diff --git "a/checkpoint-1984320/trainer_state.json" "b/checkpoint-1984320/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-1984320/trainer_state.json" @@ -0,0 +1,23483 @@ +{ + "best_metric": 3.8636531829833984, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/re-irr-sv-agr/transformer/4/checkpoints/checkpoint-915840", + "epoch": 1.0250006060157382, + "eval_steps": 10, + "global_step": 1984320, + "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": 11.009, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8095, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1651, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9594, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.7982, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.694, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.5853, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5267, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4291, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.3859, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3256, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2522, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.1968, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1645, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1134, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.089, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.0669, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0378, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0085, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 4.9983, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9686, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9489, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9122, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9128, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.8816, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8695, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8503, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8233, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.8105, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.7914, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.7841, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7687, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7612, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7491, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7362, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969820416244367e-05, + "loss": 4.7235, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.6883, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.6873, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6762, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6602, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6636, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6576, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6361, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6361, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6288, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6205, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6164, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5972, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.5849, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.5868, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5729, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5727, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.955567581237229e-05, + "loss": 4.5461, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5598, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.5338, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5539, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5278, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5255, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.518, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.513, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.4991, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5042, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4797, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4747, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945510995746097e-05, + "loss": 4.4883, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.48, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4671, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4529, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4541, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.941318021990837e-05, + "loss": 4.4609, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404794272397856e-05, + "loss": 4.4558, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.4483, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4451, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4465, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4403, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4182, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.42, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4199, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4095, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4097, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4036, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4193, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.3935, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.3795, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.928744014366177e-05, + "loss": 4.3901, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927905419615125e-05, + "loss": 4.3872, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927066824864073e-05, + "loss": 4.3929, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3719, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925392911122715e-05, + "loss": 4.3744, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3727, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3668, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3566, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3593, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921199937367455e-05, + "loss": 4.3604, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3678, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3472, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3402, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3392, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3386, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.9161700067415156e-05, + "loss": 4.3461, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.9153314119904636e-05, + "loss": 4.3322, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.9144928172394116e-05, + "loss": 4.3259, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3194, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.3281, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.2985, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.9111400761155765e-05, + "loss": 4.3173, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3088, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.315, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3032, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3084, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.90694874024069e-05, + "loss": 4.2974, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906110145489638e-05, + "loss": 4.2982, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3028, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.2857, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3022, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.2988, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.2908, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.2812, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.2801, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.2832, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.2801, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2792, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.268, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960502842377605e-05, + "loss": 4.2754, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2601, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2638, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2515, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2554, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2437, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2666, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2705, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.2571, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2336, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887667612487986e-05, + "loss": 4.2548, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886829017736934e-05, + "loss": 4.2475, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2457, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2374, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884316509244525e-05, + "loss": 4.2459, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2392, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2337, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2348, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2369, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.223, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.225, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.237, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2213, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2224, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2328, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2133, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.207637310028076, + "eval_runtime": 302.2209, + "eval_samples_per_second": 1262.623, + "eval_steps_per_second": 39.458, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.1968, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2045, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2192, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2089, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.2145, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.192, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.2047, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.1838, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2006, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.1845, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.8658723383625e-05, + "loss": 4.2007, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865033743611448e-05, + "loss": 4.1956, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.1857, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.1773, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.1703, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861681002487613e-05, + "loss": 4.1704, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860842407736561e-05, + "loss": 4.1794, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860003812985509e-05, + "loss": 4.177, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859165218234457e-05, + "loss": 4.169, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858326623483405e-05, + "loss": 4.1887, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.857488028732352e-05, + "loss": 4.1814, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.856649433981301e-05, + "loss": 4.1729, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.855810839230249e-05, + "loss": 4.164, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.85497388235957e-05, + "loss": 4.1831, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541369254888915e-05, + "loss": 4.1552, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532983307378395e-05, + "loss": 4.1677, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524597359867875e-05, + "loss": 