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": 3.851093053817749, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/4/checkpoints/checkpoint-992160", + "epoch": 1.0250006060157382, + "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": 11.0021, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8322, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.2089, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9977, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8315, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7266, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6137, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5416, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4641, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4047, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3631, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3173, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2716, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2186, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.1948, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1472, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1231, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0978, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0645, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0348, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0195, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9879, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9705, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9455, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9378, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9039, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8893, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8609, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8559, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8306, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8227, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.813, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7958, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.9723329247367764e-05, + "loss": 4.7863, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.9714943299857244e-05, + "loss": 4.7715, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7567, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.7541, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7236, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7143, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6927, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6956, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6799, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6817, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.661, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6555, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.65, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6449, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6324, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6142, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.6051, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6232, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.6141, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5911, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5789, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5871, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5626, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5747, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5429, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5658, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.549, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5287, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5233, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.534, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4946, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5095, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5155, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.5014, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4933, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4757, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4755, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.472, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4865, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4634, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.474, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4681, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4675, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4497, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4475, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.444, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4412, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4318, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4261, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4272, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4262, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4049, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.4137, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.4128, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.4128, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3974, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3968, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3878, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3828, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3841, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3874, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3791, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3883, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3787, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.361, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3605, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3702, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3666, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3651, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3532, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3443, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3571, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3348, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3404, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3354, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3343, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3249, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3262, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.3201, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.3269, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3217, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3121, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3238, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3301, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.316, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.3032, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.3016, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2991, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985677063712895e-05, + "loss": 4.3049, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977291116202375e-05, + "loss": 4.3011, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968905168691855e-05, + "loss": 4.2897, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2993, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2898, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2889, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2834, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2855, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2788, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.288, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2854, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2842, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2617, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2775, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2715, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2761, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.2636, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2728, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2619, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2793, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.249, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2662, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2512, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2479, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2504, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2386, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2424, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2488, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2396, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.205402851104736, + "eval_runtime": 302.2482, + "eval_samples_per_second": 1262.509, + "eval_steps_per_second": 39.454, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.2324, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2284, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2426, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2329, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2409, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.22, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692267173667075e-05, + "loss": 4.2222, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683881226156555e-05, + "loss": 4.2103, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2209, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.2185, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.2146, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.2183, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.1972, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.2125, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.197, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.1975, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.2034, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.1958, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.1979, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858328261363778e-05, + "loss": 4.213, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857489666612726e-05, + "loss": 4.188, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856651071861674e-05, + "loss": 4.1929, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558124771106226e-05, + "loss": 4.1916, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549755202399435e-05, + "loss": 4.1969, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1906, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1887, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1757, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1824, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.8507841843650564e-05, + "loss": 4.1696, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.8499455896140044e-05, + "loss": 4.1799, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1753, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1783, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1815, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1704, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845754253739117e-05, + "loss": 4.1753, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844915658988065e-05, + "loss": 4.1716, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.1611, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1549, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842401512615282e-05, + "loss": 4.147, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.84156291786423e-05, + "loss": 4.1548, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840724323113178e-05, + "loss": 4.153, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.1635, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.1494, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.1493, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.837371581989343e-05, + "loss": 4.1528, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836532987238292e-05, + "loss": 4.1484, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.83569439248724e-05, + "loss": 4.1487, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.8348574356165606e-05, + "loss": 4.1347, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.1331, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.1565, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.1541, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.1367, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.1368, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.1413, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.1242, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.1424, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.1169, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264731259864135e-05, + "loss": 4.1443, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256345312353615e-05, + "loss": 4.1396, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824797574364683e-05, + "loss": 4.1207, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.1167, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823120384862579e-05, + "loss": 4.1344, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.822281790111527e-05, + "loss": 4.1, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821443195360475e-05, + "loss": 4.1173, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820604600609423e-05, + "loss": 4.1279, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819766005858371e-05, + "loss": 4.1215, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.8189274111073184e-05, + "loss": 4.1126, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.1014, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817253497365961e-05, + "loss": 4.1068, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816414902614909e-05, + "loss": 4.1081, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.815576307863857e-05, + "loss": 4.1168, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814737713112805e-05, + "loss": 4.1066, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.115, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130621614910745e-05, + "loss": 4.1185, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122235667400224e-05, + "loss": 4.115, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113849719889704e-05, + "loss": 4.101, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.1077, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.1073, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.1023, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808032230865135e-05, + "loss": 4.1028, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.8071936361140827e-05, + "loss": 4.097, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806356679243404e-05, + "loss": 4.1033, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805518084492352e-05, + "loss": 4.0998, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.8046794897413e-05, + "loss": 4.0842, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803840894990248e-05, + "loss": 4.0923, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.0941, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.1003, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801326748617466e-05, + "loss": 4.0889, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800488153866413e-05, + "loss": 4.086, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799651196995735e-05, + "loss": 4.0844, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798812602244683e-05, + "loss": 4.0781, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.79797400749363e-05, + "loss": 4.0813, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797135412742578e-05, + "loss": 4.0901, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.0861, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954598611208476e-05, + "loss": 4.0958, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.0858, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.7937826716187436e-05, + "loss": 4.0751, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.0745, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0826, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0864, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.7904299304949085e-05, + "loss": 4.0861, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0773, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.0677, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.086, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870771893710734e-05, + "loss": 4.0628, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0731, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785401637749343e-05, + "loss": 4.0711, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784563042998291e-05, + "loss": 4.0691, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783724448247239e-05, + "loss": 4.0598, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0688, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0594, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0688, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780371707123404e-05, + "loss": 4.0635, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0558, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.0766, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0772, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0675, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0579, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0524, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0584, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0559, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0651, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.0461, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0559, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0586, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0581, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0451, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.053, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.0514, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0542, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.058, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0565, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0368, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.051, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0526, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0494, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.0454, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0511, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585780708782906e-05, + "loss": 4.0456, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0609, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.0356, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0501, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0409, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0349, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753549778132725e-05, + "loss": 4.0418, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0326, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751872588630621e-05, + "loss": 4.0335, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.0357, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0324, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.034352779388428, + "eval_runtime": 302.1567, + "eval_samples_per_second": 1262.891, + "eval_steps_per_second": 39.466, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0286, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0231, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0407, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.0303, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0463, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0213, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0274, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.0121, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742649684249422e-05, + "loss": 4.0295, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0244, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740972494747318e-05, + "loss": 4.0198, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0317, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0076, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.0242, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0071, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 4.01, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735942564121379e-05, + "loss": 4.0106, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735103969370327e-05, + "loss": 4.0194, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734265374619275e-05, + "loss": 4.0109, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733426779868223e-05, + "loss": 4.0318, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 4.0098, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0137, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 4.0109, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.0195, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 4.0086, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 4.0136, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 4.0028, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726721297620553e-05, + "loss": 4.0067, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9938, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 4.0092, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 4.0065, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723368556496718e-05, + "loss": 4.0076, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 4.0136, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 4.0018, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9994, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 4.007, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.9991, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9889, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9814, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.9897, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158261173783695e-05, + "loss": 3.9918, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149875226273175e-05, + "loss": 3.9991, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9934, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.9826, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.997, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9898, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9865, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709957592001379e-05, + "loss": 3.9797, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9741, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708282040379648e-05, + "loss": 4.0005, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9971, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9826, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9823, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9911, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9684, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9894, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9684, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9887, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9947, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998993686298745e-05, + "loss": 3.9747, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9653, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9869, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9578, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965466275060394e-05, + "loss": 3.9714, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9798, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9792, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9716, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9576, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692356929511526e-05, + "loss": 3.9612, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691518334760474e-05, + "loss": 3.9644, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9755, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689841145258369e-05, + "loss": 3.9638, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9758, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9772, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9766, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9605, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9698, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.973, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9625, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9665, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9644, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9622, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9669, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797829218868645e-05, + "loss": 3.9485, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.678945965016186e-05, + "loss": 3.9605, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9588, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9662, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764301807630294e-05, + "loss": 3.9569, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.675593223892351e-05, + "loss": 3.9549, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.674754629141298e-05, + "loss": 3.9548, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.673916034390246e-05, + "loss": 3.9493, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.673079077519568e-05, + "loss": 3.9467, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672240482768516e-05, + "loss": 3.9569, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9674, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9633, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9546, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9485, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.9502, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667208914262204e-05, + "loss": 3.9523, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666371957391525e-05, + "loss": 3.9599, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665533362640473e-05, + "loss": 3.9587, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9512, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.9427, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663017578387317e-05, + "loss": 3.9631, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662178983636265e-05, + "loss": 3.9399, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661340388885213e-05, + "loss": 3.951, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660503432014534e-05, + "loss": 3.9429, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659664837263482e-05, + "loss": 3.9472, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.65882624251243e-05, + "loss": 3.9371, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.9481, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.9401, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.9411, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655473501388595e-05, + "loss": 3.9507, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654634906637543e-05, + "loss": 3.9335, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653796311886491e-05, + "loss": 3.9572, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652957717135439e-05, + "loss": 3.9556, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9481, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651282165513708e-05, + "loss": 3.9392, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9359, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9391, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9381, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.647929424389874e-05, + "loss": 3.9453, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9282, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9405, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9443, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9426, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9308, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9364, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9383, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9402, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.9401, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.9456, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.9227, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.938, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9415, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.935, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353537788848395e-05, + "loss": 3.9334, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.943, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.935, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9494, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.9258, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9347, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9342, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9267, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9313, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.926, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9223, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9272, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9268, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.961202383041382, + "eval_runtime": 302.9755, + "eval_samples_per_second": 1259.478, + "eval_steps_per_second": 39.36, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9249, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.916, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9335, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9234, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9437, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.9186, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9236, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9069, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.925, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9242, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.9156, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615235694261457e-05, + "loss": 3.9215, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614398737390778e-05, + "loss": 3.9088, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613560142639726e-05, + "loss": 3.9218, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612721547888674e-05, + "loss": 3.9065, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611882953137622e-05, + "loss": 3.9051, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.61104435838657e-05, + "loss": 3.9114, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610205763635518e-05, + "loss": 3.9152, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.913, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9306, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607691617262736e-05, + "loss": 3.9119, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.606853022511684e-05, + "loss": 3.918, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606014427760631e-05, + "loss": 3.909, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605175833009579e-05, + "loss": 3.9162, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604337238258527e-05, + "loss": 3.9091, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603498643507475e-05, + "loss": 3.9155, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602661686636796e-05, + "loss": 3.9074, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601823091885744e-05, + "loss": 3.9033, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600984497134692e-05, + "loss": 3.9006, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60014590238364e-05, + "loss": 3.9097, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993089455129615e-05, + "loss": 3.9122, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9095, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9203, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967947991401784e-05, + "loss": 3.9073, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959562043891264e-05, + "loss": 3.9014, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.9095, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.9083, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593442058016343e-05, + "loss": 3.8917, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592603463265291e-05, + "loss": 3.8879, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591764868514239e-05, + "loss": 3.8933, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590926273763187e-05, + "loss": 3.9017, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590089316892508e-05, + "loss": 3.9041, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589250722141457e-05, + "loss": 3.9019, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588412127390405e-05, + "loss": 3.8889, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587573532639353e-05, + "loss": 3.9035, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586734937888301e-05, + "loss": 3.8983, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.8951, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.58505938626657e-05, + "loss": 3.8881, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584220791515518e-05, + "loss": 3.877, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583382196764466e-05, + "loss": 3.9152, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582543602013414e-05, + "loss": 3.9035, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581705007262362e-05, + "loss": 3.8933, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.58086641251131e-05, + "loss": 3.8948, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580029455640631e-05, + "loss": 3.895, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579190860889579e-05, + "loss": 3.8801, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783522661385267e-05, + "loss": 3.8975, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577513671387475e-05, + "loss": 3.8826, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576675076636423e-05, + "loss": 3.8936, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575836481885371e-05, + "loss": 3.9087, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574999525014692e-05, + "loss": 3.8854, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.57416093026364e-05, + "loss": 3.8734, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573322335512588e-05, + "loss": 3.9026, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572483740761536e-05, + "loss": 3.8696, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571645146010484e-05, + "loss": 3.8795, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570808189139805e-05, + "loss": 3.8964, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569969594388753e-05, + "loss": 3.8894, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569130999637701e-05, + "loss": 3.8839, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568292404886649e-05, + "loss": 3.8766, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567453810135597e-05, + "loss": 3.8692, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566616853264919e-05, + "loss": 3.8773, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565778258513867e-05, + "loss": 3.8911, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.564939663762814e-05, + "loss": 3.8747, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.564101069011762e-05, + "loss": 3.8921, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632641121410836e-05, + "loss": 3.8863, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624255173900316e-05, + "loss": 3.8958, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561586922638979e-05, + "loss": 3.8781, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560748327887927e-05, + "loss": 3.881, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599113710172485e-05, + "loss": 3.8884, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590727762661965e-05, + "loss": 3.8755, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582341815151445e-05, + "loss": 3.8873, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5573955867640925e-05, + "loss": 3.8785, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556558629893414e-05, + "loss": 3.8781, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557200351423614e-05, + "loss": 3.8831, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548814403913094e-05, + "loss": 3.8669, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540428456402574e-05, + "loss": 3.8736, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553205888769579e-05, + "loss": 3.8788, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552367294018526e-05, + "loss": 3.8824, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551528699267474e-05, + "loss": 3.8715, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550690104516422e-05, + "loss": 3.8743, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.54985150976537e-05, + "loss": 3.8705, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549014552894691e-05, + "loss": 3.8664, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548175958143639e-05, + "loss": 3.8676, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547337363392588e-05, + "loss": 3.8747, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546498768641536e-05, + "loss": 3.8848, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545660173890484e-05, + "loss": 3.886, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544823217019805e-05, + "loss": 3.8743, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543984622268753e-05, + "loss": 3.8654, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.543146027517701e-05, + "loss": 3.8689, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542307432766649e-05, + "loss": 3.8732, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541468838015597e-05, + "loss": 3.8775, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8775, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397932863938656e-05, + "loss": 3.873, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389546916428136e-05, + "loss": 3.8616, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381160968917616e-05, + "loss": 3.8847, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537279140021083e-05, + "loss": 3.8549, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536440545270031e-05, + "loss": 3.8748, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535601950518979e-05, + "loss": 3.8634, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534763355767927e-05, + "loss": 3.8701, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8609, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533087804146196e-05, + "loss": 3.8681, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532249209395144e-05, + "loss": 3.8641, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531410614644092e-05, + "loss": 3.8631, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.53057201989304e-05, + "loss": 3.8696, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529733425141988e-05, + "loss": 3.8583, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528896468271309e-05, + "loss": 3.8762, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.528057873520257e-05, + "loss": 3.8778, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527219278769205e-05, + "loss": 3.8735, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526380684018153e-05, + "loss": 3.8624, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255437271474746e-05, + "loss": 3.8621, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247051323964226e-05, + "loss": 3.8604, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238665376453706e-05, + "loss": 3.8615, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230279428943186e-05, + "loss": 3.8697, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221909860236395e-05, + "loss": 3.8488, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.8655, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205137965215355e-05, + "loss": 3.8641, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196752017704834e-05, + "loss": 3.8701, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188366070194314e-05, + "loss": 3.8554, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8625, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171610553977003e-05, + "loss": 3.8568, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163224606466483e-05, + "loss": 3.8718, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515483865895597e-05, + "loss": 3.8622, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514646909024918e-05, + "loss": 3.8727, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513808314273866e-05, + "loss": 3.8487, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512969719522814e-05, + "loss": 3.8627, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512131124771762e-05, + "loss": 3.8681, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511294167901083e-05, + "loss": 3.8573, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510455573150031e-05, + "loss": 3.8602, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509616978398979e-05, + "loss": 3.871, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508778383647927e-05, + "loss": 3.864, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507941426777248e-05, + "loss": 3.8778, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507102832026196e-05, + "loss": 3.8494, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506264237275144e-05, + "loss": 3.8624, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.5054256425240924e-05, + "loss": 3.8566, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504588685653413e-05, + "loss": 3.8549, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503750090902361e-05, + "loss": 3.8593, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502911496151309e-05, + "loss": 3.8532, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502072901400257e-05, + "loss": 3.8515, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8518, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.858, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.919128656387329, + "eval_runtime": 303.0214, + "eval_samples_per_second": 1259.287, + "eval_steps_per_second": 39.354, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499558755027474e-05, + "loss": 3.8503, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987201602764215e-05, + "loss": 3.8447, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978815655253695e-05, + "loss": 3.8621, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970429707743175e-05, + "loss": 3.8545, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.869, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8518, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8511, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8369, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492851634899431e-05, + "loss": 3.8519, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492013040148379e-05, + "loss": 3.8512, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491174445397327e-05, + "loss": 3.8498, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490335850646275e-05, + "loss": 3.8496, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489500531655969e-05, + "loss": 3.8391, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488661936904917e-05, + "loss": 3.8538, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487823342153865e-05, + "loss": 3.8368, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486984747402813e-05, + "loss": 3.8373, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486146152651761e-05, + "loss": 3.8402, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853075579007095e-05, + "loss": 3.8478, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844689631496575e-05, + "loss": 3.8415, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836303683986055e-05, + "loss": 3.858, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827934115279264e-05, + "loss": 3.8447, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819548167768744e-05, + "loss": 3.8534, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811162220258224e-05, + "loss": 3.8408, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802776272747704e-05, + "loss": 3.8462, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479440670404091e-05, + "loss": 3.8411, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8496, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8395, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476924886150935e-05, + "loss": 3.8401, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476087929280256e-05, + "loss": 3.8328, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475249334529205e-05, + "loss": 3.8415, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8461, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473572145027101e-05, + "loss": 3.8441, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472735188156422e-05, + "loss": 3.8516, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.47189659340537e-05, + "loss": 3.8385, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.8382, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8477, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469380809152214e-05, + "loss": 3.8453, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468543852281535e-05, + "loss": 3.8209, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8275, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.8262, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466028068028379e-05, + "loss": 3.8304, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651911111577e-05, + "loss": 3.8428, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.834, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8286, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462675326904544e-05, + "loss": 3.8358, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461838370033865e-05, + "loss": 3.8296, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460999775282813e-05, + "loss": 3.8319, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.8254, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459322585780709e-05, + "loss": 3.8073, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458483991029657e-05, + "loss": 3.8521, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457647034158978e-05, + "loss": 3.8393, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.8347, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455969844656874e-05, + "loss": 3.8301, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551328877861956e-05, + "loss": 3.8286, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542942930351436e-05, + "loss": 3.8184, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.8302, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526171035330396e-05, + "loss": 3.8246, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517785087819876e-05, + "loss": 3.8274, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509399140309356e-05, + "loss": 3.8452, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450101319279883e-05, + "loss": 3.8226, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449262724528831e-05, + "loss": 3.815, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484257676581525e-05, + "loss": 3.8395, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475871729071e-05, + "loss": 3.8078, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446748578156048e-05, + "loss": 3.8207, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445909983404996e-05, + "loss": 3.83, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450730265343174e-05, + "loss": 3.828, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442344317832654e-05, + "loss": 3.8199, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.4433958370322134e-05, + "loss": 3.816, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.4425572422811614e-05, + "loss": 3.8064, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441720285410482e-05, + "loss": 3.8155, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088169065943e-05, + "loss": 3.8275, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440043095908378e-05, + "loss": 3.8164, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439204501157326e-05, + "loss": 3.8267, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438367544286647e-05, + "loss": 3.8283, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437528949535595e-05, + "loss": 3.8356, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436690354784543e-05, + "loss": 3.8179, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435851760033491e-05, + "loss": 3.8157, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435014803162813e-05, + "loss": 3.8266, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434176208411761e-05, + "loss": 3.8121, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433337613660709e-05, + "loss": 3.8306, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432499018909657e-05, + "loss": 3.8187, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431662062038978e-05, + "loss": 3.8174, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.4308234672879257e-05, + "loss": 3.8258, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.4299848725368737e-05, + "loss": 3.8054, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.4291462777858217e-05, + "loss": 3.8136, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.4283093209151426e-05, + "loss": 3.8165, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274707261640906e-05, + "loss": 3.8241, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266321314130386e-05, + "loss": 3.8086, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4257935366619865e-05, + "loss": 3.8164, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424956579791308e-05, + "loss": 3.8113, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.424117985040256e-05, + "loss": 3.81, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.423279390289204e-05, + "loss": 3.8031, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.422440795538152e-05, + "loss": 3.8166, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.421603838667473e-05, + "loss": 3.8248, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.420765243916421e-05, + "loss": 3.8227, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.419926649165369e-05, + "loss": 3.8213, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.419088054414317e-05, + "loss": 3.8048, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.418251097543638e-05, + "loss": 3.8097, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417412502792586e-05, + "loss": 3.8141, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416573908041534e-05, + "loss": 3.8197, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415735313290482e-05, + "loss": 3.8193, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.4148983564198035e-05, + "loss": 3.8141, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140597616687515e-05, + "loss": 3.8077, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.4132211669176995e-05, + "loss": 3.8235, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.4123825721666475e-05, + "loss": 3.8007, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.4115456152959684e-05, + "loss": 3.8156, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.4107070205449164e-05, + "loss": 3.8064, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.4098684257938644e-05, + "loss": 3.8131, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.4090298310428124e-05, + "loss": 3.8022, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408192874172133e-05, + "loss": 3.8118, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407354279421081e-05, + "loss": 3.8055, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406515684670029e-05, + "loss": 3.8075, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405677089918977e-05, + "loss": 3.8118, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404840133048299e-05, + "loss": 3.8048, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404001538297247e-05, + "loss": 3.8179, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403162943546195e-05, + "loss": 3.821, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402324348795143e-05, + "loss": 3.813, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401487391924464e-05, + "loss": 3.8111, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400648797173412e-05, + "loss": 3.8027, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.39981020242236e-05, + "loss": 3.8061, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398971607671308e-05, + "loss": 3.8033, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981346508006287e-05, + "loss": 3.8171, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972960560495767e-05, + "loss": 3.7897, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964574612985247e-05, + "loss": 3.8081, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956188665474726e-05, + "loss": 3.8071, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394781909676794e-05, + "loss": 3.8135, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393943314925742e-05, + "loss": 3.8038, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.39310472017469e-05, + "loss": 3.8077, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392266125423638e-05, + "loss": 3.7995, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391429168552959e-05, + "loss": 3.8128, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.390590573801907e-05, + "loss": 3.8103, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389751979050855e-05, + "loss": 3.8147, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388913384299803e-05, + "loss": 3.7943, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388076427429124e-05, + "loss": 3.8073, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387237832678072e-05, + "loss": 3.8115, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.38639923792702e-05, + "loss": 3.8016, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385560643175968e-05, + "loss": 