, + "step": 1289216 + }, + { + "epoch": 1.02, + "learning_rate": 2.888492121467829e-05, + "loss": 3.5178, + "step": 1289728 + }, + { + "epoch": 1.02, + "learning_rate": 2.887653526716777e-05, + "loss": 3.5198, + "step": 1290240 + }, + { + "epoch": 1.02, + "learning_rate": 2.8868165698460987e-05, + "loss": 3.519, + "step": 1290752 + }, + { + "epoch": 1.02, + "learning_rate": 2.885977975095046e-05, + "loss": 3.5185, + "step": 1291264 + }, + { + "epoch": 1.02, + "learning_rate": 2.885139380343994e-05, + "loss": 3.5266, + "step": 1291776 + }, + { + "epoch": 1.02, + "learning_rate": 2.8843007855929423e-05, + "loss": 3.5162, + "step": 1292288 + }, + { + "epoch": 1.02, + "learning_rate": 2.883463828722264e-05, + "loss": 3.5141, + "step": 1292800 + }, + { + "epoch": 1.02, + "learning_rate": 2.8826252339712112e-05, + "loss": 3.511, + "step": 1293312 + }, + { + "epoch": 1.02, + "learning_rate": 2.8817866392201592e-05, + "loss": 3.5146, + "step": 1293824 + }, + { + "epoch": 1.02, + "learning_rate": 2.8809480444691072e-05, + "loss": 3.5126, + "step": 1294336 + }, + { + "epoch": 1.02, + "learning_rate": 2.8801110875984284e-05, + "loss": 3.5039, + "step": 1294848 + }, + { + "epoch": 1.02, + "learning_rate": 2.8792724928473764e-05, + "loss": 3.5186, + "step": 1295360 + }, + { + "epoch": 1.02, + "learning_rate": 2.8784338980963244e-05, + "loss": 3.5093, + "step": 1295872 + }, + { + "epoch": 1.02, + "learning_rate": 2.8775953033452724e-05, + "loss": 3.5187, + "step": 1296384 + }, + { + "epoch": 1.02, + "learning_rate": 2.8767583464745933e-05, + "loss": 3.5118, + "step": 1296896 + }, + { + "epoch": 1.02, + "learning_rate": 2.8759197517235413e-05, + "loss": 3.5139, + "step": 1297408 + }, + { + "epoch": 1.03, + "eval_loss": 3.8467087745666504, + "eval_runtime": 301.9812, + "eval_samples_per_second": 1263.625, + "eval_steps_per_second": 39.489, + "step": 1297440 + }, + { + "epoch": 0.0, + "learning_rate": 2.8750811569724893e-05, + "loss": 3.5026, + "step": 1297920 + }, + { + "epoch": 0.0, + "learning_rate": 2.8742425622214377e-05, + "loss": 3.5079, + "step": 1298432 + }, + { + "epoch": 0.0, + "learning_rate": 2.8734039674703857e-05, + "loss": 3.5185, + "step": 1298944 + }, + { + "epoch": 0.0, + "learning_rate": 2.8725670105997066e-05, + "loss": 3.5151, + "step": 1299456 + }, + { + "epoch": 0.0, + "learning_rate": 2.8717284158486546e-05, + "loss": 3.5186, + "step": 1299968 + }, + { + "epoch": 0.0, + "learning_rate": 2.8708898210976026e-05, + "loss": 3.5074, + "step": 1300480 + }, + { + "epoch": 0.0, + "learning_rate": 2.8700512263465506e-05, + "loss": 3.5028, + "step": 1300992 + }, + { + "epoch": 0.0, + "learning_rate": 2.8692142694758718e-05, + "loss": 3.5066, + "step": 1301504 + }, + { + "epoch": 0.0, + "learning_rate": 2.8683756747248198e-05, + "loss": 3.5166, + "step": 1302016 + }, + { + "epoch": 0.0, + "learning_rate": 2.8675370799737678e-05, + "loss": 3.515, + "step": 1302528 + }, + { + "epoch": 0.0, + "learning_rate": 2.8666984852227158e-05, + "loss": 3.5123, + "step": 1303040 + }, + { + "epoch": 0.0, + "learning_rate": 2.8658598904716638e-05, + "loss": 3.5203, + "step": 1303552 + }, + { + "epoch": 0.0, + "learning_rate": 2.8650229336009847e-05, + "loss": 3.5005, + "step": 1304064 + }, + { + "epoch": 0.0, + "learning_rate": 2.864184338849933e-05, + "loss": 3.5049, + "step": 1304576 + }, + { + "epoch": 0.0, + "learning_rate": 2.863345744098881e-05, + "loss": 3.5061, + "step": 1305088 + }, + { + "epoch": 0.0, + "learning_rate": 2.862508787228202e-05, + "loss": 3.4978, + "step": 1305600 + }, + { + "epoch": 0.0, + "learning_rate": 2.86167019247715e-05, + "loss": 3.5084, + "step": 1306112 + }, + { + "epoch": 0.0, + "learning_rate": 2.860831597726098e-05, + "loss": 3.5096, + "step": 1306624 + }, + { + "epoch": 0.0, + "learning_rate": 2.859993002975046e-05, + "loss": 3.5025, + "step": 1307136 + }, + { + "epoch": 0.0, + "learning_rate": 2.8591560461043672e-05, + "loss": 3.5301, + "step": 1307648 + }, + { + "epoch": 0.0, + "learning_rate": 2.8583174513533152e-05, + "loss": 3.5136, + "step": 1308160 + }, + { + "epoch": 0.0, + "learning_rate": 2.857478856602263e-05, + "loss": 3.5116, + "step": 1308672 + }, + { + "epoch": 0.0, + "learning_rate": 2.856640261851211e-05, + "loss": 3.5128, + "step": 1309184 + }, + { + "epoch": 0.0, + "learning_rate": 2.855803304980532e-05, + "loss": 3.522, + "step": 1309696 + }, + { + "epoch": 0.0, + "learning_rate": 2.85496471022948e-05, + "loss": 3.5028, + "step": 1310208 + }, + { + "epoch": 0.0, + "learning_rate": 2.854126115478428e-05, + "loss": 3.5082, + "step": 1310720 + }, + { + "epoch": 0.0, + "learning_rate": 2.8532875207273764e-05, + "loss": 3.5109, + "step": 1311232 + }, + { + "epoch": 0.0, + "learning_rate": 2.8524505638566973e-05, + "loss": 3.5064, + "step": 1311744 + }, + { + "epoch": 0.0, + "learning_rate": 2.8516119691056453e-05, + "loss": 3.5044, + "step": 1312256 + }, + { + "epoch": 0.01, + "learning_rate": 2.8507733743545933e-05, + "loss": 3.5039, + "step": 1312768 + }, + { + "epoch": 0.01, + "learning_rate": 2.8499347796035413e-05, + "loss": 3.5271, + "step": 1313280 + }, + { + "epoch": 0.01, + "learning_rate": 2.8490978227328625e-05, + "loss": 3.5112, + "step": 1313792 + }, + { + "epoch": 0.01, + "learning_rate": 2.8482592279818105e-05, + "loss": 3.5119, + "step": 1314304 + }, + { + "epoch": 0.01, + "learning_rate": 2.8474206332307585e-05, + "loss": 3.5113, + "step": 1314816 + }, + { + "epoch": 0.01, + "learning_rate": 2.8465820384797065e-05, + "loss": 3.513, + "step": 1315328 + }, + { + "epoch": 0.01, + "learning_rate": 2.8457450816090274e-05, + "loss": 3.5117, + "step": 1315840 + }, + { + "epoch": 0.01, + "learning_rate": 2.8449064868579754e-05, + "loss": 3.4966, + "step": 1316352 + }, + { + "epoch": 0.01, + "learning_rate": 2.8440678921069234e-05, + "loss": 3.5059, + "step": 1316864 + }, + { + "epoch": 0.01, + "learning_rate": 2.8432292973558718e-05, + "loss": 3.4954, + "step": 1317376 + }, + { + "epoch": 0.01, + "learning_rate": 2.8423923404851927e-05, + "loss": 3.51, + "step": 1317888 + }, + { + "epoch": 0.01, + "learning_rate": 2.8415537457341407e-05, + "loss": 3.5012, + "step": 1318400 + }, + { + "epoch": 0.01, + "learning_rate": 2.8407151509830887e-05, + "loss": 3.5161, + "step": 1318912 + }, + { + "epoch": 0.01, + "learning_rate": 2.8398765562320367e-05, + "loss": 3.507, + "step": 1319424 + }, + { + "epoch": 0.01, + "learning_rate": 2.839039599361358e-05, + "loss": 3.5067, + "step": 1319936 + }, + { + "epoch": 0.01, + "learning_rate": 2.838201004610306e-05, + "loss": 3.5137, + "step": 1320448 + }, + { + "epoch": 0.01, + "learning_rate": 2.837362409859254e-05, + "loss": 3.5056, + "step": 1320960 + }, + { + "epoch": 0.01, + "learning_rate": 2.836523815108202e-05, + "loss": 3.5118, + "step": 1321472 + }, + { + "epoch": 0.01, + "learning_rate": 2.8356868582375228e-05, + "loss": 3.4957, + "step": 1321984 + }, + { + "epoch": 0.01, + "learning_rate": 2.8348482634864708e-05, + "loss": 3.5039, + "step": 1322496 + }, + { + "epoch": 0.01, + "learning_rate": 2.8340096687354188e-05, + "loss": 3.5078, + "step": 1323008 + }, + { + "epoch": 0.01, + "learning_rate": 2.833171073984367e-05, + "loss": 3.5116, + "step": 1323520 + }, + { + "epoch": 0.01, + "learning_rate": 2.832334117113688e-05, + "loss": 3.5138, + "step": 1324032 + }, + { + "epoch": 0.01, + "learning_rate": 2.831495522362636e-05, + "loss": 3.4876, + "step": 1324544 + }, + { + "epoch": 0.01, + "learning_rate": 2.830656927611584e-05, + "loss": 3.5072, + "step": 1325056 + }, + { + "epoch": 0.01, + "learning_rate": 2.829818332860532e-05, + "loss": 3.4914, + "step": 1325568 + }, + { + "epoch": 0.01, + "learning_rate": 2.8289813759898533e-05, + "loss": 3.5209, + "step": 1326080 + }, + { + "epoch": 0.01, + "learning_rate": 2.8281427812388013e-05, + "loss": 3.4975, + "step": 1326592 + }, + { + "epoch": 0.01, + "learning_rate": 2.8273041864877493e-05, + "loss": 3.5117, + "step": 1327104 + }, + { + "epoch": 0.01, + "learning_rate": 2.8264655917366973e-05, + "loss": 3.5063, + "step": 1327616 + }, + { + "epoch": 0.01, + "learning_rate": 2.8256286348660182e-05, + "loss": 3.4932, + "step": 1328128 + }, + { + "epoch": 0.01, + "learning_rate": 2.824790040114966e-05, + "loss": 3.504, + "step": 1328640 + }, + { + "epoch": 0.01, + "learning_rate": 2.823951445363914e-05, + "loss": 3.5016, + "step": 1329152 + }, + { + "epoch": 0.01, + "learning_rate": 2.8231128506128625e-05, + "loss": 3.4859, + "step": 1329664 + }, + { + "epoch": 0.01, + "learning_rate": 2.8222758937421834e-05, + "loss": 3.4948, + "step": 1330176 + }, + { + "epoch": 0.01, + "learning_rate": 2.8214372989911314e-05, + "loss": 3.5091, + "step": 1330688 + }, + { + "epoch": 0.01, + "learning_rate": 2.8205987042400794e-05, + "loss": 3.5025, + "step": 1331200 + }, + { + "epoch": 0.01, + "learning_rate": 2.8197601094890274e-05, + "loss": 3.4948, + "step": 1331712 + }, + { + "epoch": 0.01, + "learning_rate": 2.8189231526183486e-05, + "loss": 3.4971, + "step": 1332224 + }, + { + "epoch": 0.01, + "learning_rate": 2.8180845578672966e-05, + "loss": 3.4907, + "step": 1332736 + }, + { + "epoch": 0.01, + "learning_rate": 2.8172459631162446e-05, + "loss": 3.5027, + "step": 1333248 + }, + { + "epoch": 0.01, + "learning_rate": 2.8164073683651926e-05, + "loss": 3.5046, + "step": 1333760 + }, + { + "epoch": 0.01, + "learning_rate": 2.8155704114945135e-05, + "loss": 3.5068, + "step": 1334272 + }, + { + "epoch": 0.01, + "learning_rate": 2.8147318167434615e-05, + "loss": 3.5157, + "step": 1334784 + }, + { + "epoch": 0.01, + "learning_rate": 2.8138932219924095e-05, + "loss": 3.5047, + "step": 1335296 + }, + { + "epoch": 0.01, + "learning_rate": 2.813054627241358e-05, + "loss": 3.5124, + "step": 1335808 + }, + { + "epoch": 0.01, + "learning_rate": 2.8122176703706788e-05, + "loss": 3.4945, + "step": 1336320 + }, + { + "epoch": 0.01, + "learning_rate": 2.8113790756196268e-05, + "loss": 3.5057, + "step": 1336832 + }, + { + "epoch": 0.01, + "learning_rate": 2.8105404808685748e-05, + "loss": 3.5009, + "step": 1337344 + }, + { + "epoch": 0.01, + "learning_rate": 2.8097018861175228e-05, + "loss": 3.4954, + "step": 1337856 + }, + { + "epoch": 0.01, + "learning_rate": 2.808864929246844e-05, + "loss": 3.5025, + "step": 1338368 + }, + { + "epoch": 0.01, + "learning_rate": 2.808026334495792e-05, + "loss": 3.5083, + "step": 1338880 + }, + { + "epoch": 0.01, + "learning_rate": 2.80718773974474e-05, + "loss": 3.5115, + "step": 1339392 + }, + { + "epoch": 0.01, + "learning_rate": 2.806349144993688e-05, + "loss": 3.5028, + "step": 1339904 + }, + { + "epoch": 0.01, + "learning_rate": 2.805512188123009e-05, + "loss": 3.4896, + "step": 1340416 + }, + { + "epoch": 0.01, + "learning_rate": 2.804673593371957e-05, + "loss": 3.4951, + "step": 1340928 + }, + { + "epoch": 0.01, + "learning_rate": 2.803834998620905e-05, + "loss": 3.5137, + "step": 1341440 + }, + { + "epoch": 0.01, + "learning_rate": 2.8029964038698532e-05, + "loss": 3.5094, + "step": 1341952 + }, + { + "epoch": 0.01, + "learning_rate": 2.802159446999174e-05, + "loss": 3.5047, + "step": 1342464 + }, + { + "epoch": 0.01, + "learning_rate": 2.801320852248122e-05, + "loss": 3.5111, + "step": 1342976 + }, + { + "epoch": 0.02, + "learning_rate": 2.80048225749707e-05, + "loss": 3.5083, + "step": 1343488 + }, + { + "epoch": 0.02, + "learning_rate": 2.799643662746018e-05, + "loss": 3.4945, + "step": 1344000 + }, + { + "epoch": 0.02, + "learning_rate": 2.7988067058753394e-05, + "loss": 3.5014, + "step": 1344512 + }, + { + "epoch": 0.02, + "learning_rate": 2.7979681111242874e-05, + "loss": 3.5099, + "step": 1345024 + }, + { + "epoch": 0.02, + "learning_rate": 2.7971295163732354e-05, + "loss": 3.502, + "step": 1345536 + }, + { + "epoch": 0.02, + "learning_rate": 2.7962909216221834e-05, + "loss": 3.514, + "step": 1346048 + }, + { + "epoch": 0.02, + "learning_rate": 2.7954539647515043e-05, + "loss": 3.4968, + "step": 1346560 + }, + { + "epoch": 0.02, + "learning_rate": 2.7946153700004523e-05, + "loss": 3.4969, + "step": 1347072 + }, + { + "epoch": 0.02, + "learning_rate": 2.7937767752494003e-05, + "loss": 3.499, + "step": 1347584 + }, + { + "epoch": 0.02, + "learning_rate": 2.7929381804983486e-05, + "loss": 3.5092, + "step": 1348096 + }, + { + "epoch": 0.02, + "learning_rate": 2.7921012236276695e-05, + "loss": 3.5067, + "step": 1348608 + }, + { + "epoch": 0.02, + "learning_rate": 2.7912626288766175e-05, + "loss": 3.5008, + "step": 1349120 + }, + { + "epoch": 0.02, + "learning_rate": 2.7904240341255655e-05, + "loss": 3.4974, + "step": 1349632 + }, + { + "epoch": 0.02, + "learning_rate": 2.789585439374513e-05, + "loss": 3.4984, + "step": 1350144 + }, + { + "epoch": 0.02, + "learning_rate": 2.7887484825038347e-05, + "loss": 3.5107, + "step": 1350656 + }, + { + "epoch": 0.02, + "learning_rate": 2.7879098877527827e-05, + "loss": 3.4865, + "step": 1351168 + }, + { + "epoch": 0.02, + "learning_rate": 2.7870712930017307e-05, + "loss": 3.4952, + "step": 1351680 + }, + { + "epoch": 0.02, + "learning_rate": 2.786232698250678e-05, + "loss": 3.5124, + "step": 1352192 + }, + { + "epoch": 0.02, + "learning_rate": 2.7853957413799996e-05, + "loss": 3.5005, + "step": 1352704 + }, + { + "epoch": 0.02, + "learning_rate": 2.7845571466289476e-05, + "loss": 3.497, + "step": 1353216 + }, + { + "epoch": 0.02, + "learning_rate": 2.7837185518778956e-05, + "loss": 3.5044, + "step": 1353728 + }, + { + "epoch": 0.02, + "learning_rate": 2.7828799571268433e-05, + "loss": 3.4967, + "step": 1354240 + }, + { + "epoch": 0.02, + "learning_rate": 2.782043000256165e-05, + "loss": 3.5048, + "step": 1354752 + }, + { + "epoch": 0.02, + "learning_rate": 2.781204405505113e-05, + "loss": 3.5019, + "step": 1355264 + }, + { + "epoch": 0.02, + "learning_rate": 2.7803658107540602e-05, + "loss": 3.5033, + "step": 1355776 + }, + { + "epoch": 0.02, + "learning_rate": 2.7795272160030085e-05, + "loss": 3.5096, + "step": 1356288 + }, + { + "epoch": 0.02, + "learning_rate": 2.77869025913233e-05, + "loss": 3.5106, + "step": 1356800 + }, + { + "epoch": 0.02, + "learning_rate": 2.777851664381278e-05, + "loss": 3.4987, + "step": 1357312 + }, + { + "epoch": 0.02, + "learning_rate": 2.7770130696302254e-05, + "loss": 3.5009, + "step": 1357824 + }, + { + "epoch": 0.02, + "learning_rate": 2.7761744748791734e-05, + "loss": 3.5032, + "step": 1358336 + }, + { + "epoch": 0.02, + "learning_rate": 2.775337518008495e-05, + "loss": 3.4991, + "step": 1358848 + }, + { + "epoch": 0.02, + "learning_rate": 2.774498923257443e-05, + "loss": 3.4908, + "step": 1359360 + }, + { + "epoch": 0.02, + "learning_rate": 2.7736603285063907e-05, + "loss": 3.4984, + "step": 1359872 + }, + { + "epoch": 0.02, + "learning_rate": 2.7728217337553387e-05, + "loss": 3.4965, + "step": 1360384 + }, + { + "epoch": 0.02, + "learning_rate": 2.7719847768846602e-05, + "loss": 3.5051, + "step": 1360896 + }, + { + "epoch": 0.02, + "learning_rate": 2.7711461821336076e-05, + "loss": 3.4935, + "step": 1361408 + }, + { + "epoch": 0.02, + "learning_rate": 2.7703075873825556e-05, + "loss": 3.503, + "step": 1361920 + }, + { + "epoch": 0.02, + "learning_rate": 2.769468992631504e-05, + "loss": 3.4844, + "step": 1362432 + }, + { + "epoch": 0.02, + "learning_rate": 2.768632035760825e-05, + "loss": 3.5022, + "step": 1362944 + }, + { + "epoch": 0.02, + "learning_rate": 2.7677934410097728e-05, + "loss": 3.498, + "step": 1363456 + }, + { + "epoch": 0.02, + "learning_rate": 2.7669548462587208e-05, + "loss": 3.5084, + "step": 1363968 + }, + { + "epoch": 0.02, + "learning_rate": 2.7661162515076688e-05, + "loss": 3.5067, + "step": 1364480 + }, + { + "epoch": 0.02, + "learning_rate": 2.7652792946369904e-05, + "loss": 3.502, + "step": 1364992 + }, + { + "epoch": 0.02, + "learning_rate": 2.764440699885938e-05, + "loss": 3.4913, + "step": 1365504 + }, + { + "epoch": 0.02, + "learning_rate": 2.763602105134886e-05, + "loss": 3.5021, + "step": 1366016 + }, + { + "epoch": 0.02, + "learning_rate": 2.762763510383834e-05, + "loss": 3.5082, + "step": 1366528 + }, + { + "epoch": 0.02, + "learning_rate": 2.761926553513155e-05, + "loss": 3.5096, + "step": 1367040 + }, + { + "epoch": 0.02, + "learning_rate": 2.761087958762103e-05, + "loss": 3.508, + "step": 1367552 + }, + { + "epoch": 0.02, + "learning_rate": 2.760249364011051e-05, + "loss": 3.5099, + "step": 1368064 + }, + { + "epoch": 0.02, + "learning_rate": 2.759410769259999e-05, + "loss": 3.4983, + "step": 1368576 + }, + { + "epoch": 0.02, + "learning_rate": 2.75857381238932e-05, + "loss": 3.5033, + "step": 1369088 + }, + { + "epoch": 0.02, + "learning_rate": 2.757735217638268e-05, + "loss": 3.4963, + "step": 1369600 + }, + { + "epoch": 0.02, + "learning_rate": 2.756896622887216e-05, + "loss": 3.5011, + "step": 1370112 + }, + { + "epoch": 0.02, + "learning_rate": 2.7560596660165377e-05, + "loss": 3.5011, + "step": 1370624 + }, + { + "epoch": 0.02, + "learning_rate": 2.7552210712654854e-05, + "loss": 3.4894, + "step": 1371136 + }, + { + "epoch": 0.02, + "learning_rate": 2.7543824765144334e-05, + "loss": 3.5057, + "step": 1371648 + }, + { + "epoch": 0.02, + "learning_rate": 2.7535438817633814e-05, + "loss": 3.4988, + "step": 1372160 + }, + { + "epoch": 0.02, + "learning_rate": 2.7527052870123294e-05, + "loss": 3.5042, + "step": 1372672 + }, + { + "epoch": 0.02, + "learning_rate": 2.7518666922612774e-05, + "loss": 3.4961, + "step": 1373184 + }, + { + "epoch": 0.02, + "learning_rate": 2.7510297353905983e-05, + "loss": 3.4995, + "step": 1373696 + }, + { + "epoch": 0.03, + "eval_loss": 3.847703695297241, + "eval_runtime": 304.088, + "eval_samples_per_second": 1254.87, + "eval_steps_per_second": 39.216, + "step": 1373760 + }, + { + "epoch": 1.0, + "learning_rate": 2.7501911406395463e-05, + "loss": 3.4912, + "step": 1374208 + }, + { + "epoch": 1.0, + "learning_rate": 2.7493525458884943e-05, + "loss": 3.4959, + "step": 1374720 + }, + { + "epoch": 1.0, + "learning_rate": 2.7485139511374426e-05, + "loss": 3.5038, + "step": 1375232 + }, + { + "epoch": 1.0, + "learning_rate": 2.7476753563863906e-05, + "loss": 3.502, + "step": 1375744 + }, + { + "epoch": 1.0, + "learning_rate": 2.7468367616353386e-05, + "loss": 3.5088, + "step": 1376256 + }, + { + "epoch": 1.0, + "learning_rate": 2.7459981668842866e-05, + "loss": 3.4892, + "step": 1376768 + }, + { + "epoch": 1.0, + "learning_rate": 2.7451595721332346e-05, + "loss": 3.4939, + "step": 1377280 + }, + { + "epoch": 1.0, + "learning_rate": 2.7443226152625555e-05, + "loss": 3.4946, + "step": 1377792 + }, + { + "epoch": 1.0, + "learning_rate": 2.7434840205115035e-05, + "loss": 3.5006, + "step": 1378304 + }, + { + "epoch": 1.0, + "learning_rate": 2.742645425760452e-05, + "loss": 3.5017, + "step": 1378816 + }, + { + "epoch": 1.0, + "learning_rate": 2.7418068310094e-05, + "loss": 3.4992, + "step": 1379328 + }, + { + "epoch": 1.0, + "learning_rate": 2.7409698741387207e-05, + "loss": 3.5026, + "step": 1379840 + }, + { + "epoch": 1.0, + "learning_rate": 2.7401312793876687e-05, + "loss": 3.4865, + "step": 1380352 + }, + { + "epoch": 1.0, + "learning_rate": 2.7392926846366167e-05, + "loss": 3.4897, + "step": 1380864 + }, + { + "epoch": 1.0, + "learning_rate": 2.7384540898855647e-05, + "loss": 3.4944, + "step": 1381376 + }, + { + "epoch": 1.0, + "learning_rate": 2.737617133014886e-05, + "loss": 3.4865, + "step": 1381888 + }, + { + "epoch": 1.0, + "learning_rate": 2.736780176144207e-05, + "loss": 3.4931, + "step": 1382400 + }, + { + "epoch": 1.0, + "learning_rate": 2.735941581393155e-05, + "loss": 3.4967, + "step": 1382912 + }, + { + "epoch": 1.0, + "learning_rate": 2.735102986642103e-05, + "loss": 3.4906, + "step": 1383424 + }, + { + "epoch": 1.0, + "learning_rate": 2.734264391891051e-05, + "loss": 3.5192, + "step": 1383936 + }, + { + "epoch": 1.0, + "learning_rate": 2.733425797139999e-05, + "loss": 3.4974, + "step": 1384448 + }, + { + "epoch": 1.0, + "learning_rate": 2.7325872023889472e-05, + "loss": 3.502, + "step": 1384960 + }, + { + "epoch": 1.0, + "learning_rate": 2.7317486076378952e-05, + "loss": 3.4974, + "step": 1385472 + }, + { + "epoch": 1.0, + "learning_rate": 2.7309100128868432e-05, + "loss": 3.5089, + "step": 1385984 + }, + { + "epoch": 1.0, + "learning_rate": 2.730073056016164e-05, + "loss": 3.4886, + "step": 1386496 + }, + { + "epoch": 1.0, + "learning_rate": 2.729234461265112e-05, + "loss": 3.4957, + "step": 1387008 + }, + { + "epoch": 1.0, + "learning_rate": 2.72839586651406e-05, + "loss": 3.4992, + "step": 1387520 + }, + { + "epoch": 1.0, + "learning_rate": 2.7275589096433813e-05, + "loss": 3.4965, + "step": 1388032 + }, + { + "epoch": 1.0, + "learning_rate": 2.7267203148923293e-05, + "loss": 3.4875, + "step": 1388544 + }, + { + "epoch": 1.01, + "learning_rate": 2.7258817201412773e-05, + "loss": 3.4936, + "step": 1389056 + }, + { + "epoch": 1.01, + "learning_rate": 2.7250431253902253e-05, + "loss": 3.5112, + "step": 1389568 + }, + { + "epoch": 1.01, + "learning_rate": 2.7242061685195462e-05, + "loss": 3.4989, + "step": 1390080 + }, + { + "epoch": 1.01, + "learning_rate": 2.7233675737684942e-05, + "loss": 3.4971, + "step": 1390592 + }, + { + "epoch": 1.01, + "learning_rate": 2.7225289790174426e-05, + "loss": 3.5026, + "step": 1391104 + }, + { + "epoch": 1.01, + "learning_rate": 2.7216903842663906e-05, + "loss": 3.4966, + "step": 1391616 + }, + { + "epoch": 1.01, + "learning_rate": 2.7208534273957115e-05, + "loss": 3.4975, + "step": 1392128 + }, + { + "epoch": 1.01, + "learning_rate": 2.7200148326446595e-05, + "loss": 3.4824, + "step": 1392640 + }, + { + "epoch": 1.01, + "learning_rate": 2.7191762378936075e-05, + "loss": 3.4974, + "step": 1393152 + }, + { + "epoch": 1.01, + "learning_rate": 2.7183376431425555e-05, + "loss": 3.4826, + "step": 1393664 + }, + { + "epoch": 1.01, + "learning_rate": 2.7175006862718767e-05, + "loss": 3.493, + "step": 1394176 + }, + { + "epoch": 1.01, + "learning_rate": 2.7166620915208247e-05, + "loss": 3.4895, + "step": 1394688 + }, + { + "epoch": 1.01, + "learning_rate": 2.7158234967697727e-05, + "loss": 3.5022, + "step": 1395200 + }, + { + "epoch": 1.01, + "learning_rate": 2.7149849020187207e-05, + "loss": 3.4975, + "step": 1395712 + }, + { + "epoch": 1.01, + "learning_rate": 2.7141479451480416e-05, + "loss": 3.4925, + "step": 1396224 + }, + { + "epoch": 1.01, + "learning_rate": 2.7133093503969896e-05, + "loss": 3.501, + "step": 1396736 + }, + { + "epoch": 1.01, + "learning_rate": 2.712470755645938e-05, + "loss": 3.495, + "step": 1397248 + }, + { + "epoch": 1.01, + "learning_rate": 2.711632160894886e-05, + "loss": 3.4989, + "step": 1397760 + }, + { + "epoch": 1.01, + "learning_rate": 2.710795204024207e-05, + "loss": 3.4834, + "step": 1398272 + }, + { + "epoch": 1.01, + "learning_rate": 2.709956609273155e-05, + "loss": 3.4858, + "step": 1398784 + }, + { + "epoch": 1.01, + "learning_rate": 2.709118014522103e-05, + "loss": 3.4978, + "step": 1399296 + }, + { + "epoch": 1.01, + "learning_rate": 2.708279419771051e-05, + "loss": 3.4966, + "step": 1399808 + }, + { + "epoch": 1.01, + "learning_rate": 2.707442462900372e-05, + "loss": 3.495, + "step": 1400320 + }, + { + "epoch": 1.01, + "learning_rate": 2.70660386814932e-05, + "loss": 3.4786, + "step": 1400832 + }, + { + "epoch": 1.01, + "learning_rate": 2.705765273398268e-05, + "loss": 3.4973, + "step": 1401344 + }, + { + "epoch": 1.01, + "learning_rate": 2.7049266786472154e-05, + "loss": 3.4785, + "step": 1401856 + }, + { + "epoch": 1.01, + "learning_rate": 2.704089721776537e-05, + "loss": 3.5063, + "step": 1402368 + }, + { + "epoch": 1.01, + "learning_rate": 2.703251127025485e-05, + "loss": 3.4804, + "step": 1402880 + }, + { + "epoch": 1.01, + "learning_rate": 2.7024125322744333e-05, + "loss": 3.4984, + "step": 1403392 + }, + { + "epoch": 1.01, + "learning_rate": 2.7015739375233806e-05, + "loss": 3.4908, + "step": 1403904 + }, + { + "epoch": 1.01, + "learning_rate": 2.7007369806527022e-05, + "loss": 3.4863, + "step": 1404416 + }, + { + "epoch": 1.01, + "learning_rate": 2.6998983859016502e-05, + "loss": 3.4885, + "step": 1404928 + }, + { + "epoch": 1.01, + "learning_rate": 2.6990597911505982e-05, + "loss": 3.4919, + "step": 1405440 + }, + { + "epoch": 1.01, + "learning_rate": 2.698221196399546e-05, + "loss": 3.4731, + "step": 1405952 + }, + { + "epoch": 1.01, + "learning_rate": 2.6973842395288674e-05, + "loss": 3.4839, + "step": 1406464 + }, + { + "epoch": 1.01, + "learning_rate": 2.6965456447778154e-05, + "loss": 3.4922, + "step": 1406976 + }, + { + "epoch": 1.01, + "learning_rate": 2.6957070500267628e-05, + "loss": 3.4941, + "step": 1407488 + }, + { + "epoch": 1.01, + "learning_rate": 2.6948684552757108e-05, + "loss": 3.4795, + "step": 1408000 + }, + { + "epoch": 1.01, + "learning_rate": 2.6940314984050323e-05, + "loss": 3.4858, + "step": 1408512 + }, + { + "epoch": 1.01, + "learning_rate": 2.6931929036539803e-05, + "loss": 3.4841, + "step": 1409024 + }, + { + "epoch": 1.01, + "learning_rate": 2.692354308902928e-05, + "loss": 3.4859, + "step": 1409536 + }, + { + "epoch": 1.01, + "learning_rate": 2.691515714151876e-05, + "loss": 3.489, + "step": 1410048 + }, + { + "epoch": 1.01, + "learning_rate": 2.6906787572811976e-05, + "loss": 3.4931, + "step": 1410560 + }, + { + "epoch": 1.01, + "learning_rate": 2.6898401625301456e-05, + "loss": 3.5047, + "step": 1411072 + }, + { + "epoch": 1.01, + "learning_rate": 2.6890015677790932e-05, + "loss": 3.4944, + "step": 1411584 + }, + { + "epoch": 1.01, + "learning_rate": 2.6881629730280412e-05, + "loss": 3.4985, + "step": 1412096 + }, + { + "epoch": 1.01, + "learning_rate": 2.6873260161573628e-05, + "loss": 3.4838, + "step": 1412608 + }, + { + "epoch": 1.01, + "learning_rate": 2.68648742140631e-05, + "loss": 3.49, + "step": 1413120 + }, + { + "epoch": 1.01, + "learning_rate": 2.685648826655258e-05, + "loss": 3.4925, + "step": 1413632 + }, + { + "epoch": 1.01, + "learning_rate": 2.684810231904206e-05, + "loss": 3.4789, + "step": 1414144 + }, + { + "epoch": 1.01, + "learning_rate": 2.683974912913901e-05, + "loss": 3.4935, + "step": 1414656 + }, + { + "epoch": 1.01, + "learning_rate": 2.683136318162849e-05, + "loss": 3.4931, + "step": 1415168 + }, + { + "epoch": 1.01, + "learning_rate": 2.682297723411797e-05, + "loss": 3.4974, + "step": 1415680 + }, + { + "epoch": 1.01, + "learning_rate": 2.681459128660745e-05, + "loss": 3.4895, + "step": 1416192 + }, + { + "epoch": 1.01, + "learning_rate": 2.680620533909693e-05, + "loss": 3.4766, + "step": 1416704 + }, + { + "epoch": 1.01, + "learning_rate": 2.6797819391586403e-05, + "loss": 3.4832, + "step": 1417216 + }, + { + "epoch": 1.01, + "learning_rate": 2.6789433444075886e-05, + "loss": 3.4965, + "step": 1417728 + }, + { + "epoch": 1.01, + "learning_rate": 2.6781047496565366e-05, + "loss": 3.4951, + "step": 1418240 + }, + { + "epoch": 1.01, + "learning_rate": 2.6772677927858575e-05, + "loss": 3.4927, + "step": 1418752 + }, + { + "epoch": 1.01, + "learning_rate": 2.6764291980348055e-05, + "loss": 3.4978, + "step": 1419264 + }, + { + "epoch": 1.02, + "learning_rate": 2.6755906032837535e-05, + "loss": 3.4984, + "step": 1419776 + }, + { + "epoch": 1.02, + "learning_rate": 2.6747520085327015e-05, + "loss": 3.4793, + "step": 1420288 + }, + { + "epoch": 1.02, + "learning_rate": 2.6739150516620227e-05, + "loss": 3.4947, + "step": 1420800 + }, + { + "epoch": 1.02, + "learning_rate": 2.6730764569109707e-05, + "loss": 3.492, + "step": 1421312 + }, + { + "epoch": 1.02, + "learning_rate": 2.6722378621599187e-05, + "loss": 3.4864, + "step": 1421824 + }, + { + "epoch": 1.02, + "learning_rate": 2.6713992674088667e-05, + "loss": 3.5022, + "step": 1422336 + }, + { + "epoch": 1.02, + "learning_rate": 2.6705623105381876e-05, + "loss": 3.4886, + "step": 1422848 + }, + { + "epoch": 1.02, + "learning_rate": 2.6697237157871356e-05, + "loss": 3.4799, + "step": 1423360 + }, + { + "epoch": 1.02, + "learning_rate": 2.6688851210360836e-05, + "loss": 3.4855, + "step": 1423872 + }, + { + "epoch": 1.02, + "learning_rate": 2.668046526285032e-05, + "loss": 3.4973, + "step": 1424384 + }, + { + "epoch": 1.02, + "learning_rate": 2.667209569414353e-05, + "loss": 3.4952, + "step": 1424896 + }, + { + "epoch": 1.02, + "learning_rate": 2.666370974663301e-05, + "loss": 3.4905, + "step": 1425408 + }, + { + "epoch": 1.02, + "learning_rate": 2.665532379912249e-05, + "loss": 3.4828, + "step": 1425920 + }, + { + "epoch": 1.02, + "learning_rate": 2.664693785161197e-05, + "loss": 3.4844, + "step": 1426432 + }, + { + "epoch": 1.02, + "learning_rate": 2.663856828290518e-05, + "loss": 3.5009, + "step": 1426944 + }, + { + "epoch": 1.02, + "learning_rate": 2.663018233539466e-05, + "loss": 3.4713, + "step": 1427456 + }, + { + "epoch": 1.02, + "learning_rate": 2.662179638788414e-05, + "loss": 3.4881, + "step": 1427968 + }, + { + "epoch": 1.02, + "learning_rate": 2.661341044037362e-05, + "loss": 3.4961, + "step": 1428480 + }, + { + "epoch": 1.02, + "learning_rate": 2.660504087166683e-05, + "loss": 3.4889, + "step": 1428992 + }, + { + "epoch": 1.02, + "learning_rate": 2.659665492415631e-05, + "loss": 3.4834, + "step": 1429504 + }, + { + "epoch": 1.02, + "learning_rate": 2.658826897664579e-05, + "loss": 3.494, + "step": 1430016 + }, + { + "epoch": 1.02, + "learning_rate": 2.6579883029135273e-05, + "loss": 3.4856, + "step": 1430528 + }, + { + "epoch": 1.02, + "learning_rate": 2.6571513460428482e-05, + "loss": 3.493, + "step": 1431040 + }, + { + "epoch": 1.02, + "learning_rate": 2.6563127512917962e-05, + "loss": 3.488, + "step": 1431552 + }, + { + "epoch": 1.02, + "learning_rate": 2.6554741565407442e-05, + "loss": 3.4886, + "step": 1432064 + }, + { + "epoch": 1.02, + "learning_rate": 2.6546355617896922e-05, + "loss": 3.4967, + "step": 1432576 + }, + { + "epoch": 1.02, + "learning_rate": 2.6537986049190135e-05, + "loss": 3.4986, + "step": 1433088 + }, + { + "epoch": 1.02, + "learning_rate": 2.6529600101679615e-05, + "loss": 3.4918, + "step": 1433600 + }, + { + "epoch": 1.02, + "learning_rate": 2.6521214154169095e-05, + "loss": 3.4829, + "step": 1434112 + }, + { + "epoch": 1.02, + "learning_rate": 2.6512828206658575e-05, + "loss": 3.4876, + "step": 1434624 + }, + { + "epoch": 1.02, + "learning_rate": 2.6504458637951784e-05, + "loss": 3.4858, + "step": 1435136 + }, + { + "epoch": 1.02, + "learning_rate": 2.6496072690441264e-05, + "loss": 3.4771, + "step": 1435648 + }, + { + "epoch": 1.02, + "learning_rate": 2.6487686742930744e-05, + "loss": 