3.8047, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847236863052896e-05, + "loss": 3.814, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838850915542376e-05, + "loss": 3.806, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830464968031856e-05, + "loss": 3.826, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822079020521336e-05, + "loss": 3.7959, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813709451814545e-05, + "loss": 3.8079, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805323504304025e-05, + "loss": 3.8009, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796937556793505e-05, + "loss": 3.8022, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.3788567988086714e-05, + "loss": 3.8062, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.3780182040576194e-05, + "loss": 3.7993, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771796093065674e-05, + "loss": 3.801, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763410145555154e-05, + "loss": 3.7902, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755024198044634e-05, + "loss": 3.8054, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.8933022022247314, + "eval_runtime": 303.8142, + "eval_samples_per_second": 1256.001, + "eval_steps_per_second": 39.251, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746638250534114e-05, + "loss": 3.802, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738252303023594e-05, + "loss": 3.7906, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372986635551308e-05, + "loss": 3.8082, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372149678680629e-05, + "loss": 3.8056, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371311083929577e-05, + "loss": 3.8114, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370472489178525e-05, + "loss": 3.7969, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369633894427473e-05, + "loss": 3.7984, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368796937556794e-05, + "loss": 3.7863, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367958342805742e-05, + "loss": 3.7995, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.36711974805469e-05, + "loss": 3.7968, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366281153303637e-05, + "loss": 3.8004, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365444196432959e-05, + "loss": 3.7918, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.36460723956228e-05, + "loss": 3.7931, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363768644811228e-05, + "loss": 3.7935, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362930050060176e-05, + "loss": 3.7861, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362091455309124e-05, + "loss": 3.7807, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361252860558072e-05, + "loss": 3.7895, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.36041426580702e-05, + "loss": 3.795, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595756710559676e-05, + "loss": 3.7919, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.3587370763049156e-05, + "loss": 3.8064, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357900119434237e-05, + "loss": 3.7959, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.3570615246831845e-05, + "loss": 3.8011, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.3562229299321325e-05, + "loss": 3.7884, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.3553843351810805e-05, + "loss": 3.7925, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354547378310402e-05, + "loss": 3.7891, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.35370878355935e-05, + "loss": 3.8016, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352870188808298e-05, + "loss": 3.7886, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352031594057246e-05, + "loss": 3.7872, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.351194637186568e-05, + "loss": 3.7832, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350356042435515e-05, + "loss": 3.7908, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349517447684463e-05, + "loss": 3.7909, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348678852933411e-05, + "loss": 3.796, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347841896062732e-05, + "loss": 3.7977, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.34700330131168e-05, + "loss": 3.7918, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346164706560628e-05, + "loss": 3.788, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345326111809576e-05, + "loss": 3.7961, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444891549388975e-05, + "loss": 3.7926, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.3436505601878455e-05, + "loss": 3.7777, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.3428119654367935e-05, + "loss": 3.7776, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.3419733706857415e-05, + "loss": 3.7738, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411364138150624e-05, + "loss": 3.7759, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.3402978190640104e-05, + "loss": 3.7918, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.3394592243129584e-05, + "loss": 3.7876, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.3386206295619064e-05, + "loss": 3.7775, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337783672691227e-05, + "loss": 3.7855, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336945077940175e-05, + "loss": 3.7798, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336106483189123e-05, + "loss": 3.7837, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335267888438071e-05, + "loss": 3.7746, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334430931567393e-05, + "loss": 3.7558, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.333592336816341e-05, + "loss": 3.8043, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332753742065289e-05, + "loss": 3.786, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331915147314237e-05, + "loss": 3.7878, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331078190443558e-05, + "loss": 3.7769, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330241233572879e-05, + "loss": 3.7843, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294026388218266e-05, + "loss": 3.7698, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.3285640440707746e-05, + "loss": 3.7784, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.3277254493197226e-05, + "loss": 3.7782, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.3268868545686706e-05, + "loss": 3.7762, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260482598176186e-05, + "loss": 3.7995, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.3252096650665666e-05, + "loss": 3.7721, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.3243710703155146e-05, + "loss": 3.7651, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323534113444836e-05, + "loss": 3.7905, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322695518693784e-05, + "loss": 3.7594, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321856923942732e-05, + "loss": 3.7694, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.32101832919168e-05, + "loss": 3.7833, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.320181372321001e-05, + "loss": 3.7833, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.319342777569949e-05, + "loss": 3.7694, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.318504182818897e-05, + "loss": 3.774, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.317667225948218e-05, + "loss": 3.7568, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316828631197166e-05, + "loss": 3.7706, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315990036446114e-05, + "loss": 3.7784, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.315151441695062e-05, + "loss": 3.768, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143144848243836e-05, + "loss": 3.7788, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134758900733316e-05, + "loss": 3.7782, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126372953222796e-05, + "loss": 3.7908, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.3117987005712276e-05, + "loss": 3.7686, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109617437005485e-05, + "loss": 3.7736, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101231489494965e-05, + "loss": 3.7779, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092845541984445e-05, + "loss": 3.7658, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.3084459594473925e-05, + "loss": 3.78, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.3076090025767134e-05, + "loss": 3.7738, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.3067704078256614e-05, + "loss": 3.7711, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.3059318130746094e-05, + "loss": 3.7785, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.3050932183235574e-05, + "loss": 3.761, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304256261452879e-05, + "loss": 3.7634, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.303417666701827e-05, + "loss": 3.7723, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302579071950775e-05, + "loss": 3.7745, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301740477199723e-05, + "loss": 3.7645, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300903520329044e-05, + "loss": 3.7689, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300064925577992e-05, + "loss": 3.7611, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.29922633082694e-05, + "loss": 3.7679, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298387736075888e-05, + "loss": 3.7591, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297550779205209e-05, + "loss": 3.7672, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296712184454157e-05, + "loss": 3.7832, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295873589703105e-05, + "loss": 3.773, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295034994952053e-05, + "loss": 3.7732, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294198038081374e-05, + "loss": 3.7597, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293359443330322e-05, + "loss": 3.7639, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29252084857927e-05, + "loss": 3.7666, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291682253828218e-05, + "loss": 3.775, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290845296957539e-05, + "loss": 3.7691, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290006702206487e-05, + "loss": 3.7729, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289168107455435e-05, + "loss": 3.7614, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288329512704383e-05, + "loss": 3.7759, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287492555833704e-05, + "loss": 3.7576, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286653961082652e-05, + "loss": 3.7703, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858153663316e-05, + "loss": 3.7569, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284976771580548e-05, + "loss": 3.7725, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.2841414525902426e-05, + "loss": 3.7578, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833028578391906e-05, + "loss": 3.764, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824642630881386e-05, + "loss": 3.7632, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816256683370866e-05, + "loss": 3.7642, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807870735860346e-05, + "loss": 3.7639, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799484788349826e-05, + "loss": 3.7604, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791098840839306e-05, + "loss": 3.771, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782712893328786e-05, + "loss": 3.7748, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774343324621995e-05, + "loss": 3.7683, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765957377111475e-05, + "loss": 3.7717, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757571429600955e-05, + "loss": 3.7552, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749185482090435e-05, + "loss": 3.7623, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274081591338365e-05, + "loss": 3.7631, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273242996587313e-05, + "loss": 3.7708, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272404401836261e-05, + "loss": 3.7453, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271565807085209e-05, + "loss": 3.7637, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.27072885021453e-05, + "loss": 3.766, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269890255463478e-05, + "loss": 3.763, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269051660712426e-05, + "loss": 3.7586, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268213065961374e-05, + "loss": 3.7633, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267376109090695e-05, + "loss": 3.7568, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266537514339643e-05, + "loss": 3.7706, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265698919588591e-05, + "loss": 3.7668, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264860324837539e-05, + "loss": 3.7695, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640233679668604e-05, + "loss": 3.7508, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631847732158084e-05, + "loss": 3.7643, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.2623461784647564e-05, + "loss": 3.7688, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.2615075837137044e-05, + "loss": 3.7588, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260670626843025e-05, + "loss": 3.7599, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259832032091973e-05, + "loss": 3.7685, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258993437340921e-05, + "loss": 3.7657, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258154842589869e-05, + "loss": 3.7783, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.25731788571919e-05, + "loss": 3.7558, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256479290968138e-05, + "loss": 3.7617, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255640696217086e-05, + "loss": 3.7604, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254802101466034e-05, + "loss": 3.7598, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253966782475729e-05, + "loss": 3.7585, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253128187724677e-05, + "loss": 3.7555, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252289592973625e-05, + "loss": 3.7605, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251450998222573e-05, + "loss": 3.7458, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250612403471521e-05, + "loss": 3.7659, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.877441167831421, + "eval_runtime": 303.1726, + "eval_samples_per_second": 1258.659, + "eval_steps_per_second": 39.334, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249773808720469e-05, + "loss": 3.7598, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248935213969417e-05, + "loss": 3.7477, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248096619218364e-05, + "loss": 3.7626, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247258024467312e-05, + "loss": 3.7612, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.24641942971626e-05, + "loss": 3.7725, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245580834965208e-05, + "loss": 3.7544, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244742240214156e-05, + "loss": 3.7566, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243903645463104e-05, + "loss": 3.7442, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.2430666885924255e-05, + "loss": 3.7562, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422280938413735e-05, + "loss": 3.755, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413894990903215e-05, + "loss": 3.757, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405509043392695e-05, + "loss": 3.7503, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239715585348964e-05, + "loss": 3.7507, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388769905979114e-05, + "loss": 3.7516, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380383958468593e-05, + "loss": 3.7485, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371998010958073e-05, + "loss": 3.7394, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363612063447553e-05, + "loss": 3.7458, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235522611593703e-05, + "loss": 3.7533, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234684016842651e-05, + "loss": 3.7504, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233845422091599e-05, + "loss": 3.7622, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.233008465220921e-05, + "loss": 3.7565, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232169870469869e-05, + "loss": 3.7624, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23133291359919e-05, + "loss": 3.7428, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230494318848138e-05, + "loss": 3.7514, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229655724097086e-05, + "loss": 3.7478, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228817129346034e-05, + "loss": 3.7577, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227978534594982e-05, + "loss": 3.7459, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.22713993984393e-05, + "loss": 3.7503, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226301345092878e-05, + "loss": 3.7437, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225462750341826e-05, + "loss": 3.7452, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224625793471147e-05, + "loss": 3.7473, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223787198720095e-05, + "loss": 3.7581, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222948603969043e-05, + "loss": 3.7568, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222111647098364e-05, + "loss": 3.7526, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221273052347312e-05, + "loss": 3.7474, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.22043445759626e-05, + "loss": 3.7502, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219595862845208e-05, + "loss": 3.7541, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218758905974529e-05, + "loss": 3.7389, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217920311223477e-05, + "loss": 3.7362, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217081716472425e-05, + "loss": 3.732, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216243121721373e-05, + "loss": 3.7395, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215406164850694e-05, + "loss": 3.7469, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214567570099642e-05, + "loss": 3.7475, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.21372897534859e-05, + "loss": 3.7405, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212890380597538e-05, + "loss": 3.7426, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120534237268596e-05, + "loss": 3.741, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112148289758076e-05, + "loss": 3.7447, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103762342247556e-05, + "loss": 3.7343, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095376394737036e-05, + "loss": 3.7167, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087006826030245e-05, + "loss": 3.7591, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078620878519725e-05, + "loss": 3.7453, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070234931009205e-05, + "loss": 3.7497, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061848983498685e-05, + "loss": 3.7387, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.2053479414791894e-05, + "loss": 3.7432, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.2045093467281374e-05, + "loss": 3.732, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036707519770854e-05, + "loss": 3.7391, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028321572260334e-05, + "loss": 3.7418, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201993562474982e-05, + "loss": 3.7352, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.20115496772393e-05, + "loss": 3.7584, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200316372972878e-05, + "loss": 3.7368, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994777782218254e-05, + "loss": 3.7255, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198640821351147e-05, + "loss": 3.7503, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197802226600095e-05, + "loss": 3.7237, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196963631849042e-05, + "loss": 3.7235, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19612503709799e-05, + "loss": 3.7485, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195288080227312e-05, + "loss": 3.7456, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.19444948547626e-05, + "loss": 3.7287, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193610890725207e-05, + "loss": 3.7357, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192772295974156e-05, + "loss": 3.7188, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919353391034775e-05, + "loss": 3.7336, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191096744352425e-05, + "loss": 3.7344, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190258149601373e-05, + "loss": 3.7325, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.1894211927306944e-05, + "loss": 3.7385, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.1885825979796424e-05, + "loss": 3.7387, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.18774400322859e-05, + "loss": 3.7499, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186905408477538e-05, + "loss": 3.7317, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186068451606859e-05, + "loss": 3.735, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185229856855807e-05, + "loss": 3.7383, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843912621047546e-05, + "loss": 3.7276, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835526673537026e-05, + "loss": 3.7404, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182715710483024e-05, + "loss": 3.7374, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181877115731972e-05, + "loss": 3.7307, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.18103852098092e-05, + "loss": 3.7454, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180199926229868e-05, + "loss": 3.7182, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179361331478816e-05, + "loss": 3.7233, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178522736727764e-05, + "loss": 3.7374, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177684141976712e-05, + "loss": 3.737, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.7273, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176008590354981e-05, + "loss": 3.7332, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175169995603929e-05, + "loss": 3.7191, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174331400852877e-05, + "loss": 3.7307, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173494443982198e-05, + "loss": 3.7222, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726558492311466e-05, + "loss": 3.7329, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.1718172544800946e-05, + "loss": 3.743, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.1709786597290426e-05, + "loss": 3.7356, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7372, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.724, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7272, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676242807248346e-05, + "loss": 3.7263, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667873238541555e-05, + "loss": 3.7384, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659487291031035e-05, + "loss": 3.7334, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651101343520515e-05, + "loss": 3.7383, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642715396009995e-05, + "loss": 3.7214, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163436220610693e-05, + "loss": 3.7353, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162597625859642e-05, + "loss": 3.7258, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.16175903110859e-05, + "loss": 3.7321, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160920436357538e-05, + "loss": 3.7182, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160081841606486e-05, + "loss": 3.7361, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159244884735807e-05, + "loss": 3.7187, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158406289984755e-05, + "loss": 3.7298, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157567695233703e-05, + "loss": 3.7209, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156729100482651e-05, + "loss": 3.734, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155890505731599e-05, + "loss": 3.7243, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155051910980547e-05, + "loss": 3.7235, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154213316229495e-05, + "loss": 3.7348, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153374721478443e-05, + "loss": 3.7385, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152537764607764e-05, + "loss": 3.7335, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.7316, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.7215, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.723, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149185023483929e-05, + "loss": 3.7271, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148346428732877e-05, + "loss": 3.73, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147507833981825e-05, + "loss": 3.7121, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.7272, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.7284, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144993687609042e-05, + "loss": 3.7278, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.14415509285799e-05, + "loss": 3.7254, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.727, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142479541236259e-05, + "loss": 3.72, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7331, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7314, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7317, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139126800112425e-05, + "loss": 3.7182, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.7286, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.7302, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7208, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357740589885896e-05, + "loss": 3.7254, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349354642375376e-05, + "loss": 3.7287, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7298, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7437, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324213178647545e-05, + "loss": 3.718, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315827231137025e-05, + "loss": 3.7277, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.729, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.7258, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129070214621293e-05, + "loss": 3.7191, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128231619870241e-05, + "loss": 3.7186, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127393025119189e-05, + "loss": 3.7245, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126554430368137e-05, + "loss": 3.7116, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125715835617085e-05, + "loss": 3.7299, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.86759090423584, + "eval_runtime": 304.9257, + "eval_samples_per_second": 1251.423, + "eval_steps_per_second": 39.108, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124877240866032e-05, + "loss": 3.7232, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12403864611498e-05, + "loss": 3.7118, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123200051363928e-05, + "loss": 3.7254, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12236309449325e-05, + "loss": 3.727, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121524499742198e-05, + "loss": 3.7344, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120685904991146e-05, + "loss": 3.7184, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1198489481204674e-05, + "loss": 3.7252, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190103533694154e-05, + "loss": 3.7124, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118171758618363e-05, + "loss": 3.7153, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117333163867311e-05, + "loss": 3.7253, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116494569116259e-05, + "loss": 3.7214, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.7123, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.1148190174945276e-05, + "loss": 3.7243, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.1139804227434756e-05, + "loss": 3.7097, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.1131418279924236e-05, + "loss": 3.7099, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.7066, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.7107, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.7193, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109787448988216e-05, + "loss": 3.7094, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108948854237164e-05, + "loss": 3.7315, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7211, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7271, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.7128, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.7145, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10475915624265e-05, + "loss": 3.7184, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103920561491598e-05, + "loss": 3.7204, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103081966740546e-05, + "loss": 3.7127, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.718, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101406415118815e-05, + "loss": 3.7058, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005678203677637e-05, + "loss": 3.7134, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997292256167117e-05, + "loss": 3.7145, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7218, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980536739949806e-05, + "loss": 3.7238, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972150792439286e-05, + "loss": 3.7205, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963764844928766e-05, + "loss": 3.7145, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.715, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.7208, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.7062, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.7028, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921867864983624e-05, + "loss": 3.6976, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.7051, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.7083, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.7172, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088834045374528e-05, + "loss": 3.7079, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087997088503849e-05, + "loss": 3.7064, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087158493752797e-05, + "loss": 3.7098, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086319899001745e-05, + "loss": 3.7143, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085481304250693e-05, + "loss": 3.7009, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6855, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.7187, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.7134, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082126925246485e-05, + "loss": 3.7204, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.7064, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080453011505127e-05, + "loss": 3.7083, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079614416754075e-05, + "loss": 3.6994, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078775822003023e-05, + "loss": 3.7038, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077937227251971e-05, + "loss": 3.712, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077100270381292e-05, + "loss": 3.6967, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.07626167563024e-05, + "loss": 3.7277, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075423080879188e-05, + "loss": 3.7083, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6881, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.7191, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.6926, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.07206870187498e-05, + "loss": 3.6911, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071230107123928e-05, + "loss": 3.7146, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.7089, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.6961, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068715960751146e-05, + "loss": 3.7009, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.067877366000094e-05, + "loss": 3.6899, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6993, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.7041, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6984, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.064524624876258e-05, + "loss": 3.7093, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636893058859525e-05, + "loss": 3.7028, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628507111349005e-05, + "loss": 3.7157, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620121163838485e-05, + "loss": 3.6997, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611735216327965e-05, + "loss": 3.7062, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.7043, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6962, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586577373796404e-05, + "loss": 3.7097, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.7044, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.6958, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056143591006858e-05, + "loss": 3.7122, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055304996255805e-05, + "loss": 3.6871, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054466401504753e-05, + "loss": 3.6885, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053627806753701e-05, + "loss": 3.7062, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052789212002649e-05, + "loss": 3.7017, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051950617251597e-05, + "loss": 3.6942, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.7033, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.050275065629867e-05, + "loss": 3.6882, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049436470878815e-05, + "loss": 3.6945, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.6901, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6973, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046922324506032e-05, + "loss": 3.7132, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.04608372975498e-05, + "loss": 3.7029, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045246772884301e-05, + "loss": 3.7077, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6929, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.043569583382197e-05, + "loss": 3.6947, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.042730988631145e-05, + "loss": 3.696, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418940317604656e-05, + "loss": 3.702, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410554370094136e-05, + "loss": 3.7, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040216842258362e-05, + "loss": 3.7072, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.03937824750731e-05, + "loss": 3.6928, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038541290636631e-05, + "loss": 3.6993, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6971, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.036864101134527e-05, + "loss": 3.6987, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036025506383475e-05, + "loss": 3.6869, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035188549512796e-05, + "loss": 3.7066, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343515926421177e-05, + "loss": 3.6901, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033512997891065e-05, + "loss": 3.6945, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032674403140013e-05, + "loss": 3.6891, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031835808388961e-05, + "loss": 3.6981, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030997213637909e-05, + "loss": 3.6937, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301586188868576e-05, + "loss": 3.6907, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293200241358056e-05, + "loss": 3.7, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284814293847536e-05, + "loss": 3.7088, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276444725140745e-05, + "loss": 3.7053, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268058777630225e-05, + "loss": 3.6971, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259672830119705e-05, + "loss": 3.6911, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251286882609185e-05, + "loss": 3.6906, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242917313902394e-05, + "loss": 3.6965, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234531366391874e-05, + "loss": 3.6966, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226145418881354e-05, + "loss": 3.6826, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217759471370834e-05, + "loss": 3.6961, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020938990266404e-05, + "loss": 3.7009, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020100395515353e-05, + "loss": 3.6918, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019261800764301e-05, + "loss": 3.6938, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018423206013249e-05, + "loss": 3.6972, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.01758624914257e-05, + "loss": 3.6909, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016749292271891e-05, + "loss": 3.6995, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015910697520839e-05, + "loss": 3.698, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015072102769787e-05, + "loss": 3.7032, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014233508018735e-05, + "loss": 3.6853, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013394913267683e-05, + "loss": 3.6978, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012556318516631e-05, + "loss": 3.6984, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011717723765579e-05, + "loss": 3.6939, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.010879129014527e-05, + "loss": 3.6951, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100421721438484e-05, + "loss": 3.6962, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0092035773927964e-05, + "loss": 3.6987, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008366620522117e-05, + "loss": 3.7153, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007528025771065e-05, + "loss": 3.6852, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006689431020013e-05, + "loss": 3.6985, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005850836268961e-05, + "loss": 3.6955, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005012241517909e-05, + "loss": 3.6926, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.00417528464723e-05, + "loss": 3.6891, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003336689896178e-05, + "loss": 3.6859, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002498095145126e-05, + "loss": 3.6954, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001659500394074e-05, + "loss": 3.6791, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000820905643022e-05, + "loss": 3.6983, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8600664138793945, + "eval_runtime": 306.9454, + "eval_samples_per_second": 1243.189, + "eval_steps_per_second": 38.851, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.99998231089197e-05, + "loss": 3.6867, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999143716140918e-05, + "loss": 3.6824, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998305121389866e-05, + "loss": 3.6958, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997466526638814e-05, + "loss": 3.6968, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996627931887762e-05, + "loss": 3.704, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.99578933713671e-05, + "loss": 3.689, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994952380266031e-05, + "loss": 3.6961, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994113785514979e-05, + "loss": 3.6799, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6842, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.696, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991599639142196e-05, + "loss": 3.6895, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990761044391144e-05, + "loss": 3.6805, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899240875204655e-05, + "loss": 3.697, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890854927694135e-05, + "loss": 3.6783, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882468980183615e-05, + "loss": 3.6827, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874083032673095e-05, + "loss": 3.671, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865697085162575e-05, + "loss": 3.6823, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857311137652055e-05, + "loss": 3.6926, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848925190141535e-05, + "loss": 3.6791, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.6986, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832153295120495e-05, + "loss": 3.6931, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823767347609975e-05, + "loss": 3.6962, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815397778903184e-05, + "loss": 3.6861, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9807011831392664e-05, + "loss": 3.6884, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.9798625883882144e-05, + "loss": 3.6884, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790239936371624e-05, + "loss": 3.6912, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781853988861104e-05, + "loss": 3.6814, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773468041350584e-05, + "loss": 3.6883, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.97650984726438e-05, + "loss": 3.6754, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975671252513328e-05, + "loss": 3.6846, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974832657762276e-05, + "loss": 3.6874, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973994063011224e-05, + "loss": 3.6891, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973157106140545e-05, + "loss": 3.6959, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972318511389493e-05, + "loss": 3.6926, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971479916638441e-05, + "loss": 3.6797, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970641321887389e-05, + "loss": 3.6863, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969802727136337e-05, + "loss": 3.6932, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968964132385284e-05, + "loss": 3.6755, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968127175514606e-05, + "loss": 3.6771, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967288580763554e-05, + "loss": 3.6708, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.9664499860125024e-05, + "loss": 3.6716, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.96561139126145e-05, + "loss": 3.6799, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964772796510398e-05, + "loss": 3.6892, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963934201759346e-05, + "loss": 3.6797, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963097244888667e-05, + "loss": 3.6759, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622586501376146e-05, + "loss": 3.6769, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614200553865626e-05, + "loss": 3.6874, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605814606355106e-05, + "loss": 3.6691, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597428658844586e-05, + "loss": 3.6589, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.9589042711334066e-05, + "loss": 3.6895, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.9580656763823546e-05, + "loss": 3.6835, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572270816313026e-05, + "loss": 3.6915, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.956390124760624e-05, + "loss": 3.6771, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955553167889945e-05, + "loss": 3.6786, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954714573138893e-05, + "loss": 3.6728, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953875978387841e-05, + "loss": 3.6755, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953037383636789e-05, + "loss": 3.6849, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.95220042676611e-05, + "loss": 3.6661, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951361832015058e-05, + "loss": 3.7007, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950523237264006e-05, + "loss": 3.6757, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.949684642512954e-05, + "loss": 3.6598, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948846047761902e-05, + "loss": 3.6901, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.94800745301085e-05, + "loss": 3.6687, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947168858259798e-05, + "loss": 3.6607, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946330263508746e-05, + "loss": 3.6831, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.9454933066380675e-05, + "loss": 3.6816, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446547118870155e-05, + "loss": 3.6712, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438161171359635e-05, + "loss": 3.6702, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9429775223849115e-05, + "loss": 3.6583, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.9421405655142324e-05, + "loss": 3.6692, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413019707631804e-05, + "loss": 3.678, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.9404633760121284e-05, + "loss": 3.6707, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.9396247812610764e-05, + "loss": 3.6765, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938787824390397e-05, + "loss": 3.6738, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937949229639345e-05, + "loss": 3.6881, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937110634888293e-05, + "loss": 3.6715, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936273678017615e-05, + "loss": 3.6771, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935435083266563e-05, + "loss": 3.6742, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.934596488515511e-05, + "loss": 3.6695, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933757893764459e-05, + "loss": 3.6838, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932919299013407e-05, + "loss": 3.6749, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932082342142728e-05, + "loss": 3.6722, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931243747391676e-05, + "loss": 3.682, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930405152640624e-05, + "loss": 3.6588, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929566557889572e-05, + "loss": 3.6641, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.92872796313852e-05, + "loss": 3.6741, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927891006267841e-05, + "loss": 3.6758, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927052411516789e-05, + "loss": 3.6637, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926213816765737e-05, + "loss": 3.6774, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925375222014685e-05, + "loss": 3.6653, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245366272636333e-05, + "loss": 3.6666, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923699670392954e-05, + "loss": 3.66, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922861075641902e-05, + "loss": 3.6711, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.92202248089085e-05, + "loss": 3.685, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211838861397976e-05, + "loss": 3.6721, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.9203452913887456e-05, + "loss": 3.6784, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919508334518067e-05, + "loss": 3.6666, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918669739767015e-05, + "loss": 3.6668, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.9178311450159625e-05, + "loss": 3.667, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169925502649105e-05, + "loss": 3.6759, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161539555138585e-05, + "loss": 3.6719, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915315360762807e-05, + "loss": 3.6744, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914476766011755e-05, + "loss": 3.6721, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913639809141076e-05, + "loss": 3.6702, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912801214390024e-05, + "loss": 3.6711, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911962619638972e-05, + "loss": 3.6689, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.91112402488792e-05, + "loss": 3.66, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.910287068017241e-05, + "loss": 3.678, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094501111465625e-05, + "loss": 3.6624, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.90861151639551e-05, + "loss": 3.6658, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907772921644458e-05, + "loss": 3.6677, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906934326893406e-05, + "loss": 3.6667, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906095732142354e-05, + "loss": 3.6683, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.9052571373913025e-05, + "loss": 3.6642, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.9044201805206234e-05, + "loss": 3.6759, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.9035815857695714e-05, + "loss": 3.6791, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.9027429910185194e-05, + "loss": 3.6758, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019043962674674e-05, + "loss": 3.6679, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.9010658015164154e-05, + "loss": 3.6683, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900228844645736e-05, + "loss": 3.6619, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899390249894684e-05, + "loss": 3.6696, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898551655143632e-05, + "loss": 3.6714, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.89771306039258e-05, + "loss": 3.6559, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896874465641528e-05, + "loss": 3.6658, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.896035870890476e-05, + "loss": 3.6699, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.895197276139424e-05, + "loss": 3.6706, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.894358681388372e-05, + "loss": 3.6647, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893521724517694e-05, + "loss": 3.668, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892683129766642e-05, + "loss": 3.6633, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891846172895963e-05, + "loss": 3.6741, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.891007578144911e-05, + "loss": 3.6696, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890168983393859e-05, + "loss": 3.6799, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889330388642807e-05, + "loss": 3.6591, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888491793891755e-05, + "loss": 3.6671, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887653199140703e-05, + "loss": 3.6743, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868162422700236e-05, + "loss": 3.6696, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859776475189716e-05, + "loss": 3.6644, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851390527679196e-05, + "loss": 3.6711, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843004580168676e-05, + "loss": 3.6702, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883463501146189e-05, + "loss": 3.6867, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882624906395137e-05, + "loss": 3.6622, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.881786311644085e-05, + "loss": 3.6697, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880947716893033e-05, + "loss": 3.6709, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.880109122141981e-05, + "loss": 3.6638, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.879272165271302e-05, + "loss": 3.6629, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.87843357052025e-05, + "loss": 3.6597, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.877594975769198e-05, + "loss": 3.6659, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.876756381018146e-05, + "loss": 3.6591, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759177862670934e-05, + "loss": 3.6681, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8565516471862793, + "eval_runtime": 305.2504, + "eval_samples_per_second": 1250.092, + "eval_steps_per_second": 39.066, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.875080829396415e-05, + "loss": 3.6649, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.874242234645363e-05, + "loss": 3.6553, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873403639894311e-05, + "loss": 3.6659, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872565045143259e-05, + "loss": 3.6733, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871726450392207e-05, + "loss": 3.6809, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870887855641155e-05, + "loss": 3.6632, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870050898770476e-05, + "loss": 3.6672, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869212304019424e-05, + "loss": 3.6572, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868373709268372e-05, + "loss": 3.6596, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.86753511451732e-05, + "loss": 3.6656, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866698157646641e-05, + "loss": 3.664, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865859562895589e-05, + "loss": 3.6562, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.8650226060249104e-05, + "loss": 3.6701, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.8641840112738584e-05, + "loss": 3.6523, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633454165228064e-05, + "loss": 3.6542, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625068217717544e-05, + "loss": 3.6433, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616682270207024e-05, + "loss": 3.6607, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608296322696503e-05, + "loss": 3.6646, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.8599910375185983e-05, + "loss": 3.6527, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.8591524427675463e-05, + "loss": 3.6686, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858313848016494e-05, + "loss": 3.667, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857475253265442e-05, + "loss": 3.6691, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856638296394763e-05, + "loss": 3.6616, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855799701643711e-05, + "loss": 3.6605, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854961106892659e-05, + "loss": 3.6616, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854122512141607e-05, + "loss": 3.669, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853283917390555e-05, + "loss": 3.6513, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852445322639503e-05, + "loss": 3.6635, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851608365768825e-05, + "loss": 3.6484, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850769771017773e-05, + "loss": 3.6563, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849931176266721e-05, + "loss": 3.6643, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849092581515669e-05, + "loss": 3.6661, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.84825562464499e-05, + "loss": 3.6605, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.847417029893938e-05, + "loss": 3.6711, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846578435142886e-05, + "loss": 3.6572, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845739840391834e-05, + "loss": 3.6602, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.844901245640782e-05, + "loss": 3.6651, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.84406265088973e-05, + "loss": 3.6464, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432256940190506e-05, + "loss": 3.6498, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423870992679986e-05, + "loss": 3.6496, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.841548504516947e-05, + "loss": 3.6455, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407099097658946e-05, + "loss": 3.6522, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398713150148426e-05, + "loss": 3.668, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390327202637906e-05, + "loss": 3.652, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838195763393112e-05, + "loss": 3.6527, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.8373571686420595e-05, + "loss": 3.6521, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.8365185738910075e-05, + "loss": 3.6589, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.8356799791399555e-05, + "loss": 3.6444, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.8348413843889035e-05, + "loss": 3.6343, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.8340027896378515e-05, + "loss": 3.6635, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.8331641948867994e-05, + "loss": 3.6581, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832327238016121e-05, + "loss": 3.6699, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831488643265069e-05, + "loss": 3.6494, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830650048514017e-05, + "loss": 3.652, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829811453762965e-05, + "loss": 3.6494, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828972859011913e-05, + "loss": 3.6468, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828135902141234e-05, + "loss": 3.6643, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827297307390182e-05, + "loss": 3.6374, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.82645871263913e-05, + "loss": 3.6765, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825620117888078e-05, + "loss": 3.6544, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824783161017399e-05, + "loss": 3.6322, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823944566266347e-05, + "loss": 3.6609, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823105971515295e-05, + "loss": 3.648, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822267376764243e-05, + "loss": 3.6347, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821428782013191e-05, + "loss": 3.6567, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.8205918251425124e-05, + "loss": 3.6611, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.8197532303914604e-05, + "loss": 3.6431, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.8189146356404084e-05, + "loss": 3.6492, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.8180760408893564e-05, + "loss": 3.6325, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.8172374461383044e-05, + "loss": 3.6461, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816400489267625e-05, + "loss": 3.6518, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815561894516573e-05, + "loss": 3.6424, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814723299765521e-05, + "loss": 3.6559, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813884705014469e-05, + "loss": 3.6434, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81304774814379e-05, + "loss": 3.6683, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812209153392738e-05, + "loss": 3.6461, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811370558641686e-05, + "loss": 3.6553, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810531963890634e-05, + "loss": 3.6481, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809693369139583e-05, + "loss": 3.6442, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808856412268904e-05, + "loss": 3.6546, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.808017817517852e-05, + "loss": 3.6465, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071792227668e-05, + "loss": 3.6526, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806340628015748e-05, + "loss": 3.6552, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805502033264696e-05, + "loss": 3.6408, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804663438513643e-05, + "loss": 3.6318, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803824843762591e-05, + "loss": 3.649, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029878868919126e-05, + "loss": 3.6536, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.80214929214086e-05, + "loss": 3.6394, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801310697389808e-05, + "loss": 3.6501, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004721026387566e-05, + "loss": 3.6392, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799635145768078e-05, + "loss": 3.6428, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.7987965510170255e-05, + "loss": 3.6382, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.7979579562659735e-05, + "loss": 3.6462, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.7971193615149215e-05, + "loss": 3.657, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.7962807667638695e-05, + "loss": 3.6509, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954421720128175e-05, + "loss": 3.6548, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946052151421384e-05, + "loss": 3.642, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937666203910864e-05, + "loss": 3.643, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929280256400344e-05, + "loss": 3.644, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7920894308889824e-05, + "loss": 3.6512, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791252474018303e-05, + "loss": 3.6473, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790413879267252e-05, + "loss": 3.6521, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.7895752845162e-05, + "loss": 3.6463, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788736689765148e-05, + "loss": 3.642, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787899732894469e-05, + "loss": 3.6516, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787061138143417e-05, + "loss": 3.6429, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786222543392365e-05, + "loss": 3.6413, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.785383948641313e-05, + "loss": 3.651, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784545353890261e-05, + "loss": 3.6419, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783708397019582e-05, + "loss": 3.6413, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.78286980226853e-05, + "loss": 3.6408, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782031207517478e-05, + "loss": 3.641, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781192612766426e-05, + "loss": 3.6472, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780354018015374e-05, + "loss": 3.6394, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795170611446954e-05, + "loss": 3.65, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7786784663936433e-05, + "loss": 3.6526, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778398716425913e-05, + "loss": 3.6549, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777001276891539e-05, + "loss": 3.6463, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776162682140487e-05, + "loss": 3.6452, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775325725269808e-05, + "loss": 3.6364, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774487130518756e-05, + "loss": 3.6499, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773648535767704e-05, + "loss": 3.6467, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772809941016652e-05, + "loss": 3.6332, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.7719713462656e-05, + "loss": 3.6426, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771134389394921e-05, + "loss": 3.6442, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770295794643869e-05, + "loss": 3.6492, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769457199892817e-05, + "loss": 3.6396, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768618605141765e-05, + "loss": 3.6415, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767781648271087e-05, + "loss": 3.6384, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766943053520035e-05, + "loss": 3.652, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766104458768983e-05, + "loss": 3.6434, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765265864017931e-05, + "loss": 3.6548, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644289071472516e-05, + "loss": 3.635, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7635903123961996e-05, + "loss": 3.6448, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627517176451476e-05, + "loss": 3.6518, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619131228940956e-05, + "loss": 3.6411, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610745281430436e-05, + "loss": 3.6426, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602375712723645e-05, + "loss": 3.6432, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.7593989765213125e-05, + "loss": 3.6512, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.7585603817702605e-05, + "loss": 3.6579, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757721787019209e-05, + "loss": 3.6445, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.7568831922681565e-05, + "loss": 3.6425, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756046235397478e-05, + "loss": 3.648, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755207640646426e-05, + "loss": 3.6411, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.7543690458953734e-05, + "loss": 3.6415, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.7535304511443214e-05, + "loss": 3.6373, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.7526918563932694e-05, + "loss": 3.6405, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751854899522591e-05, + "loss": 3.6343, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751016304771538e-05, + "loss": 3.6432, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.853645086288452, + "eval_runtime": 303.775, + "eval_samples_per_second": 1256.163, + "eval_steps_per_second": 39.256, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750177710020486e-05, + "loss": 3.6406, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749339115269434e-05, + "loss": 3.6317, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748500520518383e-05, + "loss": 3.6409, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.747661925767331e-05, + "loss": 3.6497, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746823331016279e-05, + "loss": 3.6572, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7459863741456e-05, + "loss": 3.6388, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745147779394548e-05, + "loss": 3.6466, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744309184643496e-05, + "loss": 3.6344, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743470589892444e-05, + "loss": 3.6315, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742631995141392e-05, + "loss": 3.6398, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.741795038270713e-05, + "loss": 3.6453, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.740956443519661e-05, + "loss": 3.6352, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.7401194866489816e-05, + "loss": 3.6438, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7392808918979296e-05, + "loss": 3.6283, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738442297146878e-05, + "loss": 3.6333, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737603702395826e-05, + "loss": 3.6174, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736765107644774e-05, + "loss": 3.6389, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735926512893722e-05, + "loss": 3.6405, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.73508791814267e-05, + "loss": 3.6296, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734249323391618e-05, + "loss": 3.6452, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733412366520939e-05, + "loss": 3.6456, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732573771769887e-05, + "loss": 3.6466, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731735177018835e-05, + "loss": 3.636, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730896582267783e-05, + "loss": 3.6368, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730057987516731e-05, + "loss": 3.6406, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729221030646052e-05, + "loss": 3.6451, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728382435895e-05, + "loss": 3.6281, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727543841143948e-05, + "loss": 3.6385, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726705246392897e-05, + "loss": 3.6314, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725866651641845e-05, + "loss": 3.6306, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250296947711657e-05, + "loss": 3.6395, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7241911000201137e-05, + "loss": 3.6424, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233525052690616e-05, + "loss": 3.6401, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.7225139105180096e-05, + "loss": 3.6451, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7216769536473306e-05, + "loss": 3.6338, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208383588962785e-05, + "loss": 3.6379, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7199997641452265e-05, + "loss": 3.6465, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191611693941745e-05, + "loss": 3.6243, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718322574643122e-05, + "loss": 3.6253, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174839798920705e-05, + "loss": 3.6259, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.716647023021392e-05, + "loss": 3.6186, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.71580842827034e-05, + "loss": 3.6309, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.7149698335192874e-05, + "loss": 3.644, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.7141312387682354e-05, + "loss": 3.6291, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713294281897557e-05, + "loss": 3.6294, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712455687146504e-05, + "loss": 3.6316, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711617092395452e-05, + "loss": 3.6351, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.7107784976444e-05, + "loss": 3.6211, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709939902893348e-05, + "loss": 3.6113, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709102946022669e-05, + "loss": 3.639, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708264351271617e-05, + "loss": 3.6368, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707425756520566e-05, + "loss": 3.6472, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706587161769514e-05, + "loss": 3.6275, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705750204898835e-05, + "loss": 3.6274, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704911610147783e-05, + "loss": 3.6267, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704073015396731e-05, + "loss": 3.6267, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703234420645679e-05, + "loss": 3.6393, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702397463775e-05, + "loss": 3.6118, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701558869023948e-05, + "loss": 3.6553, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700720274272896e-05, + "loss": 3.6331, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699881679521844e-05, + "loss": 3.6123, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699043084770792e-05, + "loss": 3.6356, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.6982061279001126e-05, + "loss": 3.6246, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.6973675331490606e-05, + "loss": 3.613, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696528938398009e-05, + "loss": 3.6345, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695690343646957e-05, + "loss": 3.6375, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694853386776278e-05, + "loss": 3.6189, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694014792025226e-05, + "loss": 3.6327, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693176197274174e-05, + "loss": 3.608, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692337602523122e-05, + "loss": 3.6227, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.69149900777207e-05, + "loss": 3.6244, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.690660413021018e-05, + "loss": 3.6266, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689823456150339e-05, + "loss": 3.6285, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.688984861399287e-05, + "loss": 3.6231, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688146266648235e-05, + "loss": 3.6458, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687307671897183e-05, + "loss": 3.6254, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686469077146131e-05, + "loss": 3.6346, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856321202754526e-05, + "loss": 3.6236, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6847935255244006e-05, + "loss": 3.6224, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839549307733486e-05, + "loss": 3.6339, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831163360222966e-05, + "loss": 3.6249, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.6822793791516175e-05, + "loss": 3.6272, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.6814407844005655e-05, + "loss": 3.6354, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.6806021896495135e-05, + "loss": 3.6218, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.6797635948984615e-05, + "loss": 3.6084, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789266380277824e-05, + "loss": 3.6236, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6780880432767304e-05, + "loss": 3.6319, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772494485256784e-05, + "loss": 3.6145, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764108537746264e-05, + "loss": 3.6299, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675573896903948e-05, + "loss": 3.6215, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674735302152896e-05, + "loss": 3.6159, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673896707401844e-05, + "loss": 3.6156, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673058112650792e-05, + "loss": 3.6226, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.67221951789974e-05, + "loss": 3.6377, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.671382561029061e-05, + "loss": 3.6249, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670543966278009e-05, + "loss": 3.6325, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669705371526957e-05, + "loss": 3.6213, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668866776775905e-05, + "loss": 3.62, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668029819905226e-05, + "loss": 3.6212, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667191225154174e-05, + "loss": 3.6299, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666352630403122e-05, + "loss": 3.6284, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.66551403565207e-05, + "loss": 3.6305, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664675440901018e-05, + "loss": 3.6249, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663836846149966e-05, + "loss": 3.6173, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6629998892792873e-05, + "loss": 3.6299, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662161294528235e-05, + "loss": 3.6213, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613226997771827e-05, + "loss": 3.6176, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604841050261307e-05, + "loss": 3.6257, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596455102750786e-05, + "loss": 3.6216, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588085534044e-05, + "loss": 3.6207, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6579699586533476e-05, + "loss": 3.6172, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.6571313639022955e-05, + "loss": 3.618, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.6562927691512435e-05, + "loss": 3.623, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655454174400192e-05, + "loss": 3.6225, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654617217529513e-05, + "loss": 3.6242, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653778622778461e-05, + "loss": 3.628, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652940028027409e-05, + "loss": 3.6366, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652101433276357e-05, + "loss": 3.6217, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651262838525305e-05, + "loss": 3.6252, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650425881654626e-05, + "loss": 3.6158, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649587286903574e-05, + "loss": 3.6248, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648748692152522e-05, + "loss": 3.6228, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.64791009740147e-05, + "loss": 3.6146, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.647071502650418e-05, + "loss": 3.6136, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.646234545779739e-05, + "loss": 3.626, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6453959510286876e-05, + "loss": 3.6266, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445573562776356e-05, + "loss": 3.6153, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437187615265836e-05, + "loss": 3.6189, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428818046559045e-05, + "loss": 3.6205, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420432099048525e-05, + "loss": 3.6251, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412046151538005e-05, + "loss": 3.6251, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6403660204027485e-05, + "loss": 3.6331, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395290635320694e-05, + "loss": 3.6144, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6386904687810174e-05, + "loss": 3.6233, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.6378518740299654e-05, + "loss": 3.6289, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.6370132792789134e-05, + "loss": 3.6169, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636176322408234e-05, + "loss": 3.6222, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635337727657183e-05, + "loss": 3.6255, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634499132906131e-05, + "loss": 3.6321, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633660538155079e-05, + "loss": 3.6345, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632821943404027e-05, + "loss": 3.623, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631984986533348e-05, + "loss": 3.6216, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631146391782296e-05, + "loss": 3.6278, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630307797031244e-05, + "loss": 3.6171, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629469202280192e-05, + "loss": 3.6189, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628632245409513e-05, + "loss": 3.6186, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627793650658461e-05, + "loss": 3.6151, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.626955055907409e-05, + "loss": 3.6204, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.626116461156357e-05, + "loss": 3.6169, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8520922660827637, + "eval_runtime": 303.1336, + "eval_samples_per_second": 1258.821, + "eval_steps_per_second": 39.339, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625277866405305e-05, + "loss": 3.6197, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.624440909534626e-05, + "loss": 3.6128, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.623602314783574e-05, + "loss": 3.621, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622763720032522e-05, + "loss": 3.625, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.62192512528147e-05, + "loss": 3.6339, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621088168410791e-05, + "loss": 3.6199, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620249573659739e-05, + "loss": 3.6266, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619410978908687e-05, + "loss": 3.6155, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618572384157635e-05, + "loss": 3.6108, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617735427286956e-05, + "loss": 3.615, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616896832535904e-05, + "loss": 3.6288, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616058237784852e-05, + "loss": 3.6104, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615221280914173e-05, + "loss": 3.6261, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614382686163122e-05, + "loss": 3.6054, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.61354409141207e-05, + "loss": 3.6115, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612705496661018e-05, + "loss": 3.5997, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611866901909966e-05, + "loss": 3.6176, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110283071589137e-05, + "loss": 3.6171, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610189712407861e-05, + "loss": 3.613, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609351117656809e-05, + "loss": 3.6163, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608512522905757e-05, + "loss": 3.628, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607675566035078e-05, + "loss": 3.6215, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606836971284026e-05, + "loss": 3.6172, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.605998376532974e-05, + "loss": 3.6134, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.605159781781922e-05, + "loss": 3.624, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043228249112435e-05, + "loss": 3.6172, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6034842301601914e-05, + "loss": 3.6115, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.6026456354091394e-05, + "loss": 3.6163, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.6018070406580874e-05, + "loss": 3.6087, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.6009684459070354e-05, + "loss": 3.6062, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.6001314890363563e-05, + "loss": 3.6211, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.5992928942853043e-05, + "loss": 3.617, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598454299534252e-05, + "loss": 3.6229, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.5976157047832e-05, + "loss": 3.6252, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596778747912521e-05, + "loss": 3.6124, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595940153161469e-05, + "loss": 3.6186, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595101558410417e-05, + "loss": 3.6214, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594262963659365e-05, + "loss": 3.6062, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593426006788687e-05, + "loss": 3.6086, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592587412037635e-05, + "loss": 3.6009, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591748817286583e-05, + "loss": 3.6009, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590910222535531e-05, + "loss": 3.6101, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590071627784479e-05, + "loss": 3.6262, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.5892346709138e-05, + "loss": 3.6089, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588396076162748e-05, + "loss": 3.6057, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587557481411696e-05, + "loss": 3.6149, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586718886660644e-05, + "loss": 3.6102, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585880291909592e-05, + "loss": 3.6036, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850433350389126e-05, + "loss": 3.5917, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842047402878606e-05, + "loss": 3.6161, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583366145536809e-05, + "loss": 3.6191, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582527550785757e-05, + "loss": 3.622, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581690593915078e-05, + "loss": 3.6068, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580851999164026e-05, + "loss": 3.6068, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.580013404412974e-05, + "loss": 3.6051, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.579174809661922e-05, + "loss": 3.6046, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.57833621491087e-05, + "loss": 3.62, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.577499258040191e-05, + "loss": 3.5943, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.576660663289139e-05, + "loss": 3.6289, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.575822068538087e-05, + "loss": 3.6122, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574983473787035e-05, + "loss": 3.5948, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574146516916356e-05, + "loss": 3.6126, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733079221653046e-05, + "loss": 3.6037, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5724693274142526e-05, + "loss": 3.5962, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716307326632006e-05, + "loss": 3.6089, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.5707937757925215e-05, + "loss": 3.6171, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.5699551810414695e-05, + "loss": 3.5995, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.5691165862904175e-05, + "loss": 3.6111, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.5682779915393655e-05, + "loss": 3.5884, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.5674410346686864e-05, + "loss": 3.6047, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.5666024399176344e-05, + "loss": 3.6036, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657638451665824e-05, + "loss": 3.6066, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649252504155304e-05, + "loss": 3.6034, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640866556644784e-05, + "loss": 3.6058, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.5632480609134264e-05, + "loss": 3.6219, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562411104042748e-05, + "loss": 3.6079, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561572509291696e-05, + "loss": 3.6132, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560733914540644e-05, + "loss": 3.6052, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559895319789591e-05, + "loss": 3.6011, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559058362918913e-05, + "loss": 3.6147, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558219768167861e-05, + "loss": 3.6047, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557381173416809e-05, + "loss": 3.6051, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556542578665756e-05, + "loss": 3.6154, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555705621795078e-05, + "loss": 3.6036, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554867027044026e-05, + "loss": 3.5858, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554028432292974e-05, + "loss": 3.6061, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553189837541922e-05, + "loss": 3.6094, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.5523528806712434e-05, + "loss": 3.5973, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.5515142859201914e-05, + "loss": 3.6064, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550675691169139e-05, + "loss": 3.603, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549837096418087e-05, + "loss": 3.5953, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549000139547408e-05, + "loss": 3.5999, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548161544796356e-05, + "loss": 3.6004, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473229500453036e-05, + "loss": 3.6142, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464843552942516e-05, + "loss": 3.6082, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.545647398423573e-05, + "loss": 3.6149, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.544808803672521e-05, + "loss": 3.5987, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439702089214685e-05, + "loss": 3.5991, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.543131614170417e-05, + "loss": 3.6045, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.542294657299739e-05, + "loss": 3.6086, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.541456062548686e-05, + "loss": 3.6077, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.540617467797634e-05, + "loss": 3.6091, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.539778873046582e-05, + "loss": 3.6042, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389419161759036e-05, + "loss": 3.5971, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538103321424851e-05, + "loss": 3.6099, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537264726673799e-05, + "loss": 3.6007, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536426131922747e-05, + "loss": 3.6034, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535587537171695e-05, + "loss": 3.6027, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534750580301016e-05, + "loss": 3.6013, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533911985549964e-05, + "loss": 3.6006, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.5330733907989125e-05, + "loss": 3.5969, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.5322347960478605e-05, + "loss": 3.5972, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.5313978391771814e-05, + "loss": 3.6067, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.5305592444261294e-05, + "loss": 3.6041, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.5297206496750774e-05, + "loss": 3.6002, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5288820549240254e-05, + "loss": 3.6116, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280434601729734e-05, + "loss": 3.6178, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527206503302294e-05, + "loss": 3.602, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526367908551242e-05, + "loss": 3.6014, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.52552931380019e-05, + "loss": 3.5994, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524690719049138e-05, + "loss": 3.6043, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523853762178459e-05, + "loss": 3.6008, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523015167427408e-05, + "loss": 3.5973, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522176572676356e-05, + "loss": 3.5946, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521337977925304e-05, + "loss": 3.6062, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.520501021054625e-05, + "loss": 3.5995, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519662426303573e-05, + "loss": 3.5988, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518823831552521e-05, + "loss": 3.6021, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517985236801469e-05, + "loss": 3.6025, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517146642050417e-05, + "loss": 3.5988, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516309685179738e-05, + "loss": 3.6076, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515471090428686e-05, + "loss": 3.611, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146324956776337e-05, + "loss": 3.5983, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5137939009265817e-05, + "loss": 3.6035, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129553061755297e-05, + "loss": 3.6083, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512118349304851e-05, + "loss": 3.5991, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511279754553799e-05, + "loss": 3.5996, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510441159802747e-05, + "loss": 3.6051, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509602565051695e-05, + "loss": 3.6142, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508765608181016e-05, + "loss": 3.613, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507927013429964e-05, + "loss": 3.6042, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507088418678912e-05, + "loss": 3.6005, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.50624982392786e-05, + "loss": 3.6089, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505412867057181e-05, + "loss": 3.6021, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504574272306129e-05, + "loss": 3.5956, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503735677555077e-05, + "loss": 3.6019, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502897082804025e-05, + "loss": 3.5919, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020601259333466e-05, + "loss": 3.6004, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012215311822946e-05, + "loss": 3.596, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.851813793182373, + "eval_runtime": 303.3225, + "eval_samples_per_second": 1258.037, + "eval_steps_per_second": 39.315, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003829364312426e-05, + "loss": 3.6082, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995443416801906e-05, + "loss": 3.5887, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987057469291386e-05, + "loss": 3.5997, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978671521780866e-05, + "loss": 3.6126, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970285574270346e-05, + "loss": 3.6098, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4961916005563555e-05, + "loss": 3.6071, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953530058053035e-05, + "loss": 3.6063, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945144110542515e-05, + "loss": 3.5937, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.493675816303199e-05, + "loss": 3.589, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928388594325204e-05, + "loss": 3.6018, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920002646814684e-05, + "loss": 3.6001, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4911616699304164e-05, + "loss": 3.5956, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490324713059738e-05, + "loss": 3.6064, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489486118308686e-05, + "loss": 3.5855, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488647523557634e-05, + "loss": 3.5925, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487808928806582e-05, + "loss": 3.5777, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486970334055529e-05, + "loss": 3.6003, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486131739304477e-05, + "loss": 3.5953, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485293144553425e-05, + "loss": 3.595, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484454549802373e-05, + "loss": 3.5996, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483617592931694e-05, + "loss": 3.607, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.6024, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.597, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481101808678539e-05, + "loss": 3.5947, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48026485180786e-05, + "loss": 3.6083, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479426257056808e-05, + "loss": 3.5991, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478587662305756e-05, + "loss": 3.5901, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.477749067554704e-05, + "loss": 3.5982, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769121106840246e-05, + "loss": 3.5862, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.5939, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.6033, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743963264308686e-05, + "loss": 3.5963, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735577316798166e-05, + "loss": 3.6009, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.6054, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.5964, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471043585307034e-05, + "loss": 3.6003, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470204990555982e-05, + "loss": 3.6026, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469368033685303e-05, + "loss": 3.5852, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468529438934251e-05, + "loss": 3.5902, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467690844183199e-05, + "loss": 3.5839, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466852249432147e-05, + "loss": 3.5838, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466013654681095e-05, + "loss": 3.5904, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465176697810416e-05, + "loss": 3.6048, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464338103059364e-05, + "loss": 3.5881, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463499508308312e-05, + "loss": 3.5908, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.46266091355726e-05, + "loss": 3.5931, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461823956686581e-05, + "loss": 3.5947, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.4609853619355296e-05, + "loss": 3.5841, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.4601467671844776e-05, + "loss": 3.5721, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593081724334256e-05, + "loss": 3.5913, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584695776823735e-05, + "loss": 3.6071, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.4576326208116945e-05, + "loss": 3.604, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4567940260606425e-05, + "loss": 3.5847, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559554313095904e-05, + "loss": 3.5882, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551168365585384e-05, + "loss": 3.5882, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4542798796878594e-05, + "loss": 3.5804, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534412849368073e-05, + "loss": 3.608, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526026901857553e-05, + "loss": 3.5744, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.4517640954347033e-05, + "loss": 3.6113, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450925500683651e-05, + "loss": 3.5929, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450088543812973e-05, + "loss": 3.5794, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449249949061921e-05, + "loss": 3.5928, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448411354310869e-05, + "loss": 3.5864, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447572759559817e-05, + "loss": 3.5737, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446735802689138e-05, + "loss": 3.5908, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445897207938086e-05, + "loss": 3.5995, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445058613187034e-05, + "loss": 3.5825, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444220018435982e-05, + "loss": 3.5916, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.443383061565303e-05, + "loss": 3.5671, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442544466814251e-05, + "loss": 3.5853, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441705872063199e-05, + "loss": 3.5842, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440867277312147e-05, + "loss": 3.5895, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440030320441468e-05, + "loss": 3.5843, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439191725690416e-05, + "loss": 3.5889, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438353130939364e-05, + "loss": 3.6037, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437514536188312e-05, + "loss": 3.5902, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436677579317633e-05, + "loss": 3.5929, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435838984566581e-05, + "loss": 3.5886, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435000389815529e-05, + "loss": 3.5825, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434161795064477e-05, + "loss": 3.5961, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433324838193798e-05, + "loss": 3.5841, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432486243442746e-05, + "loss": 3.5929, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431647648691694e-05, + "loss": 3.5915, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430809053940642e-05, + "loss": 3.5881, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.42997045918959e-05, + "loss": 3.5662, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.4291335023189117e-05, + "loss": 3.5889, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4282949075678596e-05, + "loss": 3.5871, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427456312816807e-05, + "loss": 3.5787, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426617718065755e-05, + "loss": 3.5881, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4257807611950765e-05, + "loss": 3.5822, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249421664440245e-05, + "loss": 3.5785, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424103571692972e-05, + "loss": 3.5783, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.42326497694192e-05, + "loss": 3.5856, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.4224280200712414e-05, + "loss": 3.5901, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.4215894253201894e-05, + "loss": 3.5918, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.4207508305691374e-05, + "loss": 3.5948, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.4199122358180854e-05, + "loss": 3.5831, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419075278947407e-05, + "loss": 3.58, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418236684196354e-05, + "loss": 3.5846, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417398089445302e-05, + "loss": 3.5907, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.41655949469425e-05, + "loss": 3.5864, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.415722537823572e-05, + "loss": 3.5917, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414883943072519e-05, + "loss": 3.586, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.414045348321467e-05, + "loss": 3.5796, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413206753570415e-05, + "loss": 3.5911, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412368158819363e-05, + "loss": 3.5844, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411531201948685e-05, + "loss": 3.5839, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410692607197633e-05, + "loss": 3.586, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409854012446581e-05, + "loss": 3.5843, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409015417695529e-05, + "loss": 3.5802, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.40817846082485e-05, + "loss": 3.5811, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407339866073798e-05, + "loss": 3.5755, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406501271322746e-05, + "loss": 3.5881, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405662676571694e-05, + "loss": 3.5892, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.4048257197010146e-05, + "loss": 3.5789, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4039871249499626e-05, + "loss": 3.593, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031485301989106e-05, + "loss": 3.5995, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023099354478586e-05, + "loss": 3.5839, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.4014713406968066e-05, + "loss": 3.5841, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400634383826128e-05, + "loss": 3.5842, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399795789075076e-05, + "loss": 3.5855, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398957194324024e-05, + "loss": 3.5836, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398118599572972e-05, + "loss": 3.5802, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397281642702293e-05, + "loss": 3.5769, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396443047951241e-05, + "loss": 3.588, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.395604453200189e-05, + "loss": 3.5831, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394765858449137e-05, + "loss": 3.5855, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.393928901578458e-05, + "loss": 3.5819, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393090306827406e-05, + "loss": 3.585, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.392251712076354e-05, + "loss": 3.5778, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391413117325302e-05, + "loss": 3.5945, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.39057452257425e-05, + "loss": 3.5906, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897375657035715e-05, + "loss": 3.5809, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888989709525195e-05, + "loss": 3.58, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.3880603762014675e-05, + "loss": 3.5915, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.3872217814504155e-05, + "loss": 3.5793, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.3863831866993635e-05, + "loss": 3.5852, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.3855462298286844e-05, + "loss": 3.5879, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.3847076350776324e-05, + "loss": 3.5957, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.3838690403265804e-05, + "loss": 3.5911, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.3830304455755284e-05, + "loss": 3.5932, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382193488704849e-05, + "loss": 3.5802, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381354893953797e-05, + "loss": 3.5935, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380516299202745e-05, + "loss": 3.5811, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379677704451693e-05, + "loss": 3.576, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378840747581015e-05, + "loss": 3.5843, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378002152829963e-05, + "loss": 3.5729, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377163558078911e-05, + "loss": 3.5853, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376324963327859e-05, + "loss": 3.5764, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.851093053817749, + "eval_runtime": 304.0549, + "eval_samples_per_second": 1255.007, + "eval_steps_per_second": 39.22, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.375486368576807e-05, + "loss": 3.5848, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.374649411706128e-05, + "loss": 3.575, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.373810816955076e-05, + "loss": 3.5785, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.372972222204024e-05, + "loss": 3.596, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.372133627452972e-05, + "loss": 3.5914, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371296670582293e-05, + "loss": 3.5949, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370458075831241e-05, + "loss": 3.5832, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369619481080189e-05, + "loss": 3.5767, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.3687808863291373e-05, + "loss": 3.5684, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367943929458458e-05, + "loss": 3.5845, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367105334707406e-05, + "loss": 