3.4915, + "step": 1436160 + }, + { + "epoch": 1.02, + "learning_rate": 2.6479300795420227e-05, + "loss": 3.4783, + "step": 1436672 + }, + { + "epoch": 1.02, + "learning_rate": 2.6470931226713436e-05, + "loss": 3.4934, + "step": 1437184 + }, + { + "epoch": 1.02, + "learning_rate": 2.6462545279202916e-05, + "loss": 3.4804, + "step": 1437696 + }, + { + "epoch": 1.02, + "learning_rate": 2.6454159331692396e-05, + "loss": 3.4925, + "step": 1438208 + }, + { + "epoch": 1.02, + "learning_rate": 2.6445773384181876e-05, + "loss": 3.4761, + "step": 1438720 + }, + { + "epoch": 1.02, + "learning_rate": 2.643740381547509e-05, + "loss": 3.488, + "step": 1439232 + }, + { + "epoch": 1.02, + "learning_rate": 2.642901786796457e-05, + "loss": 3.4832, + "step": 1439744 + }, + { + "epoch": 1.02, + "learning_rate": 2.6420631920454048e-05, + "loss": 3.4976, + "step": 1440256 + }, + { + "epoch": 1.02, + "learning_rate": 2.6412245972943528e-05, + "loss": 3.4968, + "step": 1440768 + }, + { + "epoch": 1.02, + "learning_rate": 2.6403876404236737e-05, + "loss": 3.489, + "step": 1441280 + }, + { + "epoch": 1.02, + "learning_rate": 2.6395490456726217e-05, + "loss": 3.4767, + "step": 1441792 + }, + { + "epoch": 1.02, + "learning_rate": 2.6387104509215697e-05, + "loss": 3.4885, + "step": 1442304 + }, + { + "epoch": 1.02, + "learning_rate": 2.637873494050891e-05, + "loss": 3.4951, + "step": 1442816 + }, + { + "epoch": 1.02, + "learning_rate": 2.637034899299839e-05, + "loss": 3.4979, + "step": 1443328 + }, + { + "epoch": 1.02, + "learning_rate": 2.636196304548787e-05, + "loss": 3.4925, + "step": 1443840 + }, + { + "epoch": 1.02, + "learning_rate": 2.635357709797735e-05, + "loss": 3.4979, + "step": 1444352 + }, + { + "epoch": 1.02, + "learning_rate": 2.634520752927056e-05, + "loss": 3.4876, + "step": 1444864 + }, + { + "epoch": 1.02, + "learning_rate": 2.6336821581760042e-05, + "loss": 3.4936, + "step": 1445376 + }, + { + "epoch": 1.02, + "learning_rate": 2.6328435634249522e-05, + "loss": 3.4834, + "step": 1445888 + }, + { + "epoch": 1.02, + "learning_rate": 2.6320049686739002e-05, + "loss": 3.4845, + "step": 1446400 + }, + { + "epoch": 1.02, + "learning_rate": 2.631168011803221e-05, + "loss": 3.4914, + "step": 1446912 + }, + { + "epoch": 1.02, + "learning_rate": 2.630329417052169e-05, + "loss": 3.4774, + "step": 1447424 + }, + { + "epoch": 1.02, + "learning_rate": 2.629490822301117e-05, + "loss": 3.4871, + "step": 1447936 + }, + { + "epoch": 1.02, + "learning_rate": 2.628652227550065e-05, + "loss": 3.4883, + "step": 1448448 + }, + { + "epoch": 1.02, + "learning_rate": 2.6278136327990134e-05, + "loss": 3.4865, + "step": 1448960 + }, + { + "epoch": 1.02, + "learning_rate": 2.6269750380479614e-05, + "loss": 3.4837, + "step": 1449472 + }, + { + "epoch": 1.02, + "learning_rate": 2.6261364432969094e-05, + "loss": 3.484, + "step": 1449984 + }, + { + "epoch": 1.03, + "eval_loss": 3.8495030403137207, + "eval_runtime": 305.5805, + "eval_samples_per_second": 1248.741, + "eval_steps_per_second": 39.024, + "step": 1450080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6252978485458574e-05, + "loss": 3.4756, + "step": 1450496 + }, + { + "epoch": 0.0, + "learning_rate": 2.6244592537948054e-05, + "loss": 3.4795, + "step": 1451008 + }, + { + "epoch": 0.0, + "learning_rate": 2.6236206590437534e-05, + "loss": 3.4945, + "step": 1451520 + }, + { + "epoch": 0.0, + "learning_rate": 2.622782064292701e-05, + "loss": 3.4867, + "step": 1452032 + }, + { + "epoch": 0.0, + "learning_rate": 2.6219451074220226e-05, + "loss": 3.4987, + "step": 1452544 + }, + { + "epoch": 0.0, + "learning_rate": 2.6211065126709706e-05, + "loss": 3.4756, + "step": 1453056 + }, + { + "epoch": 0.0, + "learning_rate": 2.620267917919918e-05, + "loss": 3.483, + "step": 1453568 + }, + { + "epoch": 0.0, + "learning_rate": 2.619429323168866e-05, + "loss": 3.4793, + "step": 1454080 + }, + { + "epoch": 0.0, + "learning_rate": 2.6185923662981875e-05, + "loss": 3.4917, + "step": 1454592 + }, + { + "epoch": 0.0, + "learning_rate": 2.6177537715471355e-05, + "loss": 3.4903, + "step": 1455104 + }, + { + "epoch": 0.0, + "learning_rate": 2.6169151767960832e-05, + "loss": 3.4874, + "step": 1455616 + }, + { + "epoch": 0.0, + "learning_rate": 2.6160765820450312e-05, + "loss": 3.4877, + "step": 1456128 + }, + { + "epoch": 0.0, + "learning_rate": 2.6152396251743528e-05, + "loss": 3.4727, + "step": 1456640 + }, + { + "epoch": 0.0, + "learning_rate": 2.6144010304233008e-05, + "loss": 3.4777, + "step": 1457152 + }, + { + "epoch": 0.0, + "learning_rate": 2.613562435672248e-05, + "loss": 3.4825, + "step": 1457664 + }, + { + "epoch": 0.0, + "learning_rate": 2.6127254788015697e-05, + "loss": 3.4775, + "step": 1458176 + }, + { + "epoch": 0.0, + "learning_rate": 2.611888521930891e-05, + "loss": 3.4781, + "step": 1458688 + }, + { + "epoch": 0.0, + "learning_rate": 2.611049927179839e-05, + "loss": 3.4846, + "step": 1459200 + }, + { + "epoch": 0.0, + "learning_rate": 2.610211332428787e-05, + "loss": 3.476, + "step": 1459712 + }, + { + "epoch": 0.0, + "learning_rate": 2.609372737677735e-05, + "loss": 3.5089, + "step": 1460224 + }, + { + "epoch": 0.0, + "learning_rate": 2.608534142926683e-05, + "loss": 3.4853, + "step": 1460736 + }, + { + "epoch": 0.0, + "learning_rate": 2.6076955481756306e-05, + "loss": 3.4861, + "step": 1461248 + }, + { + "epoch": 0.0, + "learning_rate": 2.6068569534245786e-05, + "loss": 3.4896, + "step": 1461760 + }, + { + "epoch": 0.0, + "learning_rate": 2.6060183586735266e-05, + "loss": 3.4932, + "step": 1462272 + }, + { + "epoch": 0.0, + "learning_rate": 2.6051814018028475e-05, + "loss": 3.4758, + "step": 1462784 + }, + { + "epoch": 0.0, + "learning_rate": 2.6043428070517955e-05, + "loss": 3.489, + "step": 1463296 + }, + { + "epoch": 0.0, + "learning_rate": 2.6035042123007435e-05, + "loss": 3.4809, + "step": 1463808 + }, + { + "epoch": 0.0, + "learning_rate": 2.6026656175496918e-05, + "loss": 3.4845, + "step": 1464320 + }, + { + "epoch": 0.0, + "learning_rate": 2.6018286606790127e-05, + "loss": 3.4726, + "step": 1464832 + }, + { + "epoch": 0.01, + "learning_rate": 2.6009900659279607e-05, + "loss": 3.4835, + "step": 1465344 + }, + { + "epoch": 0.01, + "learning_rate": 2.6001531090572823e-05, + "loss": 3.4979, + "step": 1465856 + }, + { + "epoch": 0.01, + "learning_rate": 2.5993145143062303e-05, + "loss": 3.4855, + "step": 1466368 + }, + { + "epoch": 0.01, + "learning_rate": 2.598475919555178e-05, + "loss": 3.488, + "step": 1466880 + }, + { + "epoch": 0.01, + "learning_rate": 2.597637324804126e-05, + "loss": 3.4893, + "step": 1467392 + }, + { + "epoch": 0.01, + "learning_rate": 2.596798730053074e-05, + "loss": 3.4784, + "step": 1467904 + }, + { + "epoch": 0.01, + "learning_rate": 2.595960135302022e-05, + "loss": 3.4899, + "step": 1468416 + }, + { + "epoch": 0.01, + "learning_rate": 2.59512154055097e-05, + "loss": 3.4684, + "step": 1468928 + }, + { + "epoch": 0.01, + "learning_rate": 2.594282945799918e-05, + "loss": 3.4844, + "step": 1469440 + }, + { + "epoch": 0.01, + "learning_rate": 2.5934459889292388e-05, + "loss": 3.4677, + "step": 1469952 + }, + { + "epoch": 0.01, + "learning_rate": 2.5926073941781868e-05, + "loss": 3.4828, + "step": 1470464 + }, + { + "epoch": 0.01, + "learning_rate": 2.591768799427135e-05, + "loss": 3.4775, + "step": 1470976 + }, + { + "epoch": 0.01, + "learning_rate": 2.590930204676083e-05, + "loss": 3.4904, + "step": 1471488 + }, + { + "epoch": 0.01, + "learning_rate": 2.590093247805404e-05, + "loss": 3.4856, + "step": 1472000 + }, + { + "epoch": 0.01, + "learning_rate": 2.589254653054352e-05, + "loss": 3.4805, + "step": 1472512 + }, + { + "epoch": 0.01, + "learning_rate": 2.5884160583033e-05, + "loss": 3.4877, + "step": 1473024 + }, + { + "epoch": 0.01, + "learning_rate": 2.587577463552248e-05, + "loss": 3.4831, + "step": 1473536 + }, + { + "epoch": 0.01, + "learning_rate": 2.5867405066815693e-05, + "loss": 3.4821, + "step": 1474048 + }, + { + "epoch": 0.01, + "learning_rate": 2.5859019119305173e-05, + "loss": 3.4773, + "step": 1474560 + }, + { + "epoch": 0.01, + "learning_rate": 2.5850633171794653e-05, + "loss": 3.4672, + "step": 1475072 + }, + { + "epoch": 0.01, + "learning_rate": 2.5842247224284133e-05, + "loss": 3.4861, + "step": 1475584 + }, + { + "epoch": 0.01, + "learning_rate": 2.5833877655577342e-05, + "loss": 3.4842, + "step": 1476096 + }, + { + "epoch": 0.01, + "learning_rate": 2.5825491708066822e-05, + "loss": 3.4838, + "step": 1476608 + }, + { + "epoch": 0.01, + "learning_rate": 2.5817105760556305e-05, + "loss": 3.469, + "step": 1477120 + }, + { + "epoch": 0.01, + "learning_rate": 2.5808719813045785e-05, + "loss": 3.4885, + "step": 1477632 + }, + { + "epoch": 0.01, + "learning_rate": 2.5800350244338994e-05, + "loss": 3.463, + "step": 1478144 + }, + { + "epoch": 0.01, + "learning_rate": 2.5791980675632203e-05, + "loss": 3.4923, + "step": 1478656 + }, + { + "epoch": 0.01, + "learning_rate": 2.5783594728121683e-05, + "loss": 3.4702, + "step": 1479168 + }, + { + "epoch": 0.01, + "learning_rate": 2.5775208780611167e-05, + "loss": 3.4819, + "step": 1479680 + }, + { + "epoch": 0.01, + "learning_rate": 2.5766822833100647e-05, + "loss": 3.4809, + "step": 1480192 + }, + { + "epoch": 0.01, + "learning_rate": 2.5758436885590127e-05, + "loss": 3.4749, + "step": 1480704 + }, + { + "epoch": 0.01, + "learning_rate": 2.5750050938079607e-05, + "loss": 3.4735, + "step": 1481216 + }, + { + "epoch": 0.01, + "learning_rate": 2.5741664990569087e-05, + "loss": 3.4845, + "step": 1481728 + }, + { + "epoch": 0.01, + "learning_rate": 2.5733279043058566e-05, + "loss": 3.4611, + "step": 1482240 + }, + { + "epoch": 0.01, + "learning_rate": 2.5724909474351776e-05, + "loss": 3.4676, + "step": 1482752 + }, + { + "epoch": 0.01, + "learning_rate": 2.571652352684126e-05, + "loss": 3.4828, + "step": 1483264 + }, + { + "epoch": 0.01, + "learning_rate": 2.570813757933074e-05, + "loss": 3.48, + "step": 1483776 + }, + { + "epoch": 0.01, + "learning_rate": 2.569975163182022e-05, + "loss": 3.4697, + "step": 1484288 + }, + { + "epoch": 0.01, + "learning_rate": 2.5691382063113428e-05, + "loss": 3.4723, + "step": 1484800 + }, + { + "epoch": 0.01, + "learning_rate": 2.5682996115602908e-05, + "loss": 3.4664, + "step": 1485312 + }, + { + "epoch": 0.01, + "learning_rate": 2.5674610168092388e-05, + "loss": 3.4731, + "step": 1485824 + }, + { + "epoch": 0.01, + "learning_rate": 2.5666224220581868e-05, + "loss": 3.4799, + "step": 1486336 + }, + { + "epoch": 0.01, + "learning_rate": 2.565785465187508e-05, + "loss": 3.4805, + "step": 1486848 + }, + { + "epoch": 0.01, + "learning_rate": 2.564946870436456e-05, + "loss": 3.4915, + "step": 1487360 + }, + { + "epoch": 0.01, + "learning_rate": 2.564108275685404e-05, + "loss": 3.481, + "step": 1487872 + }, + { + "epoch": 0.01, + "learning_rate": 2.563269680934352e-05, + "loss": 3.4899, + "step": 1488384 + }, + { + "epoch": 0.01, + "learning_rate": 2.562432724063673e-05, + "loss": 3.4684, + "step": 1488896 + }, + { + "epoch": 0.01, + "learning_rate": 2.5615941293126213e-05, + "loss": 3.4763, + "step": 1489408 + }, + { + "epoch": 0.01, + "learning_rate": 2.5607555345615693e-05, + "loss": 3.4802, + "step": 1489920 + }, + { + "epoch": 0.01, + "learning_rate": 2.5599169398105172e-05, + "loss": 3.4649, + "step": 1490432 + }, + { + "epoch": 0.01, + "learning_rate": 2.559079982939838e-05, + "loss": 3.4837, + "step": 1490944 + }, + { + "epoch": 0.01, + "learning_rate": 2.558241388188786e-05, + "loss": 3.4785, + "step": 1491456 + }, + { + "epoch": 0.01, + "learning_rate": 2.557402793437734e-05, + "loss": 3.4836, + "step": 1491968 + }, + { + "epoch": 0.01, + "learning_rate": 2.556564198686682e-05, + "loss": 3.4789, + "step": 1492480 + }, + { + "epoch": 0.01, + "learning_rate": 2.5557272418160034e-05, + "loss": 3.4667, + "step": 1492992 + }, + { + "epoch": 0.01, + "learning_rate": 2.5548886470649514e-05, + "loss": 3.4749, + "step": 1493504 + }, + { + "epoch": 0.01, + "learning_rate": 2.5540500523138994e-05, + "loss": 3.4806, + "step": 1494016 + }, + { + "epoch": 0.01, + "learning_rate": 2.5532130954432203e-05, + "loss": 3.4828, + "step": 1494528 + }, + { + "epoch": 0.01, + "learning_rate": 2.5523745006921683e-05, + "loss": 3.4817, + "step": 1495040 + }, + { + "epoch": 0.01, + "learning_rate": 2.5515359059411166e-05, + "loss": 3.481, + "step": 1495552 + }, + { + "epoch": 0.02, + "learning_rate": 2.5506973111900646e-05, + "loss": 3.489, + "step": 1496064 + }, + { + "epoch": 0.02, + "learning_rate": 2.5498603543193855e-05, + "loss": 3.4661, + "step": 1496576 + }, + { + "epoch": 0.02, + "learning_rate": 2.5490217595683335e-05, + "loss": 3.4834, + "step": 1497088 + }, + { + "epoch": 0.02, + "learning_rate": 2.5481831648172815e-05, + "loss": 3.4756, + "step": 1497600 + }, + { + "epoch": 0.02, + "learning_rate": 2.5473445700662295e-05, + "loss": 3.477, + "step": 1498112 + }, + { + "epoch": 0.02, + "learning_rate": 2.5465076131955508e-05, + "loss": 3.4901, + "step": 1498624 + }, + { + "epoch": 0.02, + "learning_rate": 2.5456690184444988e-05, + "loss": 3.4779, + "step": 1499136 + }, + { + "epoch": 0.02, + "learning_rate": 2.5448304236934468e-05, + "loss": 3.4668, + "step": 1499648 + }, + { + "epoch": 0.02, + "learning_rate": 2.5439918289423948e-05, + "loss": 3.4755, + "step": 1500160 + }, + { + "epoch": 0.02, + "learning_rate": 2.5431548720717157e-05, + "loss": 3.4831, + "step": 1500672 + }, + { + "epoch": 0.02, + "learning_rate": 2.5423162773206637e-05, + "loss": 3.4843, + "step": 1501184 + }, + { + "epoch": 0.02, + "learning_rate": 2.541477682569612e-05, + "loss": 3.4781, + "step": 1501696 + }, + { + "epoch": 0.02, + "learning_rate": 2.54063908781856e-05, + "loss": 3.4703, + "step": 1502208 + }, + { + "epoch": 0.02, + "learning_rate": 2.539802130947881e-05, + "loss": 3.4737, + "step": 1502720 + }, + { + "epoch": 0.02, + "learning_rate": 2.538963536196829e-05, + "loss": 3.4859, + "step": 1503232 + }, + { + "epoch": 0.02, + "learning_rate": 2.538124941445777e-05, + "loss": 3.4597, + "step": 1503744 + }, + { + "epoch": 0.02, + "learning_rate": 2.537286346694725e-05, + "loss": 3.4741, + "step": 1504256 + }, + { + "epoch": 0.02, + "learning_rate": 2.536449389824046e-05, + "loss": 3.4836, + "step": 1504768 + }, + { + "epoch": 0.02, + "learning_rate": 2.535610795072994e-05, + "loss": 3.4777, + "step": 1505280 + }, + { + "epoch": 0.02, + "learning_rate": 2.534772200321942e-05, + "loss": 3.4699, + "step": 1505792 + }, + { + "epoch": 0.02, + "learning_rate": 2.53393360557089e-05, + "loss": 3.4836, + "step": 1506304 + }, + { + "epoch": 0.02, + "learning_rate": 2.533096648700211e-05, + "loss": 3.4739, + "step": 1506816 + }, + { + "epoch": 0.02, + "learning_rate": 2.5322596918295323e-05, + "loss": 3.4775, + "step": 1507328 + }, + { + "epoch": 0.02, + "learning_rate": 2.5314210970784803e-05, + "loss": 3.4775, + "step": 1507840 + }, + { + "epoch": 0.02, + "learning_rate": 2.5305825023274283e-05, + "loss": 3.475, + "step": 1508352 + }, + { + "epoch": 0.02, + "learning_rate": 2.5297439075763763e-05, + "loss": 3.4893, + "step": 1508864 + }, + { + "epoch": 0.02, + "learning_rate": 2.5289053128253243e-05, + "loss": 3.4803, + "step": 1509376 + }, + { + "epoch": 0.02, + "learning_rate": 2.5280667180742723e-05, + "loss": 3.4797, + "step": 1509888 + }, + { + "epoch": 0.02, + "learning_rate": 2.5272281233232202e-05, + "loss": 3.4705, + "step": 1510400 + }, + { + "epoch": 0.02, + "learning_rate": 2.5263911664525415e-05, + "loss": 3.4758, + "step": 1510912 + }, + { + "epoch": 0.02, + "learning_rate": 2.5255525717014895e-05, + "loss": 3.4775, + "step": 1511424 + }, + { + "epoch": 0.02, + "learning_rate": 2.5247139769504375e-05, + "loss": 3.4668, + "step": 1511936 + }, + { + "epoch": 0.02, + "learning_rate": 2.5238753821993855e-05, + "loss": 3.4768, + "step": 1512448 + }, + { + "epoch": 0.02, + "learning_rate": 2.5230384253287064e-05, + "loss": 3.4701, + "step": 1512960 + }, + { + "epoch": 0.02, + "learning_rate": 2.5221998305776544e-05, + "loss": 3.4792, + "step": 1513472 + }, + { + "epoch": 0.02, + "learning_rate": 2.5213612358266024e-05, + "loss": 3.4694, + "step": 1513984 + }, + { + "epoch": 0.02, + "learning_rate": 2.5205242789559236e-05, + "loss": 3.4807, + "step": 1514496 + }, + { + "epoch": 0.02, + "learning_rate": 2.5196856842048716e-05, + "loss": 3.4606, + "step": 1515008 + }, + { + "epoch": 0.02, + "learning_rate": 2.5188470894538196e-05, + "loss": 3.478, + "step": 1515520 + }, + { + "epoch": 0.02, + "learning_rate": 2.5180084947027676e-05, + "loss": 3.474, + "step": 1516032 + }, + { + "epoch": 0.02, + "learning_rate": 2.5171698999517153e-05, + "loss": 3.4822, + "step": 1516544 + }, + { + "epoch": 0.02, + "learning_rate": 2.5163313052006633e-05, + "loss": 3.4826, + "step": 1517056 + }, + { + "epoch": 0.02, + "learning_rate": 2.5154927104496113e-05, + "loss": 3.4825, + "step": 1517568 + }, + { + "epoch": 0.02, + "learning_rate": 2.5146541156985593e-05, + "loss": 3.4633, + "step": 1518080 + }, + { + "epoch": 0.02, + "learning_rate": 2.5138171588278802e-05, + "loss": 3.4789, + "step": 1518592 + }, + { + "epoch": 0.02, + "learning_rate": 2.512978564076828e-05, + "loss": 3.4805, + "step": 1519104 + }, + { + "epoch": 0.02, + "learning_rate": 2.512139969325776e-05, + "loss": 3.486, + "step": 1519616 + }, + { + "epoch": 0.02, + "learning_rate": 2.5113030124550974e-05, + "loss": 3.4824, + "step": 1520128 + }, + { + "epoch": 0.02, + "learning_rate": 2.5104644177040454e-05, + "loss": 3.4809, + "step": 1520640 + }, + { + "epoch": 0.02, + "learning_rate": 2.5096258229529934e-05, + "loss": 3.4772, + "step": 1521152 + }, + { + "epoch": 0.02, + "learning_rate": 2.5087872282019414e-05, + "loss": 3.4851, + "step": 1521664 + }, + { + "epoch": 0.02, + "learning_rate": 2.5079502713312626e-05, + "loss": 3.4701, + "step": 1522176 + }, + { + "epoch": 0.02, + "learning_rate": 2.5071116765802106e-05, + "loss": 3.4738, + "step": 1522688 + }, + { + "epoch": 0.02, + "learning_rate": 2.5062747197095322e-05, + "loss": 3.4783, + "step": 1523200 + }, + { + "epoch": 0.02, + "learning_rate": 2.5054361249584802e-05, + "loss": 3.4683, + "step": 1523712 + }, + { + "epoch": 0.02, + "learning_rate": 2.5045975302074275e-05, + "loss": 3.4737, + "step": 1524224 + }, + { + "epoch": 0.02, + "learning_rate": 2.5037589354563755e-05, + "loss": 3.4799, + "step": 1524736 + }, + { + "epoch": 0.02, + "learning_rate": 2.5029203407053235e-05, + "loss": 3.4745, + "step": 1525248 + }, + { + "epoch": 0.02, + "learning_rate": 2.5020817459542715e-05, + "loss": 3.47, + "step": 1525760 + }, + { + "epoch": 0.02, + "learning_rate": 2.5012447890835928e-05, + "loss": 3.4794, + "step": 1526272 + }, + { + "epoch": 0.03, + "eval_loss": 3.850419044494629, + "eval_runtime": 305.2365, + "eval_samples_per_second": 1250.149, + "eval_steps_per_second": 39.068, + "step": 1526400 + }, + { + "epoch": 1.0, + "learning_rate": 2.5004061943325408e-05, + "loss": 3.4664, + "step": 1526784 + }, + { + "epoch": 1.0, + "learning_rate": 2.499567599581489e-05, + "loss": 3.4708, + "step": 1527296 + }, + { + "epoch": 1.0, + "learning_rate": 2.4987290048304368e-05, + "loss": 3.4798, + "step": 1527808 + }, + { + "epoch": 1.0, + "learning_rate": 2.4978904100793848e-05, + "loss": 3.4762, + "step": 1528320 + }, + { + "epoch": 1.0, + "learning_rate": 2.4970518153283328e-05, + "loss": 3.4881, + "step": 1528832 + }, + { + "epoch": 1.0, + "learning_rate": 2.4962132205772808e-05, + "loss": 3.4626, + "step": 1529344 + }, + { + "epoch": 1.0, + "learning_rate": 2.495374625826229e-05, + "loss": 3.4701, + "step": 1529856 + }, + { + "epoch": 1.0, + "learning_rate": 2.49453766895555e-05, + "loss": 3.4643, + "step": 1530368 + }, + { + "epoch": 1.0, + "learning_rate": 2.493699074204498e-05, + "loss": 3.4787, + "step": 1530880 + }, + { + "epoch": 1.0, + "learning_rate": 2.492860479453446e-05, + "loss": 3.4799, + "step": 1531392 + }, + { + "epoch": 1.0, + "learning_rate": 2.492021884702394e-05, + "loss": 3.4681, + "step": 1531904 + }, + { + "epoch": 1.0, + "learning_rate": 2.4911849278317152e-05, + "loss": 3.4836, + "step": 1532416 + }, + { + "epoch": 1.0, + "learning_rate": 2.4903463330806632e-05, + "loss": 3.4602, + "step": 1532928 + }, + { + "epoch": 1.0, + "learning_rate": 2.4895077383296112e-05, + "loss": 3.4679, + "step": 1533440 + }, + { + "epoch": 1.0, + "learning_rate": 2.4886691435785592e-05, + "loss": 3.4739, + "step": 1533952 + }, + { + "epoch": 1.0, + "learning_rate": 2.48783218670788e-05, + "loss": 3.4646, + "step": 1534464 + }, + { + "epoch": 1.0, + "learning_rate": 2.4869952298372014e-05, + "loss": 3.4651, + "step": 1534976 + }, + { + "epoch": 1.0, + "learning_rate": 2.4861566350861494e-05, + "loss": 3.4731, + "step": 1535488 + }, + { + "epoch": 1.0, + "learning_rate": 2.4853180403350974e-05, + "loss": 3.4675, + "step": 1536000 + }, + { + "epoch": 1.0, + "learning_rate": 2.4844794455840454e-05, + "loss": 3.4938, + "step": 1536512 + }, + { + "epoch": 1.0, + "learning_rate": 2.4836408508329934e-05, + "loss": 3.4746, + "step": 1537024 + }, + { + "epoch": 1.0, + "learning_rate": 2.4828022560819414e-05, + "loss": 3.4717, + "step": 1537536 + }, + { + "epoch": 1.0, + "learning_rate": 2.4819636613308894e-05, + "loss": 3.4805, + "step": 1538048 + }, + { + "epoch": 1.0, + "learning_rate": 2.481125066579837e-05, + "loss": 3.4802, + "step": 1538560 + }, + { + "epoch": 1.0, + "learning_rate": 2.4802881097091586e-05, + "loss": 3.4653, + "step": 1539072 + }, + { + "epoch": 1.0, + "learning_rate": 2.4794495149581066e-05, + "loss": 3.4786, + "step": 1539584 + }, + { + "epoch": 1.0, + "learning_rate": 2.4786109202070542e-05, + "loss": 3.4699, + "step": 1540096 + }, + { + "epoch": 1.0, + "learning_rate": 2.4777723254560022e-05, + "loss": 3.472, + "step": 1540608 + }, + { + "epoch": 1.0, + "learning_rate": 2.4769353685853235e-05, + "loss": 3.4598, + "step": 1541120 + }, + { + "epoch": 1.0, + "learning_rate": 2.4760967738342715e-05, + "loss": 3.4706, + "step": 1541632 + }, + { + "epoch": 1.01, + "learning_rate": 2.4752598169635927e-05, + "loss": 3.4875, + "step": 1542144 + }, + { + "epoch": 1.01, + "learning_rate": 2.4744212222125407e-05, + "loss": 3.4721, + "step": 1542656 + }, + { + "epoch": 1.01, + "learning_rate": 2.4735826274614887e-05, + "loss": 3.4744, + "step": 1543168 + }, + { + "epoch": 1.01, + "learning_rate": 2.4727440327104367e-05, + "loss": 3.478, + "step": 1543680 + }, + { + "epoch": 1.01, + "learning_rate": 2.4719054379593844e-05, + "loss": 3.4679, + "step": 1544192 + }, + { + "epoch": 1.01, + "learning_rate": 2.4710668432083324e-05, + "loss": 3.4777, + "step": 1544704 + }, + { + "epoch": 1.01, + "learning_rate": 2.4702282484572807e-05, + "loss": 3.4584, + "step": 1545216 + }, + { + "epoch": 1.01, + "learning_rate": 2.4693896537062287e-05, + "loss": 3.4696, + "step": 1545728 + }, + { + "epoch": 1.01, + "learning_rate": 2.4685526968355496e-05, + "loss": 3.4617, + "step": 1546240 + }, + { + "epoch": 1.01, + "learning_rate": 2.4677141020844976e-05, + "loss": 3.4643, + "step": 1546752 + }, + { + "epoch": 1.01, + "learning_rate": 2.4668755073334456e-05, + "loss": 3.4691, + "step": 1547264 + }, + { + "epoch": 1.01, + "learning_rate": 2.4660369125823936e-05, + "loss": 3.4792, + "step": 1547776 + }, + { + "epoch": 1.01, + "learning_rate": 2.465199955711715e-05, + "loss": 3.4724, + "step": 1548288 + }, + { + "epoch": 1.01, + "learning_rate": 2.464361360960663e-05, + "loss": 3.4703, + "step": 1548800 + }, + { + "epoch": 1.01, + "learning_rate": 2.463522766209611e-05, + "loss": 3.4747, + "step": 1549312 + }, + { + "epoch": 1.01, + "learning_rate": 2.462684171458559e-05, + "loss": 3.4692, + "step": 1549824 + }, + { + "epoch": 1.01, + "learning_rate": 2.4618472145878797e-05, + "loss": 3.4723, + "step": 1550336 + }, + { + "epoch": 1.01, + "learning_rate": 2.4610086198368277e-05, + "loss": 3.4663, + "step": 1550848 + }, + { + "epoch": 1.01, + "learning_rate": 2.460170025085776e-05, + "loss": 3.4571, + "step": 1551360 + }, + { + "epoch": 1.01, + "learning_rate": 2.459331430334724e-05, + "loss": 3.4751, + "step": 1551872 + }, + { + "epoch": 1.01, + "learning_rate": 2.458494473464045e-05, + "loss": 3.4679, + "step": 1552384 + }, + { + "epoch": 1.01, + "learning_rate": 2.457655878712993e-05, + "loss": 3.4745, + "step": 1552896 + }, + { + "epoch": 1.01, + "learning_rate": 2.456817283961941e-05, + "loss": 3.4618, + "step": 1553408 + }, + { + "epoch": 1.01, + "learning_rate": 2.4559803270912622e-05, + "loss": 3.4723, + "step": 1553920 + }, + { + "epoch": 1.01, + "learning_rate": 2.4551417323402102e-05, + "loss": 3.4532, + "step": 1554432 + }, + { + "epoch": 1.01, + "learning_rate": 2.4543031375891582e-05, + "loss": 3.4786, + "step": 1554944 + }, + { + "epoch": 1.01, + "learning_rate": 2.4534645428381062e-05, + "loss": 3.4589, + "step": 1555456 + }, + { + "epoch": 1.01, + "learning_rate": 2.4526259480870542e-05, + "loss": 3.4661, + "step": 1555968 + }, + { + "epoch": 1.01, + "learning_rate": 2.4517873533360022e-05, + "loss": 3.4711, + "step": 1556480 + }, + { + "epoch": 1.01, + "learning_rate": 2.45094875858495e-05, + "loss": 3.464, + "step": 1556992 + }, + { + "epoch": 1.01, + "learning_rate": 2.4501101638338982e-05, + "loss": 3.4652, + "step": 1557504 + }, + { + "epoch": 1.01, + "learning_rate": 2.4492732069632194e-05, + "loss": 3.4673, + "step": 1558016 + }, + { + "epoch": 1.01, + "learning_rate": 2.448434612212167e-05, + "loss": 3.456, + "step": 1558528 + }, + { + "epoch": 1.01, + "learning_rate": 2.447596017461115e-05, + "loss": 3.4522, + "step": 1559040 + }, + { + "epoch": 1.01, + "learning_rate": 2.4467590605904363e-05, + "loss": 3.4699, + "step": 1559552 + }, + { + "epoch": 1.01, + "learning_rate": 2.4459204658393843e-05, + "loss": 3.4685, + "step": 1560064 + }, + { + "epoch": 1.01, + "learning_rate": 2.4450818710883323e-05, + "loss": 3.4543, + "step": 1560576 + }, + { + "epoch": 1.01, + "learning_rate": 2.4442432763372803e-05, + "loss": 3.4631, + "step": 1561088 + }, + { + "epoch": 1.01, + "learning_rate": 2.4434063194666016e-05, + "loss": 3.4531, + "step": 1561600 + }, + { + "epoch": 1.01, + "learning_rate": 2.4425677247155496e-05, + "loss": 3.4623, + "step": 1562112 + }, + { + "epoch": 1.01, + "learning_rate": 2.4417291299644972e-05, + "loss": 3.4676, + "step": 1562624 + }, + { + "epoch": 1.01, + "learning_rate": 2.4408905352134452e-05, + "loss": 3.4658, + "step": 1563136 + }, + { + "epoch": 1.01, + "learning_rate": 2.4400535783427668e-05, + "loss": 3.4775, + "step": 1563648 + }, + { + "epoch": 1.01, + "learning_rate": 2.4392149835917145e-05, + "loss": 3.4682, + "step": 1564160 + }, + { + "epoch": 1.01, + "learning_rate": 2.4383763888406625e-05, + "loss": 3.4827, + "step": 1564672 + }, + { + "epoch": 1.01, + "learning_rate": 2.4375377940896105e-05, + "loss": 3.4561, + "step": 1565184 + }, + { + "epoch": 1.01, + "learning_rate": 2.4367008372189317e-05, + "loss": 3.4681, + "step": 1565696 + }, + { + "epoch": 1.01, + "learning_rate": 2.4358622424678794e-05, + "loss": 3.4682, + "step": 1566208 + }, + { + "epoch": 1.01, + "learning_rate": 2.4350236477168277e-05, + "loss": 3.4512, + "step": 1566720 + }, + { + "epoch": 1.01, + "learning_rate": 2.4341850529657757e-05, + "loss": 3.4739, + "step": 1567232 + }, + { + "epoch": 1.01, + "learning_rate": 2.433348096095097e-05, + "loss": 3.4668, + "step": 1567744 + }, + { + "epoch": 1.01, + "learning_rate": 2.432511139224418e-05, + "loss": 3.4685, + "step": 1568256 + }, + { + "epoch": 1.01, + "learning_rate": 2.431672544473366e-05, + "loss": 3.469, + "step": 1568768 + }, + { + "epoch": 1.01, + "learning_rate": 2.430833949722314e-05, + "loss": 3.4536, + "step": 1569280 + }, + { + "epoch": 1.01, + "learning_rate": 2.429995354971262e-05, + "loss": 3.4651, + "step": 1569792 + }, + { + "epoch": 1.01, + "learning_rate": 2.42915676022021e-05, + "loss": 3.4662, + "step": 1570304 + }, + { + "epoch": 1.01, + "learning_rate": 2.4283181654691578e-05, + "loss": 3.4716, + "step": 1570816 + }, + { + "epoch": 1.01, + "learning_rate": 2.4274795707181058e-05, + "loss": 3.4691, + "step": 1571328 + }, + { + "epoch": 1.01, + "learning_rate": 2.4266409759670538e-05, + "loss": 3.4724, + "step": 1571840 + }, + { + "epoch": 1.02, + "learning_rate": 2.4258040190963747e-05, + "loss": 3.4729, + "step": 1572352 + }, + { + "epoch": 1.02, + "learning_rate": 2.424965424345323e-05, + "loss": 3.4584, + "step": 1572864 + }, + { + "epoch": 1.02, + "learning_rate": 2.424126829594271e-05, + "loss": 3.4707, + "step": 1573376 + }, + { + "epoch": 1.02, + "learning_rate": 2.423288234843219e-05, + "loss": 3.4624, + "step": 1573888 + }, + { + "epoch": 1.02, + "learning_rate": 2.42245127797254e-05, + "loss": 3.4717, + "step": 1574400 + }, + { + "epoch": 1.02, + "learning_rate": 2.421612683221488e-05, + "loss": 3.4756, + "step": 1574912 + }, + { + "epoch": 1.02, + "learning_rate": 2.420774088470436e-05, + "loss": 3.4624, + "step": 1575424 + }, + { + "epoch": 1.02, + "learning_rate": 2.419935493719384e-05, + "loss": 3.4581, + "step": 1575936 + }, + { + "epoch": 1.02, + "learning_rate": 2.4190985368487052e-05, + "loss": 3.4613, + "step": 1576448 + }, + { + "epoch": 1.02, + "learning_rate": 2.4182599420976532e-05, + "loss": 3.4693, + "step": 1576960 + }, + { + "epoch": 1.02, + "learning_rate": 2.4174213473466012e-05, + "loss": 3.4774, + "step": 1577472 + }, + { + "epoch": 1.02, + "learning_rate": 2.4165827525955492e-05, + "loss": 3.4631, + "step": 1577984 + }, + { + "epoch": 1.02, + "learning_rate": 2.41574579572487e-05, + "loss": 3.4618, + "step": 1578496 + }, + { + "epoch": 1.02, + "learning_rate": 2.4149072009738184e-05, + "loss": 3.4621, + "step": 1579008 + }, + { + "epoch": 1.02, + "learning_rate": 2.4140686062227664e-05, + "loss": 3.4735, + "step": 1579520 + }, + { + "epoch": 1.02, + "learning_rate": 2.4132300114717144e-05, + "loss": 3.4503, + "step": 1580032 + }, + { + "epoch": 1.02, + "learning_rate": 2.4123930546010353e-05, + "loss": 3.463, + "step": 1580544 + }, + { + "epoch": 1.02, + "learning_rate": 2.4115544598499833e-05, + "loss": 3.4697, + "step": 1581056 + }, + { + "epoch": 1.02, + "learning_rate": 2.4107158650989313e-05, + "loss": 3.4651, + "step": 1581568 + }, + { + "epoch": 1.02, + "learning_rate": 2.4098772703478793e-05, + "loss": 3.461, + "step": 1582080 + }, + { + "epoch": 1.02, + "learning_rate": 2.4090403134772006e-05, + "loss": 3.4736, + "step": 1582592 + }, + { + "epoch": 1.02, + "learning_rate": 