3.5835, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366266739956354e-05, + "loss": 3.5801, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365429783085675e-05, + "loss": 3.593, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364591188334623e-05, + "loss": 3.5644, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363752593583571e-05, + "loss": 3.5732, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362913998832519e-05, + "loss": 3.5677, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362075404081467e-05, + "loss": 3.5759, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.3612368093304145e-05, + "loss": 3.579, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.3603982145793625e-05, + "loss": 3.5755, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359559619828311e-05, + "loss": 3.585, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358721025077259e-05, + "loss": 3.588, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.35788406820658e-05, + "loss": 3.5864, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.357045473455528e-05, + "loss": 3.5813, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.356206878704476e-05, + "loss": 3.5766, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355368283953424e-05, + "loss": 3.5922, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354531327082745e-05, + "loss": 3.5776, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353692732331693e-05, + "loss": 3.5757, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352854137580641e-05, + "loss": 3.5825, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.352015542829589e-05, + "loss": 3.569, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351176948078537e-05, + "loss": 3.5755, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350339991207858e-05, + "loss": 3.5793, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3495013964568065e-05, + "loss": 3.5801, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486628017057545e-05, + "loss": 3.5849, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478242069547025e-05, + "loss": 3.5892, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469872500840234e-05, + "loss": 3.577, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.3461486553329714e-05, + "loss": 3.5818, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.3453100605819194e-05, + "loss": 3.5881, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.3444714658308674e-05, + "loss": 3.5703, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343634508960188e-05, + "loss": 3.5748, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342795914209136e-05, + "loss": 3.561, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341957319458084e-05, + "loss": 3.5696, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.341118724707032e-05, + "loss": 3.571, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.34028012995598e-05, + "loss": 3.5932, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339443173085302e-05, + "loss": 3.5696, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.33860457833425e-05, + "loss": 3.5721, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337765983583198e-05, + "loss": 3.5766, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336927388832146e-05, + "loss": 3.5777, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336088794081094e-05, + "loss": 3.5685, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335251837210415e-05, + "loss": 3.5567, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334413242459363e-05, + "loss": 3.5766, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333574647708311e-05, + "loss": 3.5842, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332736052957259e-05, + "loss": 3.5827, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.3318990960865796e-05, + "loss": 3.5717, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.3310605013355276e-05, + "loss": 3.567, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.3302219065844756e-05, + "loss": 3.5768, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.3293833118334236e-05, + "loss": 3.562, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285447170823716e-05, + "loss": 3.59, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.327707760211693e-05, + "loss": 3.56, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326869165460641e-05, + "loss": 3.5904, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326030570709589e-05, + "loss": 3.5772, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325191975958537e-05, + "loss": 3.5598, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324355019087858e-05, + "loss": 3.575, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323516424336806e-05, + "loss": 3.5731, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322677829585754e-05, + "loss": 3.5594, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321839234834702e-05, + "loss": 3.5662, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321002277964023e-05, + "loss": 3.587, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320163683212971e-05, + "loss": 3.5671, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319325088461919e-05, + "loss": 3.5694, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318486493710867e-05, + "loss": 3.5547, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.3176495368401886e-05, + "loss": 3.5695, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168109420891366e-05, + "loss": 3.5629, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3159723473380846e-05, + "loss": 3.5718, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3151337525870326e-05, + "loss": 3.5668, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3142967957163535e-05, + "loss": 3.5725, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134582009653015e-05, + "loss": 3.5814, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.3126196062142495e-05, + "loss": 3.5705, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.3117810114631975e-05, + "loss": 3.5744, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109440545925184e-05, + "loss": 3.5744, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101054598414664e-05, + "loss": 3.5686, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.3092668650904144e-05, + "loss": 3.5761, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084282703393624e-05, + "loss": 3.5664, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307591313468684e-05, + "loss": 3.5728, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306752718717632e-05, + "loss": 3.5781, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.30591412396658e-05, + "loss": 3.5688, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305075529215528e-05, + "loss": 3.5526, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304238572344849e-05, + "loss": 3.5696, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303399977593797e-05, + "loss": 3.567, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302561382842745e-05, + "loss": 3.5675, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301722788091693e-05, + "loss": 3.5661, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.30088419334064e-05, + "loss": 3.573, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300045598589588e-05, + "loss": 3.5559, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.29920864171891e-05, + "loss": 3.562, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298370046967858e-05, + "loss": 3.5654, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297531452216806e-05, + "loss": 3.578, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296692857465754e-05, + "loss": 3.5693, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295855900595075e-05, + "loss": 3.584, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.2950173058440226e-05, + "loss": 3.5602, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.2941787110929706e-05, + "loss": 3.5676, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.2933401163419186e-05, + "loss": 3.5686, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925015215908666e-05, + "loss": 3.5739, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.2916645647201875e-05, + "loss": 3.569, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.2908259699691355e-05, + "loss": 3.5758, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.2899873752180835e-05, + "loss": 3.5691, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891487804670315e-05, + "loss": 3.563, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288311823596353e-05, + "loss": 3.5768, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287473228845301e-05, + "loss": 3.5622, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286634634094249e-05, + "loss": 3.5662, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285796039343197e-05, + "loss": 3.5709, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284959082472518e-05, + "loss": 3.5663, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284120487721466e-05, + "loss": 3.563, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283281892970414e-05, + "loss": 3.5678, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282443298219362e-05, + "loss": 3.5587, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281606341348683e-05, + "loss": 3.5707, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280767746597631e-05, + "loss": 3.5714, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.279929151846579e-05, + "loss": 3.5623, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279090557095527e-05, + "loss": 3.5774, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.278251962344475e-05, + "loss": 3.5822, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774150054737965e-05, + "loss": 3.568, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765764107227445e-05, + "loss": 3.568, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757378159716925e-05, + "loss": 3.5651, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748992212206404e-05, + "loss": 3.5669, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2740622643499614e-05, + "loss": 3.564, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732236695989094e-05, + "loss": 3.5653, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2723850748478573e-05, + "loss": 3.5593, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715464800968053e-05, + "loss": 3.5716, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270709523226126e-05, + "loss": 3.5695, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269870928475074e-05, + "loss": 3.5646, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269032333724022e-05, + "loss": 3.5648, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.26819373897297e-05, + "loss": 3.5657, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267356782102292e-05, + "loss": 3.5603, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.26651818735124e-05, + "loss": 3.5768, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265679592600188e-05, + "loss": 3.576, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264840997849136e-05, + "loss": 3.5678, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264004040978457e-05, + "loss": 3.562, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263165446227405e-05, + "loss": 3.5724, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262326851476353e-05, + "loss": 3.5653, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261488256725301e-05, + "loss": 3.5677, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606512998546216e-05, + "loss": 3.5688, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2598127051035696e-05, + "loss": 3.5844, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2589741103525176e-05, + "loss": 3.5684, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581355156014656e-05, + "loss": 3.5753, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257298558730787e-05, + "loss": 3.5651, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256459963979735e-05, + "loss": 3.5768, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255621369228683e-05, + "loss": 3.564, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254782774477631e-05, + "loss": 3.5606, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253945817606952e-05, + "loss": 3.5687, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.2531072228559e-05, + "loss": 3.5561, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252268628104848e-05, + "loss": 3.5697, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251430033353796e-05, + "loss": 3.5594, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8524858951568604, + "eval_runtime": 306.0591, + "eval_samples_per_second": 1246.789, + "eval_steps_per_second": 38.963, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250593076483117e-05, + "loss": 3.5618, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249754481732065e-05, + "loss": 3.561, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248915886981013e-05, + "loss": 3.5597, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248077292229961e-05, + "loss": 3.5795, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472403353592826e-05, + "loss": 3.5701, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2464017406082306e-05, + "loss": 3.5795, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455631458571786e-05, + "loss": 3.5641, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2447245511061265e-05, + "loss": 3.5595, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2438875942354475e-05, + "loss": 3.5564, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2430489994843955e-05, + "loss": 3.5679, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2422104047333434e-05, + "loss": 3.5634, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2413718099822914e-05, + "loss": 3.5638, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405348531116124e-05, + "loss": 3.5776, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2396962583605603e-05, + "loss": 3.5501, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388576636095083e-05, + "loss": 3.5537, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.238019068858456e-05, + "loss": 3.5539, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237180474107404e-05, + "loss": 3.5576, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236343517236726e-05, + "loss": 3.5646, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235504922485674e-05, + "loss": 3.5607, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234666327734622e-05, + "loss": 3.5644, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.23382773298357e-05, + "loss": 3.5721, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232990776112891e-05, + "loss": 3.5651, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232152181361839e-05, + "loss": 3.5678, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231313586610787e-05, + "loss": 3.5595, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230474991859735e-05, + "loss": 3.5773, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229638034989056e-05, + "loss": 3.5613, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228799440238004e-05, + "loss": 3.5617, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227960845486952e-05, + "loss": 3.5593, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271222507359e-05, + "loss": 3.5548, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226285293865221e-05, + "loss": 3.56, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225446699114169e-05, + "loss": 3.5612, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224608104363117e-05, + "loss": 3.5647, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223769509612065e-05, + "loss": 3.5698, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.222932552741386e-05, + "loss": 3.5727, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.222093957990334e-05, + "loss": 3.5615, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221255363239282e-05, + "loss": 3.5675, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.22041676848823e-05, + "loss": 3.5689, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219579811617551e-05, + "loss": 3.5541, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.218741216866499e-05, + "loss": 3.5585, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217902622115447e-05, + "loss": 3.5436, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217064027364395e-05, + "loss": 3.5556, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216225432613343e-05, + "loss": 3.5549, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.2153884757426647e-05, + "loss": 3.5729, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.2145498809916126e-05, + "loss": 3.5534, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.2137112862405606e-05, + "loss": 3.5543, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212872691489508e-05, + "loss": 3.5636, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.2120357346188295e-05, + "loss": 3.5604, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.2111971398677775e-05, + "loss": 3.5563, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210358545116725e-05, + "loss": 3.5358, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209519950365673e-05, + "loss": 3.5595, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2086829934949944e-05, + "loss": 3.568, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.2078443987439424e-05, + "loss": 3.5679, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2070058039928904e-05, + "loss": 3.5548, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061672092418384e-05, + "loss": 3.5492, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.20533025237116e-05, + "loss": 3.5619, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204491657620108e-05, + "loss": 3.5487, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203653062869055e-05, + "loss": 3.5717, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202814468118003e-05, + "loss": 3.544, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201977511247325e-05, + "loss": 3.5764, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201138916496272e-05, + "loss": 3.5623, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.20030032174522e-05, + "loss": 3.5425, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199461726994168e-05, + "loss": 3.5551, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.19862477012349e-05, + "loss": 3.5617, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197786175372438e-05, + "loss": 3.5415, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196947580621386e-05, + "loss": 3.5466, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196108985870334e-05, + "loss": 3.5718, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195270391119282e-05, + "loss": 3.5546, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194433434248603e-05, + "loss": 3.5527, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193594839497551e-05, + "loss": 3.5358, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192756244746499e-05, + "loss": 3.5534, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191917649995447e-05, + "loss": 3.5461, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1910806931247676e-05, + "loss": 3.5592, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902420983737156e-05, + "loss": 3.5486, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1894035036226636e-05, + "loss": 3.5593, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1885649088716116e-05, + "loss": 3.564, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187727952000933e-05, + "loss": 3.5593, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186889357249881e-05, + "loss": 3.557, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186050762498829e-05, + "loss": 3.5541, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185212167747777e-05, + "loss": 3.5571, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184375210877098e-05, + "loss": 3.5588, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183536616126046e-05, + "loss": 3.5527, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182698021374994e-05, + "loss": 3.5576, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181859426623942e-05, + "loss": 3.558, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181022469753263e-05, + "loss": 3.5539, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180183875002211e-05, + "loss": 3.5377, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179345280251159e-05, + "loss": 3.5532, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178506685500107e-05, + "loss": 3.551, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.1776697286294285e-05, + "loss": 3.5515, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.1768311338783765e-05, + "loss": 3.5529, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.1759925391273245e-05, + "loss": 3.5562, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.1751539443762725e-05, + "loss": 3.5433, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.1743169875055934e-05, + "loss": 3.5442, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.1734783927545414e-05, + "loss": 3.5467, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.1726397980034894e-05, + "loss": 3.5617, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1718012032524374e-05, + "loss": 3.5537, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170964246381758e-05, + "loss": 3.5651, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.170125651630706e-05, + "loss": 3.5494, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.169287056879654e-05, + "loss": 3.5525, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.168448462128602e-05, + "loss": 3.5481, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.16760986737755e-05, + "loss": 3.5593, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.166772910506872e-05, + "loss": 3.5518, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.16593431575582e-05, + "loss": 3.5616, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165095721004768e-05, + "loss": 3.5536, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164257126253716e-05, + "loss": 3.5466, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163420169383037e-05, + "loss": 3.565, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162581574631985e-05, + "loss": 3.5436, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161742979880933e-05, + "loss": 3.5497, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160904385129881e-05, + "loss": 3.5577, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160067428259202e-05, + "loss": 3.5476, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.15922883350815e-05, + "loss": 3.5491, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158390238757098e-05, + "loss": 3.5512, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157551644006046e-05, + "loss": 3.5429, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156714687135367e-05, + "loss": 3.5581, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155876092384315e-05, + "loss": 3.55, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155037497633263e-05, + "loss": 3.551, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154198902882211e-05, + "loss": 3.5623, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153360308131159e-05, + "loss": 3.5642, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.15252335126048e-05, + "loss": 3.5555, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151684756509428e-05, + "loss": 3.5537, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150846161758376e-05, + "loss": 3.5489, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.150007567007324e-05, + "loss": 3.5522, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.149170610136645e-05, + "loss": 3.5454, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148332015385593e-05, + "loss": 3.5526, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147493420634541e-05, + "loss": 3.541, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146654825883489e-05, + "loss": 3.5586, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1458178690128106e-05, + "loss": 3.5496, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449792742617586e-05, + "loss": 3.5525, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441406795107066e-05, + "loss": 3.5509, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1433020847596546e-05, + "loss": 3.5478, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424651278889755e-05, + "loss": 3.5454, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1416265331379235e-05, + "loss": 3.5622, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1407879383868715e-05, + "loss": 3.5593, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.1399493436358195e-05, + "loss": 3.5556, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.1391123867651404e-05, + "loss": 3.5449, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.1382737920140884e-05, + "loss": 3.5538, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.1374351972630364e-05, + "loss": 3.5526, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1365966025119844e-05, + "loss": 3.5547, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135759645641306e-05, + "loss": 3.5561, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134921050890254e-05, + "loss": 3.5659, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134082456139202e-05, + "loss": 3.5527, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.13324386138815e-05, + "loss": 3.5622, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132406904517471e-05, + "loss": 3.5513, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131568309766419e-05, + "loss": 3.5569, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130729715015367e-05, + "loss": 3.5456, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129891120264315e-05, + "loss": 3.5474, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129054163393636e-05, + "loss": 3.5562, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128215568642584e-05, + "loss": 3.5394, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127376973891532e-05, + "loss": 3.5541, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.12653837914048e-05, + "loss": 3.5453, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8519372940063477, + "eval_runtime": 307.488, + "eval_samples_per_second": 1240.995, + "eval_steps_per_second": 38.782, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.1257014222698014e-05, + "loss": 3.552, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1248628275187494e-05, + "loss": 3.5475, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240242327676974e-05, + "loss": 3.5454, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1231856380166453e-05, + "loss": 3.5621, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122348681145966e-05, + "loss": 3.5576, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121510086394914e-05, + "loss": 3.5648, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120671491643862e-05, + "loss": 3.5469, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.1198328968928096e-05, + "loss": 3.5466, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.1189943021417576e-05, + "loss": 3.539, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118157345271079e-05, + "loss": 3.5553, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117318750520027e-05, + "loss": 3.5482, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116480155768975e-05, + "loss": 3.5497, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115641561017923e-05, + "loss": 3.5524, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114804604147245e-05, + "loss": 3.5401, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113966009396193e-05, + "loss": 3.5432, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.11312741464514e-05, + "loss": 3.5395, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112288819894088e-05, + "loss": 3.5352, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111450225143036e-05, + "loss": 3.5468, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110611630391984e-05, + "loss": 3.549, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109773035640932e-05, + "loss": 3.5463, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.10893444088988e-05, + "loss": 3.5601, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108097484019201e-05, + "loss": 3.5495, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107258889268149e-05, + "loss": 3.5496, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.1064202945170976e-05, + "loss": 3.5481, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1055816997660456e-05, + "loss": 3.5587, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047447428953665e-05, + "loss": 3.542, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.1039061481443145e-05, + "loss": 3.5487, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1030675533932625e-05, + "loss": 3.5413, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1022289586422105e-05, + "loss": 3.5434, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1013920017715314e-05, + "loss": 3.5455, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005534070204794e-05, + "loss": 3.5427, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997148122694274e-05, + "loss": 3.5538, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0988762175183754e-05, + "loss": 3.5547, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098039260647696e-05, + "loss": 3.5517, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097200665896644e-05, + "loss": 3.5497, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096362071145593e-05, + "loss": 3.5515, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095523476394541e-05, + "loss": 3.5539, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094684881643489e-05, + "loss": 3.5365, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.09384792477281e-05, + "loss": 3.5455, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093009330021758e-05, + "loss": 3.5292, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092170735270706e-05, + "loss": 3.54, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091332140519654e-05, + "loss": 3.5372, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090495183648975e-05, + "loss": 3.5602, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089656588897923e-05, + "loss": 3.5408, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088817994146871e-05, + "loss": 3.5375, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087979399395819e-05, + "loss": 3.5465, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871424425251397e-05, + "loss": 3.5481, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0863038477740877e-05, + "loss": 3.5392, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085465253023036e-05, + "loss": 3.5235, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084626658271984e-05, + "loss": 3.54, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083788063520932e-05, + "loss": 3.5537, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082951106650253e-05, + "loss": 3.5526, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082112511899201e-05, + "loss": 3.5424, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081273917148149e-05, + "loss": 3.536, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080435322397097e-05, + "loss": 3.5475, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079598365526418e-05, + "loss": 3.5292, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078759770775366e-05, + "loss": 3.5567, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077921176024314e-05, + "loss": 3.527, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077082581273262e-05, + "loss": 3.5574, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076245624402583e-05, + "loss": 3.5523, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075407029651532e-05, + "loss": 3.5286, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.07456843490048e-05, + "loss": 3.542, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073729840149428e-05, + "loss": 3.5462, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0728928832787486e-05, + "loss": 3.5238, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720542885276966e-05, + "loss": 3.5323, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0712156937766446e-05, + "loss": 3.5563, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0703770990255926e-05, + "loss": 3.54, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0695401421549135e-05, + "loss": 3.537, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0687015474038615e-05, + "loss": 3.5278, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.0678629526528095e-05, + "loss": 3.5395, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.0670243579017575e-05, + "loss": 3.5291, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.0661874010310784e-05, + "loss": 3.5469, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065348806280027e-05, + "loss": 3.5327, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064510211528975e-05, + "loss": 3.5446, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063671616777923e-05, + "loss": 3.5466, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062834659907244e-05, + "loss": 3.5438, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061996065156192e-05, + "loss": 3.54, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.06115747040514e-05, + "loss": 3.5402, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060318875654088e-05, + "loss": 3.5439, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059481918783409e-05, + "loss": 3.543, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058643324032357e-05, + "loss": 3.5389, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.057804729281305e-05, + "loss": 3.5407, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056966134530253e-05, + "loss": 3.5432, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056129177659574e-05, + "loss": 3.5403, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0552905829085224e-05, + "loss": 3.524, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544519881574704e-05, + "loss": 3.5351, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053613393406418e-05, + "loss": 3.5388, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052776436535739e-05, + "loss": 3.538, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051937841784687e-05, + "loss": 3.5407, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510992470336353e-05, + "loss": 3.5381, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502606522825826e-05, + "loss": 3.5321, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494236954119042e-05, + "loss": 3.527, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0485851006608522e-05, + "loss": 3.5332, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477465059098002e-05, + "loss": 3.5445, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.046907911158748e-05, + "loss": 3.5421, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460709542880695e-05, + "loss": 3.5486, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452323595370175e-05, + "loss": 3.5365, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.044393764785965e-05, + "loss": 3.5359, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043555170034913e-05, + "loss": 3.5334, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.0427182131642347e-05, + "loss": 3.5463, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.0418796184131827e-05, + "loss": 3.5344, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.04104102366213e-05, + "loss": 3.5481, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040202428911078e-05, + "loss": 3.5363, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393654720403996e-05, + "loss": 3.5293, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385268772893476e-05, + "loss": 3.5502, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376882825382952e-05, + "loss": 3.5331, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368496877872432e-05, + "loss": 3.5332, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0360110930361912e-05, + "loss": 3.5412, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035174136165512e-05, + "loss": 3.5395, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.03433554141446e-05, + "loss": 3.5316, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334969466634085e-05, + "loss": 3.5363, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326583519123565e-05, + "loss": 3.53, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318213950416774e-05, + "loss": 3.5395, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309828002906254e-05, + "loss": 3.5382, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301442055395734e-05, + "loss": 3.5367, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293056107885214e-05, + "loss": 3.5419, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284686539178426e-05, + "loss": 3.5556, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276300591667906e-05, + "loss": 3.5409, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267914644157386e-05, + "loss": 3.5386, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259528696646866e-05, + "loss": 3.5335, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251159127940075e-05, + "loss": 3.5349, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242773180429555e-05, + "loss": 3.5331, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023438723291904e-05, + "loss": 3.5354, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022600128540852e-05, + "loss": 3.5295, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217631716701727e-05, + "loss": 3.541, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209245769191207e-05, + "loss": 3.5366, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200859821680687e-05, + "loss": 3.5377, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192473874170167e-05, + "loss": 3.533, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018410430546338e-05, + "loss": 3.5349, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017571835795286e-05, + "loss": 3.528, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016733241044234e-05, + "loss": 3.5462, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.015894646293182e-05, + "loss": 3.5489, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015057689422503e-05, + "loss": 3.5423, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014219094671451e-05, + "loss": 3.5275, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133804999203992e-05, + "loss": 3.5347, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0125419051693472e-05, + "loss": 3.5406, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011704948298668e-05, + "loss": 3.5377, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010866353547616e-05, + "loss": 3.5395, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010027758796564e-05, + "loss": 3.5491, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.009189164045512e-05, + "loss": 3.5357, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083522071748333e-05, + "loss": 3.55, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075136124237813e-05, + "loss": 3.5345, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066750176727293e-05, + "loss": 3.5436, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058364229216773e-05, + "loss": 3.536, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049994660509982e-05, + "loss": 3.5273, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041625091803195e-05, + "loss": 3.5422, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033239144292675e-05, + "loss": 3.5276, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024853196782155e-05, + "loss": 3.5343, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016467249271635e-05, + "loss": 3.5302, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008081301761115e-05, + "loss": 3.5375, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8524911403656006, + "eval_runtime": 305.1948, + "eval_samples_per_second": 1250.319, + "eval_steps_per_second": 39.073, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999695354250595e-05, + "loss": 3.5307, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991309406740075e-05, + "loss": 3.5325, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982923459229555e-05, + "loss": 3.5464, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974537511719038e-05, + "loss": 3.5428, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966167943012247e-05, + "loss": 3.5546, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957781995501727e-05, + "loss": 3.5324, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949396047991207e-05, + "loss": 3.528, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9941026479284416e-05, + "loss": 3.5276, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.99326405317739e-05, + "loss": 3.5405, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992425458426338e-05, + "loss": 3.5327, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991586863675286e-05, + "loss": 3.5356, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990748268924234e-05, + "loss": 3.5352, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9899129499339277e-05, + "loss": 3.5276, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.989074355182876e-05, + "loss": 3.5319, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.988235760431824e-05, + "loss": 3.5241, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987397165680772e-05, + "loss": 3.5215, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.98655857092972e-05, + "loss": 3.5318, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985719976178668e-05, + "loss": 3.5334, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984881381427616e-05, + "loss": 3.5318, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984042786676564e-05, + "loss": 3.5477, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832058298058853e-05, + "loss": 3.5312, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9823672350548333e-05, + "loss": 3.5378, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815286403037813e-05, + "loss": 3.532, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806900455527293e-05, + "loss": 3.5432, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798530886820502e-05, + "loss": 3.5314, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790144939309982e-05, + "loss": 3.5347, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781758991799462e-05, + "loss": 3.5276, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773373044288945e-05, + "loss": 3.5332, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765003475582154e-05, + "loss": 3.5266, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756617528071634e-05, + "loss": 3.5298, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748231580561114e-05, + "loss": 3.5401, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739845633050594e-05, + "loss": 3.5344, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731476064343807e-05, + "loss": 3.5384, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9723090116833287e-05, + "loss": 3.5361, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714704169322767e-05, + "loss": 3.5297, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9706318221812247e-05, + "loss": 3.5417, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697948653105456e-05, + "loss": 3.5265, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689562705594936e-05, + "loss": 3.5303, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681176758084416e-05, + "loss": 3.5156, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672790810573896e-05, + "loss": 3.5234, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966440486306338e-05, + "loss": 3.5232, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9656035294356588e-05, + "loss": 3.5416, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647649346846068e-05, + "loss": 3.5281, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9639263399335548e-05, + "loss": 3.5254, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630877451825028e-05, + "loss": 3.5345, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.962250788311824e-05, + "loss": 3.5327, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.961412193560772e-05, + "loss": 3.5228, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.96057359880972e-05, + "loss": 3.5153, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.959736641939041e-05, + "loss": 3.5199, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.958898047187989e-05, + "loss": 3.5404, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.958059452436937e-05, + "loss": 3.5409, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.957220857685885e-05, + "loss": 3.526, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563839008152062e-05, + "loss": 3.5218, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955545306064154e-05, + "loss": 3.535, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954706711313102e-05, + "loss": 3.5166, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.95386811656205e-05, + "loss": 3.5368, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530295218109978e-05, + "loss": 3.5149, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521925649403194e-05, + "loss": 3.5425, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513539701892674e-05, + "loss": 3.5344, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505153754382147e-05, + "loss": 3.5202, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496767806871627e-05, + "loss": 3.5212, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488398238164843e-05, + "loss": 3.536, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480012290654323e-05, + "loss": 3.5093, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.94716263431438e-05, + "loss": 3.5182, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946324039563328e-05, + "loss": 3.5385, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454870826926495e-05, + "loss": 3.5298, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446484879415975e-05, + "loss": 3.523, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.943809893190545e-05, + "loss": 3.5128, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.9429712984394932e-05, + "loss": 3.5211, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421343415688148e-05, + "loss": 3.5149, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941295746817762e-05, + "loss": 3.5348, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.94045715206671e-05, + "loss": 3.5174, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939618557315658e-05, + "loss": 3.5314, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387816004449797e-05, + "loss": 3.5286, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379430056939273e-05, + "loss": 3.5357, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371044109428753e-05, + "loss": 3.5223, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9362658161918233e-05, + "loss": 3.5267, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.935428859321145e-05, + "loss": 3.5293, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345902645700922e-05, + "loss": 3.529, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337516698190402e-05, + "loss": 3.5262, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329130750679885e-05, + "loss": 3.5253, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320761181973095e-05, + "loss": 3.53, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312375234462575e-05, + "loss": 3.5225, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303989286952054e-05, + "loss": 3.5157, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295603339441534e-05, + "loss": 3.5168, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287233770734747e-05, + "loss": 3.5267, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278847823224227e-05, + "loss": 3.5277, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270461875713707e-05, + "loss": 3.5214, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9262075928203187e-05, + "loss": 3.5231, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253706359496396e-05, + "loss": 3.5177, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245320411985876e-05, + "loss": 3.5109, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236934464475356e-05, + "loss": 3.518, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.922854851696484e-05, + "loss": 3.5255, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220178948258048e-05, + "loss": 3.5264, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211793000747528e-05, + "loss": 3.535, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9203407053237008e-05, + "loss": 3.5301, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9195021105726488e-05, + "loss": 3.5171, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.91866515370197e-05, + "loss": 3.5225, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.917826558950918e-05, + "loss": 3.5276, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.916987964199866e-05, + "loss": 3.5271, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.916149369448814e-05, + "loss": 3.5326, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915310774697762e-05, + "loss": 3.5215, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914473817827083e-05, + "loss": 3.518, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913635223076031e-05, + "loss": 3.5363, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127966283249793e-05, + "loss": 3.5168, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9119580335739273e-05, + "loss": 3.5228, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111210767032482e-05, + "loss": 3.5269, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102824819521962e-05, + "loss": 3.5266, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094438872011442e-05, + "loss": 3.5144, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086052924500922e-05, + "loss": 3.5226, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9077683355794134e-05, + "loss": 3.5171, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069297408283614e-05, + "loss": 3.5267, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060911460773094e-05, + "loss": 3.5223, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052525513262574e-05, + "loss": 3.52, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044155944555783e-05, + "loss": 3.5321, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035769997045263e-05, + "loss": 3.5391, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027384049534746e-05, + "loss": 3.528, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018998102024226e-05, + "loss": 3.5188, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010628533317436e-05, + "loss": 3.5208, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002242585806915e-05, + "loss": 3.5191, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993856638296395e-05, + "loss": 3.5239, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985470690785875e-05, + "loss": 3.5237, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977101122079088e-05, + "loss": 3.5156, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968715174568568e-05, + "loss": 3.5236, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960329227058048e-05, + "loss": 3.5256, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951943279547528e-05, + "loss": 3.5218, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943573710840737e-05, + "loss": 3.5184, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935187763330217e-05, + "loss": 3.5217, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.89268018158197e-05, + "loss": 3.518, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.891843224711291e-05, + "loss": 3.531, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.891004629960239e-05, + "loss": 3.5323, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890166035209187e-05, + "loss": 3.5293, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889327440458135e-05, + "loss": 3.5121, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.888488845707083e-05, + "loss": 3.5256, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887651888836404e-05, + "loss": 3.5241, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886813294085352e-05, + "loss": 3.5268, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859746993343e-05, + "loss": 3.5209, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.885136104583248e-05, + "loss": 3.5371, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884299147712569e-05, + "loss": 3.5229, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.883460552961517e-05, + "loss": 3.5421, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826219582104654e-05, + "loss": 3.5174, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817833634594134e-05, + "loss": 3.5309, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809464065887343e-05, + "loss": 3.5184, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801078118376823e-05, + "loss": 3.518, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792692170866303e-05, + "loss": 3.527, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784306223355783e-05, + "loss": 3.515, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775936654648995e-05, + "loss": 3.5207, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767550707138475e-05, + "loss": 3.5172, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8759164759627955e-05, + "loss": 3.5204, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.8539352416992188, + "eval_runtime": 305.3831, + "eval_samples_per_second": 1249.548, + "eval_steps_per_second": 39.049, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750778812117435e-05, + "loss": 3.5197, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742409243410644e-05, + "loss": 3.518, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734023295900124e-05, + "loss": 3.5316, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725637348389604e-05, + "loss": 3.5253, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8717251400879087e-05, + "loss": 3.5385, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.8708881832172297e-05, + "loss": 3.5189, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.8700495884661776e-05, + "loss": 3.5187, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.8692109937151256e-05, + "loss": 3.5121, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.8683740368444466e-05, + "loss": 3.5275, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867535442093395e-05, + "loss": 3.5212, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866696847342343e-05, + "loss": 3.5183, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.865858252591291e-05, + "loss": 3.5245, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650212957206118e-05, + "loss": 3.5088, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641827009695598e-05, + "loss": 3.5208, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633441062185078e-05, + "loss": 3.5089, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625055114674558e-05, + "loss": 3.5121, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861666916716404e-05, + "loss": 3.5162, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860828321965352e-05, + "loss": 3.5159, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599897272142994e-05, + "loss": 3.5184, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591511324632474e-05, + "loss": 3.5373, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.858314175592569e-05, + "loss": 3.5183, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.857475580841517e-05, + "loss": 3.5207, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566369860904647e-05, + "loss": 3.5208, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557983913394127e-05, + "loss": 3.5254, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549614344687342e-05, + "loss": 3.5203, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541228397176822e-05, + "loss": 3.5222, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532842449666296e-05, + "loss": 3.5116, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.852445650215578e-05, + "loss": 3.5192, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516086933448995e-05, + "loss": 3.5082, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507700985938468e-05, + "loss": 3.5218, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8499315038427948e-05, + "loss": 3.522, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490929090917428e-05, + "loss": 3.521, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482559522210644e-05, + "loss": 3.5279, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.847417357470012e-05, + "loss": 3.5202, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.84657876271896e-05, + "loss": 3.5209, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845740167967908e-05, + "loss": 3.5245, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8449032110972296e-05, + "loss": 3.5125, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844064616346177e-05, + "loss": 3.5143, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843226021595125e-05, + "loss": 3.5016, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423874268440733e-05, + "loss": 3.5086, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841550469973394e-05, + "loss": 3.5127, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.840711875222342e-05, + "loss": 3.5278, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.83987328047129e-05, + "loss": 3.514, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.839034685720238e-05, + "loss": 3.5113, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381977288495594e-05, + "loss": 3.5224, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373591340985074e-05, + "loss": 3.513, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365205393474554e-05, + "loss": 3.5132, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356819445964034e-05, + "loss": 3.5019, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348449877257243e-05, + "loss": 3.5037, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340063929746723e-05, + "loss": 3.5263, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331677982236203e-05, + "loss": 3.5262, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323292034725686e-05, + "loss": 3.5091, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314922466018895e-05, + "loss": 3.5133, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306536518508375e-05, + "loss": 3.5177, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298150570997855e-05, + "loss": 3.5027, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289764623487335e-05, + "loss": 3.5246, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281395054780548e-05, + "loss": 3.5026, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273009107270028e-05, + "loss": 3.5273, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264623159759508e-05, + "loss": 3.5231, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256237212248988e-05, + "loss": 3.5082, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247867643542197e-05, + "loss": 3.5073, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239481696031677e-05, + "loss": 3.5218, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8231095748521157e-05, + "loss": 3.4937, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822270980101064e-05, + "loss": 3.5078, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821434023230385e-05, + "loss": 3.5227, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820595428479333e-05, + "loss": 3.5182, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819756833728281e-05, + "loss": 3.5077, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818918238977229e-05, + "loss": 3.4983, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.81808128210655e-05, + "loss": 3.5089, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817242687355498e-05, + "loss": 3.5036, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816404092604446e-05, + "loss": 3.5155, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.815565497853394e-05, + "loss": 3.5045, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814728540982715e-05, + "loss": 3.5173, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813889946231663e-05, + "loss": 3.5176, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.813051351480611e-05, + "loss": 3.5226, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122127567295594e-05, + "loss": 3.5081, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113757998588803e-05, + "loss": 3.5148, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105372051078283e-05, + "loss": 3.5157, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096986103567763e-05, + "loss": 3.5144, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088600156057243e-05, + "loss": 3.5157, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080230587350455e-05, + "loss": 3.5117, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071844639839935e-05, + "loss": 3.5193, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063458692329415e-05, + "loss": 3.5095, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055072744818895e-05, + "loss": 3.5001, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046703176112104e-05, + "loss": 3.5037, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038317228601584e-05, + "loss": 3.5133, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.8029931281091064e-05, + "loss": 3.5162, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.8021545333580547e-05, + "loss": 3.5089, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013175764873756e-05, + "loss": 3.5105, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004789817363236e-05, + "loss": 3.5047, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996403869852716e-05, + "loss": 3.4994, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988017922342196e-05, + "loss": 3.5035, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797964835363541e-05, + "loss": 3.5129, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797126240612489e-05, + "loss": 3.5136, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796287645861437e-05, + "loss": 3.5205, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795449051110385e-05, + "loss": 3.5168, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946120942397058e-05, + "loss": 3.5052, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937734994886538e-05, + "loss": 3.5089, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929349047376018e-05, + "loss": 3.5101, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920963099865497e-05, + "loss": 3.5153, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.791259353115871e-05, + "loss": 3.5191, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790420758364819e-05, + "loss": 3.5102, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789582163613767e-05, + "loss": 3.504, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788743568862715e-05, + "loss": 3.5225, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7879066119920362e-05, + "loss": 3.5016, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870680172409842e-05, + "loss": 3.5112, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862294224899322e-05, + "loss": 3.5131, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853908277388802e-05, + "loss": 3.5104, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.784553870868201e-05, + "loss": 3.5011, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783715276117149e-05, + "loss": 3.5133, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782876681366097e-05, + "loss": 3.5016, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782038086615045e-05, + "loss": 3.5119, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7812011297443664e-05, + "loss": 3.5099, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7803625349933144e-05, + "loss": 3.5024, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795239402422624e-05, + "loss": 3.522, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7786853454912104e-05, + "loss": 3.5254, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778483886205313e-05, + "loss": 3.5154, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7770097938694796e-05, + "loss": 3.5075, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761711991184276e-05, + "loss": 3.5059, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753326043673756e-05, + "loss": 3.5094, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7744956474966965e-05, + "loss": 3.5048, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736570527456445e-05, + "loss": 3.5159, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728184579945925e-05, + "loss": 3.5004, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719798632435405e-05, + "loss": 3.5076, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711429063728617e-05, + "loss": 3.5146, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703043116218097e-05, + "loss": 3.5145, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694657168707577e-05, + "loss": 3.5008, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686271221197057e-05, + "loss": 3.5055, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677901652490266e-05, + "loss": 3.5098, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766951570497975e-05, + "loss": 3.5106, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766112975746923e-05, + "loss": 3.5177, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765274380995871e-05, + "loss": 3.5176, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.764437424125192e-05, + "loss": 3.4991, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.76359882937414e-05, + "loss": 3.5108, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.762760234623088e-05, + "loss": 3.5126, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.761921639872036e-05, + "loss": 3.5106, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.761084683001357e-05, + "loss": 3.5087, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760246088250305e-05, + "loss": 3.5178, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759407493499253e-05, + "loss": 3.5097, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758568898748201e-05, + "loss": 3.527, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757731941877522e-05, + "loss": 3.5066, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568933471264703e-05, + "loss": 3.5172, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560547523754183e-05, + "loss": 3.5098, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7552161576243663e-05, + "loss": 3.504, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543792007536872e-05, + "loss": 3.5118, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535406060026352e-05, + "loss": 3.506, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7527020112515832e-05, + "loss": 3.5067, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518634165005312e-05, + "loss": 3.4997, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510264596298525e-05, + "loss": 3.5061, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8566198348999023, + "eval_runtime": 304.4165, + "eval_samples_per_second": 1253.516, + "eval_steps_per_second": 39.173, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501878648788005e-05, + "loss": 3.5049, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493492701277485e-05, + "loss": 3.5045, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485106753766965e-05, + "loss": 3.519, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747672080625644e-05, + "loss": 3.509, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468351237549657e-05, + "loss": 3.5288, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459965290039137e-05, + "loss": 3.5067, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451579342528617e-05, + "loss": 3.507, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.744319339501809e-05, + "loss": 3.4946, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434823826311306e-05, + "loss": 3.5148, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426437878800786e-05, + "loss": 3.5082, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418051931290266e-05, + "loss": 3.5029, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409665983779742e-05, + "loss": 3.5175, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401312793876687e-05, + "loss": 3.4966, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392926846366167e-05, + "loss": 3.5119, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384540898855647e-05, + "loss": 3.4935, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376154951345127e-05, + "loss": 3.4968, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736776900383461e-05, + "loss": 3.4962, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735938305632409e-05, + "loss": 3.5082, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7350997108813564e-05, + "loss": 3.5039, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342611161303044e-05, + "loss": 3.5227, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733424159259626e-05, + "loss": 3.5064, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7325855645085736e-05, + "loss": 3.5089, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317469697575216e-05, + "loss": 3.5062, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309083750064696e-05, + "loss": 3.5143, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300714181357912e-05, + "loss": 3.5034, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7292328233847385e-05, + "loss": 3.5137, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283942286336865e-05, + "loss": 3.4992, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.727555633882635e-05, + "loss": 3.5048, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726717039131583e-05, + "loss": 3.4921, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258800822609037e-05, + "loss": 3.5097, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250414875098517e-05, + "loss": 3.5127, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242028927587997e-05, + "loss": 3.5069, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.723365935888121e-05, + "loss": 3.5196, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.722527341137069e-05, + "loss": 3.5062, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.721688746386017e-05, + "loss": 3.5032, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720850151634965e-05, + "loss": 3.5135, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.720011556883913e-05, + "loss": 3.5027, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.719174600013234e-05, + "loss": 3.5007, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.718336005262182e-05, + "loss": 3.4904, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174974105111302e-05, + "loss": 3.497, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166588157600782e-05, + "loss": 3.5005, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.715821858889399e-05, + "loss": 3.5118, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714983264138347e-05, + "loss": 3.5068, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714144669387295e-05, + "loss": 3.4957, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713306074636243e-05, + "loss": 3.5121, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124691177655643e-05, + "loss": 3.5023, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116305230145123e-05, + "loss": 3.4971, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107919282634603e-05, + "loss": 3.4918, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099533335124083e-05, + "loss": 3.4873, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7091163766417292e-05, + "loss": 3.5143, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082777818906772e-05, + "loss": 3.5132, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074391871396256e-05, + "loss": 3.4987, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7066005923885736e-05, + "loss": 3.4976, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057636355178945e-05, + "loss": 3.5076, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049250407668425e-05, + "loss": 3.486, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040864460157905e-05, + "loss": 3.5097, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032478512647385e-05, + "loss": 3.4905, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024108943940597e-05, + "loss": 3.5095, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7015722996430077e-05, + "loss": 3.5156, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007337048919557e-05, + "loss": 3.4964, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998951101409037e-05, + "loss": 3.4908, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990581532702246e-05, + "loss": 3.5102, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982195585191726e-05, + "loss": 3.484, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973809637681206e-05, + "loss": 3.497, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696544006897442e-05, + "loss": 3.5088, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.69570541214639e-05, + "loss": 3.5069, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.694866817395338e-05, + "loss": 3.4974, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.694028222644286e-05, + "loss": 3.4868, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.693189627893234e-05, + "loss": 3.4924, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.692352671022555e-05, + "loss": 3.4903, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.691514076271503e-05, + "loss": 3.5043, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.690675481520451e-05, + "loss": 3.4912, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689836886769399e-05, + "loss": 3.5082, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.68899992989872e-05, + "loss": 3.5053, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688161335147668e-05, + "loss": 3.5103, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687322740396616e-05, + "loss": 3.4937, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864841456455643e-05, + "loss": 3.5017, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856471887748852e-05, + "loss": 3.5049, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6848085940238332e-05, + "loss": 3.4979, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839699992727812e-05, + "loss": 3.5037, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831314045217292e-05, + "loss": 3.5004, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822944476510504e-05, + "loss": 3.5032, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814558528999984e-05, + "loss": 3.4995, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6806172581489464e-05, + "loss": 3.4852, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797786633978944e-05, + "loss": 3.4954, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6789417065272153e-05, + "loss": 3.4954, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781031117761633e-05, + "loss": 3.5026, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772645170251113e-05, + "loss": 3.4984, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764259222740597e-05, + "loss": 3.495, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755889654033806e-05, + "loss": 3.4923, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747503706523286e-05, + "loss": 3.4869, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739117759012766e-05, + "loss": 3.4891, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730731811502246e-05, + "loss": 3.4961, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722362242795458e-05, + "loss": 3.5105, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713976295284938e-05, + "loss": 3.5059, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705590347774418e-05, + "loss": 3.5041, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697204400263898e-05, + "loss": 3.4941, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688834831557107e-05, + "loss": 3.4998, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680448884046587e-05, + "loss": 3.495, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6672062936536067e-05, + "loss": 3.5043, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666367698902555e-05, + "loss": 3.5049, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665529104151503e-05, + "loss": 3.498, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664692147280824e-05, + "loss": 3.4901, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663853552529772e-05, + "loss": 3.511, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.66301495777872e-05, + "loss": 3.4901, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662176363027668e-05, + "loss": 3.5007, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613394061569892e-05, + "loss": 3.4942, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605008114059372e-05, + "loss": 3.4994, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.659662216654885e-05, + "loss": 3.4896, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.658823621903833e-05, + "loss": 3.5007, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.657986665033154e-05, + "loss": 3.4915, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.657148070282102e-05, + "loss": 3.493, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563094755310504e-05, + "loss": 3.5022, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554708807799984e-05, + "loss": 3.4867, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546339239093193e-05, + "loss": 3.5098, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537953291582673e-05, + "loss": 3.5115, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529567344072153e-05, + "loss": 3.5024, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521181396561633e-05, + "loss": 3.4937, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512811827854845e-05, + "loss": 3.4953, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504425880344325e-05, + "loss": 3.4947, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496039932833805e-05, + "loss": 3.4923, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6487653985323285e-05, + "loss": 3.5013, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479284416616494e-05, + "loss": 3.4871, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470898469105974e-05, + "loss": 3.4942, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6462512521595458e-05, + "loss": 3.5027, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6454126574084938e-05, + "loss": 3.5012, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.6445757005378147e-05, + "loss": 3.49, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437371057867627e-05, + "loss": 3.4931, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428985110357107e-05, + "loss": 3.4994, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6420599162846587e-05, + "loss": 3.4973, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.64122295941398e-05, + "loss": 3.4998, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640384364662928e-05, + "loss": 3.5068, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639545769911876e-05, + "loss": 3.4874, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6387071751608232e-05, + "loss": 3.499, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378702182901448e-05, + "loss": 3.5019, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370316235390928e-05, + "loss": 3.4979, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636193028788041e-05, + "loss": 3.4963, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353544340369885e-05, + "loss": 3.5088, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.63451747716631e-05, + "loss": 3.4984, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.633678882415258e-05, + "loss": 3.5132, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632840287664206e-05, + "loss": 3.4938, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320016929131537e-05, + "loss": 3.5007, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311647360424753e-05, + "loss": 3.4978, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303261412914233e-05, + "loss": 3.4919, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6294891844207442e-05, + "loss": 3.4964, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286505896696922e-05, + "loss": 3.496, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278119949186402e-05, + "loss": 3.493, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269734001675882e-05, + "loss": 3.4901, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261348054165358e-05, + "loss": 3.494, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.857630729675293, + "eval_runtime": 303.2288, + "eval_samples_per_second": 1258.426, + "eval_steps_per_second": 39.327, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252962106654838e-05, + "loss": 3.4965, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244576159144318e-05, + "loss": 3.4906, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236190211633798e-05, + "loss": 3.5037, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622782064292701e-05, + "loss": 3.4982, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621943469541649e-05, + "loss": 3.5175, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621104874790597e-05, + "loss": 3.494, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620266280039545e-05, + "loss": 3.4942, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619429323168866e-05, + "loss": 3.4821, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618590728417814e-05, + "loss": 3.5001, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.617752133666762e-05, + "loss": 3.4963, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169135389157103e-05, + "loss": 3.4895, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160765820450312e-05, + "loss": 3.4998, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.6152396251743528e-05, + "loss": 3.4881, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6144010304233008e-05, + "loss": 3.4972, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.613562435672248e-05, + "loss": 3.4835, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127238409211964e-05, + "loss": 3.484, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118852461701444e-05, + "loss": 3.4859, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110466514190924e-05, + "loss": 3.4932, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102080566680404e-05, + "loss": 3.4923, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093694619169884e-05, + "loss": 3.5083, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085325050463093e-05, + "loss": 3.4949, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076939102952573e-05, + "loss": 3.5022, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6068553155442053e-05, + "loss": 3.4919, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060167207931536e-05, + "loss": 3.4982, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051797639224746e-05, + "loss": 3.4931, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043411691714226e-05, + "loss": 3.5002, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035025744203705e-05, + "loss": 3.4901, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6026639796693185e-05, + "loss": 3.4868, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018270227986398e-05, + "loss": 3.4836, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009884280475878e-05, + "loss": 3.4964, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6001498332965358e-05, + "loss": 3.5024, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5993112385454838e-05, + "loss": 3.4939, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984742816748047e-05, + "loss": 3.5087, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976356869237527e-05, + "loss": 3.4944, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967970921727007e-05, + "loss": 3.488, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595958497421649e-05, + "loss": 3.4999, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.59512154055097e-05, + "loss": 3.497, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594282945799918e-05, + "loss": 3.4831, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593444351048866e-05, + "loss": 3.479, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.592605756297814e-05, + "loss": 3.4834, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.591768799427135e-05, + "loss": 3.4924, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.590930204676083e-05, + "loss": 3.4978, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.590091609925031e-05, + "loss": 3.495, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589253015173979e-05, + "loss": 3.4824, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884160583033e-05, + "loss": 3.4956, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587577463552248e-05, + "loss": 3.492, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.586738868801196e-05, + "loss": 3.4853, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859002740501444e-05, + "loss": 3.4785, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850633171794653e-05, + "loss": 3.4688, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842247224284133e-05, + "loss": 3.5077, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833861276773613e-05, + "loss": 3.5, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825475329263093e-05, + "loss": 3.4884, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817105760556305e-05, + "loss": 3.4891, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808719813045785e-05, + "loss": 3.491, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800333865535265e-05, + "loss": 3.4771, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791947918024745e-05, + "loss": 3.4957, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783578349317954e-05, + "loss": 3.4836, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775192401807434e-05, + "loss": 3.4919, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766806454296914e-05, + "loss": 3.5064, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.5758420506786397e-05, + "loss": 3.4859, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.5750050938079607e-05, + "loss": 3.4755, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5741664990569087e-05, + "loss": 3.5013, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733279043058566e-05, + "loss": 3.4716, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724893095548046e-05, + "loss": 3.4799, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571652352684126e-05, + "loss": 3.4987, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570813757933074e-05, + "loss": 3.4934, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569975163182022e-05, + "loss": 3.488, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.56913656843097e-05, + "loss": 3.4797, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682996115602908e-05, + "loss": 3.4747, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674610168092388e-05, + "loss": 3.4779, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666224220581868e-05, + "loss": 3.4929, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.565783827307135e-05, + "loss": 3.4777, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.564946870436456e-05, + "loss": 3.4968, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.564108275685404e-05, + "loss": 3.4893, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.563269680934352e-05, + "loss": 3.5011, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624310861833e-05, + "loss": 3.4849, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615941293126213e-05, + "loss": 3.4857, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607555345615693e-05, + "loss": 3.4927, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599169398105172e-05, + "loss": 3.4831, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590783450594652e-05, + "loss": 3.4979, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.558241388188786e-05, + "loss": 3.4873, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557402793437734e-05, + "loss": 3.4878, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556564198686682e-05, + "loss": 3.4858, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557256039356305e-05, + "loss": 3.4724, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548886470649514e-05, + "loss": 3.4811, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540500523138994e-05, + "loss": 3.4883, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5532114575628474e-05, + "loss": 3.4885, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.5523728628117954e-05, + "loss": 3.482, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515359059411166e-05, + "loss": 3.4846, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5506973111900646e-05, + "loss": 3.4807, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498587164390126e-05, + "loss": 3.4734, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490201216879606e-05, + "loss": 3.4791, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5481831648172815e-05, + "loss": 3.4825, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473445700662295e-05, + "loss": 3.4981, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465059753151775e-05, + "loss": 3.4979, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545667380564126e-05, + "loss": 3.4884, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448304236934468e-05, + "loss": 3.4777, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439918289423948e-05, + "loss": 3.486, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431532341913427e-05, + "loss": 3.4857, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423146394402907e-05, + "loss": 3.4892, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.541477682569612e-05, + "loss": 3.4919, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.54063908781856e-05, + "loss": 3.4874, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.539800493067508e-05, + "loss": 3.4773, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389618983164553e-05, + "loss": 3.4992, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381233035654033e-05, + "loss": 3.4745, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.537286346694725e-05, + "loss": 3.4893, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.536447751943673e-05, + "loss": 3.48, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356091571926205e-05, + "loss": 3.4887, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347705624415685e-05, + "loss": 3.4786, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.53393360557089e-05, + "loss": 3.4872, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533095010819838e-05, + "loss": 3.4819, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322564160687858e-05, + "loss": 3.4833, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314178213177338e-05, + "loss": 3.4855, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305808644470554e-05, + "loss": 3.4808, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297422696960027e-05, + "loss": 3.495, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5289036749449507e-05, + "loss": 3.4981, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280650801938987e-05, + "loss": 3.4905, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272281233232202e-05, + "loss": 3.4818, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526389528572168e-05, + "loss": 3.4833, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525550933821116e-05, + "loss": 3.4828, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524712339070064e-05, + "loss": 3.4805, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238753821993855e-05, + "loss": 3.491, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230367874483328e-05, + "loss": 3.4709, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522198192697281e-05, + "loss": 3.4863, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521359597946229e-05, + "loss": 3.4863, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.52052264107555e-05, + "loss": 3.4906, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.519684046324498e-05, + "loss": 3.4784, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518845451573446e-05, + "loss": 3.4829, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.518006856822394e-05, + "loss": 3.4825, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171698999517153e-05, + "loss": 3.4923, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163313052006633e-05, + "loss": 3.4871, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154927104496113e-05, + "loss": 3.4971, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146541156985593e-05, + "loss": 3.4753, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138171588278802e-05, + "loss": 3.4876, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.512978564076828e-05, + "loss": 3.4911, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.512139969325776e-05, + "loss": 3.4821, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113013745747245e-05, + "loss": 3.4837, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104644177040454e-05, + "loss": 3.4968, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096258229529934e-05, + "loss": 3.4866, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087872282019414e-05, + "loss": 3.5044, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079486334508894e-05, + "loss": 3.4805, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071116765802106e-05, + "loss": 3.4893, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.5062730818291586e-05, + "loss": 3.4822, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5054344870781066e-05, + "loss": 3.4816, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5045958923270546e-05, + "loss": 3.4836, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5037589354563755e-05, + "loss": 3.4837, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.5029203407053235e-05, + "loss": 3.4814, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.5020817459542715e-05, + "loss": 3.4753, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.50124315120322e-05, + "loss": 3.483, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8581809997558594, + "eval_runtime": 302.934, + "eval_samples_per_second": 1259.651, + "eval_steps_per_second": 39.365, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500404556452168e-05, + "loss": 3.4806, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499565961701116e-05, + "loss": 3.4787, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498727366950064e-05, + "loss": 3.4915, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497888772199012e-05, + "loss": 3.4878, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970518153283328e-05, + "loss": 3.5021, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4962132205772808e-05, + "loss": 3.4879, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495374625826229e-05, + "loss": 3.4828, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494536031075177e-05, + "loss": 3.4693, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493699074204498e-05, + "loss": 3.4867, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492860479453446e-05, + "loss": 3.4823, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492021884702394e-05, + "loss": 3.4813, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491183289951342e-05, + "loss": 3.4831, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903463330806632e-05, + "loss": 3.4756, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895077383296112e-05, + "loss": 3.4862, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886691435785592e-05, + "loss": 3.4713, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878305488275072e-05, + "loss": 3.4726, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.486991954076455e-05, + "loss": 3.4721, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486153359325403e-05, + "loss": 3.4814, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485314764574351e-05, + "loss": 3.4793, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844761698232992e-05, + "loss": 3.4947, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.48363921295262e-05, + "loss": 3.482, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482800618201568e-05, + "loss": 3.4899, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481962023450516e-05, + "loss": 3.4816, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481123428699464e-05, + "loss": 3.4837, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802864718287853e-05, + "loss": 3.4805, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794478770777333e-05, + "loss": 3.4888, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786092823266813e-05, + "loss": 3.4791, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4777706875756293e-05, + "loss": 3.4776, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769337307049502e-05, + "loss": 3.4707, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4760951359538982e-05, + "loss": 3.4793, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752565412028462e-05, + "loss": 3.4894, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744179464517946e-05, + "loss": 3.4837, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735809895811155e-05, + "loss": 3.4919, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727423948300635e-05, + "loss": 3.48, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719038000790115e-05, + "loss": 3.4792, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710652053279595e-05, + "loss": 3.4899, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702266105769075e-05, + "loss": 3.4857, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693912915866016e-05, + "loss": 3.4681, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685526968355496e-05, + "loss": 3.4732, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677141020844976e-05, + "loss": 3.4696, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668755073334456e-05, + "loss": 3.4746, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660369125823936e-05, + "loss": 3.4882, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651983178313416e-05, + "loss": 3.481, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.46435972308029e-05, + "loss": 3.4753, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635211283292376e-05, + "loss": 3.4818, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626825335781856e-05, + "loss": 3.4756, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.461845576707507e-05, + "loss": 3.4765, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4610069819564548e-05, + "loss": 3.468, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601683872054028e-05, + "loss": 3.4536, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593297924543508e-05, + "loss": 3.4956, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458492835583672e-05, + "loss": 3.486, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576542408326197e-05, + "loss": 3.4827, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568156460815677e-05, + "loss": 3.4758, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.455978689210889e-05, + "loss": 3.4762, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455140094459837e-05, + "loss": 3.4663, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.454301499708785e-05, + "loss": 3.4813, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.453462904957733e-05, + "loss": 3.4753, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.452624310206681e-05, + "loss": 3.4773, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.451785715455629e-05, + "loss": 3.4942, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450947120704577e-05, + "loss": 3.4722, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450108525953525e-05, + "loss": 3.4675, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492715690828462e-05, + "loss": 3.4868, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484329743317942e-05, + "loss": 3.4599, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.4475943795807422e-05, + "loss": 3.4691, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.4467557848296902e-05, + "loss": 3.484, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445918827959011e-05, + "loss": 3.4806, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445080233207959e-05, + "loss": 3.4741, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444241638456907e-05, + "loss": 3.4703, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434046815862283e-05, + "loss": 3.4618, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4425660868351763e-05, + "loss": 3.4663, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417274920841243e-05, + "loss": 3.4797, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4408888973330723e-05, + "loss": 3.4694, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400519404623932e-05, + "loss": 3.4802, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392133457113416e-05, + "loss": 3.4797, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383747509602895e-05, + "loss": 3.4908, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375361562092375e-05, + "loss": 3.4719, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366991993385585e-05, + "loss": 3.4714, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358606045875064e-05, + "loss": 3.4806, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350220098364544e-05, + "loss": 3.4693, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341834150854024e-05, + "loss": 3.4892, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333464582147237e-05, + "loss": 3.4767, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325078634636717e-05, + "loss": 3.4751, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316692687126197e-05, + "loss": 3.4782, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308306739615677e-05, + "loss": 3.4622, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299937170908886e-05, + "loss": 3.4658, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.429155122339837e-05, + "loss": 3.4749, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.428316527588785e-05, + "loss": 3.4785, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274779328377326e-05, + "loss": 3.4674, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266409759670538e-05, + "loss": 3.4748, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258023812160018e-05, + "loss": 3.469, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249637864649498e-05, + "loss": 3.4671, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241251917138978e-05, + "loss": 3.4612, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423288234843219e-05, + "loss": 3.4755, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.422449640092167e-05, + "loss": 3.4834, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421611045341115e-05, + "loss": 3.4815, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207724505900627e-05, + "loss": 3.4806, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419935493719384e-05, + "loss": 3.4654, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190968989683323e-05, + "loss": 3.473, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.41825830421728e-05, + "loss": 3.4721, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417419709466228e-05, + "loss": 3.4786, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.4165827525955492e-05, + "loss": 3.4784, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4157441578444972e-05, + "loss": 3.474, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4149055630934452e-05, + "loss": 3.47, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140669683423932e-05, + "loss": 3.4855, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4132300114717144e-05, + "loss": 3.4632, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412391416720662e-05, + "loss": 3.4761, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.41155282196961e-05, + "loss": 3.469, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410714227218558e-05, + "loss": 3.4777, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4098772703478793e-05, + "loss": 3.4648, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090386755968273e-05, + "loss": 3.4775, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.4082000808457753e-05, + "loss": 3.4676, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073614860947233e-05, + "loss": 3.4744, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065245292240446e-05, + "loss": 3.4753, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4056859344729922e-05, + "loss": 3.4703, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048473397219402e-05, + "loss": 3.4835, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040087449708885e-05, + "loss": 3.4858, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031717881002094e-05, + "loss": 3.4756, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023331933491574e-05, + "loss": 3.4739, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014945985981054e-05, + "loss": 3.4691, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006560038470534e-05, + "loss": 3.4721, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998190469763747e-05, + "loss": 3.4686, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989804522253227e-05, + "loss": 3.4799, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981418574742707e-05, + "loss": 3.4573, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973032627232187e-05, + "loss": 3.4726, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964663058525396e-05, + "loss": 3.474, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956277111014876e-05, + "loss": 3.4791, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947891163504356e-05, + "loss": 3.4705, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.393950521599384e-05, + "loss": 3.4733, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931135647287048e-05, + "loss": 3.4681, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922749699776528e-05, + "loss": 3.4794, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914363752266008e-05, + "loss": 3.4791, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905977804755488e-05, + "loss": 3.4828, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.38976082360487e-05, + "loss": 3.4641, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.388922228853818e-05, + "loss": 3.4771, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.388083634102766e-05, + "loss": 3.4779, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.387245039351714e-05, + "loss": 3.4701, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386408082481035e-05, + "loss": 3.4732, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.385569487729983e-05, + "loss": 3.4834, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384730892978931e-05, + "loss": 3.4736, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838922982278793e-05, + "loss": 3.4946, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830553413572002e-05, + "loss": 3.4694, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3822167466061482e-05, + "loss": 3.4768, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.3813781518550962e-05, + "loss": 3.4717, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380539557104044e-05, + "loss": 3.4701, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3797026002333654e-05, + "loss": 3.4735, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788640054823134e-05, + "loss": 3.4721, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3780254107312614e-05, + "loss": 3.4738, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771868159802094e-05, + "loss": 3.4554, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.3763498591095303e-05, + "loss": 3.4723, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.8598008155822754, + "eval_runtime": 303.8893, + "eval_samples_per_second": 1255.691, + "eval_steps_per_second": 39.241, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.3755112643584783e-05, + "loss": 3.475, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746726696074263e-05, + "loss": 3.4659, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.3738340748563746e-05, + "loss": 3.4783, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729971179856955e-05, + "loss": 3.4799, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721585232346435e-05, + "loss": 3.4878, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713199284835915e-05, + "loss": 3.4725, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704813337325395e-05, + "loss": 3.4721, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696443768618608e-05, + "loss": 3.4615, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3688057821108088e-05, + "loss": 3.4749, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679671873597568e-05, + "loss": 3.4692, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671285926087048e-05, + "loss": 