2.4082017187261486e-05, + "loss": 3.4621, + "step": 1583104 + }, + { + "epoch": 1.02, + "learning_rate": 2.4073647618554695e-05, + "loss": 3.463, + "step": 1583616 + }, + { + "epoch": 1.02, + "learning_rate": 2.4065261671044175e-05, + "loss": 3.4676, + "step": 1584128 + }, + { + "epoch": 1.02, + "learning_rate": 2.4056875723533655e-05, + "loss": 3.4656, + "step": 1584640 + }, + { + "epoch": 1.02, + "learning_rate": 2.4048489776023138e-05, + "loss": 3.4741, + "step": 1585152 + }, + { + "epoch": 1.02, + "learning_rate": 2.4040103828512618e-05, + "loss": 3.4735, + "step": 1585664 + }, + { + "epoch": 1.02, + "learning_rate": 2.4031717881002094e-05, + "loss": 3.4647, + "step": 1586176 + }, + { + "epoch": 1.02, + "learning_rate": 2.4023331933491574e-05, + "loss": 3.4563, + "step": 1586688 + }, + { + "epoch": 1.02, + "learning_rate": 2.4014962364784787e-05, + "loss": 3.4669, + "step": 1587200 + }, + { + "epoch": 1.02, + "learning_rate": 2.4006576417274267e-05, + "loss": 3.4656, + "step": 1587712 + }, + { + "epoch": 1.02, + "learning_rate": 2.3998190469763747e-05, + "loss": 3.4519, + "step": 1588224 + }, + { + "epoch": 1.02, + "learning_rate": 2.3989804522253227e-05, + "loss": 3.4675, + "step": 1588736 + }, + { + "epoch": 1.02, + "learning_rate": 2.398143495354644e-05, + "loss": 3.4575, + "step": 1589248 + }, + { + "epoch": 1.02, + "learning_rate": 2.397304900603592e-05, + "loss": 3.4656, + "step": 1589760 + }, + { + "epoch": 1.02, + "learning_rate": 2.3964663058525396e-05, + "loss": 3.4621, + "step": 1590272 + }, + { + "epoch": 1.02, + "learning_rate": 2.3956293489818608e-05, + "loss": 3.4694, + "step": 1590784 + }, + { + "epoch": 1.02, + "learning_rate": 2.394790754230809e-05, + "loss": 3.4486, + "step": 1591296 + }, + { + "epoch": 1.02, + "learning_rate": 2.3939521594797568e-05, + "loss": 3.464, + "step": 1591808 + }, + { + "epoch": 1.02, + "learning_rate": 2.3931135647287048e-05, + "loss": 3.4646, + "step": 1592320 + }, + { + "epoch": 1.02, + "learning_rate": 2.3922749699776528e-05, + "loss": 3.4657, + "step": 1592832 + }, + { + "epoch": 1.02, + "learning_rate": 2.3914363752266008e-05, + "loss": 3.4697, + "step": 1593344 + }, + { + "epoch": 1.02, + "learning_rate": 2.3905977804755488e-05, + "loss": 3.4731, + "step": 1593856 + }, + { + "epoch": 1.02, + "learning_rate": 2.3897591857244968e-05, + "loss": 3.4501, + "step": 1594368 + }, + { + "epoch": 1.02, + "learning_rate": 2.388922228853818e-05, + "loss": 3.4677, + "step": 1594880 + }, + { + "epoch": 1.02, + "learning_rate": 2.388083634102766e-05, + "loss": 3.4737, + "step": 1595392 + }, + { + "epoch": 1.02, + "learning_rate": 2.387245039351714e-05, + "loss": 3.4709, + "step": 1595904 + }, + { + "epoch": 1.02, + "learning_rate": 2.386406444600662e-05, + "loss": 3.4698, + "step": 1596416 + }, + { + "epoch": 1.02, + "learning_rate": 2.385569487729983e-05, + "loss": 3.4728, + "step": 1596928 + }, + { + "epoch": 1.02, + "learning_rate": 2.384730892978931e-05, + "loss": 3.4644, + "step": 1597440 + }, + { + "epoch": 1.02, + "learning_rate": 2.3838922982278793e-05, + "loss": 3.4737, + "step": 1597952 + }, + { + "epoch": 1.02, + "learning_rate": 2.3830553413572002e-05, + "loss": 3.4538, + "step": 1598464 + }, + { + "epoch": 1.02, + "learning_rate": 2.3822167466061482e-05, + "loss": 3.4657, + "step": 1598976 + }, + { + "epoch": 1.02, + "learning_rate": 2.381379789735469e-05, + "loss": 3.4607, + "step": 1599488 + }, + { + "epoch": 1.02, + "learning_rate": 2.380541194984417e-05, + "loss": 3.4601, + "step": 1600000 + }, + { + "epoch": 1.02, + "learning_rate": 2.3797026002333654e-05, + "loss": 3.4646, + "step": 1600512 + }, + { + "epoch": 1.02, + "learning_rate": 2.3788640054823134e-05, + "loss": 3.4633, + "step": 1601024 + }, + { + "epoch": 1.02, + "learning_rate": 2.3780254107312614e-05, + "loss": 3.4666, + "step": 1601536 + }, + { + "epoch": 1.02, + "learning_rate": 2.3771868159802094e-05, + "loss": 3.4558, + "step": 1602048 + }, + { + "epoch": 1.02, + "learning_rate": 2.3763498591095303e-05, + "loss": 3.4708, + "step": 1602560 + }, + { + "epoch": 1.03, + "eval_loss": 3.8532090187072754, + "eval_runtime": 306.5675, + "eval_samples_per_second": 1244.721, + "eval_steps_per_second": 38.898, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.3755112643584783e-05, + "loss": 3.453, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.3746726696074263e-05, + "loss": 3.4555, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.3738340748563746e-05, + "loss": 3.4668, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.3729954801053223e-05, + "loss": 3.4694, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721585232346435e-05, + "loss": 3.4694, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713199284835915e-05, + "loss": 3.4561, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.3704813337325395e-05, + "loss": 3.454, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.3696427389814875e-05, + "loss": 3.4586, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.3688057821108088e-05, + "loss": 3.4627, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679671873597568e-05, + "loss": 3.471, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.3671285926087048e-05, + "loss": 3.4564, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.3662899978576524e-05, + "loss": 3.4712, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654530409869737e-05, + "loss": 3.4533, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646144462359217e-05, + "loss": 3.4541, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3637758514848697e-05, + "loss": 3.4614, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629372567338177e-05, + "loss": 3.4522, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621019377435118e-05, + "loss": 3.4538, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612633429924598e-05, + "loss": 3.4614, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604247482414078e-05, + "loss": 3.4536, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.359586153490356e-05, + "loss": 3.4816, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358747558739304e-05, + "loss": 3.4651, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357908963988252e-05, + "loss": 3.4629, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.3570703692371998e-05, + "loss": 3.4647, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562317744861478e-05, + "loss": 3.4721, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.355394817615469e-05, + "loss": 3.4536, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.354556222864417e-05, + "loss": 3.4639, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.353717628113365e-05, + "loss": 3.4621, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.352879033362313e-05, + "loss": 3.4566, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520420764916343e-05, + "loss": 3.4485, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351203481740582e-05, + "loss": 3.4605, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.3503665248699032e-05, + "loss": 3.4752, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495279301188515e-05, + "loss": 3.4625, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3486893353677992e-05, + "loss": 3.4664, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478507406167472e-05, + "loss": 3.4639, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.347012145865695e-05, + "loss": 3.4549, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.346173551114643e-05, + "loss": 3.4652, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345334956363591e-05, + "loss": 3.4515, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344496361612539e-05, + "loss": 3.4554, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.3436594047418604e-05, + "loss": 3.4511, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428208099908084e-05, + "loss": 3.4526, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3419822152397564e-05, + "loss": 3.4571, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411452583690773e-05, + "loss": 3.4636, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.3403066636180253e-05, + "loss": 3.4593, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.3394680688669733e-05, + "loss": 3.4579, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.3386294741159216e-05, + "loss": 3.4646, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.3377908793648696e-05, + "loss": 3.4606, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.3369522846138173e-05, + "loss": 3.4606, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.3361136898627653e-05, + "loss": 3.4554, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3352767329920865e-05, + "loss": 3.4413, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344381382410345e-05, + "loss": 3.4658, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.3335995434899825e-05, + "loss": 3.4577, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.3327609487389305e-05, + "loss": 3.465, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.3319239918682518e-05, + "loss": 3.449, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3310853971171998e-05, + "loss": 3.4584, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302468023661474e-05, + "loss": 3.441, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294098454954687e-05, + "loss": 3.4649, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.328571250744417e-05, + "loss": 3.4475, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277326559933646e-05, + "loss": 3.4585, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3268940612423126e-05, + "loss": 3.461, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260554664912606e-05, + "loss": 3.4483, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252168717402086e-05, + "loss": 3.4511, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3243782769891566e-05, + "loss": 3.463, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235396822381046e-05, + "loss": 3.4407, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322702725367426e-05, + "loss": 3.4393, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321864130616374e-05, + "loss": 3.4588, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.321025535865322e-05, + "loss": 3.4584, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.32018694111427e-05, + "loss": 3.4415, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193499842435908e-05, + "loss": 3.4563, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185113894925388e-05, + "loss": 3.4403, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.317672794741487e-05, + "loss": 3.4478, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.316834199990435e-05, + "loss": 3.4576, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.315997243119756e-05, + "loss": 3.4559, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315158648368704e-05, + "loss": 3.4642, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314320053617652e-05, + "loss": 3.46, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3134814588666e-05, + "loss": 3.4716, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126445019959212e-05, + "loss": 3.4437, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118059072448692e-05, + "loss": 3.4585, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109673124938172e-05, + "loss": 3.4585, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101287177427652e-05, + "loss": 3.4376, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.309291760872086e-05, + "loss": 3.4598, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.308453166121034e-05, + "loss": 3.4585, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076162092503554e-05, + "loss": 3.458, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3067776144993034e-05, + "loss": 3.4609, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059390197482514e-05, + "loss": 3.4463, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.3051004249971994e-05, + "loss": 3.448, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.3042618302461474e-05, + "loss": 3.4534, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.3034232354950954e-05, + "loss": 3.4613, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.3025846407440434e-05, + "loss": 3.4557, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017460459929914e-05, + "loss": 3.4622, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009090891223126e-05, + "loss": 3.4644, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.3000704943712603e-05, + "loss": 3.4452, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992318996202083e-05, + "loss": 3.4593, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2983933048691562e-05, + "loss": 3.4479, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.2975563479984775e-05, + "loss": 3.459, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.2967177532474255e-05, + "loss": 3.47, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.2958791584963735e-05, + "loss": 3.4486, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.2950405637453215e-05, + "loss": 3.4525, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.2942036068746424e-05, + "loss": 3.4484, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.2933650121235907e-05, + "loss": 3.4588, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.2925264173725387e-05, + "loss": 3.4675, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.2916878226214867e-05, + "loss": 3.4519, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290852503631181e-05, + "loss": 3.452, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.290013908880129e-05, + "loss": 3.4452, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.289175314129077e-05, + "loss": 3.4632, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.288336719378025e-05, + "loss": 3.4369, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.287498124626973e-05, + "loss": 3.4525, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.286659529875921e-05, + "loss": 3.4545, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.285820935124869e-05, + "loss": 3.4569, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.284982340373817e-05, + "loss": 3.4483, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.284147021383511e-05, + "loss": 3.4574, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833084266324593e-05, + "loss": 3.4553, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.282469831881407e-05, + "loss": 3.4509, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.281631237130355e-05, + "loss": 3.458, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.280792642379303e-05, + "loss": 3.4546, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.279954047628251e-05, + "loss": 3.4617, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.279115452877199e-05, + "loss": 3.4636, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2782784960065202e-05, + "loss": 3.4522, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774399012554682e-05, + "loss": 3.4486, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766013065044162e-05, + "loss": 3.4534, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757627117533642e-05, + "loss": 3.4557, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749241170023122e-05, + "loss": 3.4434, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2740855222512602e-05, + "loss": 3.4554, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.273246927500208e-05, + "loss": 3.4432, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724083327491562e-05, + "loss": 3.4553, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715713758784775e-05, + "loss": 3.4507, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707344190077984e-05, + "loss": 3.4566, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2698958242567464e-05, + "loss": 3.4444, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690572295056944e-05, + "loss": 3.4483, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682186347546423e-05, + "loss": 3.4542, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2673800400035903e-05, + "loss": 3.4566, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.2665414452525383e-05, + "loss": 3.4523, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657028505014863e-05, + "loss": 3.4619, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648642557504343e-05, + "loss": 3.4436, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.2640272988797552e-05, + "loss": 3.4576, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.2631887041287032e-05, + "loss": 3.4604, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.2623501093776516e-05, + "loss": 3.459, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.2615115146265996e-05, + "loss": 3.4589, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2606745577559205e-05, + "loss": 3.466, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598359630048685e-05, + "loss": 3.4486, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2589973682538165e-05, + "loss": 3.4629, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581587735027645e-05, + "loss": 3.4434, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.2573218166320857e-05, + "loss": 3.4539, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256484859761407e-05, + "loss": 3.4508, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255646265010355e-05, + "loss": 3.4499, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.2548076702593026e-05, + "loss": 3.4528, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539690755082506e-05, + "loss": 3.4472, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531304807571986e-05, + "loss": 3.4621, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2522918860061466e-05, + "loss": 3.4371, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.251454929135468e-05, + "loss": 3.463, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.853513240814209, + "eval_runtime": 303.6303, + "eval_samples_per_second": 1256.762, + "eval_steps_per_second": 39.275, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250616334384416e-05, + "loss": 3.4421, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249777739633364e-05, + "loss": 3.4447, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248939144882312e-05, + "loss": 3.4551, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481005501312598e-05, + "loss": 3.4571, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.247263593260581e-05, + "loss": 3.4591, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.246424998509529e-05, + "loss": 3.4461, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245586403758477e-05, + "loss": 3.4388, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244747809007425e-05, + "loss": 3.4497, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243910852136746e-05, + "loss": 3.4514, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243072257385694e-05, + "loss": 3.4582, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242233662634642e-05, + "loss": 3.4502, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413950678835903e-05, + "loss": 3.4553, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405581110129112e-05, + "loss": 3.4433, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397195162618592e-05, + "loss": 3.4426, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388809215108072e-05, + "loss": 3.4494, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380423267597552e-05, + "loss": 3.4413, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2372070077694497e-05, + "loss": 3.4421, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363684130183974e-05, + "loss": 3.4514, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355298182673453e-05, + "loss": 3.4427, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346912235162933e-05, + "loss": 3.4652, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338526287652413e-05, + "loss": 3.456, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330140340141893e-05, + "loss": 3.4478, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321754392631373e-05, + "loss": 3.4527, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313368445120853e-05, + "loss": 3.4606, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304998876414066e-05, + "loss": 3.4401, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296612928903546e-05, + "loss": 3.4548, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288226981393026e-05, + "loss": 3.4477, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279841033882502e-05, + "loss": 3.4482, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271471465175718e-05, + "loss": 3.4393, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2263085517665198e-05, + "loss": 3.4486, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254715948958407e-05, + "loss": 3.463, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246330001447887e-05, + "loss": 3.4498, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237944053937367e-05, + "loss": 3.4577, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2229558106426847e-05, + "loss": 3.4533, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2221172158916327e-05, + "loss": 3.4423, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212786211405807e-05, + "loss": 3.4521, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204400263895287e-05, + "loss": 3.4419, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196014316384767e-05, + "loss": 3.442, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187644747677976e-05, + "loss": 3.4413, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179258800167456e-05, + "loss": 3.4399, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.217087285265694e-05, + "loss": 3.4468, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216250328395015e-05, + "loss": 3.4535, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154117336439628e-05, + "loss": 3.4492, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145731388929108e-05, + "loss": 3.4479, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137345441418588e-05, + "loss": 3.455, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128959493908068e-05, + "loss": 3.448, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120573546397548e-05, + "loss": 3.4512, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112187598887028e-05, + "loss": 3.443, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210381803018024e-05, + "loss": 3.4278, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209543208266972e-05, + "loss": 3.4572, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.20870461351592e-05, + "loss": 3.4459, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207866018764868e-05, + "loss": 3.4562, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.207029061894189e-05, + "loss": 3.4429, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061904671431373e-05, + "loss": 3.4421, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053518723920853e-05, + "loss": 3.4325, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045149155214062e-05, + "loss": 3.4503, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036763207703542e-05, + "loss": 3.4389, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028377260193022e-05, + "loss": 3.4458, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019991312682502e-05, + "loss": 3.4543, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011605365171982e-05, + "loss": 3.4336, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003219417661462e-05, + "loss": 3.4372, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994849848954674e-05, + "loss": 3.4565, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986463901444154e-05, + "loss": 3.428, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197807795393363e-05, + "loss": 3.427, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196969200642311e-05, + "loss": 3.4441, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961306058912594e-05, + "loss": 3.4471, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952920111402074e-05, + "loss": 3.4346, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944534163891554e-05, + "loss": 3.4459, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936164595184763e-05, + "loss": 3.4322, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927778647674243e-05, + "loss": 3.4345, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919392700163723e-05, + "loss": 3.4491, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1911006752653203e-05, + "loss": 3.445, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1902637183946415e-05, + "loss": 3.4501, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894251236435895e-05, + "loss": 3.4506, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885865288925375e-05, + "loss": 3.4574, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1877479341414855e-05, + "loss": 3.436, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869109772708064e-05, + "loss": 3.4429, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860723825197548e-05, + "loss": 3.4452, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852337877687028e-05, + "loss": 3.4279, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1843951930176508e-05, + "loss": 3.4498, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835582361469717e-05, + "loss": 3.4468, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827212792762926e-05, + "loss": 3.4473, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181882684525241e-05, + "loss": 3.4458, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.181044089774189e-05, + "loss": 3.4367, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180205495023137e-05, + "loss": 3.4358, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179366900272085e-05, + "loss": 3.4444, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178528305521033e-05, + "loss": 3.4462, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177689710769981e-05, + "loss": 3.4465, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768511160189285e-05, + "loss": 3.4512, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760141591482498e-05, + "loss": 3.4525, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175175564397198e-05, + "loss": 3.438, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743369696461458e-05, + "loss": 3.4468, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1734983748950938e-05, + "loss": 3.4351, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.172661418024415e-05, + "loss": 3.4518, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.171822823273363e-05, + "loss": 3.4557, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170984228522311e-05, + "loss": 3.4401, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170145633771259e-05, + "loss": 3.4391, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693086769005803e-05, + "loss": 3.4352, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684700821495283e-05, + "loss": 3.4473, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167631487398476e-05, + "loss": 3.4559, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166792892647424e-05, + "loss": 3.4402, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.165955935776745e-05, + "loss": 3.4436, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.165117341025693e-05, + "loss": 3.4382, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.164278746274641e-05, + "loss": 3.4476, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163440151523589e-05, + "loss": 3.4289, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1626031946529104e-05, + "loss": 3.4424, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161764599901858e-05, + "loss": 3.4346, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1609260051508064e-05, + "loss": 3.4506, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600874103997544e-05, + "loss": 3.4378, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592520914094485e-05, + "loss": 3.4464, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584134966583965e-05, + "loss": 3.4465, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575749019073445e-05, + "loss": 3.4389, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567363071562925e-05, + "loss": 3.4483, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1558977124052405e-05, + "loss": 3.4442, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1550591176541885e-05, + "loss": 3.4478, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542205229031365e-05, + "loss": 3.4543, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533819281520845e-05, + "loss": 3.4365, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525449712814054e-05, + "loss": 3.443, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517063765303534e-05, + "loss": 3.4373, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508677817793018e-05, + "loss": 3.446, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500291870282498e-05, + "loss": 3.4387, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1491922301575707e-05, + "loss": 3.4405, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483536354065187e-05, + "loss": 3.4293, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475150406554667e-05, + "loss": 3.4442, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466764459044146e-05, + "loss": 3.4384, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145839489033736e-05, + "loss": 3.4454, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.145000894282684e-05, + "loss": 3.4305, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144162299531632e-05, + "loss": 3.4422, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.14332370478058e-05, + "loss": 3.4397, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.142485110029528e-05, + "loss": 3.448, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141646515278476e-05, + "loss": 3.4397, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408079205274235e-05, + "loss": 3.4507, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139969325776372e-05, + "loss": 3.4317, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139132368905693e-05, + "loss": 3.4481, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382937741546408e-05, + "loss": 