3.4751, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662916357380257e-05, + "loss": 3.4673, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.365454678867347e-05, + "loss": 3.4712, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.364616084116295e-05, + "loss": 3.4681, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.363777489365243e-05, + "loss": 3.4627, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.362938894614191e-05, + "loss": 3.4574, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.362100299863139e-05, + "loss": 3.4625, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.361261705112087e-05, + "loss": 3.4703, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604231103610346e-05, + "loss": 3.4668, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595845156099826e-05, + "loss": 3.484, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.358747558739304e-05, + "loss": 3.4733, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357908963988252e-05, + "loss": 3.4809, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570703692371998e-05, + "loss": 3.4673, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562317744861478e-05, + "loss": 3.4715, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.355394817615469e-05, + "loss": 3.4687, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.354556222864417e-05, + "loss": 3.4803, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.353717628113365e-05, + "loss": 3.4681, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.352879033362313e-05, + "loss": 3.465, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3520420764916343e-05, + "loss": 3.462, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.351203481740582e-05, + "loss": 3.4698, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.35036488698953e-05, + "loss": 3.4736, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.349526292238478e-05, + "loss": 3.4751, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.3486893353677992e-05, + "loss": 3.4791, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.3478507406167472e-05, + "loss": 3.475, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.347012145865695e-05, + "loss": 3.467, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346173551114643e-05, + "loss": 3.477, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345336594243964e-05, + "loss": 3.4723, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444979994929124e-05, + "loss": 3.46, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436594047418604e-05, + "loss": 3.461, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.3428208099908084e-05, + "loss": 3.4554, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419838531201293e-05, + "loss": 3.4611, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.3411452583690773e-05, + "loss": 3.4755, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3403066636180253e-05, + "loss": 3.4727, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394680688669733e-05, + "loss": 3.4611, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386311119962945e-05, + "loss": 3.47, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377925172452425e-05, + "loss": 3.4662, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369539224941905e-05, + "loss": 3.4673, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361153277431385e-05, + "loss": 3.4553, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352783708724594e-05, + "loss": 3.4398, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344397761214078e-05, + "loss": 3.4866, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3336011813703558e-05, + "loss": 3.4707, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327625866193038e-05, + "loss": 3.4741, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319256297486247e-05, + "loss": 3.4622, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.331088672877946e-05, + "loss": 3.4673, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.330250078126894e-05, + "loss": 3.4566, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.329411483375842e-05, + "loss": 3.4651, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.32857288862479e-05, + "loss": 3.4654, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.327734293873738e-05, + "loss": 3.4645, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.326895699122686e-05, + "loss": 3.4832, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.326057104371634e-05, + "loss": 3.4612, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.325218509620582e-05, + "loss": 3.4545, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.324381552749903e-05, + "loss": 3.4783, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.323542957998851e-05, + "loss": 3.4504, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322704363247799e-05, + "loss": 3.4563, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321865768496747e-05, + "loss": 3.4726, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321028811626068e-05, + "loss": 3.4702, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.320190216875016e-05, + "loss": 3.4573, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.319351622123964e-05, + "loss": 3.4628, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318513027372912e-05, + "loss": 3.4473, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176760705022333e-05, + "loss": 3.4586, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3168374757511813e-05, + "loss": 3.4664, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3159988810001293e-05, + "loss": 3.4532, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315160286249077e-05, + "loss": 3.4692, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.3143233293783985e-05, + "loss": 3.4663, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.3134847346273465e-05, + "loss": 3.4823, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126461398762945e-05, + "loss": 3.4591, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311807545125242e-05, + "loss": 3.4646, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.3109705882545634e-05, + "loss": 3.469, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.3101319935035114e-05, + "loss": 3.4578, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.3092933987524594e-05, + "loss": 3.474, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084564418817806e-05, + "loss": 3.4666, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076178471307286e-05, + "loss": 3.465, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067792523796766e-05, + "loss": 3.4678, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.3059406576286243e-05, + "loss": 3.4515, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3051037007579455e-05, + "loss": 3.4517, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.304265106006894e-05, + "loss": 3.4651, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.303426511255842e-05, + "loss": 3.4656, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025879165047895e-05, + "loss": 3.4585, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017509596341108e-05, + "loss": 3.4621, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3009123648830588e-05, + "loss": 3.4512, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000737701320064e-05, + "loss": 3.4593, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2992351753809548e-05, + "loss": 3.4517, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.298398218510276e-05, + "loss": 3.4599, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.297559623759224e-05, + "loss": 3.4752, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967210290081717e-05, + "loss": 3.4674, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958824342571197e-05, + "loss": 3.4669, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.295045477386441e-05, + "loss": 3.4564, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2942068826353892e-05, + "loss": 3.4618, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.293368287884337e-05, + "loss": 3.4579, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.292529693133285e-05, + "loss": 3.4688, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291692736262606e-05, + "loss": 3.4623, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908541415115538e-05, + "loss": 3.469, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900155467605018e-05, + "loss": 3.4585, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.28917695200945e-05, + "loss": 3.4701, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883399951387714e-05, + "loss": 3.4548, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.287501400387719e-05, + "loss": 3.4642, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286662805636667e-05, + "loss": 3.4548, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.285824210885615e-05, + "loss": 3.4678, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849872540149363e-05, + "loss": 3.4553, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841486592638843e-05, + "loss": 3.4625, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.2833100645128323e-05, + "loss": 3.4569, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824714697617803e-05, + "loss": 3.4617, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281634512891101e-05, + "loss": 3.4608, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280795918140049e-05, + "loss": 3.4579, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279957323388997e-05, + "loss": 3.4701, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2791187286379455e-05, + "loss": 3.4752, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782817717672664e-05, + "loss": 3.467, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2774431770162144e-05, + "loss": 3.468, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.2766045822651624e-05, + "loss": 3.4547, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.2757659875141104e-05, + "loss": 3.4605, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.2749290306434316e-05, + "loss": 3.4606, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.2740904358923796e-05, + "loss": 3.4682, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732518411413276e-05, + "loss": 3.444, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2724132463902756e-05, + "loss": 3.4626, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715762895195965e-05, + "loss": 3.4637, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707376947685445e-05, + "loss": 3.4628, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698991000174925e-05, + "loss": 3.457, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.269060505266441e-05, + "loss": 3.4607, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682235483957618e-05, + "loss": 3.457, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673849536447098e-05, + "loss": 3.468, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665463588936578e-05, + "loss": 3.4666, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2657077641426058e-05, + "loss": 3.4731, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.264870807271927e-05, + "loss": 3.4526, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.264032212520875e-05, + "loss": 3.4639, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.263193617769823e-05, + "loss": 3.4678, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.262355023018771e-05, + "loss": 3.46, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.261518066148092e-05, + "loss": 3.4615, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.26067947139704e-05, + "loss": 3.471, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.259840876645988e-05, + "loss": 3.4654, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2590022818949362e-05, + "loss": 3.4777, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258165325024257e-05, + "loss": 3.461, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257326730273205e-05, + "loss": 3.4654, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256488135522153e-05, + "loss": 3.461, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255649540771101e-05, + "loss": 3.4615, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2548125839004224e-05, + "loss": 3.4574, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539739891493704e-05, + "loss": 3.4598, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531353943983184e-05, + "loss": 3.4656, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.2522967996472664e-05, + "loss": 3.4454, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251458204896214e-05, + "loss": 3.4649, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8618083000183105, + "eval_runtime": 304.303, + "eval_samples_per_second": 1253.984, + "eval_steps_per_second": 39.188, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2506212480255353e-05, + "loss": 3.4622, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497826532744833e-05, + "loss": 3.4556, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2489440585234316e-05, + "loss": 3.4645, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.2481054637723792e-05, + "loss": 3.469, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472685069017005e-05, + "loss": 3.4774, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464299121506485e-05, + "loss": 3.4619, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.245591317399596e-05, + "loss": 3.4618, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244752722648544e-05, + "loss": 3.4493, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.2439157657778657e-05, + "loss": 3.463, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.2430771710268137e-05, + "loss": 3.4589, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.2422385762757614e-05, + "loss": 3.461, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.2413999815247094e-05, + "loss": 3.4565, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405630246540306e-05, + "loss": 3.4575, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397244299029786e-05, + "loss": 3.4553, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388858351519266e-05, + "loss": 3.4554, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380472404008746e-05, + "loss": 3.4473, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237210283530196e-05, + "loss": 3.4499, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363716887791435e-05, + "loss": 3.4574, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355330940280915e-05, + "loss": 3.4579, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346944992770395e-05, + "loss": 3.4688, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233857542406361e-05, + "loss": 3.4643, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330189476553088e-05, + "loss": 3.4712, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321803529042568e-05, + "loss": 3.4495, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313417581532047e-05, + "loss": 3.4613, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.230504801282526e-05, + "loss": 3.4569, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.229666206531474e-05, + "loss": 3.4684, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.228827611780422e-05, + "loss": 3.4548, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.22798901702937e-05, + "loss": 3.458, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.227152060158691e-05, + "loss": 3.4498, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.226313465407639e-05, + "loss": 3.4556, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.225474870656587e-05, + "loss": 3.4589, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.224636275905535e-05, + "loss": 3.4677, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223799319034856e-05, + "loss": 3.4692, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222960724283804e-05, + "loss": 3.4633, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.222122129532752e-05, + "loss": 3.4557, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212835347817e-05, + "loss": 3.4612, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.220446577911021e-05, + "loss": 3.4619, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2196079831599694e-05, + "loss": 3.452, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187693884089174e-05, + "loss": 3.4475, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2179307936578653e-05, + "loss": 3.4441, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170938367871863e-05, + "loss": 3.4521, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2162552420361343e-05, + "loss": 3.4591, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2154166472850823e-05, + "loss": 3.46, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.2145780525340302e-05, + "loss": 3.4532, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137410956633515e-05, + "loss": 3.4552, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2129025009122995e-05, + "loss": 3.4562, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120639061612475e-05, + "loss": 3.4557, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.2112253114101955e-05, + "loss": 3.446, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103883545395164e-05, + "loss": 3.4294, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2095497597884647e-05, + "loss": 3.4703, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2087111650374127e-05, + "loss": 3.4581, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078725702863607e-05, + "loss": 3.4655, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070356134156816e-05, + "loss": 3.4529, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061970186646296e-05, + "loss": 3.4559, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053584239135776e-05, + "loss": 3.4456, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045198291625256e-05, + "loss": 3.4529, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203682872291847e-05, + "loss": 3.4571, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.202844277540795e-05, + "loss": 3.4514, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.202005682789743e-05, + "loss": 3.4751, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.201167088038691e-05, + "loss": 3.4509, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003301311680118e-05, + "loss": 3.4421, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.19949153641696e-05, + "loss": 3.4645, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198652941665908e-05, + "loss": 3.4402, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197814346914856e-05, + "loss": 3.4382, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.196977390044177e-05, + "loss": 3.4651, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.196138795293125e-05, + "loss": 3.4592, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.195300200542073e-05, + "loss": 3.4461, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.194461605791021e-05, + "loss": 3.4533, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936246489203422e-05, + "loss": 3.4372, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927860541692902e-05, + "loss": 3.4494, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1919474594182382e-05, + "loss": 3.4527, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191108864667186e-05, + "loss": 3.4463, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190271907796507e-05, + "loss": 3.4558, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1894333130454555e-05, + "loss": 3.4544, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885947182944035e-05, + "loss": 3.4681, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187756123543351e-05, + "loss": 3.4492, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1869191666726724e-05, + "loss": 3.4532, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860805719216204e-05, + "loss": 3.4556, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1852419771705684e-05, + "loss": 3.4461, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1844033824195163e-05, + "loss": 3.4607, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1835664255488376e-05, + "loss": 3.4583, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827278307977856e-05, + "loss": 3.4521, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818892360467332e-05, + "loss": 3.4612, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810506412956812e-05, + "loss": 3.4373, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1802136844250025e-05, + "loss": 3.4404, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793750896739505e-05, + "loss": 3.4558, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785364949228985e-05, + "loss": 3.454, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776979001718465e-05, + "loss": 3.446, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768609433011677e-05, + "loss": 3.4538, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760223485501157e-05, + "loss": 3.4374, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.1751837537990634e-05, + "loss": 3.4471, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743451590480117e-05, + "loss": 3.4409, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173508202177333e-05, + "loss": 3.4522, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726696074262806e-05, + "loss": 3.4637, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718310126752286e-05, + "loss": 3.4561, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709924179241766e-05, + "loss": 3.4575, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.170155461053498e-05, + "loss": 3.4458, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.169316866302446e-05, + "loss": 3.4506, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168478271551394e-05, + "loss": 3.4468, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167639676800342e-05, + "loss": 3.4609, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166802719929663e-05, + "loss": 3.4534, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659641251786107e-05, + "loss": 3.4593, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651255304275587e-05, + "loss": 3.4446, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.164286935676507e-05, + "loss": 3.4578, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.163449978805828e-05, + "loss": 3.4472, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.162611384054776e-05, + "loss": 3.4527, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.161772789303724e-05, + "loss": 3.4435, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160934194552672e-05, + "loss": 3.4559, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600988755623665e-05, + "loss": 3.4447, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592602808113145e-05, + "loss": 3.4529, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584216860602625e-05, + "loss": 3.4424, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575830913092105e-05, + "loss": 3.4566, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.156744496558158e-05, + "loss": 3.4469, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155905901807106e-05, + "loss": 3.4463, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155067307056054e-05, + "loss": 3.46, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1542287123050024e-05, + "loss": 3.4628, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533917554343234e-05, + "loss": 3.4573, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1525531606832714e-05, + "loss": 3.452, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1517145659322193e-05, + "loss": 3.4466, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508759711811673e-05, + "loss": 3.4464, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1500390143104886e-05, + "loss": 3.4498, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1492004195594366e-05, + "loss": 3.4535, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483618248083846e-05, + "loss": 3.4384, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475232300573326e-05, + "loss": 3.451, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466862731866535e-05, + "loss": 3.4524, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458476784356015e-05, + "loss": 3.4517, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.1450090836845495e-05, + "loss": 3.4484, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441704889334978e-05, + "loss": 3.4477, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433335320628187e-05, + "loss": 3.4457, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424949373117667e-05, + "loss": 3.458, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416563425607147e-05, + "loss": 3.4558, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408177478096627e-05, + "loss": 3.4586, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139980790938984e-05, + "loss": 3.4439, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139142196187932e-05, + "loss": 3.4539, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.13830360143688e-05, + "loss": 3.4551, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.137465006685828e-05, + "loss": 3.4489, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136628049815149e-05, + "loss": 3.4537, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.135789455064097e-05, + "loss": 3.4552, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.134950860313045e-05, + "loss": 3.4547, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134112265561993e-05, + "loss": 3.4677, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133275308691314e-05, + "loss": 3.4469, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.132436713940262e-05, + "loss": 3.455, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.13159811918921e-05, + "loss": 3.4538, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.130759524438158e-05, + "loss": 3.4511, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.129922567567479e-05, + "loss": 3.4429, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290839728164273e-05, + "loss": 3.4449, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282453780653753e-05, + "loss": 3.451, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127406783314323e-05, + "loss": 3.4371, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265698264436442e-05, + "loss": 3.4552, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.86381196975708, + "eval_runtime": 306.2354, + "eval_samples_per_second": 1246.071, + "eval_steps_per_second": 38.941, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257312316925922e-05, + "loss": 3.4514, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1248926369415402e-05, + "loss": 3.4432, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240540421904882e-05, + "loss": 3.4526, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232154474394362e-05, + "loss": 3.4569, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.1223784905687575e-05, + "loss": 3.4648, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215398958177054e-05, + "loss": 3.4484, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.120701301066653e-05, + "loss": 3.4559, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.119862706315601e-05, + "loss": 3.4404, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.1190257494449227e-05, + "loss": 3.4435, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181871546938703e-05, + "loss": 3.454, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173485599428183e-05, + "loss": 3.4488, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165099651917663e-05, + "loss": 3.4423, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156730083210876e-05, + "loss": 3.456, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.1148344135700356e-05, + "loss": 3.4401, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.1139958188189836e-05, + "loss": 3.4401, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131572240679316e-05, + "loss": 3.438, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123186293168796e-05, + "loss": 3.4393, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114800345658276e-05, + "loss": 3.4493, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106414398147756e-05, + "loss": 3.4408, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098028450637236e-05, + "loss": 3.4623, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089658881930448e-05, + "loss": 3.4522, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081272934419928e-05, + "loss": 3.4583, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072886986909408e-05, + "loss": 3.4431, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064501039398884e-05, + "loss": 3.4455, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056131470692097e-05, + "loss": 3.4516, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047745523181577e-05, + "loss": 3.4538, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039359575671057e-05, + "loss": 3.4452, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1030973628160537e-05, + "loss": 3.4465, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.102260405945375e-05, + "loss": 3.4374, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.101421811194323e-05, + "loss": 3.4456, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.100583216443271e-05, + "loss": 3.4482, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997446216922186e-05, + "loss": 3.4556, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.09890766482154e-05, + "loss": 3.4551, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.098069070070488e-05, + "loss": 3.4534, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972304753194358e-05, + "loss": 3.4473, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0963918805683838e-05, + "loss": 3.4473, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095554923697705e-05, + "loss": 3.4524, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094716328946653e-05, + "loss": 3.4426, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.093877734195601e-05, + "loss": 3.438, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.093039139444549e-05, + "loss": 3.4327, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.0922021825738703e-05, + "loss": 3.4399, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.0913635878228183e-05, + "loss": 3.4453, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090524993071766e-05, + "loss": 3.4532, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089686398320714e-05, + "loss": 3.4454, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888494414500352e-05, + "loss": 3.4432, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880108466989832e-05, + "loss": 3.4464, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.0871722519479312e-05, + "loss": 3.4472, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.0863336571968792e-05, + "loss": 3.4348, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.0854967003262004e-05, + "loss": 3.4208, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084658105575148e-05, + "loss": 3.4544, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.0838195108240964e-05, + "loss": 3.45, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.0829809160730444e-05, + "loss": 3.4567, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.0821439592023653e-05, + "loss": 3.4412, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813070023316866e-05, + "loss": 3.4426, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804684075806346e-05, + "loss": 3.4358, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796298128295826e-05, + "loss": 3.4405, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787912180785306e-05, + "loss": 3.45, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.0779526233274786e-05, + "loss": 3.4346, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.0771140285764266e-05, + "loss": 3.4676, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762754338253745e-05, + "loss": 3.4458, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754368390743225e-05, + "loss": 3.4274, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.0745998822036435e-05, + "loss": 3.4555, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.0737612874525918e-05, + "loss": 3.4293, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.0729226927015398e-05, + "loss": 3.4275, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.0720840979504878e-05, + "loss": 3.4538, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712471410798087e-05, + "loss": 3.4471, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704085463287567e-05, + "loss": 3.4371, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695699515777047e-05, + "loss": 3.4401, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687313568266527e-05, + "loss": 3.4292, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.067894399955974e-05, + "loss": 3.4377, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.067055805204922e-05, + "loss": 3.442, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.06621721045387e-05, + "loss": 3.4372, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.065378615702818e-05, + "loss": 3.445, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645416588321388e-05, + "loss": 3.4418, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.063703064081087e-05, + "loss": 3.4551, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.062864469330035e-05, + "loss": 3.4403, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.062025874578983e-05, + "loss": 3.444, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.061188917708304e-05, + "loss": 3.4433, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.060350322957252e-05, + "loss": 3.4369, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595117282062e-05, + "loss": 3.4513, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.058673133455148e-05, + "loss": 3.4465, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578361765844693e-05, + "loss": 3.4378, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0569975818334173e-05, + "loss": 3.4519, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561589870823653e-05, + "loss": 3.4257, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553203923313133e-05, + "loss": 3.4261, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544834354606342e-05, + "loss": 3.4477, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536448407095825e-05, + "loss": 3.4423, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528062459585305e-05, + "loss": 3.4359, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519676512074782e-05, + "loss": 3.4466, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511306943367994e-05, + "loss": 3.4283, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502920995857474e-05, + "loss": 3.4335, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.0494535048346954e-05, + "loss": 3.4326, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.0486149100836434e-05, + "loss": 3.4371, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477779532129647e-05, + "loss": 3.4538, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469393584619127e-05, + "loss": 3.4433, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461007637108606e-05, + "loss": 3.4504, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452621689598083e-05, + "loss": 3.4343, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444252120891296e-05, + "loss": 3.437, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435866173380775e-05, + "loss": 3.4376, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.0427480225870255e-05, + "loss": 3.4465, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419094278359735e-05, + "loss": 3.4427, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410724709652948e-05, + "loss": 3.4488, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402338762142428e-05, + "loss": 3.4372, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393952814631904e-05, + "loss": 3.4415, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.0385566867121388e-05, + "loss": 3.4413, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.03771972984146e-05, + "loss": 3.4403, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036881135090408e-05, + "loss": 3.4302, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.0360425403393557e-05, + "loss": 3.4487, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035205583468677e-05, + "loss": 3.433, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034366988717625e-05, + "loss": 3.4396, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033528393966573e-05, + "loss": 3.431, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032689799215521e-05, + "loss": 3.4429, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031851204464469e-05, + "loss": 3.4383, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031012609713417e-05, + "loss": 3.4355, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030174014962365e-05, + "loss": 3.4453, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029335420211313e-05, + "loss": 3.4533, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.028498463340634e-05, + "loss": 3.4506, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.027659868589582e-05, + "loss": 3.4395, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.02682127383853e-05, + "loss": 3.4382, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.025982679087478e-05, + "loss": 3.436, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.025145722216799e-05, + "loss": 3.4398, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.024307127465747e-05, + "loss": 3.4398, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.023468532714695e-05, + "loss": 3.4279, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226299379636434e-05, + "loss": 3.4392, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217929810929643e-05, + "loss": 3.4459, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209543863419123e-05, + "loss": 3.4361, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201157915908603e-05, + "loss": 3.4366, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192771968398083e-05, + "loss": 3.4396, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184402399691295e-05, + "loss": 3.4369, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176016452180775e-05, + "loss": 3.4449, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167630504670255e-05, + "loss": 3.4415, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.015924455715973e-05, + "loss": 3.4489, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150874988452944e-05, + "loss": 3.432, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142489040942424e-05, + "loss": 3.4427, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134103093431904e-05, + "loss": 3.4444, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125717145921384e-05, + "loss": 3.44, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117347577214596e-05, + "loss": 3.4413, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108961629704076e-05, + "loss": 3.4418, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100575682193556e-05, + "loss": 3.4454, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092189734683033e-05, + "loss": 3.4587, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083820165976245e-05, + "loss": 3.4342, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007543421846573e-05, + "loss": 3.4475, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067048270955205e-05, + "loss": 3.4407, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058662323444685e-05, + "loss": 3.4397, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050292754737898e-05, + "loss": 3.4343, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041906807227378e-05, + "loss": 3.4361, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033520859716858e-05, + "loss": 3.4435, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025134912206338e-05, + "loss": 3.4271, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001676534349955e-05, + "loss": 3.4422, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.863616466522217, + "eval_runtime": 303.5705, + "eval_samples_per_second": 1257.009, + "eval_steps_per_second": 39.282, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.000837939598903e-05, + "loss": 3.4385, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999993448478507e-05, + "loss": 3.435, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991607500967987e-05, + "loss": 3.4418, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.99832379322612e-05, + "loss": 3.4447, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997485198475068e-05, + "loss": 3.4514, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996646603724016e-05, + "loss": 3.4384, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995808008972964e-05, + "loss": 3.4469, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994971052102285e-05, + "loss": 3.4295, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.9941324573512328e-05, + "loss": 3.4338, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993293862600181e-05, + "loss": 3.4435, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992455267849129e-05, + "loss": 3.4379, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.9916183109784504e-05, + "loss": 3.4315, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.9907813541077713e-05, + "loss": 3.4467, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.9899427593567193e-05, + "loss": 3.4267, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.9891041646056673e-05, + "loss": 3.4312, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.9882655698546153e-05, + "loss": 3.4213, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874269751035633e-05, + "loss": 3.4313, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9865883803525113e-05, + "loss": 3.4399, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.9857497856014593e-05, + "loss": 3.4298, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.9849111908504073e-05, + "loss": 3.4492, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984074233979728e-05, + "loss": 3.4437, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832356392286765e-05, + "loss": 3.4439, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823970444776245e-05, + "loss": 3.4357, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815584497265725e-05, + "loss": 3.439, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807214928558934e-05, + "loss": 3.4412, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798828981048414e-05, + "loss": 3.4411, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.9790443033537894e-05, + "loss": 3.4335, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.9782057086027374e-05, + "loss": 3.4381, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.9773687517320586e-05, + "loss": 3.4274, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765301569810066e-05, + "loss": 3.4354, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756915622299546e-05, + "loss": 3.4387, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748529674789026e-05, + "loss": 3.4408, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740160106082235e-05, + "loss": 3.4463, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.973177415857172e-05, + "loss": 3.4457, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.97233882110612e-05, + "loss": 3.4324, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.971500226355068e-05, + "loss": 3.4394, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.9706632694843888e-05, + "loss": 3.444, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698246747333368e-05, + "loss": 3.4286, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.968987717862658e-05, + "loss": 3.43, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.968149123111606e-05, + "loss": 3.4236, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.967310528360554e-05, + "loss": 3.4245, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.966471933609502e-05, + "loss": 3.4344, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.96563333885845e-05, + "loss": 3.4433, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.964794744107398e-05, + "loss": 3.4337, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639561493563456e-05, + "loss": 3.4303, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631175546052936e-05, + "loss": 3.4327, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622805977346152e-05, + "loss": 3.4403, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.961442002983563e-05, + "loss": 3.4221, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960603408232511e-05, + "loss": 3.4113, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959764813481459e-05, + "loss": 3.4403, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.95892785661078e-05, + "loss": 3.4378, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.958089261859728e-05, + "loss": 3.4443, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.957250667108676e-05, + "loss": 3.4299, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564137102379974e-05, + "loss": 3.4317, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.9555751154869454e-05, + "loss": 3.4263, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954736520735893e-05, + "loss": 3.4302, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953897925984841e-05, + "loss": 3.4393, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953059331233789e-05, + "loss": 3.4214, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.9522207364827373e-05, + "loss": 3.4575, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.9513821417316853e-05, + "loss": 3.43, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.9505435469806333e-05, + "loss": 3.415, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.9497065901099542e-05, + "loss": 3.4455, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.9488679953589022e-05, + "loss": 3.4236, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.9480294006078502e-05, + "loss": 3.4162, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9471908058567982e-05, + "loss": 3.4402, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.9463538489861195e-05, + "loss": 3.4368, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455152542350675e-05, + "loss": 3.4299, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446766594840155e-05, + "loss": 3.4258, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.9438380647329635e-05, + "loss": 3.4158, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9430011078622844e-05, + "loss": 3.4245, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421625131112327e-05, + "loss": 3.4348, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413239183601807e-05, + "loss": 3.4251, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404853236091284e-05, + "loss": 3.4325, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396483667384496e-05, + "loss": 3.4285, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388097719873976e-05, + "loss": 3.4461, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379711772363456e-05, + "loss": 3.4297, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371325824852936e-05, + "loss": 3.4371, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936295625614615e-05, + "loss": 3.4322, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935457030863563e-05, + "loss": 3.4266, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.934618436112511e-05, + "loss": 3.441, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337798413614585e-05, + "loss": 3.4319, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329428844907797e-05, + "loss": 3.4319, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.9321042897397277e-05, + "loss": 3.439, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312656949886757e-05, + "loss": 3.415, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304271002376237e-05, + "loss": 3.4188, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.929590143366945e-05, + "loss": 3.4326, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.928751548615893e-05, + "loss": 3.434, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279129538648406e-05, + "loss": 3.4199, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.927074359113789e-05, + "loss": 3.4374, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262374022431102e-05, + "loss": 3.4212, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9253988074920582e-05, + "loss": 3.4207, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.924560212741006e-05, + "loss": 3.4178, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.923721617989954e-05, + "loss": 3.4261, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.922884661119275e-05, + "loss": 3.4434, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.922046066368223e-05, + "loss": 3.4324, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.921207471617171e-05, + "loss": 3.4383, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.920368876866119e-05, + "loss": 3.425, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195319199954403e-05, + "loss": 3.4259, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.918693325244388e-05, + "loss": 3.4254, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.917854730493336e-05, + "loss": 3.4369, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170177736226576e-05, + "loss": 3.4315, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9161791788716056e-05, + "loss": 3.4345, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153405841205532e-05, + "loss": 3.4313, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9145019893695012e-05, + "loss": 3.4306, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136650324988225e-05, + "loss": 3.4297, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128264377477705e-05, + "loss": 3.427, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.9119878429967185e-05, + "loss": 3.4209, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111492482456665e-05, + "loss": 3.4367, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103139292553606e-05, + "loss": 3.424, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094753345043086e-05, + "loss": 3.428, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086367397532566e-05, + "loss": 3.4256, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077981450022046e-05, + "loss": 3.4258, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.906959550251153e-05, + "loss": 3.4295, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.9061209555001006e-05, + "loss": 3.425, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052823607490486e-05, + "loss": 3.4374, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044437659979966e-05, + "loss": 3.4409, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.9036068091273175e-05, + "loss": 3.4397, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.902768214376266e-05, + "loss": 3.428, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901929619625214e-05, + "loss": 3.4314, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.9010910248741618e-05, + "loss": 3.4256, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.9002540680034827e-05, + "loss": 3.4303, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.8994154732524307e-05, + "loss": 3.4315, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.8985768785013787e-05, + "loss": 3.4195, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977382837503267e-05, + "loss": 3.4253, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896901326879648e-05, + "loss": 3.4331, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896062732128596e-05, + "loss": 3.4299, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895224137377544e-05, + "loss": 3.425, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894385542626492e-05, + "loss": 3.4262, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.893548585755813e-05, + "loss": 3.4258, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.8927099910047612e-05, + "loss": 3.4349, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918713962537092e-05, + "loss": 3.4305, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910328015026572e-05, + "loss": 3.4415, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.890195844631978e-05, + "loss": 3.4202, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889357249880926e-05, + "loss": 3.4301, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888518655129874e-05, + "loss": 3.4354, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.887680060378822e-05, + "loss": 3.4309, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868431035081433e-05, + "loss": 3.4286, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8860045087570913e-05, + "loss": 3.4325, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851659140060393e-05, + "loss": 3.4317, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843273192549873e-05, + "loss": 3.4464, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8834903623843082e-05, + "loss": 3.427, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826517676332566e-05, + "loss": 3.4316, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818131728822046e-05, + "loss": 3.4339, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8809745781311526e-05, + "loss": 3.4242, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801359833801006e-05, + "loss": 3.4248, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8792990265094215e-05, + "loss": 3.4235, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784604317583695e-05, + "loss": 3.4293, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776218370073175e-05, + "loss": 3.421, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8767832422562655e-05, + "loss": 3.4279, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.866431713104248, + "eval_runtime": 303.2925, + "eval_samples_per_second": 1258.162, + "eval_steps_per_second": 39.318, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759462853855867e-05, + "loss": 3.425, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8751076906345347e-05, + "loss": 3.4223, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742690958834827e-05, + "loss": 3.43, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734305011324304e-05, + "loss": 3.4391, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8725935442617516e-05, + "loss": 3.4449, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.8717549495107e-05, + "loss": 3.4282, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870916354759648e-05, + "loss": 3.4322, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.8700777600085956e-05, + "loss": 3.4224, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.869240803137917e-05, + "loss": 3.423, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8684022083868648e-05, + "loss": 3.4305, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675636136358128e-05, + "loss": 3.4298, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667250188847608e-05, + "loss": 3.4213, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.865888062014082e-05, + "loss": 3.4365, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.86504946726303e-05, + "loss": 3.4165, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8642108725119777e-05, + "loss": 3.4206, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633722777609257e-05, + "loss": 3.4103, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.862535320890247e-05, + "loss": 3.4246, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8616967261391953e-05, + "loss": 3.4298, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.860858131388143e-05, + "loss": 3.4178, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.860019536637091e-05, + "loss": 3.4353, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.8591825797664122e-05, + "loss": 3.4322, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.85834398501536e-05, + "loss": 3.4368, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.8575053902643082e-05, + "loss": 3.4248, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.8566667955132562e-05, + "loss": 3.4273, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558298386425774e-05, + "loss": 3.4294, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854991243891525e-05, + "loss": 3.4351, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.854152649140473e-05, + "loss": 3.4193, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853314054389421e-05, + "loss": 3.4279, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.8524770975187423e-05, + "loss": 3.4168, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516385027676903e-05, + "loss": 3.4228, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.8507999080166383e-05, + "loss": 3.4313, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.8499613132655863e-05, + "loss": 3.4308, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.8491243563949072e-05, + "loss": 3.428, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.8482857616438552e-05, + "loss": 3.4389, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.8474471668928036e-05, + "loss": 3.425, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.8466085721417516e-05, + "loss": 3.4264, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457716152710725e-05, + "loss": 3.4314, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449330205200205e-05, + "loss": 3.4165, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440960636493417e-05, + "loss": 3.4196, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432574688982897e-05, + "loss": 3.4181, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424188741472377e-05, + "loss": 3.4151, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.8415802793961857e-05, + "loss": 3.4202, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407416846451337e-05, + "loss": 3.4375, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8399030898940817e-05, + "loss": 3.4224, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390644951430297e-05, + "loss": 3.4204, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382259003919777e-05, + "loss": 3.4207, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.8373889435212986e-05, + "loss": 3.4282, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836550348770247e-05, + "loss": 3.4114, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.835711754019195e-05, + "loss": 3.4026, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.834873159268143e-05, + "loss": 3.4322, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340362023974638e-05, + "loss": 3.4283, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331976076464118e-05, + "loss": 3.4377, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323590128953598e-05, + "loss": 3.4185, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315204181443078e-05, + "loss": 3.4178, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.830683461273629e-05, + "loss": 3.4168, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.829844866522577e-05, + "loss": 3.4178, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.829006271771525e-05, + "loss": 3.4342, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281676770204727e-05, + "loss": 3.407, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.827330720149794e-05, + "loss": 3.4468, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264921253987423e-05, + "loss": 3.4245, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256535306476903e-05, + "loss": 3.4017, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.824814935896638e-05, + "loss": 3.4302, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8239779790259592e-05, + "loss": 3.4157, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231393842749072e-05, + "loss": 3.405, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8223007895238552e-05, + "loss": 3.4271, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214621947728032e-05, + "loss": 3.431, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206252379021244e-05, + "loss": 3.416, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8197866431510724e-05, + "loss": 3.4185, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.81894804840002e-05, + "loss": 3.4062, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818109453648968e-05, + "loss": 3.415, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.8172724967782893e-05, + "loss": 3.4225, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164339020272377e-05, + "loss": 3.4133, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8155953072761853e-05, + "loss": 3.4246, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147567125251333e-05, + "loss": 3.4143, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.8139197556544546e-05, + "loss": 3.4382, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.8130811609034022e-05, + "loss": 3.417, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.8122425661523505e-05, + "loss": 3.4278, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8114039714012985e-05, + "loss": 3.4205, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105670145306198e-05, + "loss": 3.4176, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097284197795674e-05, + "loss": 3.4275, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088898250285154e-05, + "loss": 3.419, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.8080512302774634e-05, + "loss": 3.4252, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.8072142734067847e-05, + "loss": 3.4254, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.8063756786557327e-05, + "loss": 3.4105, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.8055370839046807e-05, + "loss": 3.401, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046984891536287e-05, + "loss": 3.4222, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038615322829496e-05, + "loss": 3.4241, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.8030229375318976e-05, + "loss": 3.4114, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.802184342780846e-05, + "loss": 3.4231, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801345748029794e-05, + "loss": 3.4119, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.8005087911591148e-05, + "loss": 3.4122, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.7996701964080628e-05, + "loss": 3.4082, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.7988316016570108e-05, + "loss": 3.4176, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.797994644786332e-05, + "loss": 3.4299, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.79715605003528e-05, + "loss": 3.422, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.796317455284228e-05, + "loss": 3.4271, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795478860533176e-05, + "loss": 3.415, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794641903662497e-05, + "loss": 3.4157, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793803308911445e-05, + "loss": 3.4166, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.792964714160393e-05, + "loss": 3.4247, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.792126119409341e-05, + "loss": 3.4198, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912891625386622e-05, + "loss": 3.4272, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904505677876102e-05, + "loss": 3.4201, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7896119730365582e-05, + "loss": 3.4167, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887733782855062e-05, + "loss": 3.4224, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879364214148274e-05, + "loss": 3.4168, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870978266637754e-05, + "loss": 3.4148, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862592319127234e-05, + "loss": 3.4234, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7854206371616714e-05, + "loss": 3.4145, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845836802909923e-05, + "loss": 3.4159, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.7837450855399403e-05, + "loss": 3.4146, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7829064907888883e-05, + "loss": 3.4143, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820678960378363e-05, + "loss": 3.4224, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812293012867846e-05, + "loss": 3.4131, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803907065357326e-05, + "loss": 3.424, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795521117846803e-05, + "loss": 3.4284, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7787151549140015e-05, + "loss": 3.4312, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778765601629495e-05, + "loss": 3.4181, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.7770379654118975e-05, + "loss": 3.4193, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.7761993706608455e-05, + "loss": 3.4117, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.7753624137901668e-05, + "loss": 3.4246, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745238190391148e-05, + "loss": 3.4189, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736852242880624e-05, + "loss": 3.4073, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728466295370104e-05, + "loss": 3.4152, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.7720096726663317e-05, + "loss": 3.4213, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.77117107791528e-05, + "loss": 3.4237, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703324831642277e-05, + "loss": 3.4147, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7694938884131757e-05, + "loss": 3.4139, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.768656931542497e-05, + "loss": 3.4134, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767818336791445e-05, + "loss": 3.4287, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.766979742040393e-05, + "loss": 3.418, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.766141147289341e-05, + "loss": 3.4307, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765304190418662e-05, + "loss": 3.4123, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.7644655956676098e-05, + "loss": 3.4191, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.7636270009165578e-05, + "loss": 3.4274, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627884061655058e-05, + "loss": 3.4178, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.761951449294827e-05, + "loss": 3.4178, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.761112854543775e-05, + "loss": 3.4192, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.760274259792723e-05, + "loss": 3.4276, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759435665041671e-05, + "loss": 3.4313, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758598708170992e-05, + "loss": 3.4197, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.75776011341994e-05, + "loss": 3.4203, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.7569215186688883e-05, + "loss": 3.4261, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.7560829239178363e-05, + "loss": 3.4131, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.7552459670471572e-05, + "loss": 3.4158, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754407372296105e-05, + "loss": 3.4138, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753568777545053e-05, + "loss": 3.4174, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.752730182794001e-05, + "loss": 3.4138, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.7518932259233224e-05, + "loss": 3.4158, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.8669962882995605, + "eval_runtime": 303.7727, + "eval_samples_per_second": 1256.173, + "eval_steps_per_second": 39.256, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510546311722704e-05, + "loss": 3.4165, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7502160364212184e-05, + "loss": 3.4113, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493774416701664e-05, + "loss": 3.4169, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485404847994873e-05, + "loss": 3.427, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.7477018900484353e-05, + "loss": 3.4355, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7468632952973833e-05, + "loss": 3.4181, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460247005463316e-05, + "loss": 3.4251, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451877436756525e-05, + "loss": 3.411, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443491489246005e-05, + "loss": 3.4117, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7435105541735485e-05, + "loss": 3.4156, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426719594224965e-05, + "loss": 3.4237, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.7418350025518178e-05, + "loss": 3.4148, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.740998045681139e-05, + "loss": 3.422, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7401594509300867e-05, + "loss": 3.4057, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7393208561790347e-05, + "loss": 3.41, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384822614279827e-05, + "loss": 3.3973, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376436666769307e-05, + "loss": 3.4166, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7368050719258787e-05, + "loss": 3.4171, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.735966477174827e-05, + "loss": 3.4073, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735127882423775e-05, + "loss": 3.4233, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.734290925553096e-05, + "loss": 3.4241, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.733452330802044e-05, + "loss": 3.4247, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.732613736050992e-05, + "loss": 3.4146, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.73177514129994e-05, + "loss": 3.4149, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.730938184429261e-05, + "loss": 3.4221, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.730099589678209e-05, + "loss": 3.4224, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.729260994927157e-05, + "loss": 3.4084, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7284224001761048e-05, + "loss": 3.4158, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.727585443305426e-05, + "loss": 3.4088, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.726746848554374e-05, + "loss": 3.4077, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7259082538033224e-05, + "loss": 3.4196, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.72506965905227e-05, + "loss": 3.4207, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242327021815913e-05, + "loss": 3.4194, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7233941074305393e-05, + "loss": 3.4259, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7225555126794873e-05, + "loss": 3.4138, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7217169179284353e-05, + "loss": 3.4186, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208783231773833e-05, + "loss": 3.4229, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200397284263312e-05, + "loss": 3.4045, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7192011336752792e-05, + "loss": 3.4069, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183625389242272e-05, + "loss": 3.4085, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.717525582053548e-05, + "loss": 3.4009, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716686987302496e-05, + "loss": 3.4103, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.715848392551444e-05, + "loss": 3.4259, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7150097978003925e-05, + "loss": 3.408, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141728409297134e-05, + "loss": 3.4104, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.7133342461786614e-05, + "loss": 3.4153, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.7124956514276094e-05, + "loss": 3.4175, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.7116570566765574e-05, + "loss": 3.3995, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7108200998058786e-05, + "loss": 3.3928, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099815050548266e-05, + "loss": 3.42, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091429103037746e-05, + "loss": 3.418, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7083043155527226e-05, + "loss": 3.4289, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.7074673586820435e-05, + "loss": 3.4074, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.7066287639309915e-05, + "loss": 3.4072, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.7057901691799395e-05, + "loss": 3.4064, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704951574428888e-05, + "loss": 3.4062, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7041146175582087e-05, + "loss": 3.4239, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032760228071567e-05, + "loss": 3.394, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.7024374280561047e-05, + "loss": 3.4365, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7015988333050524e-05, + "loss": 3.4149, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.700761876434374e-05, + "loss": 3.3952, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.699923281683322e-05, + "loss": 3.4176, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.69908468693227e-05, + "loss": 3.4052, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.6982460921812176e-05, + "loss": 3.3952, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697409135310539e-05, + "loss": 3.4166, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.696570540559487e-05, + "loss": 3.4197, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.695731945808435e-05, + "loss": 3.4028, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694893351057383e-05, + "loss": 3.4155, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694056394186704e-05, + "loss": 3.3943, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693217799435652e-05, + "loss": 3.4036, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6923792046845998e-05, + "loss": 3.408, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915406099335478e-05, + "loss": 3.4066, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6907036530628694e-05, + "loss": 3.4116, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898650583118173e-05, + "loss": 3.4078, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.689026463560765e-05, + "loss": 3.4284, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.688187868809713e-05, + "loss": 3.4089, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873509119390342e-05, + "loss": 3.4196, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6865123171879822e-05, + "loss": 3.4069, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6856737224369302e-05, + "loss": 3.405, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848351276858782e-05, + "loss": 3.4181, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6839981708151995e-05, + "loss": 3.4063, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.683159576064147e-05, + "loss": 3.4139, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682320981313095e-05, + "loss": 3.4204, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.681482386562043e-05, + "loss": 3.4034, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806454296913647e-05, + "loss": 3.3914, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6798068349403124e-05, + "loss": 3.4093, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789698780696336e-05, + "loss": 3.4149, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6781312833185816e-05, + "loss": 3.398, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6772926885675296e-05, + "loss": 3.4143, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764540938164776e-05, + "loss": 3.4055, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6756154990654256e-05, + "loss": 3.3974, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747769043143736e-05, + "loss": 3.3988, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739383095633216e-05, + "loss": 3.406, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6730997148122696e-05, + "loss": 3.4216, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722627579415905e-05, + "loss": 3.4105, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6714241631905385e-05, + "loss": 3.4162, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705855684394865e-05, + "loss": 3.4051, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697469736884348e-05, + "loss": 3.4055, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6689100168177557e-05, + "loss": 3.4062, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680714220667037e-05, + "loss": 3.4126, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672328273156517e-05, + "loss": 3.4123, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6663942325645997e-05, + "loss": 3.4158, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.665557275693921e-05, + "loss": 3.4113, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.664718680942869e-05, + "loss": 3.4032, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.663880086191817e-05, + "loss": 3.4152, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.663041491440765e-05, + "loss": 3.4081, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.662204534570086e-05, + "loss": 3.4035, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.661365939819034e-05, + "loss": 3.4094, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.660527345067982e-05, + "loss": 3.4077, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.659690388197303e-05, + "loss": 3.4068, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.658851793446251e-05, + "loss": 3.4023, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.658013198695199e-05, + "loss": 3.403, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657174603944147e-05, + "loss": 3.4113, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656336009193095e-05, + "loss": 3.4098, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.655497414442043e-05, + "loss": 3.4063, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654658819690991e-05, + "loss": 3.4164, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653820224939939e-05, + "loss": 3.4222, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.65298326806926e-05, + "loss": 3.4078, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.652144673318208e-05, + "loss": 3.4124, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651306078567156e-05, + "loss": 3.4005, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504691216964772e-05, + "loss": 3.4107, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6496305269454252e-05, + "loss": 3.4088, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487919321943732e-05, + "loss": 3.4007, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479533374433212e-05, + "loss": 3.3998, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6471163805726425e-05, + "loss": 3.413, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.64627778582159e-05, + "loss": 3.4109, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454391910705385e-05, + "loss": 3.4021, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.6446005963194864e-05, + "loss": 3.4036, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.6437636394488074e-05, + "loss": 3.4083, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.6429250446977554e-05, + "loss": 3.4134, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420864499467033e-05, + "loss": 3.4108, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.6412478551956513e-05, + "loss": 3.4207, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6404108983249726e-05, + "loss": 3.4004, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395723035739206e-05, + "loss": 3.4089, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6387337088228686e-05, + "loss": 3.4158, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6378951140718166e-05, + "loss": 3.4038, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370581572011375e-05, + "loss": 3.4079, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6362195624500855e-05, + "loss": 3.4118, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353809676990338e-05, + "loss": 3.4184, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345423729479818e-05, + "loss": 3.4185, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6337054160773027e-05, + "loss": 3.4096, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328668213262507e-05, + "loss": 3.4104, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6320282265751987e-05, + "loss": 3.4137, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6311896318241467e-05, + "loss": 3.4027, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.630352674953468e-05, + "loss": 3.405, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.629514080202416e-05, + "loss": 3.4051, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.628675485451364e-05, + "loss": 3.4021, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.627836890700312e-05, + "loss": 3.4093, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.626999933829633e-05, + "loss": 3.4032, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.869433879852295, + "eval_runtime": 303.3489, + "eval_samples_per_second": 1257.928, + "eval_steps_per_second": 39.311, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.626161339078581e-05, + "loss": 3.4005, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.625322744327529e-05, + "loss": 3.4035, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244841495764772e-05, + "loss": 3.4105, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236455548254252e-05, + "loss": 3.4138, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.622808597954746e-05, + "loss": 3.4215, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.621970003203694e-05, + "loss": 3.4095, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.621131408452642e-05, + "loss": 3.4156, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.62029281370159e-05, + "loss": 3.401, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.6194558568309113e-05, + "loss": 3.3988, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.6186172620798593e-05, + "loss": 3.4049, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.6177786673288073e-05, + "loss": 3.4178, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616940072577755e-05, + "loss": 3.4031, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6161047535874495e-05, + "loss": 3.4149, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152661588363975e-05, + "loss": 3.3937, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6144275640853455e-05, + "loss": 3.4005, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.6135889693342935e-05, + "loss": 3.3894, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.6127503745832415e-05, + "loss": 3.4063, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6119117798321894e-05, + "loss": 3.4049, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110731850811374e-05, + "loss": 3.4015, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6102345903300854e-05, + "loss": 3.4039, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.6093976334594067e-05, + "loss": 3.4165, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085590387083547e-05, + "loss": 3.4116, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6077204439573023e-05, + "loss": 3.4055, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068818492062503e-05, + "loss": 3.404, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.6060448923355716e-05, + "loss": 3.4159, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.6052062975845196e-05, + "loss": 3.4082, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.6043677028334676e-05, + "loss": 3.3999, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6035291080824156e-05, + "loss": 3.4072, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.6026921512117368e-05, + "loss": 3.3992, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.6018535564606848e-05, + "loss": 3.3944, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.6010149617096325e-05, + "loss": 3.4104, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.6001763669585808e-05, + "loss": 3.4065, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.599341047968275e-05, + "loss": 3.4141, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598502453217223e-05, + "loss": 3.4143, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597663858466171e-05, + "loss": 3.4018, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.596825263715119e-05, + "loss": 3.4085, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.595986668964067e-05, + "loss": 3.4117, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.595148074213015e-05, + "loss": 3.3979, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.594309479461963e-05, + "loss": 3.4023, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.593470884710911e-05, + "loss": 3.3924, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5926339278402322e-05, + "loss": 3.3924, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.59179533308918e-05, + "loss": 3.4015, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.590956738338128e-05, + "loss": 3.4177, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5901181435870762e-05, + "loss": 3.4015, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.589281186716397e-05, + "loss": 3.3969, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.588442591965345e-05, + "loss": 3.4062, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.587603997214293e-05, + "loss": 3.4033, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.586765402463241e-05, + "loss": 3.3923, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5859284455925623e-05, + "loss": 3.3813, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850898508415103e-05, + "loss": 3.4069, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842512560904583e-05, + "loss": 3.4119, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5834126613394063e-05, + "loss": 3.415, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825757044687272e-05, + "loss": 3.3992, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5817371097176752e-05, + "loss": 3.3967, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5808985149666232e-05, + "loss": 3.3975, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5800599202155712e-05, + "loss": 3.3954, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5792229633448924e-05, + "loss": 3.4145, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783843685938404e-05, + "loss": 3.3877, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775457738427884e-05, + "loss": 3.4213, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5767071790917364e-05, + "loss": 3.4047, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758702222210573e-05, + "loss": 3.3891, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5750316274700057e-05, + "loss": 3.4049, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741930327189537e-05, + "loss": 3.3971, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733544379679017e-05, + "loss": 3.3865, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5725174810972226e-05, + "loss": 3.4018, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.5716788863461706e-05, + "loss": 3.4101, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.5708402915951186e-05, + "loss": 3.395, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5700016968440666e-05, + "loss": 3.4038, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691647399733878e-05, + "loss": 3.383, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.5683261452223358e-05, + "loss": 3.3968, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.5674875504712838e-05, + "loss": 3.397, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.5666489557202318e-05, + "loss": 3.3993, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.5658119988495527e-05, + "loss": 3.397, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.564973404098501e-05, + "loss": 3.3994, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564134809347449e-05, + "loss": 3.4154, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.56329785247677e-05, + "loss": 3.4014, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.562459257725718e-05, + "loss": 3.4078, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.561620662974666e-05, + "loss": 3.3986, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560782068223614e-05, + "loss": 3.3951, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.5599451113529352e-05, + "loss": 3.4086, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.5591065166018832e-05, + "loss": 3.4002, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.5582679218508312e-05, + "loss": 3.4013, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.5574293270997792e-05, + "loss": 3.4067, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565923702291e-05, + "loss": 3.3971, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.555753775478048e-05, + "loss": 3.3773, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.5549151807269964e-05, + "loss": 3.3994, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.5540782238563173e-05, + "loss": 3.4024, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5532396291052653e-05, + "loss": 3.3924, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.5524010343542133e-05, + "loss": 3.4017, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.5515624396031613e-05, + "loss": 3.3965, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5507238448521093e-05, + "loss": 3.3883, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498852501010573e-05, + "loss": 3.3913, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490466553500053e-05, + "loss": 3.3956, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5482080605989533e-05, + "loss": 3.4066, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.5473711037282745e-05, + "loss": 3.4024, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.5465325089772222e-05, + "loss": 3.4085, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.5456939142261702e-05, + "loss": 3.3929, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.5448553194751182e-05, + "loss": 3.3954, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.5440183626044394e-05, + "loss": 3.3981, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431797678533874e-05, + "loss": 3.4034, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5423411731023354e-05, + "loss": 3.4013, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5415025783512834e-05, + "loss": 3.4046, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.5406656214806047e-05, + "loss": 3.3971, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5398270267295527e-05, + "loss": 3.393, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389884319785007e-05, + "loss": 3.4044, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381498372274487e-05, + "loss": 3.3971, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5373128803567696e-05, + "loss": 3.3981, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364742856057176e-05, + "loss": 3.3981, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5356356908546656e-05, + "loss": 3.3964, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5347987339839868e-05, + "loss": 3.3967, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339601392329348e-05, + "loss": 3.3894, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5331215444818828e-05, + "loss": 3.3923, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322829497308308e-05, + "loss": 3.4031, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5314443549797788e-05, + "loss": 3.4, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5306057602287268e-05, + "loss": 3.3958, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297671654776748e-05, + "loss": 3.4059, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5289285707266228e-05, + "loss": 3.4142, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.528091613855944e-05, + "loss": 3.3964, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.527253019104892e-05, + "loss": 3.3967, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.52641442435384e-05, + "loss": 3.3942, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255758296027878e-05, + "loss": 3.4018, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5247388727321091e-05, + "loss": 3.3963, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5239002779810571e-05, + "loss": 3.3921, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230616832300049e-05, + "loss": 3.3905, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5222247263593262e-05, + "loss": 3.4047, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213861316082742e-05, + "loss": 3.3966, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205475368572222e-05, + "loss": 3.3954, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.51970894210617e-05, + "loss": 3.3979, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188719852354912e-05, + "loss": 3.3998, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5180333904844394e-05, + "loss": 3.3958, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5171947957333874e-05, + "loss": 3.403, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.516356200982335e-05, + "loss": 3.4065, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5155192441116565e-05, + "loss": 3.3918, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.5146806493606045e-05, + "loss": 3.3987, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5138420546095521e-05, + "loss": 3.4064, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.5130034598585003e-05, + "loss": 3.3939, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.5121665029878215e-05, + "loss": 3.3939, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113279082367695e-05, + "loss": 3.4005, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.5104893134857173e-05, + "loss": 3.411, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.5096507187346653e-05, + "loss": 3.4076, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5088137618639866e-05, + "loss": 3.4009, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.5079751671129344e-05, + "loss": 3.3993, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5071365723618824e-05, + "loss": 3.4038, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062979776108304e-05, + "loss": 3.3975, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054610207401518e-05, + "loss": 3.3915, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5046224259890995e-05, + "loss": 3.4007, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037838312380475e-05, + "loss": 3.3883, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5029452364869956e-05, + "loss": 3.3989, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5021082796163169e-05, + "loss": 3.392, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8694632053375244, + "eval_runtime": 304.2644, + "eval_samples_per_second": 1254.143, + "eval_steps_per_second": 39.193, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012696848652647e-05, + "loss": 3.4012, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5004310901142127e-05, + "loss": 3.3889, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995924953631607e-05, + "loss": 3.3987, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987555384924818e-05, + "loss": 3.4093, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4979169437414298e-05, + "loss": 3.4064, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970783489903778e-05, + "loss": 3.4054, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4962397542393258e-05, + "loss": 3.4046, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.495401159488274e-05, + "loss": 3.391, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945642026175949e-05, + "loss": 3.3896, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4937256078665428e-05, + "loss": 3.3982, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.492887013115491e-05, + "loss": 3.3986, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.492048418364439e-05, + "loss": 3.3972, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4912114614937601e-05, + "loss": 3.4058, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.490372866742708e-05, + "loss": 3.3818, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.489534271991656e-05, + "loss": 3.3907, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.488695677240604e-05, + "loss": 3.3773, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878587203699252e-05, + "loss": 3.399, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4870201256188731e-05, + "loss": 3.3915, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861815308678211e-05, + "loss": 3.3943, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4853445739971422e-05, + "loss": 3.3989, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4845059792460902e-05, + "loss": 3.4033, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836673844950382e-05, + "loss": 3.4018, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4828287897439864e-05, + "loss": 3.3961, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4819918328733073e-05, + "loss": 3.3935, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811532381222555e-05, + "loss": 3.4092, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4803146433712034e-05, + "loss": 3.3976, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794760486201514e-05, + "loss": 3.3873, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4786390917494725e-05, + "loss": 3.3969, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4778004969984205e-05, + "loss": 3.3856, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769619022473685e-05, + "loss": 3.3913, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4761233074963165e-05, + "loss": 3.4007, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752863506256376e-05, + "loss": 3.3952, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4744477558745856e-05, + "loss": 3.4, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4736091611235336e-05, + "loss": 3.4069, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727705663724817e-05, + "loss": 3.3939, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4719336095018027e-05, + "loss": 3.3981, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710950147507507e-05, + "loss": 3.4019, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702564199996988e-05, + "loss": 3.3855, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.4694194631290197e-05, + "loss": 3.3909, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.4685808683779679e-05, + "loss": 3.3839, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.4677422736269159e-05, + "loss": 3.3855, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4669036788758639e-05, + "loss": 3.3909, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660650841248119e-05, + "loss": 3.4065, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4652264893737597e-05, + "loss": 3.3884, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643878946227077e-05, + "loss": 3.3903, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4635492998716557e-05, + "loss": 3.3949, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.4627123430009771e-05, + "loss": 3.3946, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.4618737482499248e-05, + "loss": 3.3847, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4610351534988728e-05, + "loss": 3.3718, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.460196558747821e-05, + "loss": 3.3909, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.4593596018771418e-05, + "loss": 3.4054, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.4585210071260898e-05, + "loss": 3.4028, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.457682412375038e-05, + "loss": 3.3861, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.456843817623986e-05, + "loss": 3.3861, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.456006860753307e-05, + "loss": 3.3868, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.455168266002255e-05, + "loss": 3.3801, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.454329671251203e-05, + "loss": 3.4102, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.453491076500151e-05, + "loss": 3.3769, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4526541196294721e-05, + "loss": 3.4112, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4518155248784201e-05, + "loss": 3.3937, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509769301273681e-05, + "loss": 3.3817, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4501383353763163e-05, + "loss": 3.3947, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4493013785056372e-05, + "loss": 3.3889, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484627837545852e-05, + "loss": 3.3757, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4476241890035334e-05, + "loss": 3.3916, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467855942524814e-05, + "loss": 3.4003, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4459486373818024e-05, + "loss": 3.3852, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4451100426307504e-05, + "loss": 3.392, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442714478796984e-05, + "loss": 3.3735, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4434328531286464e-05, + "loss": 3.3867, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425958962579675e-05, + "loss": 3.3859, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417573015069155e-05, + "loss": 3.3909, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4409187067558635e-05, + "loss": 3.3861, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400801120048115e-05, + "loss": 3.3879, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4392431551341326e-05, + "loss": 3.4045, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4384045603830806e-05, + "loss": 3.3923, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375659656320287e-05, + "loss": 3.3963, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4367273708809767e-05, + "loss": 3.3905, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358904140102978e-05, + "loss": 3.3856, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4350518192592458e-05, + "loss": 3.3984, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4342132245081938e-05, + "loss": 3.3883, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333746297571418e-05, + "loss": 3.3957, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4325376728864629e-05, + "loss": 3.3935, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316990781354109e-05, + "loss": 3.3899, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308604833843589e-05, + "loss": 3.3677, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4300218886333069e-05, + "loss": 3.3917, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.429184931762628e-05, + "loss": 3.3889, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.428347974891949e-05, + "loss": 3.3811, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.427509380140897e-05, + "loss": 3.3892, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.426670785389845e-05, + "loss": 3.3858, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.425832190638793e-05, + "loss": 3.38, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249935958877412e-05, + "loss": 3.3794, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4241550011366892e-05, + "loss": 3.3897, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4233164063856368e-05, + "loss": 3.3927, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224794495149582e-05, + "loss": 3.3932, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4216408547639062e-05, + "loss": 3.3986, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4208022600128542e-05, + "loss": 3.3862, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.419963665261802e-05, + "loss": 3.3847, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4191267083911233e-05, + "loss": 3.39, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.4182881136400713e-05, + "loss": 3.3924, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.4174495188890195e-05, + "loss": 3.3905, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.4166109241379671e-05, + "loss": 3.3939, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157739672672884e-05, + "loss": 3.3893, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4149353725162365e-05, + "loss": 3.3837, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140967777651842e-05, + "loss": 3.3947, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4132581830141322e-05, + "loss": 3.388, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.4124212261434536e-05, + "loss": 3.386, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.4115826313924016e-05, + "loss": 3.388, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.4107440366413494e-05, + "loss": 3.386, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.4099070797706707e-05, + "loss": 3.3845, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.4090684850196187e-05, + "loss": 3.3835, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4082298902685667e-05, + "loss": 3.3788, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.4073912955175145e-05, + "loss": 3.3927, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4065527007664625e-05, + "loss": 3.3948, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4057141060154105e-05, + "loss": 3.3831, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048755112643587e-05, + "loss": 3.3958, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4040369165133066e-05, + "loss": 3.4013, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.4031999596426276e-05, + "loss": 3.389, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.4023613648915757e-05, + "loss": 3.3871, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.4015227701405237e-05, + "loss": 3.3876, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.4006841753894717e-05, + "loss": 3.3885, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3998472185187928e-05, + "loss": 3.3858, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.3990086237677408e-05, + "loss": 3.3828, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981700290166888e-05, + "loss": 3.3832, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3973314342656368e-05, + "loss": 3.3918, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964944773949579e-05, + "loss": 3.3878, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3956558826439059e-05, + "loss": 3.3894, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3948172878928538e-05, + "loss": 3.3843, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.393980331022175e-05, + "loss": 3.3875, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.393141736271123e-05, + "loss": 3.3842, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3923031415200711e-05, + "loss": 3.3988, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.391464546769019e-05, + "loss": 3.3957, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.39062758989834e-05, + "loss": 3.3854, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897889951472882e-05, + "loss": 3.3868, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3889504003962362e-05, + "loss": 3.3967, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3881118056451841e-05, + "loss": 3.3823, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872748487745052e-05, + "loss": 3.389, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3864362540234532e-05, + "loss": 3.39, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855976592724012e-05, + "loss": 3.4011, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3847590645213492e-05, + "loss": 3.3936, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.383920469770297e-05, + "loss": 3.3959, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830835128996183e-05, + "loss": 3.3855, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3822449181485665e-05, + "loss": 3.4003, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3814063233975145e-05, + "loss": 3.3835, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805693665268354e-05, + "loss": 3.38, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3797307717757835e-05, + "loss": 3.3893, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788921770247315e-05, + "loss": 3.378, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3780535822736792e-05, + "loss": 3.3907, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3772166254030006e-05, + "loss": 3.3802, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.8706774711608887, + "eval_runtime": 304.1285, + "eval_samples_per_second": 1254.703, + "eval_steps_per_second": 39.21, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763780306519486e-05, + "loss": 3.3867, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3755394359008966e-05, + "loss": 3.3821, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3747008411498444e-05, + "loss": 3.3862, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3738622463987924e-05, + "loss": 3.4017, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3730252895281137e-05, + "loss": 3.3926, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721866947770618e-05, + "loss": 3.4024, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3713481000260095e-05, + "loss": 