3.4488, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374551794035888e-05, + "loss": 3.448, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366165846525368e-05, + "loss": 3.4463, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.135779627781858e-05, + "loss": 3.4535, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.134941033030806e-05, + "loss": 3.4398, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134102438279754e-05, + "loss": 3.4532, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133263843528702e-05, + "loss": 3.4323, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324268866580232e-05, + "loss": 3.4446, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.131589929787344e-05, + "loss": 3.4386, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130751335036292e-05, + "loss": 3.4407, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299127402852405e-05, + "loss": 3.4391, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.129074145534188e-05, + "loss": 3.4348, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.128235550783136e-05, + "loss": 3.4502, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127396956032084e-05, + "loss": 3.4276, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.126558361281032e-05, + "loss": 3.4559, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.855330467224121, + "eval_runtime": 306.9928, + "eval_samples_per_second": 1242.997, + "eval_steps_per_second": 38.845, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257214044103534e-05, + "loss": 3.435, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248828096593014e-05, + "loss": 3.4323, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240442149082494e-05, + "loss": 3.4422, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1232056201571974e-05, + "loss": 3.4464, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223670254061454e-05, + "loss": 3.4443, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1215284306550934e-05, + "loss": 3.4395, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1206898359040413e-05, + "loss": 3.431, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1198528790333626e-05, + "loss": 3.4371, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1190142842823106e-05, + "loss": 3.4403, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181756895312586e-05, + "loss": 3.4487, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173370947802062e-05, + "loss": 3.4395, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1165001379095275e-05, + "loss": 3.439, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1156615431584755e-05, + "loss": 3.4364, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1148245862877967e-05, + "loss": 3.4303, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1139859915367447e-05, + "loss": 3.4367, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1131473967856927e-05, + "loss": 3.4296, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.1123088020346407e-05, + "loss": 3.4331, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.1114702072835887e-05, + "loss": 3.4385, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.1106316125325364e-05, + "loss": 3.4301, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.1097930177814844e-05, + "loss": 3.455, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.1089544230304327e-05, + "loss": 3.4501, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1081174661597536e-05, + "loss": 3.4377, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1072788714087016e-05, + "loss": 3.4432, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1064402766576496e-05, + "loss": 3.4495, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1056016819065976e-05, + "loss": 3.4311, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047630871555456e-05, + "loss": 3.4457, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039244924044936e-05, + "loss": 3.4371, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.103085897653442e-05, + "loss": 3.4352, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022473029023896e-05, + "loss": 3.4286, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101410346031711e-05, + "loss": 3.4405, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005717512806588e-05, + "loss": 3.4488, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997347944099797e-05, + "loss": 3.443, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.098896199658928e-05, + "loss": 3.4451, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.098057604907876e-05, + "loss": 3.4387, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.097219010156824e-05, + "loss": 3.433, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963804154057717e-05, + "loss": 3.4457, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955418206547197e-05, + "loss": 3.4344, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0947032259036677e-05, + "loss": 3.4263, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.093866269032989e-05, + "loss": 3.4294, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.093027674281937e-05, + "loss": 3.4292, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.092189079530885e-05, + "loss": 3.4358, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913521226602062e-05, + "loss": 3.4419, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.090513527909154e-05, + "loss": 3.4394, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.089674933158102e-05, + "loss": 3.4334, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.08883633840705e-05, + "loss": 3.4424, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0879977436559982e-05, + "loss": 3.4401, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871591489049462e-05, + "loss": 3.4395, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0863205541538942e-05, + "loss": 3.4341, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085483597283215e-05, + "loss": 3.413, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084645002532163e-05, + "loss": 3.4501, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083806407781111e-05, + "loss": 3.4323, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.082967813030059e-05, + "loss": 3.4465, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821308561593803e-05, + "loss": 3.4305, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.0812938992887012e-05, + "loss": 3.4346, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0804553045376492e-05, + "loss": 3.4224, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0796167097865972e-05, + "loss": 3.437, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0787781150355452e-05, + "loss": 3.4284, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0779395202844935e-05, + "loss": 3.4331, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0771009255334415e-05, + "loss": 3.4453, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762623307823895e-05, + "loss": 3.4267, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754237360313372e-05, + "loss": 3.4253, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0745867791606584e-05, + "loss": 3.4438, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737481844096064e-05, + "loss": 3.4191, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729112275389277e-05, + "loss": 3.4157, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0720726327878757e-05, + "loss": 3.4366, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0712340380368237e-05, + "loss": 3.4338, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0703954432857717e-05, + "loss": 3.4264, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695568485347193e-05, + "loss": 3.4349, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687182537836673e-05, + "loss": 3.417, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678796590326153e-05, + "loss": 3.4262, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.067042702161937e-05, + "loss": 3.4367, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662041074108846e-05, + "loss": 3.4313, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653655126598326e-05, + "loss": 3.4429, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645269179087806e-05, + "loss": 3.4371, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636883231577286e-05, + "loss": 3.4455, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628497284066766e-05, + "loss": 3.4235, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620111336556245e-05, + "loss": 3.4368, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061172538904573e-05, + "loss": 3.433, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603355820338938e-05, + "loss": 3.4177, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0594969872828418e-05, + "loss": 3.4372, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586583925317898e-05, + "loss": 3.4373, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578197977807374e-05, + "loss": 3.4363, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.056982840910059e-05, + "loss": 3.4418, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056144246159007e-05, + "loss": 3.4209, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055305651407955e-05, + "loss": 3.425, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544670566569027e-05, + "loss": 3.4338, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536284619058507e-05, + "loss": 3.4347, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0527898671547987e-05, + "loss": 3.4376, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0519512724037467e-05, + "loss": 3.4374, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.051114315533068e-05, + "loss": 3.4428, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050275720782016e-05, + "loss": 3.432, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049437126030964e-05, + "loss": 3.4324, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.048598531279912e-05, + "loss": 3.4258, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477615744092328e-05, + "loss": 3.4403, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.046922979658181e-05, + "loss": 3.4428, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.046084384907129e-05, + "loss": 3.4299, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.045245790156077e-05, + "loss": 3.4263, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044408833285398e-05, + "loss": 3.4254, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043570238534346e-05, + "loss": 3.4329, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.042731643783294e-05, + "loss": 3.4482, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.041893049032242e-05, + "loss": 3.4276, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410577300419365e-05, + "loss": 3.4337, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402191352908845e-05, + "loss": 3.4303, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393805405398322e-05, + "loss": 3.4354, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385419457887802e-05, + "loss": 3.4228, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377033510377282e-05, + "loss": 3.4334, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.036864756286676e-05, + "loss": 3.4205, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360261615356245e-05, + "loss": 3.4382, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0351892046649454e-05, + "loss": 3.4299, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343506099138934e-05, + "loss": 3.4339, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335120151628414e-05, + "loss": 3.4328, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326734204117894e-05, + "loss": 3.4344, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318348256607374e-05, + "loss": 3.4348, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0309962309096854e-05, + "loss": 3.4334, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301592740390066e-05, + "loss": 3.4358, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293206792879546e-05, + "loss": 3.444, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0284820845369026e-05, + "loss": 3.426, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276434897858503e-05, + "loss": 3.4323, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268048950347983e-05, + "loss": 3.4281, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0259663002837466e-05, + "loss": 3.4316, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.025129343413068e-05, + "loss": 3.4292, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0242907486620155e-05, + "loss": 3.4291, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234521539109635e-05, + "loss": 3.4216, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226135591599115e-05, + "loss": 3.4294, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217749644088595e-05, + "loss": 3.4299, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209380075381808e-05, + "loss": 3.4327, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0200994127871288e-05, + "loss": 3.4165, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192608180360767e-05, + "loss": 3.4327, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184222232850247e-05, + "loss": 3.4278, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175836285339727e-05, + "loss": 3.4364, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0167450337829207e-05, + "loss": 3.4318, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159064390318684e-05, + "loss": 3.4388, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150678442808167e-05, + "loss": 3.4201, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014230887410138e-05, + "loss": 3.4402, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013392292659086e-05, + "loss": 3.4341, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125536979080336e-05, + "loss": 3.4374, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0117151031569816e-05, + "loss": 3.437, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.010878146286303e-05, + "loss": 3.4395, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.010039551535251e-05, + "loss": 3.4302, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.009200956784199e-05, + "loss": 3.4412, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.008362362033147e-05, + "loss": 3.4248, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.007525405162468e-05, + "loss": 3.4338, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.006688448291789e-05, + "loss": 3.4278, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.005849853540737e-05, + "loss": 3.4318, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050112587896853e-05, + "loss": 3.4261, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041726640386333e-05, + "loss": 3.4254, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.003334069287581e-05, + "loss": 3.4368, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002495474536529e-05, + "loss": 3.4198, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.001656879785477e-05, + "loss": 3.4436, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.857438802719116, + "eval_runtime": 304.0024, + "eval_samples_per_second": 1255.224, + "eval_steps_per_second": 39.227, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008199229147982e-05, + "loss": 3.4207, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999813281637462e-05, + "loss": 3.4255, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991427334126942e-05, + "loss": 3.4258, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983041386616422e-05, + "loss": 3.4357, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997467181790963e-05, + "loss": 3.4359, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996628587039911e-05, + "loss": 3.4238, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.995789992288859e-05, + "loss": 3.4262, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949513975378075e-05, + "loss": 3.4277, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941144406671284e-05, + "loss": 3.4267, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932758459160764e-05, + "loss": 3.4381, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924372511650244e-05, + "loss": 3.4256, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9915986564139724e-05, + "loss": 3.4302, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907616995432936e-05, + "loss": 3.4246, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899231047922416e-05, + "loss": 3.4187, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890845100411896e-05, + "loss": 3.4297, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882459152901376e-05, + "loss": 3.4185, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874105962998318e-05, + "loss": 3.4213, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865720015487797e-05, + "loss": 3.4284, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857334067977277e-05, + "loss": 3.4202, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9848948120466757e-05, + "loss": 3.4419, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9840562172956237e-05, + "loss": 3.44, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9832176225445717e-05, + "loss": 3.4295, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823806656738926e-05, + "loss": 3.4282, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815420709228406e-05, + "loss": 3.4359, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.980703476171789e-05, + "loss": 3.4249, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.979864881420737e-05, + "loss": 3.4291, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979026286669685e-05, + "loss": 3.4266, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978187691918633e-05, + "loss": 3.4259, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977349097167581e-05, + "loss": 3.4225, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9765105024165286e-05, + "loss": 3.4242, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.97567354554585e-05, + "loss": 3.4362, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.974836588675171e-05, + "loss": 3.4357, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.973997993924119e-05, + "loss": 3.4356, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.973159399173067e-05, + "loss": 3.4277, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972320804422015e-05, + "loss": 3.4198, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971482209670963e-05, + "loss": 3.4343, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706436149199107e-05, + "loss": 3.4251, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.969805020168859e-05, + "loss": 3.416, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689680632981803e-05, + "loss": 3.42, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681294685471283e-05, + "loss": 3.4158, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967290873796076e-05, + "loss": 3.4234, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9664539169253972e-05, + "loss": 3.4292, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656153221743452e-05, + "loss": 3.4314, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647767274232932e-05, + "loss": 3.4287, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639381326722412e-05, + "loss": 3.4264, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9630995379211892e-05, + "loss": 3.4317, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622609431701372e-05, + "loss": 3.4263, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614223484190852e-05, + "loss": 3.4253, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605837536680332e-05, + "loss": 3.4005, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597467967973544e-05, + "loss": 3.4408, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589082020463024e-05, + "loss": 3.4216, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580696072952504e-05, + "loss": 3.4356, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572326504245713e-05, + "loss": 3.4197, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9563956935538926e-05, + "loss": 3.4212, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9555570988028406e-05, + "loss": 3.4131, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9547185040517886e-05, + "loss": 3.4252, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538799093007366e-05, + "loss": 3.4203, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530413145496846e-05, + "loss": 3.4208, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522027197986326e-05, + "loss": 3.4313, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513641250475806e-05, + "loss": 3.4176, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505255302965286e-05, + "loss": 3.4101, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496885734258498e-05, + "loss": 3.4339, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9488499786747978e-05, + "loss": 3.4123, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9480113839237458e-05, + "loss": 3.4043, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471727891726938e-05, + "loss": 3.4288, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9463341944216415e-05, + "loss": 3.4241, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9454955996705895e-05, + "loss": 3.4165, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446570049195374e-05, + "loss": 3.4207, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438200480488587e-05, + "loss": 3.407, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9429814532978067e-05, + "loss": 3.4158, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9421428585467547e-05, + "loss": 3.4276, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9413042637957027e-05, + "loss": 3.42, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404673069250236e-05, + "loss": 3.4335, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396287121739716e-05, + "loss": 3.4239, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.93879011742292e-05, + "loss": 3.4357, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.937951522671868e-05, + "loss": 3.4126, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9371145658011888e-05, + "loss": 3.4282, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362759710501368e-05, + "loss": 3.4188, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354373762990848e-05, + "loss": 3.4111, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9345987815480328e-05, + "loss": 3.4249, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.933761824677354e-05, + "loss": 3.4296, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.932923229926302e-05, + "loss": 3.4208, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9320862730556233e-05, + "loss": 3.4332, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.931247678304571e-05, + "loss": 3.4085, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.930409083553519e-05, + "loss": 3.4095, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.929570488802467e-05, + "loss": 3.4276, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287318940514153e-05, + "loss": 3.4256, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9278932993003633e-05, + "loss": 3.4264, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270547045493113e-05, + "loss": 3.4294, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262177476786322e-05, + "loss": 3.4276, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9253791529275802e-05, + "loss": 3.4252, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9245405581765282e-05, + "loss": 3.4226, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9237019634254762e-05, + "loss": 3.415, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228650065547974e-05, + "loss": 3.4331, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9220264118037454e-05, + "loss": 3.4261, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9211878170526934e-05, + "loss": 3.4229, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9203508601820143e-05, + "loss": 3.4168, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.9195122654309623e-05, + "loss": 3.4129, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186736706799107e-05, + "loss": 3.4179, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178350759288587e-05, + "loss": 3.4368, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9169964811778066e-05, + "loss": 3.4181, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9161595243071276e-05, + "loss": 3.4244, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.9153209295560756e-05, + "loss": 3.4179, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.9144823348050235e-05, + "loss": 3.4197, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136437400539715e-05, + "loss": 3.4174, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.9128051453029195e-05, + "loss": 3.4179, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.9119665505518675e-05, + "loss": 3.4112, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111295936811888e-05, + "loss": 3.4299, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102909989301364e-05, + "loss": 3.4218, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.9094524041790844e-05, + "loss": 3.4206, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.9086138094280324e-05, + "loss": 3.4177, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077768525573537e-05, + "loss": 3.4249, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069382578063017e-05, + "loss": 3.4252, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9060996630552497e-05, + "loss": 3.4218, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052610683041977e-05, + "loss": 3.4263, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044241114335186e-05, + "loss": 3.433, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.903585516682467e-05, + "loss": 3.4178, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.902746921931415e-05, + "loss": 3.4234, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.901908327180363e-05, + "loss": 3.4137, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.901069732429311e-05, + "loss": 3.4234, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.900231137678259e-05, + "loss": 3.4196, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.899392542927207e-05, + "loss": 3.4162, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985539481761545e-05, + "loss": 3.4156, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.897716991305476e-05, + "loss": 3.4204, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.896878396554424e-05, + "loss": 3.4218, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.896041439683745e-05, + "loss": 3.4222, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.895202844932693e-05, + "loss": 3.4098, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.894364250181641e-05, + "loss": 3.419, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.893525655430589e-05, + "loss": 3.4176, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892687060679537e-05, + "loss": 3.4249, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.891848465928485e-05, + "loss": 3.4218, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.891009871177433e-05, + "loss": 3.426, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890171276426381e-05, + "loss": 3.4106, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889334319555702e-05, + "loss": 3.4298, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.88849572480465e-05, + "loss": 3.4269, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887657130053598e-05, + "loss": 3.4265, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868185353025462e-05, + "loss": 3.4262, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.885981578431867e-05, + "loss": 3.4272, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885142983680815e-05, + "loss": 3.421, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884304388929763e-05, + "loss": 3.4305, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883465794178711e-05, + "loss": 3.4127, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.8826288373080324e-05, + "loss": 3.4249, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.8817918804373536e-05, + "loss": 3.4185, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8809532856863016e-05, + "loss": 3.4209, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801146909352493e-05, + "loss": 3.4145, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.8792760961841973e-05, + "loss": 3.4145, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784391393135185e-05, + "loss": 3.4253, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776005445624665e-05, + "loss": 3.4158, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767619498114145e-05, + "loss": 3.4302, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8587706089019775, + "eval_runtime": 306.2409, + "eval_samples_per_second": 1246.049, + "eval_steps_per_second": 38.94, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759233550603625e-05, + "loss": 3.4096, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8750847603093105e-05, + "loss": 3.4128, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742461655582585e-05, + "loss": 3.4141, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.8734075708072065e-05, + "loss": 3.4296, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725689760561545e-05, + "loss": 3.4263, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717320191854757e-05, + "loss": 3.4124, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8708934244344237e-05, + "loss": 3.417, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700548296833717e-05, + "loss": 3.4144, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692162349323197e-05, + "loss": 3.4138, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683792780616406e-05, + "loss": 3.4305, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675406833105886e-05, + "loss": 3.4146, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.866702088559537e-05, + "loss": 3.4149, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658634938084846e-05, + "loss": 3.4254, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.865026536937806e-05, + "loss": 3.4022, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.864187942186754e-05, + "loss": 3.4169, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.863349347435702e-05, + "loss": 3.4071, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.862512390565023e-05, + "loss": 3.4147, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861673795813971e-05, + "loss": 3.4155, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.860835201062919e-05, + "loss": 3.4066, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.859996606311867e-05, + "loss": 3.4267, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591580115608148e-05, + "loss": 3.4276, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583194168097628e-05, + "loss": 3.4227, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.857482459939084e-05, + "loss": 3.4207, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856643865188032e-05, + "loss": 3.4212, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.85580527043698e-05, + "loss": 3.4182, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854966675685928e-05, + "loss": 3.4155, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.854128080934876e-05, + "loss": 3.4202, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.853289486183824e-05, + "loss": 3.42, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.852450891432772e-05, + "loss": 3.4089, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.85161229668172e-05, + "loss": 3.4128, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.8507753398110412e-05, + "loss": 3.4226, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.849938382940362e-05, + "loss": 3.4287, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.84909978818931e-05, + "loss": 3.4241, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848261193438258e-05, + "loss": 3.4193, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847422598687206e-05, + "loss": 3.4097, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.846584003936154e-05, + "loss": 3.4179, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457454091851024e-05, + "loss": 3.421, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.84490681443405e-05, + "loss": 3.4089, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440698575633714e-05, + "loss": 3.4104, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.8432312628123193e-05, + "loss": 3.4065, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8423926680612673e-05, + "loss": 3.4142, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8415557111905886e-05, + "loss": 3.4148, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8407171164395366e-05, + "loss": 3.4201, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398785216884846e-05, + "loss": 3.4181, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8390399269374322e-05, + "loss": 3.4164, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8382013321863802e-05, + "loss": 3.4177, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8373627374353282e-05, + "loss": 3.4146, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8365241426842762e-05, + "loss": 3.4212, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8356855479332242e-05, + "loss": 3.3875, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8348485910625455e-05, + "loss": 3.4245, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340099963114935e-05, + "loss": 3.414, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331714015604415e-05, + "loss": 3.427, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323328068093895e-05, + "loss": 3.4116, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.831497487819084e-05, + "loss": 3.4135, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.830658893068032e-05, + "loss": 3.3987, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8298202983169796e-05, + "loss": 3.413, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8289817035659276e-05, + "loss": 3.4138, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281431088148756e-05, + "loss": 3.4085, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273045140638236e-05, + "loss": 3.4217, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264659193127716e-05, + "loss": 3.41, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.825628962442093e-05, + "loss": 3.3943, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.824790367691041e-05, + "loss": 3.4239, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.823951772939989e-05, + "loss": 3.4053, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231131781889368e-05, + "loss": 3.3939, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222745834378848e-05, + "loss": 3.4144, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214359886868328e-05, + "loss": 3.4123, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8205973939357808e-05, + "loss": 3.3991, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197587991847288e-05, + "loss": 3.4164, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.81892184231405e-05, + "loss": 3.3973, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.8180832475629977e-05, + "loss": 3.4028, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.8172446528119457e-05, + "loss": 3.4188, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164060580608937e-05, + "loss": 3.4089, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.815569101190215e-05, + "loss": 3.4238, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814730506439163e-05, + "loss": 3.4111, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813891911688111e-05, + "loss": 3.4249, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813053316937059e-05, + "loss": 3.4052, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8122163600663802e-05, + "loss": 3.422, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811377765315328e-05, + "loss": 3.4044, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.8105391705642762e-05, + "loss": 3.4041, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.8097005758132242e-05, + "loss": 3.4118, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.808863618942545e-05, + "loss": 3.4171, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.808025024191493e-05, + "loss": 3.4129, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.807186429440441e-05, + "loss": 3.4242, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806347834689389e-05, + "loss": 3.3989, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8055108778187103e-05, + "loss": 3.3999, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046722830676583e-05, + "loss": 3.4146, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8038353261969796e-05, + "loss": 3.418, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8029967314459276e-05, + "loss": 3.4115, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8021581366948752e-05, + "loss": 3.4205, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8013195419438232e-05, + "loss": 3.4126, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8004825850731448e-05, + "loss": 3.4152, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996439903220925e-05, + "loss": 3.4129, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7988053955710405e-05, + "loss": 3.4052, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979668008199885e-05, + "loss": 3.4215, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971282060689364e-05, + "loss": 3.4188, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7962896113178844e-05, + "loss": 3.4112, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7954526544472057e-05, + "loss": 3.4096, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7946140596961537e-05, + "loss": 3.3999, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7937754649451017e-05, + "loss": 3.412, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929368701940497e-05, + "loss": 3.4255, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7920982754429977e-05, + "loss": 3.4103, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912596806919457e-05, + "loss": 3.4179, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904227238212666e-05, + "loss": 3.4089, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.789584129070215e-05, + "loss": 3.407, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.788745534319163e-05, + "loss": 3.4094, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879069395681106e-05, + "loss": 3.4053, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870683448170586e-05, + "loss": 3.402, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862313879463798e-05, + "loss": 3.4196, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7853927931953278e-05, + "loss": 3.4146, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845541984442758e-05, + "loss": 3.4052, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837156036932238e-05, + "loss": 3.4111, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782878646822545e-05, + "loss": 3.4089, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7820400520714927e-05, + "loss": 3.4184, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7812014573204407e-05, + "loss": 3.4084, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803628625693887e-05, + "loss": 3.4181, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.779524267818337e-05, + "loss": 3.4201, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.778687310947658e-05, + "loss": 3.4063, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777848716196606e-05, + "loss": 3.4116, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.777010121445554e-05, + "loss": 3.4048, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.776171526694502e-05, + "loss": 3.4127, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.77533293194345e-05, + "loss": 3.4115, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.774494337192398e-05, + "loss": 3.4048, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.7736557424413462e-05, + "loss": 3.4011, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772817147690294e-05, + "loss": 3.4094, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771980190819615e-05, + "loss": 3.4131, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771143233948936e-05, + "loss": 3.4126, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.770304639197884e-05, + "loss": 3.3992, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694660444468324e-05, + "loss": 3.4052, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686274496957804e-05, + "loss": 3.4073, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7677888549447284e-05, + "loss": 3.4174, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766950260193676e-05, + "loss": 3.4131, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766111665442624e-05, + "loss": 3.419, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765273070691572e-05, + "loss": 3.3988, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.7644361138208933e-05, + "loss": 3.424, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.7635975190698413e-05, + "loss": 3.4106, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627589243187893e-05, + "loss": 3.419, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619203295677373e-05, + "loss": 3.414, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7610833726970582e-05, + "loss": 3.4188, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602447779460062e-05, + "loss": 3.4108, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.759406183194954e-05, + "loss": 3.4236, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7585675884439025e-05, + "loss": 3.3985, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577306315732234e-05, + "loss": 3.4139, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7568936747025447e-05, + "loss": 3.4077, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560550799514927e-05, + "loss": 3.4088, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552164852004407e-05, + "loss": 3.404, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543778904493886e-05, + "loss": 3.4055, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535392956983366e-05, + "loss": 3.4107, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7527007009472846e-05, + "loss": 3.4078, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518637440766055e-05, + "loss": 3.4158, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8598690032958984, + "eval_runtime": 305.1148, + "eval_samples_per_second": 1250.647, + "eval_steps_per_second": 39.084, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510251493255535e-05, + "loss": 3.3993, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501865545745015e-05, + "loss": 3.4042, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493479598234495e-05, + "loss": 3.4018, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.748509365072398e-05, + "loss": 3.4186, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.7476724082017188e-05, + "loss": 3.4184, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468338134506668e-05, + "loss": 3.4008, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.745996856579988e-05, + "loss": 3.406, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451582618289357e-05, + "loss": 3.405, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.744319667077884e-05, + "loss": 3.4077, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.743481072326832e-05, + "loss": 3.4171, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.74264247757578e-05, + "loss": 3.4036, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741803882824728e-05, + "loss": 3.4079, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.740965288073676e-05, + "loss": 3.4146, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.740128331202997e-05, + "loss": 3.3947, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739289736451945e-05, + "loss": 3.4067, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.7384511417008932e-05, + "loss": 3.3954, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.7376125469498412e-05, + "loss": 3.4018, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736773952198789e-05, + "loss": 3.4071, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735935357447737e-05, + "loss": 3.3972, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735096762696685e-05, + "loss": 3.4151, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.734258167945633e-05, + "loss": 3.4174, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.733421211074954e-05, + "loss": 3.4118, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7325842542042754e-05, + "loss": 3.41, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317456594532234e-05, + "loss": 3.412, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.730907064702171e-05, + "loss": 3.412, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.730068469951119e-05, + "loss": 3.4042, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.729229875200067e-05, + "loss": 3.4058, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.728391280449015e-05, + "loss": 3.411, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275526856979633e-05, + "loss": 3.3988, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267140909469113e-05, + "loss": 3.4017, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7258771340762323e-05, + "loss": 3.4151, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.725040177205553e-05, + "loss": 3.4125, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.724201582454501e-05, + "loss": 3.4187, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233629877034495e-05, + "loss": 3.4081, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225243929523975e-05, + "loss": 3.4004, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7216857982013455e-05, + "loss": 3.4069, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208472034502935e-05, + "loss": 3.4104, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200086086992415e-05, + "loss": 3.3953, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.719170013948189e-05, + "loss": 3.3985, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183330570775104e-05, + "loss": 3.3989, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7174944623264587e-05, + "loss": 3.3975, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166575054557796e-05, + "loss": 3.4065, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158189107047276e-05, + "loss": 3.4098, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149803159536756e-05, + "loss": 3.4103, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141417212026236e-05, + "loss": 3.4025, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133031264515713e-05, + "loss": 3.412, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.7124645317005196e-05, + "loss": 3.4027, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.7116259369494676e-05, + "loss": 3.412, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.7107873421984156e-05, + "loss": 3.3796, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.7099503853277365e-05, + "loss": 3.4115, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.7091117905766845e-05, + "loss": 3.4032, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.7082731958256325e-05, + "loss": 3.4182, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.7074346010745805e-05, + "loss": 3.3984, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.7065976442039017e-05, + "loss": 3.401, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057590494528497e-05, + "loss": 3.3942, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.7049204547017977e-05, + "loss": 3.3984, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.7040834978311186e-05, + "loss": 3.4105, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.7032449030800666e-05, + "loss": 3.3922, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.702406308329015e-05, + "loss": 3.413, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701567713577963e-05, + "loss": 3.4004, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700730756707284e-05, + "loss": 3.3824, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.699892161956232e-05, + "loss": 3.4136, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.69905356720518e-05, + "loss": 3.3988, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.698214972454128e-05, + "loss": 3.3818, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.697376377703076e-05, + "loss": 3.4078, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965377829520242e-05, + "loss": 3.4027, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.6956991882009722e-05, + "loss": 3.3883, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.69486059344992e-05, + "loss": 3.4088, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694023636579241e-05, + "loss": 3.3867, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.693185041828189e-05, + "loss": 3.3926, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923464470771367e-05, + "loss": 3.4053, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.691507852326085e-05, + "loss": 3.4024, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906708954554063e-05, + "loss": 3.4097, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898323007043543e-05, + "loss": 3.4023, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.688993705953302e-05, + "loss": 3.4132, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.68815511120225e-05, + "loss": 3.3953, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873181543315712e-05, + "loss": 3.4133, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6864795595805196e-05, + "loss": 3.3916, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856409648294672e-05, + "loss": 3.3933, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848040079587885e-05, + "loss": 3.4025, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839654132077365e-05, + "loss": 3.4024, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.683126818456684e-05, + "loss": 3.405, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.682288223705632e-05, + "loss": 3.4123, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814496289545804e-05, + "loss": 3.3945, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806110342035284e-05, + "loss": 3.3902, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797724394524764e-05, + "loss": 3.4, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789354825817973e-05, + "loss": 3.4119, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.6780968878307453e-05, + "loss": 3.3989, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.6772582930796933e-05, + "loss": 3.4097, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.6764196983286413e-05, + "loss": 3.407, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.6755811035775897e-05, + "loss": 3.4061, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.6747425088265377e-05, + "loss": 3.4011, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.6739039140754853e-05, + "loss": 3.3956, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.6730653193244333e-05, + "loss": 3.4084, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.6722283624537546e-05, + "loss": 3.4055, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.6713897677027026e-05, + "loss": 3.4064, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.6705511729516506e-05, + "loss": 3.3975, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.6697125782005985e-05, + "loss": 3.3919, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.6688772592102927e-05, + "loss": 3.4002, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.6680386644592407e-05, + "loss": 3.4131, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672000697081887e-05, + "loss": 3.4003, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663614749571367e-05, + "loss": 3.4063, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6655228802060847e-05, + "loss": 3.3983, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.664685923335406e-05, + "loss": 3.3971, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.663847328584354e-05, + "loss": 3.4016, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.663008733833302e-05, + "loss": 3.3909, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621701390822496e-05, + "loss": 3.3928, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.661331544331198e-05, + "loss": 3.4046, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.660492949580146e-05, + "loss": 3.4027, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.659654354829094e-05, + "loss": 3.3983, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.6588173979584148e-05, + "loss": 3.3985, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.657980441087736e-05, + "loss": 3.3965, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.657141846336684e-05, + "loss": 3.4115, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.656303251585632e-05, + "loss": 3.3981, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.65546465683458e-05, + "loss": 3.409, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.654626062083528e-05, + "loss": 3.41, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.653787467332476e-05, + "loss": 3.3999, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.652948872581424e-05, + "loss": 3.3991, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.652110277830372e-05, + "loss": 3.3986, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.651273320959693e-05, + "loss": 3.399, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504347262086413e-05, + "loss": 3.4075, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6495961314575893e-05, + "loss": 3.3921, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487575367065373e-05, + "loss": 3.3928, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479205798358582e-05, + "loss": 3.3991, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6470819850848062e-05, + "loss": 3.4009, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462450282141274e-05, + "loss": 3.4002, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454064334630754e-05, + "loss": 3.3918, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445678387120234e-05, + "loss": 3.3982, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437292439609714e-05, + "loss": 3.3932, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6428906492099194e-05, + "loss": 3.4085, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420520544588674e-05, + "loss": 3.4003, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641213459707815e-05, + "loss": 3.4084, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.6403748649567634e-05, + "loss": 3.3892, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395379080860846e-05, + "loss": 3.4113, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6386993133350326e-05, + "loss": 3.4004, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378607185839803e-05, + "loss": 3.408, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370221238329283e-05, + "loss": 3.4076, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.6361851669622495e-05, + "loss": 3.4056, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6353465722111975e-05, + "loss": 3.3981, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.6345079774601455e-05, + "loss": 3.4133, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.6336693827090935e-05, + "loss": 3.3875, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.6328324258384148e-05, + "loss": 3.4049, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.6319954689677357e-05, + "loss": 3.3988, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.6311568742166837e-05, + "loss": 3.3989, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630318279465632e-05, + "loss": 3.3949, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.62947968471458e-05, + "loss": 3.3948, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628642727843901e-05, + "loss": 3.3979, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627804133092849e-05, + "loss": 3.4017, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.626965538341797e-05, + "loss": 3.4034, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.8619349002838135, + "eval_runtime": 306.9878, + "eval_samples_per_second": 1243.017, + "eval_steps_per_second": 38.845, + "step": 2060640 + }, + { + "epoch": 1.0, + "learning_rate": 1.626126943590745e-05, + "loss": 3.3946, + "step": 2060800 + }, + { + "epoch": 1.0, + "learning_rate": 1.625288348839693e-05, + "loss": 3.392, + "step": 2061312 + }, + { + "epoch": 1.0, + "learning_rate": 1.624449754088641e-05, + "loss": 3.3919, + "step": 2061824 + }, + { + "epoch": 1.0, + "learning_rate": 1.623611159337589e-05, + "loss": 3.4098, + "step": 2062336 + }, + { + "epoch": 1.0, + "learning_rate": 1.622772564586537e-05, + "loss": 3.4074, + "step": 2062848 + }, + { + "epoch": 1.0, + "learning_rate": 1.6219356077158578e-05, + "loss": 3.3931, + "step": 2063360 + }, + { + "epoch": 1.0, + "learning_rate": 1.6210970129648058e-05, + "loss": 3.3968, + "step": 2063872 + }, + { + "epoch": 1.0, + "learning_rate": 1.6202584182137538e-05, + "loss": 3.394, + "step": 2064384 + }, + { + "epoch": 1.0, + "learning_rate": 1.619419823462702e-05, + "loss": 3.3967, + "step": 2064896 + }, + { + "epoch": 1.0, + "learning_rate": 1.618582866592023e-05, + "loss": 3.4039, + "step": 2065408 + }, + { + "epoch": 1.0, + "learning_rate": 1.617744271840971e-05, + "loss": 3.3994, + "step": 2065920 + }, + { + "epoch": 1.0, + "learning_rate": 1.616905677089919e-05, + "loss": 3.3956, + "step": 2066432 + }, + { + "epoch": 1.0, + "learning_rate": 1.616067082338867e-05, + "loss": 3.4061, + "step": 2066944 + }, + { + "epoch": 1.0, + "learning_rate": 1.6152301254681883e-05, + "loss": 3.3825, + "step": 2067456 + }, + { + "epoch": 1.0, + "learning_rate": 1.6143931685975095e-05, + "loss": 3.3951, + "step": 2067968 + }, + { + "epoch": 1.0, + "learning_rate": 1.6135545738464572e-05, + "loss": 3.3833, + "step": 2068480 + }, + { + "epoch": 1.0, + "learning_rate": 1.6127159790954052e-05, + "loss": 3.3965, + "step": 2068992 + }, + { + "epoch": 1.0, + "learning_rate": 1.611877384344353e-05, + "loss": 3.401, + "step": 2069504 + }, + { + "epoch": 1.0, + "learning_rate": 1.611038789593301e-05, + "loss": 3.3817, + "step": 2070016 + }, + { + "epoch": 1.0, + "learning_rate": 1.610200194842249e-05, + "loss": 3.4036, + "step": 2070528 + }, + { + "epoch": 1.0, + "learning_rate": 1.6093616000911975e-05, + "loss": 3.4084, + "step": 2071040 + }, + { + "epoch": 1.0, + "learning_rate": 1.6085246432205184e-05, + "loss": 3.402, + "step": 2071552 + }, + { + "epoch": 1.0, + "learning_rate": 1.6076876863498393e-05, + "loss": 3.4022, + "step": 2072064 + }, + { + "epoch": 1.0, + "learning_rate": 1.6068490915987873e-05, + "loss": 3.4013, + "step": 2072576 + }, + { + "epoch": 1.0, + "learning_rate": 1.6060104968477353e-05, + "loss": 3.4034, + "step": 2073088 + }, + { + "epoch": 1.0, + "learning_rate": 1.6051719020966836e-05, + "loss": 3.3944, + "step": 2073600 + }, + { + "epoch": 1.0, + "learning_rate": 1.6043333073456316e-05, + "loss": 3.395, + "step": 2074112 + }, + { + "epoch": 1.0, + "learning_rate": 1.6034947125945796e-05, + "loss": 3.4001, + "step": 2074624 + }, + { + "epoch": 1.0, + "learning_rate": 1.6026561178435276e-05, + "loss": 3.39, + "step": 2075136 + }, + { + "epoch": 1.0, + "learning_rate": 1.6018175230924753e-05, + "loss": 3.3922, + "step": 2075648 + }, + { + "epoch": 1.01, + "learning_rate": 1.6009805662217965e-05, + "loss": 3.4041, + "step": 2076160 + }, + { + "epoch": 1.01, + "learning_rate": 1.6001436093511178e-05, + "loss": 3.4065, + "step": 2076672 + }, + { + "epoch": 1.01, + "learning_rate": 1.5993050146000658e-05, + "loss": 3.3993, + "step": 2077184 + }, + { + "epoch": 1.01, + "learning_rate": 1.5984664198490138e-05, + "loss": 3.4042, + "step": 2077696 + }, + { + "epoch": 1.01, + "learning_rate": 1.5976278250979618e-05, + "loss": 3.3868, + "step": 2078208 + }, + { + "epoch": 1.01, + "learning_rate": 1.5967892303469098e-05, + "loss": 3.3988, + "step": 2078720 + }, + { + "epoch": 1.01, + "learning_rate": 1.5959506355958574e-05, + "loss": 3.4028, + "step": 