3.3901, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3705095052749575e-05, + "loss": 3.3836, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696725484042789e-05, + "loss": 3.3752, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3688339536532265e-05, + "loss": 3.3906, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679953589021745e-05, + "loss": 3.3883, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3671567641511227e-05, + "loss": 3.386, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.366319807280444e-05, + "loss": 3.3974, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654812125293918e-05, + "loss": 3.369, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3646426177783398e-05, + "loss": 3.3784, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3638040230272878e-05, + "loss": 3.3748, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.362967066156609e-05, + "loss": 3.3834, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3621284714055568e-05, + "loss": 3.3836, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612898766545048e-05, + "loss": 3.3798, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3604512819034528e-05, + "loss": 3.3907, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359614325032774e-05, + "loss": 3.3922, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.3587757302817219e-05, + "loss": 3.3911, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.3579371355306699e-05, + "loss": 3.3877, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.357098540779618e-05, + "loss": 3.3832, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.356261583908939e-05, + "loss": 3.3988, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3554229891578872e-05, + "loss": 3.3819, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545843944068351e-05, + "loss": 3.3818, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3537457996557831e-05, + "loss": 3.3878, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3529088427851042e-05, + "loss": 3.3762, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520702480340522e-05, + "loss": 3.3814, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.3512316532830002e-05, + "loss": 3.3855, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.3503930585319482e-05, + "loss": 3.3881, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.3495561016612693e-05, + "loss": 3.3921, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.3487175069102173e-05, + "loss": 3.3958, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478789121591653e-05, + "loss": 3.3831, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3470403174081134e-05, + "loss": 3.3889, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3462033605374344e-05, + "loss": 3.3948, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3453647657863823e-05, + "loss": 3.3768, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3445261710353305e-05, + "loss": 3.3822, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436875762842785e-05, + "loss": 3.3699, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3428506194135996e-05, + "loss": 3.3783, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3420120246625476e-05, + "loss": 3.3761, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411734299114956e-05, + "loss": 3.4037, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3403348351604436e-05, + "loss": 3.3765, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394978782897647e-05, + "loss": 3.3788, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3386592835387126e-05, + "loss": 3.3827, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3378206887876606e-05, + "loss": 3.3842, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369820940366088e-05, + "loss": 3.3749, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3361451371659297e-05, + "loss": 3.3628, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3353065424148777e-05, + "loss": 3.3834, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3344679476638259e-05, + "loss": 3.3931, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3336293529127739e-05, + "loss": 3.3915, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.332792396042095e-05, + "loss": 3.3796, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.331953801291043e-05, + "loss": 3.3736, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.331115206539991e-05, + "loss": 3.3817, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.330276611788939e-05, + "loss": 3.3705, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.32943965491826e-05, + "loss": 3.3989, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.328601060167208e-05, + "loss": 3.3689, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.327762465416156e-05, + "loss": 3.3991, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3269238706651042e-05, + "loss": 3.3855, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260869137944251e-05, + "loss": 3.3683, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.325248319043373e-05, + "loss": 3.383, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3244097242923212e-05, + "loss": 3.3831, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235727674216422e-05, + "loss": 3.3675, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3227341726705903e-05, + "loss": 3.3744, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218955779195383e-05, + "loss": 3.3955, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3210569831684863e-05, + "loss": 3.3767, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3202200262978074e-05, + "loss": 3.3794, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193814315467554e-05, + "loss": 3.3644, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3185428367957034e-05, + "loss": 3.3803, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3177042420446514e-05, + "loss": 3.3738, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.3168672851739725e-05, + "loss": 3.38, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.3160286904229205e-05, + "loss": 3.3772, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151900956718684e-05, + "loss": 3.3812, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3143515009208166e-05, + "loss": 3.3908, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3135145440501375e-05, + "loss": 3.3805, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126759492990857e-05, + "loss": 3.3843, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.3118373545480337e-05, + "loss": 3.3834, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.3109987597969813e-05, + "loss": 3.3798, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.3101618029263028e-05, + "loss": 3.3865, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.3093232081752508e-05, + "loss": 3.3778, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.3084846134241987e-05, + "loss": 3.383, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.3076460186731466e-05, + "loss": 3.388, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.3068090618024678e-05, + "loss": 3.3783, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3059704670514158e-05, + "loss": 3.3612, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3051318723003636e-05, + "loss": 3.3799, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042932775493116e-05, + "loss": 3.3765, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3034563206786329e-05, + "loss": 3.378, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3026177259275809e-05, + "loss": 3.3771, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017791311765287e-05, + "loss": 3.3834, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.3009405364254767e-05, + "loss": 3.3662, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.3001019416744247e-05, + "loss": 3.3697, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.2992633469233729e-05, + "loss": 3.3753, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2984247521723209e-05, + "loss": 3.3866, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975861574212689e-05, + "loss": 3.3777, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.29674920055059e-05, + "loss": 3.3936, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.295910605799538e-05, + "loss": 3.3714, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.295072011048486e-05, + "loss": 3.3769, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.294235054177807e-05, + "loss": 3.3803, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.293396459426755e-05, + "loss": 3.382, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.292557864675703e-05, + "loss": 3.3789, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2917192699246512e-05, + "loss": 3.3856, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.290882313053972e-05, + "loss": 3.3805, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.29004371830292e-05, + "loss": 3.374, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2892051235518682e-05, + "loss": 3.3875, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2883665288008162e-05, + "loss": 3.3747, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2875279340497642e-05, + "loss": 3.3746, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866909771790853e-05, + "loss": 3.3803, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2858523824280333e-05, + "loss": 3.3744, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2850154255573544e-05, + "loss": 3.374, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841768308063024e-05, + "loss": 3.3789, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2833382360552504e-05, + "loss": 3.3679, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824996413041984e-05, + "loss": 3.3829, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2816610465531465e-05, + "loss": 3.3835, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2808224518020942e-05, + "loss": 3.3731, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799838570510422e-05, + "loss": 3.3876, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2791452622999903e-05, + "loss": 3.3937, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2783083054293116e-05, + "loss": 3.3795, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2774697106782593e-05, + "loss": 3.3787, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2766311159272074e-05, + "loss": 3.3765, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757925211761554e-05, + "loss": 3.3755, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.2749555643054765e-05, + "loss": 3.376, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.2741169695544245e-05, + "loss": 3.3747, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732783748033725e-05, + "loss": 3.3687, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2724397800523205e-05, + "loss": 3.3821, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2716028231816416e-05, + "loss": 3.3796, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2707642284305896e-05, + "loss": 3.3766, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2699256336795375e-05, + "loss": 3.377, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690870389284855e-05, + "loss": 3.3783, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2682500820578066e-05, + "loss": 3.3729, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.2674114873067546e-05, + "loss": 3.3878, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.2665728925557028e-05, + "loss": 3.3877, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.2657359356850237e-05, + "loss": 3.3785, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.2648973409339719e-05, + "loss": 3.3729, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2640587461829199e-05, + "loss": 3.3818, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2632201514318678e-05, + "loss": 3.3766, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.262383194561189e-05, + "loss": 3.3771, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.261544599810137e-05, + "loss": 3.3789, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.260706005059085e-05, + "loss": 3.396, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.259867410308033e-05, + "loss": 3.377, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590288155569809e-05, + "loss": 3.3854, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.258191858686302e-05, + "loss": 3.3782, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.25735326393525e-05, + "loss": 3.3888, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2565146691841982e-05, + "loss": 3.3745, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556760744331461e-05, + "loss": 3.371, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.254839117562467e-05, + "loss": 3.3822, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2540005228114152e-05, + "loss": 3.3654, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2531619280603632e-05, + "loss": 3.3807, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2523233333093112e-05, + "loss": 3.3686, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.872615098953247, + "eval_runtime": 302.7513, + "eval_samples_per_second": 1260.411, + "eval_steps_per_second": 39.389, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514863764386323e-05, + "loss": 3.3805, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2506477816875803e-05, + "loss": 3.3754, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2498091869365283e-05, + "loss": 3.3735, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2489722300658494e-05, + "loss": 3.392, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2481336353147974e-05, + "loss": 3.3837, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472950405637454e-05, + "loss": 3.3928, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2464564458126933e-05, + "loss": 3.3778, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2456194889420144e-05, + "loss": 3.3717, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447808941909624e-05, + "loss": 3.3725, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2439422994399106e-05, + "loss": 3.3796, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2431037046888584e-05, + "loss": 3.3763, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2422667478181797e-05, + "loss": 3.3773, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2414281530671277e-05, + "loss": 3.3889, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2405895583160757e-05, + "loss": 3.3619, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2397509635650235e-05, + "loss": 3.3655, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2389140066943447e-05, + "loss": 3.3677, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2380754119432927e-05, + "loss": 3.3712, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2372368171922405e-05, + "loss": 3.3742, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363982224411887e-05, + "loss": 3.3752, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2355612655705098e-05, + "loss": 3.3753, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2347226708194578e-05, + "loss": 3.3836, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338840760684058e-05, + "loss": 3.3778, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2330454813173538e-05, + "loss": 3.3801, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.232208524446675e-05, + "loss": 3.3731, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.231369929695623e-05, + "loss": 3.3896, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2305313349445709e-05, + "loss": 3.3728, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2296927401935188e-05, + "loss": 3.3728, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2288557833228401e-05, + "loss": 3.3728, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.228017188571788e-05, + "loss": 3.3681, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.227178593820736e-05, + "loss": 3.3729, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.226339999069684e-05, + "loss": 3.3741, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2255030421990052e-05, + "loss": 3.3789, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2246660853283262e-05, + "loss": 3.3828, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2238274905772742e-05, + "loss": 3.385, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2229888958262222e-05, + "loss": 3.3753, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.2221503010751704e-05, + "loss": 3.3801, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.2213117063241182e-05, + "loss": 3.3831, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2204731115730662e-05, + "loss": 3.3678, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2196361547023875e-05, + "loss": 3.3719, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.2187975599513353e-05, + "loss": 3.3596, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.2179589652002833e-05, + "loss": 3.3687, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2171203704492313e-05, + "loss": 3.3679, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162817756981794e-05, + "loss": 3.3875, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2154431809471273e-05, + "loss": 3.3685, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2146045861960753e-05, + "loss": 3.3682, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2137659914450233e-05, + "loss": 3.3789, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.2129290345743443e-05, + "loss": 3.3735, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2120904398232923e-05, + "loss": 3.3684, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2112518450722405e-05, + "loss": 3.3468, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2104132503211885e-05, + "loss": 3.3723, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2095762934505094e-05, + "loss": 3.383, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2087376986994576e-05, + "loss": 3.3832, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2078991039484056e-05, + "loss": 3.3696, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2070621470777267e-05, + "loss": 3.3641, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2062235523266746e-05, + "loss": 3.3734, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2053849575756226e-05, + "loss": 3.3604, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2045463628245706e-05, + "loss": 3.3859, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2037077680735186e-05, + "loss": 3.3585, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2028691733224666e-05, + "loss": 3.3911, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2020305785714146e-05, + "loss": 3.3758, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011919838203624e-05, + "loss": 3.358, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2003550269496837e-05, + "loss": 3.37, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1995164321986317e-05, + "loss": 3.3761, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1986778374475797e-05, + "loss": 3.3572, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1978392426965277e-05, + "loss": 3.3639, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1970022858258488e-05, + "loss": 3.3834, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1961636910747968e-05, + "loss": 3.3712, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.195325096323745e-05, + "loss": 3.3678, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944865015726928e-05, + "loss": 3.3527, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.193649544702014e-05, + "loss": 3.3688, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.192810949950962e-05, + "loss": 3.3633, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1919723551999098e-05, + "loss": 3.3735, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1911337604488578e-05, + "loss": 3.364, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.190296803578179e-05, + "loss": 3.3732, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.189458208827127e-05, + "loss": 3.3777, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.188619614076075e-05, + "loss": 3.3753, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.187781019325023e-05, + "loss": 3.3719, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1869440624543441e-05, + "loss": 3.3691, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1861054677032921e-05, + "loss": 3.375, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1852668729522401e-05, + "loss": 3.3765, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1844282782011881e-05, + "loss": 3.3699, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835913213305094e-05, + "loss": 3.3741, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1827527265794572e-05, + "loss": 3.3722, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1819141318284052e-05, + "loss": 3.3704, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1810755370773532e-05, + "loss": 3.3528, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1802385802066744e-05, + "loss": 3.3696, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793999854556223e-05, + "loss": 3.3658, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1785613907045703e-05, + "loss": 3.3691, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.1777227959535184e-05, + "loss": 3.3689, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768858390828393e-05, + "loss": 3.3729, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1760472443317875e-05, + "loss": 3.359, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1752086495807355e-05, + "loss": 3.3576, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.1743700548296835e-05, + "loss": 3.3635, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1735330979590046e-05, + "loss": 3.3778, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.1726945032079526e-05, + "loss": 3.3693, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.1718559084569006e-05, + "loss": 3.3793, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.1710173137058485e-05, + "loss": 3.365, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1701803568351696e-05, + "loss": 3.3707, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1693417620841176e-05, + "loss": 3.3641, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.1685031673330656e-05, + "loss": 3.3763, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1676645725820136e-05, + "loss": 3.3673, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1668276157113347e-05, + "loss": 3.3776, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1659890209602829e-05, + "loss": 3.3691, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1651504262092309e-05, + "loss": 3.3653, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1643118314581787e-05, + "loss": 3.3818, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1634748745875e-05, + "loss": 3.3623, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.162636279836448e-05, + "loss": 3.3654, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1617976850853958e-05, + "loss": 3.3746, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1609590903343437e-05, + "loss": 3.3611, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.160123771344038e-05, + "loss": 3.3651, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592851765929862e-05, + "loss": 3.3707, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.158446581841934e-05, + "loss": 3.3579, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.157607987090882e-05, + "loss": 3.3744, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.15676939233983e-05, + "loss": 3.3692, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1559307975887782e-05, + "loss": 3.3659, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.155092202837726e-05, + "loss": 3.3763, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.154253608086674e-05, + "loss": 3.3821, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1534166512159953e-05, + "loss": 3.3727, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1525780564649431e-05, + "loss": 3.3691, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1517394617138911e-05, + "loss": 3.3654, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1509008669628391e-05, + "loss": 3.3663, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1500639100921604e-05, + "loss": 3.3644, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1492253153411082e-05, + "loss": 3.37, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483867205900564e-05, + "loss": 3.3565, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1475481258390043e-05, + "loss": 3.3743, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1467111689683254e-05, + "loss": 3.3672, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1458725742172734e-05, + "loss": 3.3687, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1450339794662214e-05, + "loss": 3.3666, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1441953847151694e-05, + "loss": 3.3643, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1433584278444905e-05, + "loss": 3.3628, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1425198330934385e-05, + "loss": 3.3787, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.1416812383423865e-05, + "loss": 3.3774, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1408442814717077e-05, + "loss": 3.3697, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1400056867206556e-05, + "loss": 3.3619, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1391670919696036e-05, + "loss": 3.3688, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1383284972185517e-05, + "loss": 3.3697, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1374915403478728e-05, + "loss": 3.3693, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1366529455968206e-05, + "loss": 3.3714, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.1358143508457688e-05, + "loss": 3.3839, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1349757560947168e-05, + "loss": 3.3682, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1341387992240379e-05, + "loss": 3.3789, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.1333002044729859e-05, + "loss": 3.3679, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1324616097219339e-05, + "loss": 3.3756, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1316230149708819e-05, + "loss": 3.3629, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130786058100203e-05, + "loss": 3.3648, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.129947463349151e-05, + "loss": 3.3722, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.129108868598099e-05, + "loss": 3.3575, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.128270273847047e-05, + "loss": 3.3694, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.127433316976368e-05, + "loss": 3.3611, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.8729324340820312, + "eval_runtime": 303.0207, + "eval_samples_per_second": 1259.29, + "eval_steps_per_second": 39.354, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.126594722225316e-05, + "loss": 3.3644, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1257561274742642e-05, + "loss": 3.3653, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.124917532723212e-05, + "loss": 3.364, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.12407893797216e-05, + "loss": 3.3796, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1232419811014812e-05, + "loss": 3.3743, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1224033863504292e-05, + "loss": 3.3841, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.121564791599377e-05, + "loss": 3.3668, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1207261968483252e-05, + "loss": 3.3658, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1198892399776463e-05, + "loss": 3.359, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1190506452265941e-05, + "loss": 3.3726, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1182120504755423e-05, + "loss": 3.3665, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1173734557244903e-05, + "loss": 3.368, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1165364988538114e-05, + "loss": 3.3729, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1156979041027594e-05, + "loss": 3.3592, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1148593093517073e-05, + "loss": 3.3595, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1140207146006553e-05, + "loss": 3.358, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1131837577299764e-05, + "loss": 3.3549, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1123451629789244e-05, + "loss": 3.3635, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1115065682278724e-05, + "loss": 3.3655, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1106679734768206e-05, + "loss": 3.3647, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1098310166061415e-05, + "loss": 3.3775, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1089924218550895e-05, + "loss": 3.3681, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1081538271040377e-05, + "loss": 3.3689, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1073152323529855e-05, + "loss": 3.3654, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1064782754823067e-05, + "loss": 3.3789, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1056396807312547e-05, + "loss": 3.3619, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1048010859802027e-05, + "loss": 3.3665, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1039624912291505e-05, + "loss": 3.3621, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1031255343584718e-05, + "loss": 3.3634, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1022869396074198e-05, + "loss": 3.3648, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1014483448563678e-05, + "loss": 3.3607, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1006097501053158e-05, + "loss": 3.3725, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.09977443111501e-05, + "loss": 3.3718, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0989358363639581e-05, + "loss": 3.3702, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0980972416129061e-05, + "loss": 3.3679, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.097258646861854e-05, + "loss": 3.3679, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0964200521108021e-05, + "loss": 3.3727, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0955814573597501e-05, + "loss": 3.3556, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.0947428626086979e-05, + "loss": 3.3638, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0939042678576459e-05, + "loss": 3.3474, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0930673109869672e-05, + "loss": 3.361, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.0922287162359152e-05, + "loss": 3.3559, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.091390121484863e-05, + "loss": 3.3784, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0905515267338111e-05, + "loss": 3.3608, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0897145698631322e-05, + "loss": 3.3571, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.0888759751120802e-05, + "loss": 3.3664, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0880373803610282e-05, + "loss": 3.3681, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0871987856099762e-05, + "loss": 3.3582, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.0863618287392973e-05, + "loss": 3.3412, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.0855232339882453e-05, + "loss": 3.3588, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0846846392371933e-05, + "loss": 3.3752, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.0838460444861413e-05, + "loss": 3.3731, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.0830090876154625e-05, + "loss": 3.3636, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0821704928644104e-05, + "loss": 3.3527, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0813318981133583e-05, + "loss": 3.3662, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0804933033623065e-05, + "loss": 3.3484, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0796563464916274e-05, + "loss": 3.3776, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0788177517405756e-05, + "loss": 3.3479, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0779791569895236e-05, + "loss": 3.3779, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0771405622384716e-05, + "loss": 3.3712, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0763036053677927e-05, + "loss": 3.3479, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0754650106167407e-05, + "loss": 3.3617, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0746264158656886e-05, + "loss": 3.3672, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0737878211146365e-05, + "loss": 3.3437, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0729508642439577e-05, + "loss": 3.3539, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0721122694929057e-05, + "loss": 3.3748, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0712736747418537e-05, + "loss": 3.361, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0704350799908017e-05, + "loss": 3.3571, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0695981231201228e-05, + "loss": 3.3482, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0687595283690708e-05, + "loss": 3.3591, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.067920933618019e-05, + "loss": 3.3504, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0670823388669668e-05, + "loss": 3.3664, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.066245381996288e-05, + "loss": 3.3511, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.065406787245236e-05, + "loss": 3.3656, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0645681924941838e-05, + "loss": 3.3657, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0637295977431318e-05, + "loss": 3.3659, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0628926408724531e-05, + "loss": 3.3619, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.062054046121401e-05, + "loss": 3.3598, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.061215451370349e-05, + "loss": 3.3657, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.060376856619297e-05, + "loss": 3.3666, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0595398997486182e-05, + "loss": 3.3606, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0587013049975661e-05, + "loss": 3.3633, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0578627102465141e-05, + "loss": 3.3638, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0570241154954621e-05, + "loss": 3.3603, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0561871586247834e-05, + "loss": 3.3442, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0553485638737312e-05, + "loss": 3.3573, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0545099691226792e-05, + "loss": 3.3587, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0536730122520005e-05, + "loss": 3.3582, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0528344175009485e-05, + "loss": 3.3602, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0519958227498963e-05, + "loss": 3.3614, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511572279988444e-05, + "loss": 3.3523, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0503186332477924e-05, + "loss": 3.345, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0494800384967403e-05, + "loss": 3.356, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0486414437456883e-05, + "loss": 3.3661, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.0478028489946364e-05, + "loss": 3.3611, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.0469658921239575e-05, + "loss": 3.3688, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0461272973729053e-05, + "loss": 3.357, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0452887026218535e-05, + "loss": 3.3593, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.0444501078708015e-05, + "loss": 3.3568, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0436131510001226e-05, + "loss": 3.3677, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0427745562490706e-05, + "loss": 3.3577, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.0419359614980186e-05, + "loss": 3.369, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.0410973667469666e-05, + "loss": 3.3574, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0402604098762876e-05, + "loss": 3.3541, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.0394218151252356e-05, + "loss": 3.371, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.0385832203741836e-05, + "loss": 3.3555, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0377446256231316e-05, + "loss": 3.3532, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.0369076687524527e-05, + "loss": 3.3613, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0360690740014007e-05, + "loss": 3.3578, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.035232117130722e-05, + "loss": 3.3516, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0343935223796698e-05, + "loss": 3.3606, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.033554927628618e-05, + "loss": 3.3511, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.032716332877566e-05, + "loss": 3.3634, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.031877738126514e-05, + "loss": 3.3603, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0310391433754618e-05, + "loss": 3.358, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.03020054862441e-05, + "loss": 3.3628, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.029361953873358e-05, + "loss": 3.377, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0285249970026788e-05, + "loss": 3.3625, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.027686402251627e-05, + "loss": 3.357, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.026847807500575e-05, + "loss": 3.3552, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.026009212749523e-05, + "loss": 3.3566, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.025172255878844e-05, + "loss": 3.3545, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.024333661127792e-05, + "loss": 3.358, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.02349506637674e-05, + "loss": 3.3493, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.022656471625688e-05, + "loss": 3.3605, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0218195147550091e-05, + "loss": 3.3592, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0209809200039571e-05, + "loss": 3.3611, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0201423252529053e-05, + "loss": 3.3556, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0193037305018531e-05, + "loss": 3.3563, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0184667736311742e-05, + "loss": 3.3524, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0176281788801224e-05, + "loss": 3.3664, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0167895841290704e-05, + "loss": 3.3716, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0159509893780182e-05, + "loss": 3.3637, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0151140325073394e-05, + "loss": 3.3529, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0142754377562874e-05, + "loss": 3.3589, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0134368430052353e-05, + "loss": 3.364, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0125982482541834e-05, + "loss": 3.3583, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0117612913835045e-05, + "loss": 3.3624, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0109226966324525e-05, + "loss": 3.3698, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0100841018814005e-05, + "loss": 3.3546, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0092455071303485e-05, + "loss": 3.3725, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0084085502596696e-05, + "loss": 3.3568, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0075699555086177e-05, + "loss": 3.3653, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0067313607575656e-05, + "loss": 3.3593, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0058927660065135e-05, + "loss": 3.3489, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.0050558091358348e-05, + "loss": 3.3647, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0042172143847826e-05, + "loss": 3.3508, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.0033786196337306e-05, + "loss": 3.3571, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.0025400248826788e-05, + "loss": 3.3528, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0017030680119999e-05, + "loss": 3.359, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.872735023498535, + "eval_runtime": 302.6931, + "eval_samples_per_second": 1260.653, + "eval_steps_per_second": 39.396, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.0008644732609477e-05, + "loss": 3.3542, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 1.0000258785098959e-05, + "loss": 3.3581, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.991872837588438e-06, + "loss": 3.3683, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.98350326888165e-06, + "loss": 3.3653, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.97511732137113e-06, + "loss": 3.3763, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.96673137386061e-06, + "loss": 3.3572, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.958345426350089e-06, + "loss": 3.3517, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.9499758576433e-06, + "loss": 3.3533, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.94158991013278e-06, + "loss": 3.3633, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.93320396262226e-06, + "loss": 3.3547, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.92481801511174e-06, + "loss": 3.3608, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.91644844640495e-06, + "loss": 3.3576, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.90806249889443e-06, + "loss": 3.35, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.899676551383912e-06, + "loss": 3.3526, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.891306982677121e-06, + "loss": 3.3499, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.882921035166603e-06, + "loss": 3.3445, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.874535087656083e-06, + "loss": 3.3543, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.866149140145563e-06, + "loss": 3.3563, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.857779571438774e-06, + "loss": 3.3541, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.849393623928254e-06, + "loss": 3.3701, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.841007676417734e-06, + "loss": 3.3567, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.832621728907212e-06, + "loss": 3.3618, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.824235781396693e-06, + "loss": 3.3571, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.815866212689904e-06, + "loss": 3.3657, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.807480265179384e-06, + "loss": 3.3539, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.799094317668864e-06, + "loss": 3.3586, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.790724748962075e-06, + "loss": 3.3508, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.782338801451555e-06, + "loss": 3.3571, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.773952853941037e-06, + "loss": 3.3469, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.765566906430515e-06, + "loss": 3.354, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.757197337723727e-06, + "loss": 3.363, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.748827769016938e-06, + "loss": 3.3593, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.740441821506418e-06, + "loss": 3.3643, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.732055873995898e-06, + "loss": 3.3626, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.723669926485378e-06, + "loss": 3.3539, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.715283978974858e-06, + "loss": 3.3667, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.706898031464338e-06, + "loss": 3.3471, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.698528462757549e-06, + "loss": 3.3532, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.690142515247029e-06, + "loss": 3.3413, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.681756567736509e-06, + "loss": 3.3493, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.673370620225989e-06, + "loss": 3.3457, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.664984672715468e-06, + "loss": 3.3675, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.656598725204948e-06, + "loss": 3.3514, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.648212777694428e-06, + "loss": 3.3492, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.639826830183908e-06, + "loss": 3.3598, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.631457261477119e-06, + "loss": 3.3562, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.6230713139666e-06, + "loss": 3.3485, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.614685366456079e-06, + "loss": 3.3367, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.606299418945559e-06, + "loss": 3.3443, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.597929850238772e-06, + "loss": 3.366, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.58954390272825e-06, + "loss": 3.3647, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.58115795521773e-06, + "loss": 3.3518, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.572772007707211e-06, + "loss": 3.3469, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.564402439000422e-06, + "loss": 3.3578, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.5560164914899e-06, + "loss": 3.3412, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.547630543979382e-06, + "loss": 3.3616, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.539244596468862e-06, + "loss": 3.3424, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.530875027762073e-06, + "loss": 3.3679, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.522489080251553e-06, + "loss": 3.3574, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.514103132741033e-06, + "loss": 3.3457, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.505717185230513e-06, + "loss": 3.3469, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.497347616523723e-06, + "loss": 3.3598, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.488961669013203e-06, + "loss": 3.3361, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.480575721502683e-06, + "loss": 3.3448, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.472189773992163e-06, + "loss": 3.363, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.463820205285374e-06, + "loss": 3.3542, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.455434257774854e-06, + "loss": 3.3502, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.447048310264336e-06, + "loss": 3.3396, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.438662362753814e-06, + "loss": 3.3472, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.430292794047026e-06, + "loss": 3.3419, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.421906846536506e-06, + "loss": 3.3589, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.413520899025986e-06, + "loss": 3.3407, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.405134951515465e-06, + "loss": 3.3575, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.396765382808677e-06, + "loss": 3.355, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.388379435298157e-06, + "loss": 3.3628, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.379993487787637e-06, + "loss": 3.3478, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.371607540277117e-06, + "loss": 3.3543, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.363237971570328e-06, + "loss": 3.3563, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.354852024059808e-06, + "loss": 3.3553, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.346466076549288e-06, + "loss": 3.3508, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.338080129038768e-06, + "loss": 3.3525, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.329710560331978e-06, + "loss": 3.3542, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.32132461282146e-06, + "loss": 3.3476, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.312938665310938e-06, + "loss": 3.3414, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.304569096604151e-06, + "loss": 3.3422, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.29618314909363e-06, + "loss": 3.3509, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.287813580386842e-06, + "loss": 3.3517, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.279427632876322e-06, + "loss": 3.3475, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.271041685365802e-06, + "loss": 3.3507, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.262655737855281e-06, + "loss": 3.3425, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.254269790344761e-06, + "loss": 3.3367, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.245883842834241e-06, + "loss": 3.3447, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.237497895323721e-06, + "loss": 3.3523, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.2291119478132e-06, + "loss": 3.3514, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.220742379106412e-06, + "loss": 3.3603, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.212356431595892e-06, + "loss": 3.3551, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.203970484085372e-06, + "loss": 3.3426, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.195584536574852e-06, + "loss": 3.3477, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.187214967868063e-06, + "loss": 3.3526, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.178829020357543e-06, + "loss": 3.3528, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.170443072847024e-06, + "loss": 3.3588, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.162073504140233e-06, + "loss": 3.3462, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.153687556629713e-06, + "loss": 3.3442, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.145301609119195e-06, + "loss": 3.3641, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.136915661608673e-06, + "loss": 3.3426, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.128546092901886e-06, + "loss": 3.3479, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.120160145391366e-06, + "loss": 3.3517, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.111774197880846e-06, + "loss": 3.3523, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.103404629174056e-06, + "loss": 3.3407, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.095018681663536e-06, + "loss": 3.3499, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.086632734153016e-06, + "loss": 3.3428, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.078246786642496e-06, + "loss": 3.3544, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.069860839131976e-06, + "loss": 3.3492, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.061474891621456e-06, + "loss": 3.3455, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.053105322914667e-06, + "loss": 3.3567, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.044719375404147e-06, + "loss": 3.3653, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.036333427893627e-06, + "loss": 3.3548, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.027947480383107e-06, + "loss": 3.3448, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.019561532872587e-06, + "loss": 3.349, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.011175585362067e-06, + "loss": 3.3461, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.002789637851547e-06, + "loss": 3.3503, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.994403690341027e-06, + "loss": 3.3481, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.986034121634238e-06, + "loss": 3.3395, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.977648174123717e-06, + "loss": 3.3505, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.969262226613197e-06, + "loss": 3.3507, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.960876279102679e-06, + "loss": 3.3506, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.952506710395888e-06, + "loss": 3.3465, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.94412076288537e-06, + "loss": 3.346, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.93573481537485e-06, + "loss": 3.3453, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.927348867864328e-06, + "loss": 3.3588, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.91897929915754e-06, + "loss": 3.3589, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.91059335164702e-06, + "loss": 3.3576, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.9022074041365e-06, + "loss": 3.3405, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.893821456625979e-06, + "loss": 3.3523, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.885451887919191e-06, + "loss": 3.3518, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.877065940408671e-06, + "loss": 3.352, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.868679992898151e-06, + "loss": 3.3477, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.860294045387631e-06, + "loss": 3.3637, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.851924476680842e-06, + "loss": 3.3456, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.843538529170322e-06, + "loss": 3.3654, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.835152581659802e-06, + "loss": 3.3454, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.826766634149282e-06, + "loss": 3.3592, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.818397065442494e-06, + "loss": 3.346, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.810011117931974e-06, + "loss": 3.3446, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.801625170421452e-06, + "loss": 3.3543, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.793239222910932e-06, + "loss": 3.3413, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.784869654204145e-06, + "loss": 3.3498, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.776483706693625e-06, + "loss": 3.3431, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.768097759183105e-06, + "loss": 3.3459, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.874270439147949, + "eval_runtime": 302.7349, + "eval_samples_per_second": 1260.479, + "eval_steps_per_second": 39.391, + "step": 2518560 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.7198670093922437e+18, + "trial_name": null, + "trial_params": null +}