2079232 + }, + { + "epoch": 1.01, + "learning_rate": 1.5951120408448058e-05, + "loss": 3.3834, + "step": 2079744 + }, + { + "epoch": 1.01, + "learning_rate": 1.5942734460937537e-05, + "loss": 3.3916, + "step": 2080256 + }, + { + "epoch": 1.01, + "learning_rate": 1.593436489223075e-05, + "loss": 3.3908, + "step": 2080768 + }, + { + "epoch": 1.01, + "learning_rate": 1.5925978944720227e-05, + "loss": 3.3889, + "step": 2081280 + }, + { + "epoch": 1.01, + "learning_rate": 1.591760937601344e-05, + "loss": 3.3923, + "step": 2081792 + }, + { + "epoch": 1.01, + "learning_rate": 1.590922342850292e-05, + "loss": 3.4021, + "step": 2082304 + }, + { + "epoch": 1.01, + "learning_rate": 1.59008374809924e-05, + "loss": 3.4003, + "step": 2082816 + }, + { + "epoch": 1.01, + "learning_rate": 1.589245153348188e-05, + "loss": 3.3947, + "step": 2083328 + }, + { + "epoch": 1.01, + "learning_rate": 1.588406558597136e-05, + "loss": 3.4014, + "step": 2083840 + }, + { + "epoch": 1.01, + "learning_rate": 1.587567963846084e-05, + "loss": 3.392, + "step": 2084352 + }, + { + "epoch": 1.01, + "learning_rate": 1.586729369095032e-05, + "loss": 3.4017, + "step": 2084864 + }, + { + "epoch": 1.01, + "learning_rate": 1.58589077434398e-05, + "loss": 3.3746, + "step": 2085376 + }, + { + "epoch": 1.01, + "learning_rate": 1.585053817473301e-05, + "loss": 3.4003, + "step": 2085888 + }, + { + "epoch": 1.01, + "learning_rate": 1.584215222722249e-05, + "loss": 3.3907, + "step": 2086400 + }, + { + "epoch": 1.01, + "learning_rate": 1.583376627971197e-05, + "loss": 3.4043, + "step": 2086912 + }, + { + "epoch": 1.01, + "learning_rate": 1.582538033220145e-05, + "loss": 3.3902, + "step": 2087424 + }, + { + "epoch": 1.01, + "learning_rate": 1.5817027142298393e-05, + "loss": 3.3886, + "step": 2087936 + }, + { + "epoch": 1.01, + "learning_rate": 1.5808641194787873e-05, + "loss": 3.3856, + "step": 2088448 + }, + { + "epoch": 1.01, + "learning_rate": 1.5800255247277353e-05, + "loss": 3.3902, + "step": 2088960 + }, + { + "epoch": 1.01, + "learning_rate": 1.5791869299766833e-05, + "loss": 3.3996, + "step": 2089472 + }, + { + "epoch": 1.01, + "learning_rate": 1.5783483352256313e-05, + "loss": 3.3813, + "step": 2089984 + }, + { + "epoch": 1.01, + "learning_rate": 1.5775097404745792e-05, + "loss": 3.4022, + "step": 2090496 + }, + { + "epoch": 1.01, + "learning_rate": 1.5766711457235272e-05, + "loss": 3.3951, + "step": 2091008 + }, + { + "epoch": 1.01, + "learning_rate": 1.575834188852848e-05, + "loss": 3.3705, + "step": 2091520 + }, + { + "epoch": 1.01, + "learning_rate": 1.574995594101796e-05, + "loss": 3.4016, + "step": 2092032 + }, + { + "epoch": 1.01, + "learning_rate": 1.5741569993507445e-05, + "loss": 3.3866, + "step": 2092544 + }, + { + "epoch": 1.01, + "learning_rate": 1.5733184045996925e-05, + "loss": 3.3735, + "step": 2093056 + }, + { + "epoch": 1.01, + "learning_rate": 1.5724798098486405e-05, + "loss": 3.3922, + "step": 2093568 + }, + { + "epoch": 1.01, + "learning_rate": 1.571641215097588e-05, + "loss": 3.3934, + "step": 2094080 + }, + { + "epoch": 1.01, + "learning_rate": 1.570802620346536e-05, + "loss": 3.3831, + "step": 2094592 + }, + { + "epoch": 1.01, + "learning_rate": 1.569964025595484e-05, + "loss": 3.3991, + "step": 2095104 + }, + { + "epoch": 1.01, + "learning_rate": 1.5691270687248054e-05, + "loss": 3.3751, + "step": 2095616 + }, + { + "epoch": 1.01, + "learning_rate": 1.5682884739737534e-05, + "loss": 3.3825, + "step": 2096128 + }, + { + "epoch": 1.01, + "learning_rate": 1.5674498792227014e-05, + "loss": 3.3963, + "step": 2096640 + }, + { + "epoch": 1.01, + "learning_rate": 1.5666112844716494e-05, + "loss": 3.3942, + "step": 2097152 + }, + { + "epoch": 1.01, + "learning_rate": 1.5657743276009703e-05, + "loss": 3.3962, + "step": 2097664 + }, + { + "epoch": 1.01, + "learning_rate": 1.5649357328499183e-05, + "loss": 3.3957, + "step": 2098176 + }, + { + "epoch": 1.01, + "learning_rate": 1.5640971380988666e-05, + "loss": 3.3994, + "step": 2098688 + }, + { + "epoch": 1.01, + "learning_rate": 1.5632585433478146e-05, + "loss": 3.3893, + "step": 2099200 + }, + { + "epoch": 1.01, + "learning_rate": 1.5624215864771355e-05, + "loss": 3.4021, + "step": 2099712 + }, + { + "epoch": 1.01, + "learning_rate": 1.5615829917260835e-05, + "loss": 3.3851, + "step": 2100224 + }, + { + "epoch": 1.01, + "learning_rate": 1.5607443969750315e-05, + "loss": 3.3818, + "step": 2100736 + }, + { + "epoch": 1.01, + "learning_rate": 1.5599074401043527e-05, + "loss": 3.3904, + "step": 2101248 + }, + { + "epoch": 1.01, + "learning_rate": 1.5590688453533007e-05, + "loss": 3.3949, + "step": 2101760 + }, + { + "epoch": 1.01, + "learning_rate": 1.5582302506022487e-05, + "loss": 3.3938, + "step": 2102272 + }, + { + "epoch": 1.01, + "learning_rate": 1.55739329373157e-05, + "loss": 3.4027, + "step": 2102784 + }, + { + "epoch": 1.01, + "learning_rate": 1.5565546989805176e-05, + "loss": 3.3862, + "step": 2103296 + }, + { + "epoch": 1.01, + "learning_rate": 1.5557161042294656e-05, + "loss": 3.377, + "step": 2103808 + }, + { + "epoch": 1.01, + "learning_rate": 1.5548775094784136e-05, + "loss": 3.3903, + "step": 2104320 + }, + { + "epoch": 1.01, + "learning_rate": 1.5540405526077352e-05, + "loss": 3.4026, + "step": 2104832 + }, + { + "epoch": 1.01, + "learning_rate": 1.553201957856683e-05, + "loss": 3.387, + "step": 2105344 + }, + { + "epoch": 1.01, + "learning_rate": 1.552363363105631e-05, + "loss": 3.3986, + "step": 2105856 + }, + { + "epoch": 1.01, + "learning_rate": 1.551524768354579e-05, + "loss": 3.399, + "step": 2106368 + }, + { + "epoch": 1.02, + "learning_rate": 1.550686173603527e-05, + "loss": 3.3945, + "step": 2106880 + }, + { + "epoch": 1.02, + "learning_rate": 1.549847578852475e-05, + "loss": 3.3933, + "step": 2107392 + }, + { + "epoch": 1.02, + "learning_rate": 1.549010621981796e-05, + "loss": 3.3852, + "step": 2107904 + }, + { + "epoch": 1.02, + "learning_rate": 1.548172027230744e-05, + "loss": 3.3984, + "step": 2108416 + }, + { + "epoch": 1.02, + "learning_rate": 1.547333432479692e-05, + "loss": 3.3967, + "step": 2108928 + }, + { + "epoch": 1.02, + "learning_rate": 1.54649483772864e-05, + "loss": 3.3936, + "step": 2109440 + }, + { + "epoch": 1.02, + "learning_rate": 1.545656242977588e-05, + "loss": 3.3895, + "step": 2109952 + }, + { + "epoch": 1.02, + "learning_rate": 1.5448176482265357e-05, + "loss": 3.3812, + "step": 2110464 + }, + { + "epoch": 1.02, + "learning_rate": 1.5439790534754837e-05, + "loss": 3.3919, + "step": 2110976 + }, + { + "epoch": 1.02, + "learning_rate": 1.543140458724432e-05, + "loss": 3.4058, + "step": 2111488 + }, + { + "epoch": 1.02, + "learning_rate": 1.5423035018537533e-05, + "loss": 3.3884, + "step": 2112000 + }, + { + "epoch": 1.02, + "learning_rate": 1.541464907102701e-05, + "loss": 3.3946, + "step": 2112512 + }, + { + "epoch": 1.02, + "learning_rate": 1.5406279502320222e-05, + "loss": 3.3884, + "step": 2113024 + }, + { + "epoch": 1.02, + "learning_rate": 1.5397893554809702e-05, + "loss": 3.3889, + "step": 2113536 + }, + { + "epoch": 1.02, + "learning_rate": 1.5389507607299182e-05, + "loss": 3.3888, + "step": 2114048 + }, + { + "epoch": 1.02, + "learning_rate": 1.5381121659788662e-05, + "loss": 3.3857, + "step": 2114560 + }, + { + "epoch": 1.02, + "learning_rate": 1.5372735712278142e-05, + "loss": 3.3825, + "step": 2115072 + }, + { + "epoch": 1.02, + "learning_rate": 1.5364349764767622e-05, + "loss": 3.3947, + "step": 2115584 + }, + { + "epoch": 1.02, + "learning_rate": 1.5355963817257102e-05, + "loss": 3.3925, + "step": 2116096 + }, + { + "epoch": 1.02, + "learning_rate": 1.534759424855031e-05, + "loss": 3.3869, + "step": 2116608 + }, + { + "epoch": 1.02, + "learning_rate": 1.533920830103979e-05, + "loss": 3.394, + "step": 2117120 + }, + { + "epoch": 1.02, + "learning_rate": 1.5330838732333004e-05, + "loss": 3.3846, + "step": 2117632 + }, + { + "epoch": 1.02, + "learning_rate": 1.5322452784822483e-05, + "loss": 3.4004, + "step": 2118144 + }, + { + "epoch": 1.02, + "learning_rate": 1.5314066837311963e-05, + "loss": 3.3876, + "step": 2118656 + }, + { + "epoch": 1.02, + "learning_rate": 1.5305680889801443e-05, + "loss": 3.397, + "step": 2119168 + }, + { + "epoch": 1.02, + "learning_rate": 1.5297294942290923e-05, + "loss": 3.4002, + "step": 2119680 + }, + { + "epoch": 1.02, + "learning_rate": 1.5288925373584136e-05, + "loss": 3.3894, + "step": 2120192 + }, + { + "epoch": 1.02, + "learning_rate": 1.5280539426073616e-05, + "loss": 3.3895, + "step": 2120704 + }, + { + "epoch": 1.02, + "learning_rate": 1.5272153478563096e-05, + "loss": 3.3893, + "step": 2121216 + }, + { + "epoch": 1.02, + "learning_rate": 1.5263767531052576e-05, + "loss": 3.387, + "step": 2121728 + }, + { + "epoch": 1.02, + "learning_rate": 1.5255397962345785e-05, + "loss": 3.395, + "step": 2122240 + }, + { + "epoch": 1.02, + "learning_rate": 1.5247012014835266e-05, + "loss": 3.3826, + "step": 2122752 + }, + { + "epoch": 1.02, + "learning_rate": 1.5238626067324746e-05, + "loss": 3.3831, + "step": 2123264 + }, + { + "epoch": 1.02, + "learning_rate": 1.5230240119814226e-05, + "loss": 3.392, + "step": 2123776 + }, + { + "epoch": 1.02, + "learning_rate": 1.5221854172303706e-05, + "loss": 3.391, + "step": 2124288 + }, + { + "epoch": 1.02, + "learning_rate": 1.5213484603596917e-05, + "loss": 3.39, + "step": 2124800 + }, + { + "epoch": 1.02, + "learning_rate": 1.5205098656086397e-05, + "loss": 3.383, + "step": 2125312 + }, + { + "epoch": 1.02, + "learning_rate": 1.5196712708575877e-05, + "loss": 3.3844, + "step": 2125824 + }, + { + "epoch": 1.02, + "learning_rate": 1.5188326761065359e-05, + "loss": 3.3848, + "step": 2126336 + }, + { + "epoch": 1.02, + "learning_rate": 1.5179940813554835e-05, + "loss": 3.4004, + "step": 2126848 + }, + { + "epoch": 1.02, + "learning_rate": 1.5171554866044315e-05, + "loss": 3.3868, + "step": 2127360 + }, + { + "epoch": 1.02, + "learning_rate": 1.5163168918533797e-05, + "loss": 3.4022, + "step": 2127872 + }, + { + "epoch": 1.02, + "learning_rate": 1.5154782971023277e-05, + "loss": 3.3783, + "step": 2128384 + }, + { + "epoch": 1.02, + "learning_rate": 1.5146413402316486e-05, + "loss": 3.399, + "step": 2128896 + }, + { + "epoch": 1.02, + "learning_rate": 1.5138027454805968e-05, + "loss": 3.3928, + "step": 2129408 + }, + { + "epoch": 1.02, + "learning_rate": 1.5129641507295447e-05, + "loss": 3.3949, + "step": 2129920 + }, + { + "epoch": 1.02, + "learning_rate": 1.5121255559784927e-05, + "loss": 3.3978, + "step": 2130432 + }, + { + "epoch": 1.02, + "learning_rate": 1.5112885991078138e-05, + "loss": 3.3937, + "step": 2130944 + }, + { + "epoch": 1.02, + "learning_rate": 1.5104500043567618e-05, + "loss": 3.3929, + "step": 2131456 + }, + { + "epoch": 1.02, + "learning_rate": 1.5096114096057098e-05, + "loss": 3.3983, + "step": 2131968 + }, + { + "epoch": 1.02, + "learning_rate": 1.5087728148546578e-05, + "loss": 3.3852, + "step": 2132480 + }, + { + "epoch": 1.02, + "learning_rate": 1.5079358579839789e-05, + "loss": 3.3936, + "step": 2132992 + }, + { + "epoch": 1.02, + "learning_rate": 1.5070989011133001e-05, + "loss": 3.3905, + "step": 2133504 + }, + { + "epoch": 1.02, + "learning_rate": 1.5062603063622483e-05, + "loss": 3.3884, + "step": 2134016 + }, + { + "epoch": 1.02, + "learning_rate": 1.505421711611196e-05, + "loss": 3.3844, + "step": 2134528 + }, + { + "epoch": 1.02, + "learning_rate": 1.504583116860144e-05, + "loss": 3.3903, + "step": 2135040 + }, + { + "epoch": 1.02, + "learning_rate": 1.5037461599894654e-05, + "loss": 3.3873, + "step": 2135552 + }, + { + "epoch": 1.02, + "learning_rate": 1.502907565238413e-05, + "loss": 3.3873, + "step": 2136064 + }, + { + "epoch": 1.02, + "learning_rate": 1.5020689704873612e-05, + "loss": 3.3921, + "step": 2136576 + }, + { + "epoch": 1.03, + "eval_loss": 3.8619747161865234, + "eval_runtime": 306.8785, + "eval_samples_per_second": 1243.46, + "eval_steps_per_second": 38.859, + "step": 2136960 + }, + { + "epoch": 0.0, + "learning_rate": 1.5012303757363092e-05, + "loss": 3.3942, + "step": 2137088 + }, + { + "epoch": 0.0, + "learning_rate": 1.5003917809852572e-05, + "loss": 3.3788, + "step": 2137600 + }, + { + "epoch": 0.0, + "learning_rate": 1.4995531862342052e-05, + "loss": 3.3843, + "step": 2138112 + }, + { + "epoch": 0.0, + "learning_rate": 1.4987145914831532e-05, + "loss": 3.3972, + "step": 2138624 + }, + { + "epoch": 0.0, + "learning_rate": 1.4978776346124743e-05, + "loss": 3.3927, + "step": 2139136 + }, + { + "epoch": 0.0, + "learning_rate": 1.4970390398614223e-05, + "loss": 3.3849, + "step": 2139648 + }, + { + "epoch": 0.0, + "learning_rate": 1.4962020829907433e-05, + "loss": 3.3925, + "step": 2140160 + }, + { + "epoch": 0.0, + "learning_rate": 1.4953634882396913e-05, + "loss": 3.3834, + "step": 2140672 + }, + { + "epoch": 0.0, + "learning_rate": 1.4945248934886393e-05, + "loss": 3.3865, + "step": 2141184 + }, + { + "epoch": 0.0, + "learning_rate": 1.4936862987375875e-05, + "loss": 3.3899, + "step": 2141696 + }, + { + "epoch": 0.0, + "learning_rate": 1.4928477039865355e-05, + "loss": 3.3955, + "step": 2142208 + }, + { + "epoch": 0.0, + "learning_rate": 1.4920091092354835e-05, + "loss": 3.3834, + "step": 2142720 + }, + { + "epoch": 0.0, + "learning_rate": 1.4911705144844313e-05, + "loss": 3.3971, + "step": 2143232 + }, + { + "epoch": 0.0, + "learning_rate": 1.4903335576137526e-05, + "loss": 3.3696, + "step": 2143744 + }, + { + "epoch": 0.0, + "learning_rate": 1.4894949628627005e-05, + "loss": 3.3879, + "step": 2144256 + }, + { + "epoch": 0.0, + "learning_rate": 1.4886563681116485e-05, + "loss": 3.3742, + "step": 2144768 + }, + { + "epoch": 0.0, + "learning_rate": 1.4878177733605964e-05, + "loss": 3.3867, + "step": 2145280 + }, + { + "epoch": 0.0, + "learning_rate": 1.4869791786095444e-05, + "loss": 3.3886, + "step": 2145792 + }, + { + "epoch": 0.0, + "learning_rate": 1.4861405838584924e-05, + "loss": 3.3731, + "step": 2146304 + }, + { + "epoch": 0.0, + "learning_rate": 1.4853019891074405e-05, + "loss": 3.3911, + "step": 2146816 + }, + { + "epoch": 0.0, + "learning_rate": 1.4844633943563885e-05, + "loss": 3.3988, + "step": 2147328 + }, + { + "epoch": 0.0, + "learning_rate": 1.4836280753660829e-05, + "loss": 3.389, + "step": 2147840 + }, + { + "epoch": 0.0, + "learning_rate": 1.4827894806150308e-05, + "loss": 3.3934, + "step": 2148352 + }, + { + "epoch": 0.0, + "learning_rate": 1.4819508858639785e-05, + "loss": 3.3905, + "step": 2148864 + }, + { + "epoch": 0.0, + "learning_rate": 1.4811122911129267e-05, + "loss": 3.396, + "step": 2149376 + }, + { + "epoch": 0.0, + "learning_rate": 1.4802736963618747e-05, + "loss": 3.383, + "step": 2149888 + }, + { + "epoch": 0.0, + "learning_rate": 1.4794351016108227e-05, + "loss": 3.3822, + "step": 2150400 + }, + { + "epoch": 0.0, + "learning_rate": 1.4785965068597707e-05, + "loss": 3.3911, + "step": 2150912 + }, + { + "epoch": 0.0, + "learning_rate": 1.4777579121087187e-05, + "loss": 3.3792, + "step": 2151424 + }, + { + "epoch": 0.0, + "learning_rate": 1.4769209552380397e-05, + "loss": 3.3809, + "step": 2151936 + }, + { + "epoch": 0.01, + "learning_rate": 1.4760823604869877e-05, + "loss": 3.398, + "step": 2152448 + }, + { + "epoch": 0.01, + "learning_rate": 1.4752454036163088e-05, + "loss": 3.392, + "step": 2152960 + }, + { + "epoch": 0.01, + "learning_rate": 1.4744068088652568e-05, + "loss": 3.3866, + "step": 2153472 + }, + { + "epoch": 0.01, + "learning_rate": 1.4735682141142048e-05, + "loss": 3.3963, + "step": 2153984 + }, + { + "epoch": 0.01, + "learning_rate": 1.472729619363153e-05, + "loss": 3.3793, + "step": 2154496 + }, + { + "epoch": 0.01, + "learning_rate": 1.4718926624924739e-05, + "loss": 3.3886, + "step": 2155008 + }, + { + "epoch": 0.01, + "learning_rate": 1.471054067741422e-05, + "loss": 3.3885, + "step": 2155520 + }, + { + "epoch": 0.01, + "learning_rate": 1.47021547299037e-05, + "loss": 3.3745, + "step": 2156032 + }, + { + "epoch": 0.01, + "learning_rate": 1.469376878239318e-05, + "loss": 3.3829, + "step": 2156544 + }, + { + "epoch": 0.01, + "learning_rate": 1.468538283488266e-05, + "loss": 3.3819, + "step": 2157056 + }, + { + "epoch": 0.01, + "learning_rate": 1.467699688737214e-05, + "loss": 3.377, + "step": 2157568 + }, + { + "epoch": 0.01, + "learning_rate": 1.4668627318665351e-05, + "loss": 3.3834, + "step": 2158080 + }, + { + "epoch": 0.01, + "learning_rate": 1.4660241371154831e-05, + "loss": 3.3908, + "step": 2158592 + }, + { + "epoch": 0.01, + "learning_rate": 1.4651855423644311e-05, + "loss": 3.3894, + "step": 2159104 + }, + { + "epoch": 0.01, + "learning_rate": 1.464346947613379e-05, + "loss": 3.3839, + "step": 2159616 + }, + { + "epoch": 0.01, + "learning_rate": 1.4635083528623269e-05, + "loss": 3.3911, + "step": 2160128 + }, + { + "epoch": 0.01, + "learning_rate": 1.4626697581112749e-05, + "loss": 3.3798, + "step": 2160640 + }, + { + "epoch": 0.01, + "learning_rate": 1.461831163360223e-05, + "loss": 3.3912, + "step": 2161152 + }, + { + "epoch": 0.01, + "learning_rate": 1.460992568609171e-05, + "loss": 3.3712, + "step": 2161664 + }, + { + "epoch": 0.01, + "learning_rate": 1.4601556117384921e-05, + "loss": 3.3877, + "step": 2162176 + }, + { + "epoch": 0.01, + "learning_rate": 1.4593170169874401e-05, + "loss": 3.3802, + "step": 2162688 + }, + { + "epoch": 0.01, + "learning_rate": 1.4584784222363881e-05, + "loss": 3.3967, + "step": 2163200 + }, + { + "epoch": 0.01, + "learning_rate": 1.4576398274853361e-05, + "loss": 3.3802, + "step": 2163712 + }, + { + "epoch": 0.01, + "learning_rate": 1.4568028706146572e-05, + "loss": 3.3766, + "step": 2164224 + }, + { + "epoch": 0.01, + "learning_rate": 1.4559642758636052e-05, + "loss": 3.3759, + "step": 2164736 + }, + { + "epoch": 0.01, + "learning_rate": 1.4551256811125532e-05, + "loss": 3.3802, + "step": 2165248 + }, + { + "epoch": 0.01, + "learning_rate": 1.4542887242418743e-05, + "loss": 3.3924, + "step": 2165760 + }, + { + "epoch": 0.01, + "learning_rate": 1.4534501294908223e-05, + "loss": 3.3692, + "step": 2166272 + }, + { + "epoch": 0.01, + "learning_rate": 1.4526115347397703e-05, + "loss": 3.395, + "step": 2166784 + }, + { + "epoch": 0.01, + "learning_rate": 1.4517729399887184e-05, + "loss": 3.385, + "step": 2167296 + }, + { + "epoch": 0.01, + "learning_rate": 1.4509359831180393e-05, + "loss": 3.3648, + "step": 2167808 + }, + { + "epoch": 0.01, + "learning_rate": 1.4500973883669875e-05, + "loss": 3.3908, + "step": 2168320 + }, + { + "epoch": 0.01, + "learning_rate": 1.4492587936159355e-05, + "loss": 3.3735, + "step": 2168832 + }, + { + "epoch": 0.01, + "learning_rate": 1.4484201988648835e-05, + "loss": 3.3659, + "step": 2169344 + }, + { + "epoch": 0.01, + "learning_rate": 1.4475816041138315e-05, + "loss": 3.3758, + "step": 2169856 + }, + { + "epoch": 0.01, + "learning_rate": 1.4467430093627795e-05, + "loss": 3.3848, + "step": 2170368 + }, + { + "epoch": 0.01, + "learning_rate": 1.4459044146117273e-05, + "loss": 3.3757, + "step": 2170880 + }, + { + "epoch": 0.01, + "learning_rate": 1.4450658198606753e-05, + "loss": 3.3801, + "step": 2171392 + }, + { + "epoch": 0.01, + "learning_rate": 1.4442288629899967e-05, + "loss": 3.3693, + "step": 2171904 + }, + { + "epoch": 0.01, + "learning_rate": 1.4433902682389444e-05, + "loss": 3.372, + "step": 2172416 + }, + { + "epoch": 0.01, + "learning_rate": 1.4425516734878924e-05, + "loss": 3.3836, + "step": 2172928 + }, + { + "epoch": 0.01, + "learning_rate": 1.4417130787368406e-05, + "loss": 3.3878, + "step": 2173440 + }, + { + "epoch": 0.01, + "learning_rate": 1.4408761218661618e-05, + "loss": 3.389, + "step": 2173952 + }, + { + "epoch": 0.01, + "learning_rate": 1.4400391649954829e-05, + "loss": 3.3824, + "step": 2174464 + }, + { + "epoch": 0.01, + "learning_rate": 1.4392005702444309e-05, + "loss": 3.3915, + "step": 2174976 + }, + { + "epoch": 0.01, + "learning_rate": 1.4383619754933789e-05, + "loss": 3.3779, + "step": 2175488 + }, + { + "epoch": 0.01, + "learning_rate": 1.4375233807423269e-05, + "loss": 3.3888, + "step": 2176000 + }, + { + "epoch": 0.01, + "learning_rate": 1.4366847859912747e-05, + "loss": 3.3774, + "step": 2176512 + }, + { + "epoch": 0.01, + "learning_rate": 1.4358461912402227e-05, + "loss": 3.3745, + "step": 2177024 + }, + { + "epoch": 0.01, + "learning_rate": 1.4350075964891707e-05, + "loss": 3.3806, + "step": 2177536 + }, + { + "epoch": 0.01, + "learning_rate": 1.4341690017381187e-05, + "loss": 3.3785, + "step": 2178048 + }, + { + "epoch": 0.01, + "learning_rate": 1.4333320448674398e-05, + "loss": 3.3884, + "step": 2178560 + }, + { + "epoch": 0.01, + "learning_rate": 1.4324934501163878e-05, + "loss": 3.3919, + "step": 2179072 + }, + { + "epoch": 0.01, + "learning_rate": 1.431654855365336e-05, + "loss": 3.381, + "step": 2179584 + }, + { + "epoch": 0.01, + "learning_rate": 1.4308162606142839e-05, + "loss": 3.3623, + "step": 2180096 + }, + { + "epoch": 0.01, + "learning_rate": 1.4299793037436048e-05, + "loss": 3.3839, + "step": 2180608 + }, + { + "epoch": 0.01, + "learning_rate": 1.4291423468729262e-05, + "loss": 3.3901, + "step": 2181120 + }, + { + "epoch": 0.01, + "learning_rate": 1.4283037521218742e-05, + "loss": 3.3814, + "step": 2181632 + }, + { + "epoch": 0.01, + "learning_rate": 1.427465157370822e-05, + "loss": 3.3863, + "step": 2182144 + }, + { + "epoch": 0.01, + "learning_rate": 1.42662656261977e-05, + "loss": 3.3923, + "step": 2182656 + }, + { + "epoch": 0.02, + "learning_rate": 1.425787967868718e-05, + "loss": 3.3811, + "step": 2183168 + }, + { + "epoch": 0.02, + "learning_rate": 1.424949373117666e-05, + "loss": 3.3838, + "step": 2183680 + }, + { + "epoch": 0.02, + "learning_rate": 1.4241124162469871e-05, + "loss": 3.3758, + "step": 2184192 + }, + { + "epoch": 0.02, + "learning_rate": 1.4232738214959351e-05, + "loss": 3.3898, + "step": 2184704 + }, + { + "epoch": 0.02, + "learning_rate": 1.4224352267448831e-05, + "loss": 3.3868, + "step": 2185216 + }, + { + "epoch": 0.02, + "learning_rate": 1.4215966319938311e-05, + "loss": 3.3845, + "step": 2185728 + }, + { + "epoch": 0.02, + "learning_rate": 1.4207580372427793e-05, + "loss": 3.3778, + "step": 2186240 + }, + { + "epoch": 0.02, + "learning_rate": 1.4199210803721002e-05, + "loss": 3.372, + "step": 2186752 + }, + { + "epoch": 0.02, + "learning_rate": 1.4190824856210484e-05, + "loss": 3.3795, + "step": 2187264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4182438908699964e-05, + "loss": 3.3939, + "step": 2187776 + }, + { + "epoch": 0.02, + "learning_rate": 1.4174052961189443e-05, + "loss": 3.3833, + "step": 2188288 + }, + { + "epoch": 0.02, + "learning_rate": 1.4165667013678922e-05, + "loss": 3.3808, + "step": 2188800 + }, + { + "epoch": 0.02, + "learning_rate": 1.4157297444972134e-05, + "loss": 3.3823, + "step": 2189312 + }, + { + "epoch": 0.02, + "learning_rate": 1.4148911497461614e-05, + "loss": 3.381, + "step": 2189824 + }, + { + "epoch": 0.02, + "learning_rate": 1.4140525549951094e-05, + "loss": 3.3791, + "step": 2190336 + }, + { + "epoch": 0.02, + "learning_rate": 1.4132139602440572e-05, + "loss": 3.3788, + "step": 2190848 + }, + { + "epoch": 0.02, + "learning_rate": 1.4123753654930052e-05, + "loss": 3.3734, + "step": 2191360 + }, + { + "epoch": 0.02, + "learning_rate": 1.4115384086223265e-05, + "loss": 3.3839, + "step": 2191872 + }, + { + "epoch": 0.02, + "learning_rate": 1.4106998138712746e-05, + "loss": 3.3827, + "step": 2192384 + }, + { + "epoch": 0.02, + "learning_rate": 1.4098612191202223e-05, + "loss": 3.3787, + "step": 2192896 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090226243691703e-05, + "loss": 3.3799, + "step": 2193408 + }, + { + "epoch": 0.02, + "learning_rate": 1.4081856674984917e-05, + "loss": 3.3769, + "step": 2193920 + }, + { + "epoch": 0.02, + "learning_rate": 1.4073470727474394e-05, + "loss": 3.3915, + "step": 2194432 + }, + { + "epoch": 0.02, + "learning_rate": 1.4065084779963875e-05, + "loss": 3.3802, + "step": 2194944 + }, + { + "epoch": 0.02, + "learning_rate": 1.4056698832453355e-05, + "loss": 3.3828, + "step": 2195456 + }, + { + "epoch": 0.02, + "learning_rate": 1.4048329263746568e-05, + "loss": 3.3871, + "step": 2195968 + }, + { + "epoch": 0.02, + "learning_rate": 1.4039943316236046e-05, + "loss": 3.3844, + "step": 2196480 + }, + { + "epoch": 0.02, + "learning_rate": 1.4031557368725526e-05, + "loss": 3.3821, + "step": 2196992 + }, + { + "epoch": 0.02, + "learning_rate": 1.4023171421215006e-05, + "loss": 3.3791, + "step": 2197504 + }, + { + "epoch": 0.02, + "learning_rate": 1.4014785473704486e-05, + "loss": 3.3785, + "step": 2198016 + }, + { + "epoch": 0.02, + "learning_rate": 1.4006399526193968e-05, + "loss": 3.385, + "step": 2198528 + }, + { + "epoch": 0.02, + "learning_rate": 1.3998029957487177e-05, + "loss": 3.3724, + "step": 2199040 + }, + { + "epoch": 0.02, + "learning_rate": 1.3989644009976657e-05, + "loss": 3.3782, + "step": 2199552 + }, + { + "epoch": 0.02, + "learning_rate": 1.3981258062466138e-05, + "loss": 3.3757, + "step": 2200064 + }, + { + "epoch": 0.02, + "learning_rate": 1.3972872114955618e-05, + "loss": 3.3821, + "step": 2200576 + }, + { + "epoch": 0.02, + "learning_rate": 1.3964502546248829e-05, + "loss": 3.3811, + "step": 2201088 + }, + { + "epoch": 0.02, + "learning_rate": 1.3956116598738309e-05, + "loss": 3.3741, + "step": 2201600 + }, + { + "epoch": 0.02, + "learning_rate": 1.3947730651227789e-05, + "loss": 3.3716, + "step": 2202112 + }, + { + "epoch": 0.02, + "learning_rate": 1.3939344703717269e-05, + "loss": 3.3787, + "step": 2202624 + }, + { + "epoch": 0.02, + "learning_rate": 1.3930958756206749e-05, + "loss": 3.3904, + "step": 2203136 + }, + { + "epoch": 0.02, + "learning_rate": 1.3922572808696227e-05, + "loss": 3.3792, + "step": 2203648 + }, + { + "epoch": 0.02, + "learning_rate": 1.3914186861185707e-05, + "loss": 3.3888, + "step": 2204160 + }, + { + "epoch": 0.02, + "learning_rate": 1.3905800913675187e-05, + "loss": 3.3699, + "step": 2204672 + }, + { + "epoch": 0.02, + "learning_rate": 1.3897431344968401e-05, + "loss": 3.3875, + "step": 2205184 + }, + { + "epoch": 0.02, + "learning_rate": 1.3889045397457878e-05, + "loss": 3.3839, + "step": 2205696 + }, + { + "epoch": 0.02, + "learning_rate": 1.3880659449947358e-05, + "loss": 3.3837, + "step": 2206208 + }, + { + "epoch": 0.02, + "learning_rate": 1.387227350243684e-05, + "loss": 3.3888, + "step": 2206720 + }, + { + "epoch": 0.02, + "learning_rate": 1.3863903933730049e-05, + "loss": 3.3828, + "step": 2207232 + }, + { + "epoch": 0.02, + "learning_rate": 1.385551798621953e-05, + "loss": 3.3884, + "step": 2207744 + }, + { + "epoch": 0.02, + "learning_rate": 1.384713203870901e-05, + "loss": 3.3894, + "step": 2208256 + }, + { + "epoch": 0.02, + "learning_rate": 1.383874609119849e-05, + "loss": 3.3708, + "step": 2208768 + }, + { + "epoch": 0.02, + "learning_rate": 1.3830376522491701e-05, + "loss": 3.3841, + "step": 2209280 + }, + { + "epoch": 0.02, + "learning_rate": 1.3822006953784913e-05, + "loss": 3.3783, + "step": 2209792 + }, + { + "epoch": 0.02, + "learning_rate": 1.3813621006274393e-05, + "loss": 3.3819, + "step": 2210304 + }, + { + "epoch": 0.02, + "learning_rate": 1.3805235058763873e-05, + "loss": 3.3729, + "step": 2210816 + }, + { + "epoch": 0.02, + "learning_rate": 1.3796849111253352e-05, + "loss": 3.3798, + "step": 2211328 + }, + { + "epoch": 0.02, + "learning_rate": 1.3788463163742831e-05, + "loss": 3.3761, + "step": 2211840 + }, + { + "epoch": 0.02, + "learning_rate": 1.3780077216232311e-05, + "loss": 3.3786, + "step": 2212352 + }, + { + "epoch": 0.02, + "learning_rate": 1.3771691268721793e-05, + "loss": 3.3813, + "step": 2212864 + }, + { + "epoch": 0.03, + "eval_loss": 3.8633737564086914, + "eval_runtime": 310.4867, + "eval_samples_per_second": 1229.009, + "eval_steps_per_second": 38.407, + "step": 2213280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3763321700015002e-05, + "loss": 3.3822, + "step": 2213376 + }, + { + "epoch": 1.0, + "learning_rate": 1.3754935752504484e-05, + "loss": 3.3697, + "step": 2213888 + }, + { + "epoch": 1.0, + "learning_rate": 1.3746549804993964e-05, + "loss": 3.3754, + "step": 2214400 + }, + { + "epoch": 1.0, + "learning_rate": 1.3738163857483444e-05, + "loss": 3.3873, + "step": 2214912 + }, + { + "epoch": 1.0, + "learning_rate": 1.3729777909972924e-05, + "loss": 3.3824, + "step": 2215424 + }, + { + "epoch": 1.0, + "learning_rate": 1.3721391962462404e-05, + "loss": 3.3785, + "step": 2215936 + }, + { + "epoch": 1.0, + "learning_rate": 1.3713006014951882e-05, + "loss": 3.3796, + "step": 2216448 + }, + { + "epoch": 1.0, + "learning_rate": 1.3704636446245094e-05, + "loss": 3.3724, + "step": 2216960 + }, + { + "epoch": 1.0, + "learning_rate": 1.3696250498734576e-05, + "loss": 3.3751, + "step": 2217472 + }, + { + "epoch": 1.0, + "learning_rate": 1.3687864551224056e-05, + "loss": 3.3837, + "step": 2217984 + }, + { + "epoch": 1.0, + "learning_rate": 1.3679478603713533e-05, + "loss": 3.3819, + "step": 2218496 + }, + { + "epoch": 1.0, + "learning_rate": 1.3671109035006747e-05, + "loss": 3.3783, + "step": 2219008 + }, + { + "epoch": 1.0, + "learning_rate": 1.3662723087496227e-05, + "loss": 3.3894, + "step": 2219520 + }, + { + "epoch": 1.0, + "learning_rate": 1.3654337139985703e-05, + "loss": 3.3579, + "step": 2220032 + }, + { + "epoch": 1.0, + "learning_rate": 1.3645951192475185e-05, + "loss": 3.378, + "step": 2220544 + }, + { + "epoch": 1.0, + "learning_rate": 1.3637581623768397e-05, + "loss": 3.363, + "step": 2221056 + }, + { + "epoch": 1.0, + "learning_rate": 1.3629212055061608e-05, + "loss": 3.3796, + "step": 2221568 + }, + { + "epoch": 1.0, + "learning_rate": 1.3620826107551088e-05, + "loss": 3.3733, + "step": 2222080 + }, + { + "epoch": 1.0, + "learning_rate": 1.3612440160040568e-05, + "loss": 3.3685, + "step": 2222592 + }, + { + "epoch": 1.0, + "learning_rate": 1.3604054212530048e-05, + "loss": 3.3764, + "step": 2223104 + }, + { + "epoch": 1.0, + "learning_rate": 1.3595668265019528e-05, + "loss": 3.3922, + "step": 2223616 + }, + { + "epoch": 1.0, + "learning_rate": 1.3587282317509006e-05, + "loss": 3.3781, + "step": 2224128 + }, + { + "epoch": 1.0, + "learning_rate": 1.3578912748802219e-05, + "loss": 3.3824, + "step": 2224640 + }, + { + "epoch": 1.0, + "learning_rate": 1.35705268012917e-05, + "loss": 3.3864, + "step": 2225152 + }, + { + "epoch": 1.0, + "learning_rate": 1.3562140853781177e-05, + "loss": 3.3858, + "step": 2225664 + }, + { + "epoch": 1.0, + "learning_rate": 1.3553754906270657e-05, + "loss": 3.3711, + "step": 2226176 + }, + { + "epoch": 1.0, + "learning_rate": 1.3545368958760139e-05, + "loss": 3.3741, + "step": 2226688 + }, + { + "epoch": 1.0, + "learning_rate": 1.3536983011249619e-05, + "loss": 3.3821, + "step": 2227200 + }, + { + "epoch": 1.0, + "learning_rate": 1.3528597063739098e-05, + "loss": 3.3669, + "step": 2227712 + }, + { + "epoch": 1.0, + "learning_rate": 1.3520211116228578e-05, + "loss": 3.3717, + "step": 2228224 + }, + { + "epoch": 1.01, + "learning_rate": 1.351184154752179e-05, + "loss": 3.386, + "step": 2228736 + }, + { + "epoch": 1.01, + "learning_rate": 1.3503471978815e-05, + "loss": 3.3842, + "step": 2229248 + }, + { + "epoch": 1.01, + "learning_rate": 1.349508603130448e-05, + "loss": 3.3823, + "step": 2229760 + }, + { + "epoch": 1.01, + "learning_rate": 1.348670008379396e-05, + "loss": 3.3838, + "step": 2230272 + }, + { + "epoch": 1.01, + "learning_rate": 1.347831413628344e-05, + "loss": 3.369, + "step": 2230784 + }, + { + "epoch": 1.01, + "learning_rate": 1.346992818877292e-05, + "loss": 3.3789, + "step": 2231296 + }, + { + "epoch": 1.01, + "learning_rate": 1.3461542241262402e-05, + "loss": 3.3818, + "step": 2231808 + }, + { + "epoch": 1.01, + "learning_rate": 1.345317267255561e-05, + "loss": 3.3622, + "step": 2232320 + }, + { + "epoch": 1.01, + "learning_rate": 1.3444786725045092e-05, + "loss": 3.3753, + "step": 2232832 + }, + { + "epoch": 1.01, + "learning_rate": 1.3436400777534572e-05, + "loss": 3.3702, + "step": 2233344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3428014830024052e-05, + "loss": 3.3649, + "step": 2233856 + }, + { + "epoch": 1.01, + "learning_rate": 1.3419645261317263e-05, + "loss": 3.3739, + "step": 2234368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3411259313806743e-05, + "loss": 3.3886, + "step": 2234880 + }, + { + "epoch": 1.01, + "learning_rate": 1.3402873366296223e-05, + "loss": 3.3726, + "step": 2235392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3394487418785703e-05, + "loss": 3.3761, + "step": 2235904 + }, + { + "epoch": 1.01, + "learning_rate": 1.3386101471275181e-05, + "loss": 3.38, + "step": 2236416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3377715523764661e-05, + "loss": 3.3716, + "step": 2236928 + }, + { + "epoch": 1.01, + "learning_rate": 1.3369329576254141e-05, + "loss": 3.3804, + "step": 2237440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3360943628743623e-05, + "loss": 3.3607, + "step": 2237952 + }, + { + "epoch": 1.01, + "learning_rate": 1.3352574060036832e-05, + "loss": 3.3734, + "step": 2238464 + }, + { + "epoch": 1.01, + "learning_rate": 1.3344188112526312e-05, + "loss": 3.3732, + "step": 2238976 + }, + { + "epoch": 1.01, + "learning_rate": 1.3335802165015793e-05, + "loss": 3.3849, + "step": 2239488 + }, + { + "epoch": 1.01, + "learning_rate": 1.3327416217505273e-05, + "loss": 3.3737, + "step": 2240000 + }, + { + "epoch": 1.01, + "learning_rate": 1.3319063027602217e-05, + "loss": 3.3666, + "step": 2240512 + }, + { + "epoch": 1.01, + "learning_rate": 1.3310677080091697e-05, + "loss": 3.3661, + "step": 2241024 + }, + { + "epoch": 1.01, + "learning_rate": 1.3302291132581177e-05, + "loss": 3.3705, + "step": 2241536 + }, + { + "epoch": 1.01, + "learning_rate": 1.3293905185070655e-05, + "loss": 3.3827, + "step": 2242048 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285519237560135e-05, + "loss": 3.361, + "step": 2242560 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277133290049615e-05, + "loss": 3.3827, + "step": 2243072 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268747342539095e-05, + "loss": 3.3725, + "step": 2243584 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260377773832305e-05, + "loss": 3.3602, + "step": 2244096 + }, + { + "epoch": 1.01, + "learning_rate": 1.3251991826321785e-05, + "loss": 3.3804, + "step": 2244608 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243605878811265e-05, + "loss": 3.3665, + "step": 2245120 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235219931300747e-05, + "loss": 3.3578, + "step": 2245632 + }, + { + "epoch": 1.01, + "learning_rate": 1.3226833983790227e-05, + "loss": 3.3645, + "step": 2246144 + }, + { + "epoch": 1.01, + "learning_rate": 1.3218448036279707e-05, + "loss": 3.3754, + "step": 2246656 + }, + { + "epoch": 1.01, + "learning_rate": 1.3210062088769187e-05, + "loss": 3.3698, + "step": 2247168 + }, + { + "epoch": 1.01, + "learning_rate": 1.3201676141258665e-05, + "loss": 3.3661, + "step": 2247680 + }, + { + "epoch": 1.01, + "learning_rate": 1.3193306572551878e-05, + "loss": 3.3671, + "step": 2248192 + }, + { + "epoch": 1.01, + "learning_rate": 1.3184920625041358e-05, + "loss": 3.3645, + "step": 2248704 + }, + { + "epoch": 1.01, + "learning_rate": 1.3176534677530836e-05, + "loss": 3.3696, + "step": 2249216 + }, + { + "epoch": 1.01, + "learning_rate": 1.3168148730020316e-05, + "loss": 3.3758, + "step": 2249728 + }, + { + "epoch": 1.01, + "learning_rate": 1.3159779161313528e-05, + "loss": 3.3774, + "step": 2250240 + }, + { + "epoch": 1.01, + "learning_rate": 1.3151409592606739e-05, + "loss": 3.3777, + "step": 2250752 + }, + { + "epoch": 1.01, + "learning_rate": 1.3143023645096219e-05, + "loss": 3.3776, + "step": 2251264 + }, + { + "epoch": 1.01, + "learning_rate": 1.31346376975857e-05, + "loss": 3.3689, + "step": 2251776 + }, + { + "epoch": 1.01, + "learning_rate": 1.312625175007518e-05, + "loss": 3.3771, + "step": 2252288 + }, + { + "epoch": 1.01, + "learning_rate": 1.311786580256466e-05, + "loss": 3.3698, + "step": 2252800 + }, + { + "epoch": 1.01, + "learning_rate": 1.3109479855054139e-05, + "loss": 3.3684, + "step": 2253312 + }, + { + "epoch": 1.01, + "learning_rate": 1.3101110286347351e-05, + "loss": 3.3659, + "step": 2253824 + }, + { + "epoch": 1.01, + "learning_rate": 1.3092724338836831e-05, + "loss": 3.3706, + "step": 2254336 + }, + { + "epoch": 1.01, + "learning_rate": 1.308433839132631e-05, + "loss": 3.3809, + "step": 2254848 + }, + { + "epoch": 1.01, + "learning_rate": 1.307595244381579e-05, + "loss": 3.3808, + "step": 2255360 + }, + { + "epoch": 1.01, + "learning_rate": 1.306756649630527e-05, + "loss": 3.3743, + "step": 2255872 + }, + { + "epoch": 1.01, + "learning_rate": 1.305918054879475e-05, + "loss": 3.353, + "step": 2256384 + }, + { + "epoch": 1.01, + "learning_rate": 1.3050794601284231e-05, + "loss": 3.3726, + "step": 2256896 + }, + { + "epoch": 1.01, + "learning_rate": 1.304242503257744e-05, + "loss": 3.3802, + "step": 2257408 + }, + { + "epoch": 1.01, + "learning_rate": 1.303403908506692e-05, + "loss": 3.3752, + "step": 2257920 + }, + { + "epoch": 1.01, + "learning_rate": 1.3025653137556402e-05, + "loss": 3.3713, + "step": 2258432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3017267190045882e-05, + "loss": 3.3844, + "step": 2258944 + }, + { + "epoch": 1.02, + "learning_rate": 1.3008881242535362e-05, + "loss": 3.3715, + "step": 2259456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3000511673828572e-05, + "loss": 3.3722, + "step": 2259968 + }, + { + "epoch": 1.02, + "learning_rate": 1.2992125726318052e-05, + "loss": 3.368, + "step": 2260480 + }, + { + "epoch": 1.02, + "learning_rate": 1.2983739778807532e-05, + "loss": 3.3784, + "step": 2260992 + }, + { + "epoch": 1.02, + "learning_rate": 1.2975353831297012e-05, + "loss": 3.377, + "step": 2261504 + }, + { + "epoch": 1.02, + "learning_rate": 1.296696788378649e-05, + "loss": 3.3783, + "step": 2262016 + }, + { + "epoch": 1.02, + "learning_rate": 1.295858193627597e-05, + "loss": 3.3657, + "step": 2262528 + }, + { + "epoch": 1.02, + "learning_rate": 1.295019598876545e-05, + "loss": 3.3649, + "step": 2263040 + }, + { + "epoch": 1.02, + "learning_rate": 1.2941810041254932e-05, + "loss": 3.3673, + "step": 2263552 + }, + { + "epoch": 1.02, + "learning_rate": 1.2933440472548141e-05, + "loss": 3.3819, + "step": 2264064 + }, + { + "epoch": 1.02, + "learning_rate": 1.2925054525037621e-05, + "loss": 3.374, + "step": 2264576 + }, + { + "epoch": 1.02, + "learning_rate": 1.2916668577527103e-05, + "loss": 3.372, + "step": 2265088 + }, + { + "epoch": 1.02, + "learning_rate": 1.2908299008820312e-05, + "loss": 3.3717, + "step": 2265600 + }, + { + "epoch": 1.02, + "learning_rate": 1.2899913061309794e-05, + "loss": 3.3704, + "step": 2266112 + }, + { + "epoch": 1.02, + "learning_rate": 1.2891527113799274e-05, + "loss": 3.37, + "step": 2266624 + }, + { + "epoch": 1.02, + "learning_rate": 1.2883141166288754e-05, + "loss": 3.3665, + "step": 2267136 + }, + { + "epoch": 1.02, + "learning_rate": 1.2874755218778233e-05, + "loss": 3.3673, + "step": 2267648 + }, + { + "epoch": 1.02, + "learning_rate": 1.2866369271267713e-05, + "loss": 3.3753, + "step": 2268160 + }, + { + "epoch": 1.02, + "learning_rate": 1.2857983323757195e-05, + "loss": 3.3736, + "step": 2268672 + }, + { + "epoch": 1.02, + "learning_rate": 1.2849613755050404e-05, + "loss": 3.3673, + "step": 2269184 + }, + { + "epoch": 1.02, + "learning_rate": 1.2841244186343615e-05, + "loss": 3.3703, + "step": 2269696 + }, + { + "epoch": 1.02, + "learning_rate": 1.2832858238833095e-05, + "loss": 3.368, + "step": 2270208 + }, + { + "epoch": 1.02, + "learning_rate": 1.2824472291322575e-05, + "loss": 3.3811, + "step": 2270720 + }, + { + "epoch": 1.02, + "learning_rate": 1.2816086343812057e-05, + "loss": 3.3728, + "step": 2271232 + }, + { + "epoch": 1.02, + "learning_rate": 1.2807716775105266e-05, + "loss": 3.3736, + "step": 2271744 + }, + { + "epoch": 1.02, + "learning_rate": 1.2799330827594747e-05, + "loss": 3.3733, + "step": 2272256 + }, + { + "epoch": 1.02, + "learning_rate": 1.2790944880084227e-05, + "loss": 3.3767, + "step": 2272768 + }, + { + "epoch": 1.02, + "learning_rate": 1.2782558932573707e-05, + "loss": 3.37, + "step": 2273280 + }, + { + "epoch": 1.02, + "learning_rate": 1.2774172985063187e-05, + "loss": 3.3655, + "step": 2273792 + }, + { + "epoch": 1.02, + "learning_rate": 1.2765787037552667e-05, + "loss": 3.3725, + "step": 2274304 + }, + { + "epoch": 1.02, + "learning_rate": 1.2757401090042145e-05, + "loss": 3.3719, + "step": 2274816 + }, + { + "epoch": 1.02, + "learning_rate": 1.2749015142531625e-05, + "loss": 3.3621, + "step": 2275328 + }, + { + "epoch": 1.02, + "learning_rate": 1.274064557382484e-05, + "loss": 3.3673, + "step": 2275840 + }, + { + "epoch": 1.02, + "learning_rate": 1.273225962631432e-05, + "loss": 3.3669, + "step": 2276352 + }, + { + "epoch": 1.02, + "learning_rate": 1.2723873678803796e-05, + "loss": 3.3705, + "step": 2276864 + }, + { + "epoch": 1.02, + "learning_rate": 1.271550411009701e-05, + "loss": 3.3656, + "step": 2277376 + }, + { + "epoch": 1.02, + "learning_rate": 1.270711816258649e-05, + "loss": 3.3683, + "step": 2277888 + }, + { + "epoch": 1.02, + "learning_rate": 1.2698732215075967e-05, + "loss": 3.3627, + "step": 2278400 + }, + { + "epoch": 1.02, + "learning_rate": 1.2690346267565448e-05, + "loss": 3.3685, + "step": 2278912 + }, + { + "epoch": 1.02, + "learning_rate": 1.2681960320054928e-05, + "loss": 3.3813, + "step": 2279424 + }, + { + "epoch": 1.02, + "learning_rate": 1.2673574372544408e-05, + "loss": 3.3694, + "step": 2279936 + }, + { + "epoch": 1.02, + "learning_rate": 1.2665188425033888e-05, + "loss": 3.38, + "step": 2280448 + }, + { + "epoch": 1.02, + "learning_rate": 1.2656802477523368e-05, + "loss": 3.3599, + "step": 2280960 + }, + { + "epoch": 1.02, + "learning_rate": 1.2648432908816579e-05, + "loss": 3.3749, + "step": 2281472 + }, + { + "epoch": 1.02, + "learning_rate": 1.2640046961306059e-05, + "loss": 3.3749, + "step": 2281984 + }, + { + "epoch": 1.02, + "learning_rate": 1.263166101379554e-05, + "loss": 3.375, + "step": 2282496 + }, + { + "epoch": 1.02, + "learning_rate": 1.262327506628502e-05, + "loss": 3.373, + "step": 2283008 + }, + { + "epoch": 1.02, + "learning_rate": 1.261490549757823e-05, + "loss": 3.3754, + "step": 2283520 + }, + { + "epoch": 1.02, + "learning_rate": 1.2606519550067711e-05, + "loss": 3.3819, + "step": 2284032 + }, + { + "epoch": 1.02, + "learning_rate": 1.2598133602557191e-05, + "loss": 3.3779, + "step": 2284544 + }, + { + "epoch": 1.02, + "learning_rate": 1.2589747655046671e-05, + "loss": 3.3639, + "step": 2285056 + }, + { + "epoch": 1.02, + "learning_rate": 1.2581378086339882e-05, + "loss": 3.3727, + "step": 2285568 + }, + { + "epoch": 1.02, + "learning_rate": 1.2573008517633093e-05, + "loss": 3.3722, + "step": 2286080 + }, + { + "epoch": 1.02, + "learning_rate": 1.2564622570122573e-05, + "loss": 3.3703, + "step": 2286592 + }, + { + "epoch": 1.02, + "learning_rate": 1.2556236622612053e-05, + "loss": 3.3612, + "step": 2287104 + }, + { + "epoch": 1.02, + "learning_rate": 1.2547850675101533e-05, + "loss": 3.3714, + "step": 2287616 + }, + { + "epoch": 1.02, + "learning_rate": 1.2539481106394743e-05, + "loss": 3.3626, + "step": 2288128 + }, + { + "epoch": 1.02, + "learning_rate": 1.2531095158884223e-05, + "loss": 3.3751, + "step": 2288640 + }, + { + "epoch": 1.02, + "learning_rate": 1.2522709211373703e-05, + "loss": 3.3645, + "step": 2289152 + }, + { + "epoch": 1.03, + "eval_loss": 3.865407705307007, + "eval_runtime": 310.8336, + "eval_samples_per_second": 1227.638, + "eval_steps_per_second": 38.365, + "step": 2289600 + }, + { + "epoch": 0.0, + "learning_rate": 1.2514323263863183e-05, + "loss": 3.3788, + "step": 2289664 + }, + { + "epoch": 0.0, + "learning_rate": 1.2505937316352665e-05, + "loss": 3.3605, + "step": 2290176 + }, + { + "epoch": 0.0, + "learning_rate": 1.2497551368842143e-05, + "loss": 3.3657, + "step": 2290688 + }, + { + "epoch": 0.0, + "learning_rate": 1.2489165421331623e-05, + "loss": 3.3784, + "step": 2291200 + }, + { + "epoch": 0.0, + "learning_rate": 1.2480795852624836e-05, + "loss": 3.3746, + "step": 2291712 + }, + { + "epoch": 0.0, + "learning_rate": 1.2472409905114314e-05, + "loss": 3.3689, + "step": 2292224 + }, + { + "epoch": 0.0, + "learning_rate": 1.2464023957603794e-05, + "loss": 3.3646, + "step": 2292736 + }, + { + "epoch": 0.0, + "learning_rate": 1.2455638010093276e-05, + "loss": 3.3618, + "step": 2293248 + }, + { + "epoch": 0.0, + "learning_rate": 1.2447268441386486e-05, + "loss": 3.3645, + "step": 2293760 + }, + { + "epoch": 0.0, + "learning_rate": 1.2438882493875966e-05, + "loss": 3.3737, + "step": 2294272 + }, + { + "epoch": 0.0, + "learning_rate": 1.2430496546365446e-05, + "loss": 3.3717, + "step": 2294784 + }, + { + "epoch": 0.0, + "learning_rate": 1.2422110598854926e-05, + "loss": 3.3719, + "step": 2295296 + }, + { + "epoch": 0.0, + "learning_rate": 1.2413741030148137e-05, + "loss": 3.3768, + "step": 2295808 + }, + { + "epoch": 0.0, + "learning_rate": 1.2405371461441348e-05, + "loss": 3.3515, + "step": 2296320 + }, + { + "epoch": 0.0, + "learning_rate": 1.2396985513930828e-05, + "loss": 3.3651, + "step": 2296832 + }, + { + "epoch": 0.0, + "learning_rate": 1.238859956642031e-05, + "loss": 3.3547, + "step": 2297344 + }, + { + "epoch": 0.0, + "learning_rate": 1.2380213618909788e-05, + "loss": 3.368, + "step": 2297856 + }, + { + "epoch": 0.0, + "learning_rate": 1.2371827671399268e-05, + "loss": 3.3604, + "step": 2298368 + }, + { + "epoch": 0.0, + "learning_rate": 1.2363441723888748e-05, + "loss": 3.3637, + "step": 2298880 + }, + { + "epoch": 0.0, + "learning_rate": 1.235505577637823e-05, + "loss": 3.366, + "step": 2299392 + }, + { + "epoch": 0.0, + "learning_rate": 1.2346669828867707e-05, + "loss": 3.3828, + "step": 2299904 + }, + { + "epoch": 0.0, + "learning_rate": 1.2338300260160918e-05, + "loss": 3.3706, + "step": 2300416 + }, + { + "epoch": 0.0, + "learning_rate": 1.23299143126504e-05, + "loss": 3.3711, + "step": 2300928 + }, + { + "epoch": 0.0, + "learning_rate": 1.2321528365139878e-05, + "loss": 3.3726, + "step": 2301440 + }, + { + "epoch": 0.0, + "learning_rate": 1.2313142417629358e-05, + "loss": 3.3827, + "step": 2301952 + }, + { + "epoch": 0.0, + "learning_rate": 1.230477284892257e-05, + "loss": 3.356, + "step": 2302464 + }, + { + "epoch": 0.0, + "learning_rate": 1.229638690141205e-05, + "loss": 3.3659, + "step": 2302976 + }, + { + "epoch": 0.0, + "learning_rate": 1.2288000953901529e-05, + "loss": 3.3759, + "step": 2303488 + }, + { + "epoch": 0.0, + "learning_rate": 1.227961500639101e-05, + "loss": 3.3553, + "step": 2304000 + }, + { + "epoch": 0.0, + "learning_rate": 1.2271245437684221e-05, + "loss": 3.3638, + "step": 2304512 + }, + { + "epoch": 0.01, + "learning_rate": 1.2262859490173701e-05, + "loss": 3.3725, + "step": 2305024 + }, + { + "epoch": 0.01, + "learning_rate": 1.2254489921466912e-05, + "loss": 3.3768, + "step": 2305536 + }, + { + "epoch": 0.01, + "learning_rate": 1.2246103973956392e-05, + "loss": 3.3717, + "step": 2306048 + }, + { + "epoch": 0.01, + "learning_rate": 1.2237718026445872e-05, + "loss": 3.3738, + "step": 2306560 + }, + { + "epoch": 0.01, + "learning_rate": 1.2229332078935352e-05, + "loss": 3.3602, + "step": 2307072 + }, + { + "epoch": 0.01, + "learning_rate": 1.2220946131424832e-05, + "loss": 3.3713, + "step": 2307584 + }, + { + "epoch": 0.01, + "learning_rate": 1.2212560183914312e-05, + "loss": 3.3672, + "step": 2308096 + }, + { + "epoch": 0.01, + "learning_rate": 1.2204190615207524e-05, + "loss": 3.3531, + "step": 2308608 + }, + { + "epoch": 0.01, + "learning_rate": 1.2195804667697003e-05, + "loss": 3.3689, + "step": 2309120 + }, + { + "epoch": 0.01, + "learning_rate": 1.2187418720186482e-05, + "loss": 3.3571, + "step": 2309632 + }, + { + "epoch": 0.01, + "learning_rate": 1.2179032772675964e-05, + "loss": 3.3574, + "step": 2310144 + }, + { + "epoch": 0.01, + "learning_rate": 1.2170663203969173e-05, + "loss": 3.3653, + "step": 2310656 + }, + { + "epoch": 0.01, + "learning_rate": 1.2162277256458653e-05, + "loss": 3.3776, + "step": 2311168 + }, + { + "epoch": 0.01, + "learning_rate": 1.2153891308948135e-05, + "loss": 3.3599, + "step": 2311680 + }, + { + "epoch": 0.01, + "learning_rate": 1.2145505361437615e-05, + "loss": 3.3719, + "step": 2312192 + }, + { + "epoch": 0.01, + "learning_rate": 1.2137119413927093e-05, + "loss": 3.3698, + "step": 2312704 + }, + { + "epoch": 0.01, + "learning_rate": 1.2128733466416575e-05, + "loss": 3.3668, + "step": 2313216 + }, + { + "epoch": 0.01, + "learning_rate": 1.2120347518906055e-05, + "loss": 3.3695, + "step": 2313728 + }, + { + "epoch": 0.01, + "learning_rate": 1.2111961571395533e-05, + "loss": 3.3505, + "step": 2314240 + }, + { + "epoch": 0.01, + "learning_rate": 1.2103592002688745e-05, + "loss": 3.3665, + "step": 2314752 + }, + { + "epoch": 0.01, + "learning_rate": 1.2095206055178225e-05, + "loss": 3.3636, + "step": 2315264 + }, + { + "epoch": 0.01, + "learning_rate": 1.2086820107667705e-05, + "loss": 3.3711, + "step": 2315776 + }, + { + "epoch": 0.01, + "learning_rate": 1.2078434160157184e-05, + "loss": 3.3674, + "step": 2316288 + }, + { + "epoch": 0.01, + "learning_rate": 1.2070064591450396e-05, + "loss": 3.3555, + "step": 2316800 + }, + { + "epoch": 0.01, + "learning_rate": 1.2061678643939876e-05, + "loss": 3.3543, + "step": 2317312 + }, + { + "epoch": 0.01, + "learning_rate": 1.2053292696429356e-05, + "loss": 3.3591, + "step": 2317824 + }, + { + "epoch": 0.01, + "learning_rate": 1.2044923127722567e-05, + "loss": 3.378, + "step": 2318336 + }, + { + "epoch": 0.01, + "learning_rate": 1.2036537180212047e-05, + "loss": 3.3507, + "step": 2318848 + }, + { + "epoch": 0.01, + "learning_rate": 1.2028151232701527e-05, + "loss": 3.3697, + "step": 2319360 + }, + { + "epoch": 0.01, + "learning_rate": 1.2019765285191007e-05, + "loss": 3.3654, + "step": 2319872 + }, + { + "epoch": 0.01, + "learning_rate": 1.2011395716484217e-05, + "loss": 3.3496, + "step": 2320384 + }, + { + "epoch": 0.01, + "learning_rate": 1.2003009768973699e-05, + "loss": 3.3681, + "step": 2320896 + }, + { + "epoch": 0.01, + "learning_rate": 1.1994623821463179e-05, + "loss": 3.3618, + "step": 2321408 + }, + { + "epoch": 0.01, + "learning_rate": 1.1986237873952657e-05, + "loss": 3.3478, + "step": 2321920 + }, + { + "epoch": 0.01, + "learning_rate": 1.1977851926442137e-05, + "loss": 3.3521, + "step": 2322432 + }, + { + "epoch": 0.01, + "learning_rate": 1.1969465978931619e-05, + "loss": 3.3703, + "step": 2322944 + }, + { + "epoch": 0.01, + "learning_rate": 1.1961080031421097e-05, + "loss": 3.3584, + "step": 2323456 + }, + { + "epoch": 0.01, + "learning_rate": 1.1952694083910577e-05, + "loss": 3.3537, + "step": 2323968 + }, + { + "epoch": 0.01, + "learning_rate": 1.194432451520379e-05, + "loss": 3.3531, + "step": 2324480 + }, + { + "epoch": 0.01, + "learning_rate": 1.1935954946497e-05, + "loss": 3.3557, + "step": 2324992 + }, + { + "epoch": 0.01, + "learning_rate": 1.192756899898648e-05, + "loss": 3.361, + "step": 2325504 + }, + { + "epoch": 0.01, + "learning_rate": 1.191918305147596e-05, + "loss": 3.3668, + "step": 2326016 + }, + { + "epoch": 0.01, + "learning_rate": 1.191079710396544e-05, + "loss": 3.3663, + "step": 2326528 + }, + { + "epoch": 0.01, + "learning_rate": 1.1902427535258653e-05, + "loss": 3.37, + "step": 2327040 + }, + { + "epoch": 0.01, + "learning_rate": 1.1894041587748131e-05, + "loss": 3.3658, + "step": 2327552 + }, + { + "epoch": 0.01, + "learning_rate": 1.1885655640237611e-05, + "loss": 3.3666, + "step": 2328064 + }, + { + "epoch": 0.01, + "learning_rate": 1.1877269692727091e-05, + "loss": 3.3639, + "step": 2328576 + }, + { + "epoch": 0.01, + "learning_rate": 1.1868883745216571e-05, + "loss": 3.3566, + "step": 2329088 + }, + { + "epoch": 0.01, + "learning_rate": 1.186049779770605e-05, + "loss": 3.3577, + "step": 2329600 + }, + { + "epoch": 0.01, + "learning_rate": 1.185211185019553e-05, + "loss": 3.3614, + "step": 2330112 + }, + { + "epoch": 0.01, + "learning_rate": 1.184372590268501e-05, + "loss": 3.3621, + "step": 2330624 + }, + { + "epoch": 0.01, + "learning_rate": 1.1835372712781952e-05, + "loss": 3.3656, + "step": 2331136 + }, + { + "epoch": 0.01, + "learning_rate": 1.1826986765271434e-05, + "loss": 3.3743, + "step": 2331648 + }, + { + "epoch": 0.01, + "learning_rate": 1.1818600817760914e-05, + "loss": 3.3624, + "step": 2332160 + }, + { + "epoch": 0.01, + "learning_rate": 1.1810214870250392e-05, + "loss": 3.3464, + "step": 2332672 + }, + { + "epoch": 0.01, + "learning_rate": 1.1801828922739872e-05, + "loss": 3.3613, + "step": 2333184 + }, + { + "epoch": 0.01, + "learning_rate": 1.1793442975229354e-05, + "loss": 3.3692, + "step": 2333696 + }, + { + "epoch": 0.01, + "learning_rate": 1.1785057027718834e-05, + "loss": 3.37, + "step": 2334208 + }, + { + "epoch": 0.01, + "learning_rate": 1.1776671080208312e-05, + "loss": 3.3581, + "step": 2334720 + }, + { + "epoch": 0.01, + "learning_rate": 1.1768301511501525e-05, + "loss": 3.3731, + "step": 2335232 + }, + { + "epoch": 0.02, + "learning_rate": 1.1759931942794735e-05, + "loss": 3.3658, + "step": 2335744 + }, + { + "epoch": 0.02, + "learning_rate": 1.1751545995284215e-05, + "loss": 3.3603, + "step": 2336256 + }, + { + "epoch": 0.02, + "learning_rate": 1.1743160047773695e-05, + "loss": 3.3599, + "step": 2336768 + }, + { + "epoch": 0.02, + "learning_rate": 1.1734774100263175e-05, + "loss": 3.3709, + "step": 2337280 + }, + { + "epoch": 0.02, + "learning_rate": 1.1726388152752655e-05, + "loss": 3.3659, + "step": 2337792 + }, + { + "epoch": 0.02, + "learning_rate": 1.1718018584045866e-05, + "loss": 3.3693, + "step": 2338304 + }, + { + "epoch": 0.02, + "learning_rate": 1.1709632636535346e-05, + "loss": 3.3565, + "step": 2338816 + }, + { + "epoch": 0.02, + "learning_rate": 1.1701246689024826e-05, + "loss": 3.3563, + "step": 2339328 + }, + { + "epoch": 0.02, + "learning_rate": 1.1692860741514307e-05, + "loss": 3.3576, + "step": 2339840 + }, + { + "epoch": 0.02, + "learning_rate": 1.1684474794003786e-05, + "loss": 3.3711, + "step": 2340352 + }, + { + "epoch": 0.02, + "learning_rate": 1.1676088846493266e-05, + "loss": 3.3656, + "step": 2340864 + }, + { + "epoch": 0.02, + "learning_rate": 1.1667702898982746e-05, + "loss": 3.362, + "step": 2341376 + }, + { + "epoch": 0.02, + "learning_rate": 1.1659333330275956e-05, + "loss": 3.3587, + "step": 2341888 + }, + { + "epoch": 0.02, + "learning_rate": 1.1650947382765436e-05, + "loss": 3.3583, + "step": 2342400 + }, + { + "epoch": 0.02, + "learning_rate": 1.1642561435254918e-05, + "loss": 3.3659, + "step": 2342912 + }, + { + "epoch": 0.02, + "learning_rate": 1.1634175487744396e-05, + "loss": 3.3526, + "step": 2343424 + }, + { + "epoch": 0.02, + "learning_rate": 1.1625789540233876e-05, + "loss": 3.3584, + "step": 2343936 + }, + { + "epoch": 0.02, + "learning_rate": 1.1617419971527089e-05, + "loss": 3.3647, + "step": 2344448 + }, + { + "epoch": 0.02, + "learning_rate": 1.1609034024016569e-05, + "loss": 3.3644, + "step": 2344960 + }, + { + "epoch": 0.02, + "learning_rate": 1.1600648076506047e-05, + "loss": 3.359, + "step": 2345472 + }, + { + "epoch": 0.02, + "learning_rate": 1.1592262128995527e-05, + "loss": 3.3639, + "step": 2345984 + }, + { + "epoch": 0.02, + "learning_rate": 1.158389256028874e-05, + "loss": 3.3543, + "step": 2346496 + }, + { + "epoch": 0.02, + "learning_rate": 1.157550661277822e-05, + "loss": 3.3687, + "step": 2347008 + }, + { + "epoch": 0.02, + "learning_rate": 1.15671206652677e-05, + "loss": 3.3659, + "step": 2347520 + }, + { + "epoch": 0.02, + "learning_rate": 1.155873471775718e-05, + "loss": 3.3595, + "step": 2348032 + }, + { + "epoch": 0.02, + "learning_rate": 1.155034877024666e-05, + "loss": 3.3709, + "step": 2348544 + }, + { + "epoch": 0.02, + "learning_rate": 1.1541962822736138e-05, + "loss": 3.3685, + "step": 2349056 + }, + { + "epoch": 0.02, + "learning_rate": 1.1533576875225619e-05, + "loss": 3.3597, + "step": 2349568 + }, + { + "epoch": 0.02, + "learning_rate": 1.152520730651883e-05, + "loss": 3.3582, + "step": 2350080 + }, + { + "epoch": 0.02, + "learning_rate": 1.151682135900831e-05, + "loss": 3.363, + "step": 2350592 + }, + { + "epoch": 0.02, + "learning_rate": 1.150843541149779e-05, + "loss": 3.3591, + "step": 2351104 + }, + { + "epoch": 0.02, + "learning_rate": 1.150004946398727e-05, + "loss": 3.3542, + "step": 2351616 + }, + { + "epoch": 0.02, + "learning_rate": 1.149166351647675e-05, + "loss": 3.3607, + "step": 2352128 + }, + { + "epoch": 0.02, + "learning_rate": 1.148327756896623e-05, + "loss": 3.3575, + "step": 2352640 + }, + { + "epoch": 0.02, + "learning_rate": 1.147489162145571e-05, + "loss": 3.3636, + "step": 2353152 + }, + { + "epoch": 0.02, + "learning_rate": 1.1466538431552653e-05, + "loss": 3.3539, + "step": 2353664 + }, + { + "epoch": 0.02, + "learning_rate": 1.1458152484042133e-05, + "loss": 3.3641, + "step": 2354176 + }, + { + "epoch": 0.02, + "learning_rate": 1.1449766536531611e-05, + "loss": 3.3539, + "step": 2354688 + }, + { + "epoch": 0.02, + "learning_rate": 1.1441380589021091e-05, + "loss": 3.3573, + "step": 2355200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1432994641510573e-05, + "loss": 3.3651, + "step": 2355712 + }, + { + "epoch": 0.02, + "learning_rate": 1.1424608694000051e-05, + "loss": 3.3649, + "step": 2356224 + }, + { + "epoch": 0.02, + "learning_rate": 1.1416222746489531e-05, + "loss": 3.3665, + "step": 2356736 + }, + { + "epoch": 0.02, + "learning_rate": 1.1407836798979011e-05, + "loss": 3.3506, + "step": 2357248 + }, + { + "epoch": 0.02, + "learning_rate": 1.1399467230272223e-05, + "loss": 3.3676, + "step": 2357760 + }, + { + "epoch": 0.02, + "learning_rate": 1.1391081282761702e-05, + "loss": 3.365, + "step": 2358272 + }, + { + "epoch": 0.02, + "learning_rate": 1.1382695335251182e-05, + "loss": 3.3632, + "step": 2358784 + }, + { + "epoch": 0.02, + "learning_rate": 1.1374309387740663e-05, + "loss": 3.3656, + "step": 2359296 + }, + { + "epoch": 0.02, + "learning_rate": 1.1365939819033874e-05, + "loss": 3.3646, + "step": 2359808 + }, + { + "epoch": 0.02, + "learning_rate": 1.1357553871523354e-05, + "loss": 3.3736, + "step": 2360320 + }, + { + "epoch": 0.02, + "learning_rate": 1.1349167924012834e-05, + "loss": 3.366, + "step": 2360832 + }, + { + "epoch": 0.02, + "learning_rate": 1.1340781976502314e-05, + "loss": 3.3552, + "step": 2361344 + }, + { + "epoch": 0.02, + "learning_rate": 1.1332412407795525e-05, + "loss": 3.3619, + "step": 2361856 + }, + { + "epoch": 0.02, + "learning_rate": 1.1324042839088736e-05, + "loss": 3.3594, + "step": 2362368 + }, + { + "epoch": 0.02, + "learning_rate": 1.1315656891578216e-05, + "loss": 3.3583, + "step": 2362880 + }, + { + "epoch": 0.02, + "learning_rate": 1.1307270944067697e-05, + "loss": 3.3549, + "step": 2363392 + }, + { + "epoch": 0.02, + "learning_rate": 1.1298884996557175e-05, + "loss": 3.3611, + "step": 2363904 + }, + { + "epoch": 0.02, + "learning_rate": 1.1290499049046655e-05, + "loss": 3.3561, + "step": 2364416 + }, + { + "epoch": 0.02, + "learning_rate": 1.1282113101536135e-05, + "loss": 3.3661, + "step": 2364928 + }, + { + "epoch": 0.02, + "learning_rate": 1.1273727154025615e-05, + "loss": 3.3543, + "step": 2365440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8663580417633057, + "eval_runtime": 303.6064, + "eval_samples_per_second": 1256.861, + "eval_steps_per_second": 39.278, + "step": 2365920 + }, + { + "epoch": 1.0, + "learning_rate": 1.1265357585318826e-05, + "loss": 3.3605, + "step": 2365952 + }, + { + "epoch": 1.0, + "learning_rate": 1.1256971637808308e-05, + "loss": 3.3556, + "step": 2366464 + }, + { + "epoch": 1.0, + "learning_rate": 1.1248585690297788e-05, + "loss": 3.3516, + "step": 2366976 + }, + { + "epoch": 1.0, + "learning_rate": 1.1240199742787266e-05, + "loss": 3.3674, + "step": 2367488 + }, + { + "epoch": 1.0, + "learning_rate": 1.1231813795276746e-05, + "loss": 3.3645, + "step": 2368000 + }, + { + "epoch": 1.0, + "learning_rate": 1.1223427847766228e-05, + "loss": 3.3601, + "step": 2368512 + }, + { + "epoch": 1.0, + "learning_rate": 1.1215041900255706e-05, + "loss": 3.3526, + "step": 2369024 + }, + { + "epoch": 1.0, + "learning_rate": 1.1206672331548918e-05, + "loss": 3.3518, + "step": 2369536 + }, + { + "epoch": 1.0, + "learning_rate": 1.1198286384038398e-05, + "loss": 3.3606, + "step": 2370048 + }, + { + "epoch": 1.0, + "learning_rate": 1.1189900436527878e-05, + "loss": 3.3606, + "step": 2370560 + }, + { + "epoch": 1.0, + "learning_rate": 1.1181514489017356e-05, + "loss": 3.3623, + "step": 2371072 + }, + { + "epoch": 1.0, + "learning_rate": 1.1173144920310569e-05, + "loss": 3.3611, + "step": 2371584 + }, + { + "epoch": 1.0, + "learning_rate": 1.1164758972800049e-05, + "loss": 3.368, + "step": 2372096 + }, + { + "epoch": 1.0, + "learning_rate": 1.1156373025289529e-05, + "loss": 3.3405, + "step": 2372608 + }, + { + "epoch": 1.0, + "learning_rate": 1.1147987077779009e-05, + "loss": 3.3551, + "step": 2373120 + }, + { + "epoch": 1.0, + "learning_rate": 1.113961750907222e-05, + "loss": 3.3494, + "step": 2373632 + }, + { + "epoch": 1.0, + "learning_rate": 1.1131247940365432e-05, + "loss": 3.3568, + "step": 2374144 + }, + { + "epoch": 1.0, + "learning_rate": 1.1122861992854912e-05, + "loss": 3.3526, + "step": 2374656 + }, + { + "epoch": 1.0, + "learning_rate": 1.111447604534439e-05, + "loss": 3.3545, + "step": 2375168 + }, + { + "epoch": 1.0, + "learning_rate": 1.110609009783387e-05, + "loss": 3.3541, + "step": 2375680 + }, + { + "epoch": 1.0, + "learning_rate": 1.1097704150323352e-05, + "loss": 3.3739, + "step": 2376192 + }, + { + "epoch": 1.0, + "learning_rate": 1.108931820281283e-05, + "loss": 3.3597, + "step": 2376704 + }, + { + "epoch": 1.0, + "learning_rate": 1.1080948634106043e-05, + "loss": 3.3592, + "step": 2377216 + }, + { + "epoch": 1.0, + "learning_rate": 1.1072562686595523e-05, + "loss": 3.3651, + "step": 2377728 + }, + { + "epoch": 1.0, + "learning_rate": 1.1064176739085003e-05, + "loss": 3.3717, + "step": 2378240 + }, + { + "epoch": 1.0, + "learning_rate": 1.1055790791574481e-05, + "loss": 3.3517, + "step": 2378752 + }, + { + "epoch": 1.0, + "learning_rate": 1.1047404844063963e-05, + "loss": 3.3528, + "step": 2379264 + }, + { + "epoch": 1.0, + "learning_rate": 1.1039018896553442e-05, + "loss": 3.3659, + "step": 2379776 + }, + { + "epoch": 1.0, + "learning_rate": 1.103063294904292e-05, + "loss": 3.3479, + "step": 2380288 + }, + { + "epoch": 1.0, + "learning_rate": 1.10222470015324e-05, + "loss": 3.3559, + "step": 2380800 + }, + { + "epoch": 1.01, + "learning_rate": 1.1013877432825613e-05, + "loss": 3.3597, + "step": 2381312 + }, + { + "epoch": 1.01, + "learning_rate": 1.1005507864118824e-05, + "loss": 3.3687, + "step": 2381824 + }, + { + "epoch": 1.01, + "learning_rate": 1.0997121916608304e-05, + "loss": 3.3605, + "step": 2382336 + }, + { + "epoch": 1.01, + "learning_rate": 1.0988735969097784e-05, + "loss": 3.3613, + "step": 2382848 + }, + { + "epoch": 1.01, + "learning_rate": 1.0980350021587264e-05, + "loss": 3.3518, + "step": 2383360 + }, + { + "epoch": 1.01, + "learning_rate": 1.0971964074076744e-05, + "loss": 3.3646, + "step": 2383872 + }, + { + "epoch": 1.01, + "learning_rate": 1.0963578126566224e-05, + "loss": 3.361, + "step": 2384384 + }, + { + "epoch": 1.01, + "learning_rate": 1.0955208557859435e-05, + "loss": 3.3452, + "step": 2384896 + }, + { + "epoch": 1.01, + "learning_rate": 1.0946822610348916e-05, + "loss": 3.3583, + "step": 2385408 + }, + { + "epoch": 1.01, + "learning_rate": 1.0938436662838394e-05, + "loss": 3.3473, + "step": 2385920 + }, + { + "epoch": 1.01, + "learning_rate": 1.0930050715327874e-05, + "loss": 3.3521, + "step": 2386432 + }, + { + "epoch": 1.01, + "learning_rate": 1.0921681146621087e-05, + "loss": 3.3546, + "step": 2386944 + }, + { + "epoch": 1.01, + "learning_rate": 1.0913295199110565e-05, + "loss": 3.366, + "step": 2387456 + }, + { + "epoch": 1.01, + "learning_rate": 1.0904909251600045e-05, + "loss": 3.3561, + "step": 2387968 + }, + { + "epoch": 1.01, + "learning_rate": 1.0896523304089527e-05, + "loss": 3.3576, + "step": 2388480 + }, + { + "epoch": 1.01, + "learning_rate": 1.0888137356579007e-05, + "loss": 3.3641, + "step": 2388992 + }, + { + "epoch": 1.01, + "learning_rate": 1.0879751409068485e-05, + "loss": 3.3515, + "step": 2389504 + }, + { + "epoch": 1.01, + "learning_rate": 1.0871365461557965e-05, + "loss": 3.363, + "step": 2390016 + }, + { + "epoch": 1.01, + "learning_rate": 1.0862995892851177e-05, + "loss": 3.3426, + "step": 2390528 + }, + { + "epoch": 1.01, + "learning_rate": 1.0854609945340656e-05, + "loss": 3.3512, + "step": 2391040 + }, + { + "epoch": 1.01, + "learning_rate": 1.0846223997830136e-05, + "loss": 3.3564, + "step": 2391552 + }, + { + "epoch": 1.01, + "learning_rate": 1.0837838050319617e-05, + "loss": 3.3624, + "step": 2392064 + }, + { + "epoch": 1.01, + "learning_rate": 1.0829452102809097e-05, + "loss": 3.3592, + "step": 2392576 + }, + { + "epoch": 1.01, + "learning_rate": 1.0821066155298575e-05, + "loss": 3.3429, + "step": 2393088 + }, + { + "epoch": 1.01, + "learning_rate": 1.0812680207788055e-05, + "loss": 3.3499, + "step": 2393600 + }, + { + "epoch": 1.01, + "learning_rate": 1.0804310639081268e-05, + "loss": 3.3457, + "step": 2394112 + }, + { + "epoch": 1.01, + "learning_rate": 1.0795924691570746e-05, + "loss": 3.3665, + "step": 2394624 + }, + { + "epoch": 1.01, + "learning_rate": 1.0787538744060228e-05, + "loss": 3.3389, + "step": 2395136 + }, + { + "epoch": 1.01, + "learning_rate": 1.0779152796549708e-05, + "loss": 3.3607, + "step": 2395648 + }, + { + "epoch": 1.01, + "learning_rate": 1.0770766849039188e-05, + "loss": 3.3553, + "step": 2396160 + }, + { + "epoch": 1.01, + "learning_rate": 1.0762397280332399e-05, + "loss": 3.3419, + "step": 2396672 + }, + { + "epoch": 1.01, + "learning_rate": 1.0754011332821879e-05, + "loss": 3.3571, + "step": 2397184 + }, + { + "epoch": 1.01, + "learning_rate": 1.0745625385311358e-05, + "loss": 3.3522, + "step": 2397696 + }, + { + "epoch": 1.01, + "learning_rate": 1.0737239437800838e-05, + "loss": 3.3368, + "step": 2398208 + }, + { + "epoch": 1.01, + "learning_rate": 1.0728853490290318e-05, + "loss": 3.3437, + "step": 2398720 + }, + { + "epoch": 1.01, + "learning_rate": 1.0720467542779798e-05, + "loss": 3.3618, + "step": 2399232 + }, + { + "epoch": 1.01, + "learning_rate": 1.0712081595269278e-05, + "loss": 3.3474, + "step": 2399744 + }, + { + "epoch": 1.01, + "learning_rate": 1.0703695647758758e-05, + "loss": 3.3471, + "step": 2400256 + }, + { + "epoch": 1.01, + "learning_rate": 1.0695326079051969e-05, + "loss": 3.3446, + "step": 2400768 + }, + { + "epoch": 1.01, + "learning_rate": 1.0686940131541449e-05, + "loss": 3.3454, + "step": 2401280 + }, + { + "epoch": 1.01, + "learning_rate": 1.0678554184030929e-05, + "loss": 3.3523, + "step": 2401792 + }, + { + "epoch": 1.01, + "learning_rate": 1.0670168236520409e-05, + "loss": 3.3551, + "step": 2402304 + }, + { + "epoch": 1.01, + "learning_rate": 1.066179866781362e-05, + "loss": 3.3546, + "step": 2402816 + }, + { + "epoch": 1.01, + "learning_rate": 1.0653429099106832e-05, + "loss": 3.3621, + "step": 2403328 + }, + { + "epoch": 1.01, + "learning_rate": 1.064504315159631e-05, + "loss": 3.3584, + "step": 2403840 + }, + { + "epoch": 1.01, + "learning_rate": 1.063665720408579e-05, + "loss": 3.3528, + "step": 2404352 + }, + { + "epoch": 1.01, + "learning_rate": 1.0628271256575272e-05, + "loss": 3.3558, + "step": 2404864 + }, + { + "epoch": 1.01, + "learning_rate": 1.0619885309064752e-05, + "loss": 3.3483, + "step": 2405376 + }, + { + "epoch": 1.01, + "learning_rate": 1.061149936155423e-05, + "loss": 3.3501, + "step": 2405888 + }, + { + "epoch": 1.01, + "learning_rate": 1.0603129792847443e-05, + "loss": 3.353, + "step": 2406400 + }, + { + "epoch": 1.01, + "learning_rate": 1.0594743845336923e-05, + "loss": 3.3496, + "step": 2406912 + }, + { + "epoch": 1.01, + "learning_rate": 1.0586357897826401e-05, + "loss": 3.3589, + "step": 2407424 + }, + { + "epoch": 1.01, + "learning_rate": 1.0577971950315883e-05, + "loss": 3.3579, + "step": 2407936 + }, + { + "epoch": 1.01, + "learning_rate": 1.0569586002805363e-05, + "loss": 3.3554, + "step": 2408448 + }, + { + "epoch": 1.01, + "learning_rate": 1.0561200055294843e-05, + "loss": 3.3389, + "step": 2408960 + }, + { + "epoch": 1.01, + "learning_rate": 1.055281410778432e-05, + "loss": 3.3477, + "step": 2409472 + }, + { + "epoch": 1.01, + "learning_rate": 1.0544428160273802e-05, + "loss": 3.3649, + "step": 2409984 + }, + { + "epoch": 1.01, + "learning_rate": 1.0536058591567013e-05, + "loss": 3.3563, + "step": 2410496 + }, + { + "epoch": 1.01, + "learning_rate": 1.0527672644056493e-05, + "loss": 3.3506, + "step": 2411008 + }, + { + "epoch": 1.01, + "learning_rate": 1.0519286696545973e-05, + "loss": 3.3666, + "step": 2411520 + }, + { + "epoch": 1.02, + "learning_rate": 1.0510900749035453e-05, + "loss": 3.3539, + "step": 2412032 + }, + { + "epoch": 1.02, + "learning_rate": 1.0502531180328664e-05, + "loss": 3.3508, + "step": 2412544 + }, + { + "epoch": 1.02, + "learning_rate": 1.0494145232818144e-05, + "loss": 3.3514, + "step": 2413056 + }, + { + "epoch": 1.02, + "learning_rate": 1.0485759285307624e-05, + "loss": 3.3586, + "step": 2413568 + }, + { + "epoch": 1.02, + "learning_rate": 1.0477373337797104e-05, + "loss": 3.3529, + "step": 2414080 + }, + { + "epoch": 1.02, + "learning_rate": 1.0469003769090316e-05, + "loss": 3.364, + "step": 2414592 + }, + { + "epoch": 1.02, + "learning_rate": 1.0460617821579794e-05, + "loss": 3.3413, + "step": 2415104 + }, + { + "epoch": 1.02, + "learning_rate": 1.0452231874069274e-05, + "loss": 3.3527, + "step": 2415616 + }, + { + "epoch": 1.02, + "learning_rate": 1.0443845926558756e-05, + "loss": 3.3476, + "step": 2416128 + }, + { + "epoch": 1.02, + "learning_rate": 1.0435459979048234e-05, + "loss": 3.3606, + "step": 2416640 + }, + { + "epoch": 1.02, + "learning_rate": 1.0427074031537714e-05, + "loss": 3.3612, + "step": 2417152 + }, + { + "epoch": 1.02, + "learning_rate": 1.0418688084027194e-05, + "loss": 3.3494, + "step": 2417664 + }, + { + "epoch": 1.02, + "learning_rate": 1.0410302136516674e-05, + "loss": 3.3516, + "step": 2418176 + }, + { + "epoch": 1.02, + "learning_rate": 1.0401932567809885e-05, + "loss": 3.3495, + "step": 2418688 + }, + { + "epoch": 1.02, + "learning_rate": 1.0393546620299367e-05, + "loss": 3.3548, + "step": 2419200 + }, + { + "epoch": 1.02, + "learning_rate": 1.0385160672788847e-05, + "loss": 3.3371, + "step": 2419712 + }, + { + "epoch": 1.02, + "learning_rate": 1.0376774725278325e-05, + "loss": 3.3502, + "step": 2420224 + }, + { + "epoch": 1.02, + "learning_rate": 1.0368405156571537e-05, + "loss": 3.355, + "step": 2420736 + }, + { + "epoch": 1.02, + "learning_rate": 1.0360019209061017e-05, + "loss": 3.3518, + "step": 2421248 + }, + { + "epoch": 1.02, + "learning_rate": 1.0351633261550496e-05, + "loss": 3.3533, + "step": 2421760 + }, + { + "epoch": 1.02, + "learning_rate": 1.0343247314039976e-05, + "loss": 3.3548, + "step": 2422272 + }, + { + "epoch": 1.02, + "learning_rate": 1.0334877745333188e-05, + "loss": 3.3413, + "step": 2422784 + }, + { + "epoch": 1.02, + "learning_rate": 1.0326491797822668e-05, + "loss": 3.362, + "step": 2423296 + }, + { + "epoch": 1.02, + "learning_rate": 1.0318105850312148e-05, + "loss": 3.3548, + "step": 2423808 + }, + { + "epoch": 1.02, + "learning_rate": 1.0309719902801628e-05, + "loss": 3.3494, + "step": 2424320 + }, + { + "epoch": 1.02, + "learning_rate": 1.0301350334094839e-05, + "loss": 3.3605, + "step": 2424832 + }, + { + "epoch": 1.02, + "learning_rate": 1.029296438658432e-05, + "loss": 3.3588, + "step": 2425344 + }, + { + "epoch": 1.02, + "learning_rate": 1.0284578439073799e-05, + "loss": 3.3504, + "step": 2425856 + }, + { + "epoch": 1.02, + "learning_rate": 1.0276192491563279e-05, + "loss": 3.3472, + "step": 2426368 + }, + { + "epoch": 1.02, + "learning_rate": 1.0267806544052759e-05, + "loss": 3.3538, + "step": 2426880 + }, + { + "epoch": 1.02, + "learning_rate": 1.0259420596542238e-05, + "loss": 3.3481, + "step": 2427392 + }, + { + "epoch": 1.02, + "learning_rate": 1.0251034649031718e-05, + "loss": 3.3447, + "step": 2427904 + }, + { + "epoch": 1.02, + "learning_rate": 1.024266508032493e-05, + "loss": 3.3483, + "step": 2428416 + }, + { + "epoch": 1.02, + "learning_rate": 1.0234279132814411e-05, + "loss": 3.3488, + "step": 2428928 + }, + { + "epoch": 1.02, + "learning_rate": 1.0225893185303889e-05, + "loss": 3.3521, + "step": 2429440 + }, + { + "epoch": 1.02, + "learning_rate": 1.0217507237793369e-05, + "loss": 3.3456, + "step": 2429952 + }, + { + "epoch": 1.02, + "learning_rate": 1.0209137669086582e-05, + "loss": 3.354, + "step": 2430464 + }, + { + "epoch": 1.02, + "learning_rate": 1.020075172157606e-05, + "loss": 3.344, + "step": 2430976 + }, + { + "epoch": 1.02, + "learning_rate": 1.019236577406554e-05, + "loss": 3.3533, + "step": 2431488 + }, + { + "epoch": 1.02, + "learning_rate": 1.0183979826555021e-05, + "loss": 3.3515, + "step": 2432000 + }, + { + "epoch": 1.02, + "learning_rate": 1.0175593879044501e-05, + "loss": 3.3553, + "step": 2432512 + }, + { + "epoch": 1.02, + "learning_rate": 1.016720793153398e-05, + "loss": 3.3581, + "step": 2433024 + }, + { + "epoch": 1.02, + "learning_rate": 1.015882198402346e-05, + "loss": 3.3443, + "step": 2433536 + }, + { + "epoch": 1.02, + "learning_rate": 1.0150452415316672e-05, + "loss": 3.3525, + "step": 2434048 + }, + { + "epoch": 1.02, + "learning_rate": 1.014206646780615e-05, + "loss": 3.3592, + "step": 2434560 + }, + { + "epoch": 1.02, + "learning_rate": 1.013368052029563e-05, + "loss": 3.3561, + "step": 2435072 + }, + { + "epoch": 1.02, + "learning_rate": 1.0125294572785112e-05, + "loss": 3.3569, + "step": 2435584 + }, + { + "epoch": 1.02, + "learning_rate": 1.0116925004078323e-05, + "loss": 3.3536, + "step": 2436096 + }, + { + "epoch": 1.02, + "learning_rate": 1.0108539056567803e-05, + "loss": 3.3657, + "step": 2436608 + }, + { + "epoch": 1.02, + "learning_rate": 1.0100153109057283e-05, + "loss": 3.3526, + "step": 2437120 + }, + { + "epoch": 1.02, + "learning_rate": 1.0091767161546763e-05, + "loss": 3.3476, + "step": 2437632 + }, + { + "epoch": 1.02, + "learning_rate": 1.0083397592839975e-05, + "loss": 3.3527, + "step": 2438144 + }, + { + "epoch": 1.02, + "learning_rate": 1.0075028024133184e-05, + "loss": 3.3494, + "step": 2438656 + }, + { + "epoch": 1.02, + "learning_rate": 1.0066642076622664e-05, + "loss": 3.3503, + "step": 2439168 + }, + { + "epoch": 1.02, + "learning_rate": 1.0058256129112146e-05, + "loss": 3.3444, + "step": 2439680 + }, + { + "epoch": 1.02, + "learning_rate": 1.0049870181601624e-05, + "loss": 3.3549, + "step": 2440192 + }, + { + "epoch": 1.02, + "learning_rate": 1.0041484234091104e-05, + "loss": 3.3437, + "step": 2440704 + }, + { + "epoch": 1.02, + "learning_rate": 1.0033098286580584e-05, + "loss": 3.3563, + "step": 2441216 + }, + { + "epoch": 1.02, + "learning_rate": 1.0024712339070066e-05, + "loss": 3.3486, + "step": 2441728 + }, + { + "epoch": 1.03, + "learning_rate": 1.0016342770363275e-05, + "loss": 3.3531, + "step": 2442240 + }, + { + "epoch": 1.03, + "eval_loss": 3.8659331798553467, + "eval_runtime": 302.8583, + "eval_samples_per_second": 1259.965, + "eval_steps_per_second": 39.375, + "step": 2442240 + }, + { + "epoch": 0.0, + "learning_rate": 1.0007956822852756e-05, + "loss": 3.3425, + "step": 2442752 + }, + { + "epoch": 0.0, + "learning_rate": 9.999570875342236e-06, + "loss": 3.3442, + "step": 2443264 + }, + { + "epoch": 0.0, + "learning_rate": 9.991184927831715e-06, + "loss": 3.3555, + "step": 2443776 + }, + { + "epoch": 0.0, + "learning_rate": 9.982815359124927e-06, + "loss": 3.3575, + "step": 2444288 + }, + { + "epoch": 0.0, + "learning_rate": 9.974429411614407e-06, + "loss": 3.3536, + "step": 2444800 + }, + { + "epoch": 0.0, + "learning_rate": 9.966043464103887e-06, + "loss": 3.3454, + "step": 2445312 + }, + { + "epoch": 0.0, + "learning_rate": 9.957657516593367e-06, + "loss": 3.3425, + "step": 2445824 + }, + { + "epoch": 0.0, + "learning_rate": 9.949287947886578e-06, + "loss": 3.3452, + "step": 2446336 + }, + { + "epoch": 0.0, + "learning_rate": 9.940902000376058e-06, + "loss": 3.3551, + "step": 2446848 + }, + { + "epoch": 0.0, + "learning_rate": 9.932516052865538e-06, + "loss": 3.349, + "step": 2447360 + }, + { + "epoch": 0.0, + "learning_rate": 9.924130105355018e-06, + "loss": 3.3558, + "step": 2447872 + }, + { + "epoch": 0.0, + "learning_rate": 9.915760536648228e-06, + "loss": 3.3608, + "step": 2448384 + }, + { + "epoch": 0.0, + "learning_rate": 9.90737458913771e-06, + "loss": 3.3346, + "step": 2448896 + }, + { + "epoch": 0.0, + "learning_rate": 9.898988641627188e-06, + "loss": 3.3425, + "step": 2449408 + }, + { + "epoch": 0.0, + "learning_rate": 9.890602694116668e-06, + "loss": 3.3397, + "step": 2449920 + }, + { + "epoch": 0.0, + "learning_rate": 9.882216746606148e-06, + "loss": 3.3464, + "step": 2450432 + }, + { + "epoch": 0.0, + "learning_rate": 9.87384717789936e-06, + "loss": 3.3459, + "step": 2450944 + }, + { + "epoch": 0.0, + "learning_rate": 9.865461230388839e-06, + "loss": 3.3482, + "step": 2451456 + }, + { + "epoch": 0.0, + "learning_rate": 9.857075282878319e-06, + "loss": 3.3436, + "step": 2451968 + }, + { + "epoch": 0.0, + "learning_rate": 9.8486893353678e-06, + "loss": 3.3623, + "step": 2452480 + }, + { + "epoch": 0.0, + "learning_rate": 9.84031976666101e-06, + "loss": 3.351, + "step": 2452992 + }, + { + "epoch": 0.0, + "learning_rate": 9.831933819150491e-06, + "loss": 3.3496, + "step": 2453504 + }, + { + "epoch": 0.0, + "learning_rate": 9.823547871639971e-06, + "loss": 3.3531, + "step": 2454016 + }, + { + "epoch": 0.0, + "learning_rate": 9.815161924129451e-06, + "loss": 3.3644, + "step": 2454528 + }, + { + "epoch": 0.0, + "learning_rate": 9.80677597661893e-06, + "loss": 3.3408, + "step": 2455040 + }, + { + "epoch": 0.0, + "learning_rate": 9.798390029108411e-06, + "loss": 3.3491, + "step": 2455552 + }, + { + "epoch": 0.0, + "learning_rate": 9.790004081597891e-06, + "loss": 3.3514, + "step": 2456064 + }, + { + "epoch": 0.0, + "learning_rate": 9.78161813408737e-06, + "loss": 3.3394, + "step": 2456576 + }, + { + "epoch": 0.0, + "learning_rate": 9.773248565380582e-06, + "loss": 3.3449, + "step": 2457088 + }, + { + "epoch": 0.01, + "learning_rate": 9.764862617870062e-06, + "loss": 3.3483, + "step": 2457600 + }, + { + "epoch": 0.01, + "learning_rate": 9.756493049163273e-06, + "loss": 3.3619, + "step": 2458112 + }, + { + "epoch": 0.01, + "learning_rate": 9.748107101652753e-06, + "loss": 3.3471, + "step": 2458624 + }, + { + "epoch": 0.01, + "learning_rate": 9.739721154142232e-06, + "loss": 3.3519, + "step": 2459136 + }, + { + "epoch": 0.01, + "learning_rate": 9.731335206631712e-06, + "loss": 3.3468, + "step": 2459648 + }, + { + "epoch": 0.01, + "learning_rate": 9.722949259121192e-06, + "loss": 3.3501, + "step": 2460160 + }, + { + "epoch": 0.01, + "learning_rate": 9.714563311610672e-06, + "loss": 3.3521, + "step": 2460672 + }, + { + "epoch": 0.01, + "learning_rate": 9.706177364100152e-06, + "loss": 3.3361, + "step": 2461184 + }, + { + "epoch": 0.01, + "learning_rate": 9.697791416589632e-06, + "loss": 3.3458, + "step": 2461696 + }, + { + "epoch": 0.01, + "learning_rate": 9.689421847882843e-06, + "loss": 3.3368, + "step": 2462208 + }, + { + "epoch": 0.01, + "learning_rate": 9.681035900372323e-06, + "loss": 3.344, + "step": 2462720 + }, + { + "epoch": 0.01, + "learning_rate": 9.672666331665535e-06, + "loss": 3.3439, + "step": 2463232 + }, + { + "epoch": 0.01, + "learning_rate": 9.664280384155015e-06, + "loss": 3.3584, + "step": 2463744 + }, + { + "epoch": 0.01, + "learning_rate": 9.655894436644494e-06, + "loss": 3.3454, + "step": 2464256 + }, + { + "epoch": 0.01, + "learning_rate": 9.647508489133975e-06, + "loss": 3.348, + "step": 2464768 + }, + { + "epoch": 0.01, + "learning_rate": 9.639122541623455e-06, + "loss": 3.3529, + "step": 2465280 + }, + { + "epoch": 0.01, + "learning_rate": 9.630736594112934e-06, + "loss": 3.3449, + "step": 2465792 + }, + { + "epoch": 0.01, + "learning_rate": 9.622350646602414e-06, + "loss": 3.3552, + "step": 2466304 + }, + { + "epoch": 0.01, + "learning_rate": 9.613981077895626e-06, + "loss": 3.3298, + "step": 2466816 + }, + { + "epoch": 0.01, + "learning_rate": 9.605595130385106e-06, + "loss": 3.3436, + "step": 2467328 + }, + { + "epoch": 0.01, + "learning_rate": 9.597209182874584e-06, + "loss": 3.3502, + "step": 2467840 + }, + { + "epoch": 0.01, + "learning_rate": 9.588823235364066e-06, + "loss": 3.3535, + "step": 2468352 + }, + { + "epoch": 0.01, + "learning_rate": 9.580437287853546e-06, + "loss": 3.349, + "step": 2468864 + }, + { + "epoch": 0.01, + "learning_rate": 9.572051340343024e-06, + "loss": 3.3316, + "step": 2469376 + }, + { + "epoch": 0.01, + "learning_rate": 9.563665392832504e-06, + "loss": 3.3454, + "step": 2469888 + }, + { + "epoch": 0.01, + "learning_rate": 9.555279445321986e-06, + "loss": 3.3332, + "step": 2470400 + }, + { + "epoch": 0.01, + "learning_rate": 9.546926255418927e-06, + "loss": 3.3589, + "step": 2470912 + }, + { + "epoch": 0.01, + "learning_rate": 9.538540307908407e-06, + "loss": 3.3338, + "step": 2471424 + }, + { + "epoch": 0.01, + "learning_rate": 9.530154360397887e-06, + "loss": 3.3517, + "step": 2471936 + }, + { + "epoch": 0.01, + "learning_rate": 9.521768412887367e-06, + "loss": 3.3429, + "step": 2472448 + }, + { + "epoch": 0.01, + "learning_rate": 9.51339884418058e-06, + "loss": 3.3318, + "step": 2472960 + }, + { + "epoch": 0.01, + "learning_rate": 9.505012896670058e-06, + "loss": 3.3488, + "step": 2473472 + }, + { + "epoch": 0.01, + "learning_rate": 9.496626949159538e-06, + "loss": 3.345, + "step": 2473984 + }, + { + "epoch": 0.01, + "learning_rate": 9.48824100164902e-06, + "loss": 3.3253, + "step": 2474496 + }, + { + "epoch": 0.01, + "learning_rate": 9.479855054138498e-06, + "loss": 3.3333, + "step": 2475008 + }, + { + "epoch": 0.01, + "learning_rate": 9.47148548543171e-06, + "loss": 3.352, + "step": 2475520 + }, + { + "epoch": 0.01, + "learning_rate": 9.46309953792119e-06, + "loss": 3.3419, + "step": 2476032 + }, + { + "epoch": 0.01, + "learning_rate": 9.45471359041067e-06, + "loss": 3.3352, + "step": 2476544 + }, + { + "epoch": 0.01, + "learning_rate": 9.446327642900148e-06, + "loss": 3.3374, + "step": 2477056 + }, + { + "epoch": 0.01, + "learning_rate": 9.43794169538963e-06, + "loss": 3.3334, + "step": 2477568 + }, + { + "epoch": 0.01, + "learning_rate": 9.42955574787911e-06, + "loss": 3.3412, + "step": 2478080 + }, + { + "epoch": 0.01, + "learning_rate": 9.421169800368588e-06, + "loss": 3.3489, + "step": 2478592 + }, + { + "epoch": 0.01, + "learning_rate": 9.412783852858068e-06, + "loss": 3.3452, + "step": 2479104 + }, + { + "epoch": 0.01, + "learning_rate": 9.40441428415128e-06, + "loss": 3.356, + "step": 2479616 + }, + { + "epoch": 0.01, + "learning_rate": 9.39602833664076e-06, + "loss": 3.3453, + "step": 2480128 + }, + { + "epoch": 0.01, + "learning_rate": 9.387642389130239e-06, + "loss": 3.3493, + "step": 2480640 + }, + { + "epoch": 0.01, + "learning_rate": 9.37925644161972e-06, + "loss": 3.3411, + "step": 2481152 + }, + { + "epoch": 0.01, + "learning_rate": 9.3708704941092e-06, + "loss": 3.3409, + "step": 2481664 + }, + { + "epoch": 0.01, + "learning_rate": 9.362484546598679e-06, + "loss": 3.3446, + "step": 2482176 + }, + { + "epoch": 0.01, + "learning_rate": 9.35409859908816e-06, + "loss": 3.3379, + "step": 2482688 + }, + { + "epoch": 0.01, + "learning_rate": 9.34571265157764e-06, + "loss": 3.3406, + "step": 2483200 + }, + { + "epoch": 0.01, + "learning_rate": 9.337343082870851e-06, + "loss": 3.35, + "step": 2483712 + }, + { + "epoch": 0.01, + "learning_rate": 9.328973514164062e-06, + "loss": 3.3492, + "step": 2484224 + }, + { + "epoch": 0.01, + "learning_rate": 9.320587566653542e-06, + "loss": 3.3429, + "step": 2484736 + }, + { + "epoch": 0.01, + "learning_rate": 9.312201619143022e-06, + "loss": 3.3281, + "step": 2485248 + }, + { + "epoch": 0.01, + "learning_rate": 9.303815671632502e-06, + "loss": 3.3406, + "step": 2485760 + }, + { + "epoch": 0.01, + "learning_rate": 9.295429724121982e-06, + "loss": 3.3536, + "step": 2486272 + }, + { + "epoch": 0.01, + "learning_rate": 9.287060155415193e-06, + "loss": 3.3504, + "step": 2486784 + }, + { + "epoch": 0.01, + "learning_rate": 9.278674207904674e-06, + "loss": 3.3417, + "step": 2487296 + }, + { + "epoch": 0.01, + "learning_rate": 9.270288260394153e-06, + "loss": 3.3574, + "step": 2487808 + }, + { + "epoch": 0.02, + "learning_rate": 9.261902312883633e-06, + "loss": 3.3455, + "step": 2488320 + }, + { + "epoch": 0.02, + "learning_rate": 9.253532744176845e-06, + "loss": 3.3373, + "step": 2488832 + }, + { + "epoch": 0.02, + "learning_rate": 9.245146796666325e-06, + "loss": 3.3438, + "step": 2489344 + }, + { + "epoch": 0.02, + "learning_rate": 9.236760849155803e-06, + "loss": 3.3501, + "step": 2489856 + }, + { + "epoch": 0.02, + "learning_rate": 9.228374901645285e-06, + "loss": 3.3431, + "step": 2490368 + }, + { + "epoch": 0.02, + "learning_rate": 9.219988954134765e-06, + "loss": 3.356, + "step": 2490880 + }, + { + "epoch": 0.02, + "learning_rate": 9.211603006624243e-06, + "loss": 3.3365, + "step": 2491392 + }, + { + "epoch": 0.02, + "learning_rate": 9.203217059113723e-06, + "loss": 3.3378, + "step": 2491904 + }, + { + "epoch": 0.02, + "learning_rate": 9.194831111603205e-06, + "loss": 3.3402, + "step": 2492416 + }, + { + "epoch": 0.02, + "learning_rate": 9.186461542896414e-06, + "loss": 3.3515, + "step": 2492928 + }, + { + "epoch": 0.02, + "learning_rate": 9.178075595385895e-06, + "loss": 3.3477, + "step": 2493440 + }, + { + "epoch": 0.02, + "learning_rate": 9.169689647875375e-06, + "loss": 3.3437, + "step": 2493952 + }, + { + "epoch": 0.02, + "learning_rate": 9.161303700364855e-06, + "loss": 3.3429, + "step": 2494464 + }, + { + "epoch": 0.02, + "learning_rate": 9.152934131658066e-06, + "loss": 3.3418, + "step": 2494976 + }, + { + "epoch": 0.02, + "learning_rate": 9.144548184147546e-06, + "loss": 3.349, + "step": 2495488 + }, + { + "epoch": 0.02, + "learning_rate": 9.136162236637026e-06, + "loss": 3.3259, + "step": 2496000 + }, + { + "epoch": 0.02, + "learning_rate": 9.127776289126504e-06, + "loss": 3.3419, + "step": 2496512 + }, + { + "epoch": 0.02, + "learning_rate": 9.119406720419717e-06, + "loss": 3.3496, + "step": 2497024 + }, + { + "epoch": 0.02, + "learning_rate": 9.111020772909197e-06, + "loss": 3.3417, + "step": 2497536 + }, + { + "epoch": 0.02, + "learning_rate": 9.102634825398677e-06, + "loss": 3.3424, + "step": 2498048 + }, + { + "epoch": 0.02, + "learning_rate": 9.094248877888157e-06, + "loss": 3.3483, + "step": 2498560 + }, + { + "epoch": 0.02, + "learning_rate": 9.085879309181367e-06, + "loss": 3.3339, + "step": 2499072 + }, + { + "epoch": 0.02, + "learning_rate": 9.077493361670847e-06, + "loss": 3.3487, + "step": 2499584 + }, + { + "epoch": 0.02, + "learning_rate": 9.069107414160329e-06, + "loss": 3.3473, + "step": 2500096 + }, + { + "epoch": 0.02, + "learning_rate": 9.060721466649807e-06, + "loss": 3.3414, + "step": 2500608 + }, + { + "epoch": 0.02, + "learning_rate": 9.05235189794302e-06, + "loss": 3.3497, + "step": 2501120 + }, + { + "epoch": 0.02, + "learning_rate": 9.0439659504325e-06, + "loss": 3.3514, + "step": 2501632 + }, + { + "epoch": 0.02, + "learning_rate": 9.035580002921978e-06, + "loss": 3.3418, + "step": 2502144 + }, + { + "epoch": 0.02, + "learning_rate": 9.027194055411458e-06, + "loss": 3.3409, + "step": 2502656 + }, + { + "epoch": 0.02, + "learning_rate": 9.01880810790094e-06, + "loss": 3.3418, + "step": 2503168 + }, + { + "epoch": 0.02, + "learning_rate": 9.01042216039042e-06, + "loss": 3.3414, + "step": 2503680 + }, + { + "epoch": 0.02, + "learning_rate": 9.002036212879898e-06, + "loss": 3.3334, + "step": 2504192 + }, + { + "epoch": 0.02, + "learning_rate": 8.99366664417311e-06, + "loss": 3.3368, + "step": 2504704 + }, + { + "epoch": 0.02, + "learning_rate": 8.98528069666259e-06, + "loss": 3.338, + "step": 2505216 + }, + { + "epoch": 0.02, + "learning_rate": 8.976894749152069e-06, + "loss": 3.3487, + "step": 2505728 + }, + { + "epoch": 0.02, + "learning_rate": 8.96850880164155e-06, + "loss": 3.3362, + "step": 2506240 + }, + { + "epoch": 0.02, + "learning_rate": 8.960139232934761e-06, + "loss": 3.3447, + "step": 2506752 + }, + { + "epoch": 0.02, + "learning_rate": 8.951753285424241e-06, + "loss": 3.3357, + "step": 2507264 + }, + { + "epoch": 0.02, + "learning_rate": 8.943367337913721e-06, + "loss": 3.3424, + "step": 2507776 + }, + { + "epoch": 0.02, + "learning_rate": 8.934981390403201e-06, + "loss": 3.3387, + "step": 2508288 + }, + { + "epoch": 0.02, + "learning_rate": 8.92659544289268e-06, + "loss": 3.3527, + "step": 2508800 + }, + { + "epoch": 0.02, + "learning_rate": 8.918209495382159e-06, + "loss": 3.3467, + "step": 2509312 + }, + { + "epoch": 0.02, + "learning_rate": 8.90982354787164e-06, + "loss": 3.3381, + "step": 2509824 + }, + { + "epoch": 0.02, + "learning_rate": 8.901453979164852e-06, + "loss": 3.3414, + "step": 2510336 + }, + { + "epoch": 0.02, + "learning_rate": 8.893068031654331e-06, + "loss": 3.344, + "step": 2510848 + }, + { + "epoch": 0.02, + "learning_rate": 8.884682084143811e-06, + "loss": 3.3473, + "step": 2511360 + }, + { + "epoch": 0.02, + "learning_rate": 8.876296136633291e-06, + "loss": 3.3471, + "step": 2511872 + }, + { + "epoch": 0.02, + "learning_rate": 8.867926567926504e-06, + "loss": 3.348, + "step": 2512384 + }, + { + "epoch": 0.02, + "learning_rate": 8.859540620415984e-06, + "loss": 3.3543, + "step": 2512896 + }, + { + "epoch": 0.02, + "learning_rate": 8.851154672905462e-06, + "loss": 3.3427, + "step": 2513408 + }, + { + "epoch": 0.02, + "learning_rate": 8.842768725394942e-06, + "loss": 3.3425, + "step": 2513920 + }, + { + "epoch": 0.02, + "learning_rate": 8.834399156688155e-06, + "loss": 3.3407, + "step": 2514432 + }, + { + "epoch": 0.02, + "learning_rate": 8.826029587981365e-06, + "loss": 3.3448, + "step": 2514944 + }, + { + "epoch": 0.02, + "learning_rate": 8.817643640470845e-06, + "loss": 3.3407, + "step": 2515456 + }, + { + "epoch": 0.02, + "learning_rate": 8.809257692960325e-06, + "loss": 3.3337, + "step": 2515968 + }, + { + "epoch": 0.02, + "learning_rate": 8.800871745449805e-06, + "loss": 3.3446, + "step": 2516480 + }, + { + "epoch": 0.02, + "learning_rate": 8.792485797939285e-06, + "loss": 3.338, + "step": 2516992 + }, + { + "epoch": 0.02, + "learning_rate": 8.784099850428765e-06, + "loss": 3.3459, + "step": 2517504 + }, + { + "epoch": 0.02, + "learning_rate": 8.775713902918245e-06, + "loss": 3.3393, + "step": 2518016 + }, + { + "epoch": 0.02, + "learning_rate": 8.767344334211456e-06, + "loss": 3.3405, + "step": 2518528 + }, + { + "epoch": 0.03, + "eval_loss": 3.867267370223999, + "eval_runtime": 301.7936, + "eval_samples_per_second": 1264.411, + "eval_steps_per_second": 39.514, + "step": 2518560 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7415424135364936e+18, + "trial_name": null, + "trial_params": null +}