4.1657, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851621141235735e-05, + "loss": 4.1584, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850782546484683e-05, + "loss": 4.1492, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849943951733631e-05, + "loss": 4.1501, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.8491069948629524e-05, + "loss": 4.1548, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.8482684001119e-05, + "loss": 4.1533, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847429805360848e-05, + "loss": 4.1539, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.8465912106097964e-05, + "loss": 4.1527, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.8457526158587444e-05, + "loss": 4.1513, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.8449140211076924e-05, + "loss": 4.1481, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.8440754263566404e-05, + "loss": 4.1318, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843238469485961e-05, + "loss": 4.137, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842399874734909e-05, + "loss": 4.1327, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841561279983857e-05, + "loss": 4.1284, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840722685232805e-05, + "loss": 4.1384, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.839885728362126e-05, + "loss": 4.1396, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839047133611074e-05, + "loss": 4.1273, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.838208538860022e-05, + "loss": 4.1265, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83736994410897e-05, + "loss": 4.1296, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836531349357918e-05, + "loss": 4.1312, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835692754606866e-05, + "loss": 4.1323, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834854159855814e-05, + "loss": 4.1226, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.8340188408655086e-05, + "loss": 4.1204, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.8331802461144566e-05, + "loss": 4.1243, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.8323416513634046e-05, + "loss": 4.1165, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.8315030566123526e-05, + "loss": 4.1194, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.8306644618613006e-05, + "loss": 4.1097, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298275049906215e-05, + "loss": 4.1225, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289889102395695e-05, + "loss": 4.0954, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281503154885175e-05, + "loss": 4.12, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273117207374655e-05, + "loss": 4.1087, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.106, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.1145, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824797574364683e-05, + "loss": 4.1009, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823958979613631e-05, + "loss": 4.0953, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1112, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.0843, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.0861, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820606238489796e-05, + "loss": 4.1004, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819767643738744e-05, + "loss": 4.1008, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.0937, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.0827, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817253497365961e-05, + "loss": 4.084, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816414902614909e-05, + "loss": 4.0893, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.0975, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.0889, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139007562421265e-05, + "loss": 4.0939, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130621614910745e-05, + "loss": 4.0931, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.0939, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.075, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.8105480151182914e-05, + "loss": 4.0784, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.8097094203672393e-05, + "loss": 4.0866, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.8088708256161873e-05, + "loss": 4.076, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808033868745508e-05, + "loss": 4.0787, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807195273994456e-05, + "loss": 4.0716, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806356679243404e-05, + "loss": 4.0936, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805518084492352e-05, + "loss": 4.0728, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.0612, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.0729, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.80300393811957e-05, + "loss": 4.0741, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802165343368518e-05, + "loss": 4.0808, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801326748617466e-05, + "loss": 4.0644, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800489791746787e-05, + "loss": 4.0654, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799651196995735e-05, + "loss": 4.0744, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798812602244683e-05, + "loss": 4.0628, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.79797400749363e-05, + "loss": 4.0584, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0626, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.0703, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954598611208476e-05, + "loss": 4.0701, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.0651, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.0488, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.0553, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0571, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0613, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0571, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0518, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.0439, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0589, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.026, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786240232500395e-05, + "loss": 4.0519, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0421, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.0537, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0394, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0507, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0389, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.0395, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0488, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.036, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.0485, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0522, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.7770206038799423e-05, + "loss": 4.0434, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.7761820091288903e-05, + "loss": 4.0349, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.7753434143778383e-05, + "loss": 4.0379, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774504819626786e-05, + "loss": 4.0406, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0287, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0446, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.0282, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.0365, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0311, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.027, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0172, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.0242, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.016, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.037, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0458, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0317, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0103, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0325, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0236, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0272, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.0224, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0245, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585780708782906e-05, + "loss": 4.0196, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577394761272386e-05, + "loss": 4.0208, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.0191, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0241, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0166, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.754388372883777e-05, + "loss": 4.0099, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753549778132725e-05, + "loss": 4.0266, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0186, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751872588630621e-05, + "loss": 4.0112, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.0261, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0078, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.040642738342285, + "eval_runtime": 301.9306, + "eval_samples_per_second": 1263.837, + "eval_steps_per_second": 39.496, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 3.9944, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0006, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0196, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.012, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0153, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 3.9956, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0103, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 3.9869, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742648046369049e-05, + "loss": 4.0128, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.741809451617997e-05, + "loss": 3.9934, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740970856866945e-05, + "loss": 4.01, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.004, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739296943125587e-05, + "loss": 3.9969, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738458348374535e-05, + "loss": 3.9886, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737619753623483e-05, + "loss": 3.9864, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736781158872431e-05, + "loss": 3.9868, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735944202001752e-05, + "loss": 3.9928, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.7351056072507e-05, + "loss": 3.9946, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734267012499648e-05, + "loss": 3.9913, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733428417748596e-05, + "loss": 4.0051, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 4.0017, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 3.9974, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 3.9895, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.001, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 3.9816, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 3.993, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 3.9909, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726721297620553e-05, + "loss": 3.9876, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9755, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 3.9784, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 3.9816, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723370194377091e-05, + "loss": 3.9881, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 3.9895, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 3.9817, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9821, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 3.9811, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.719177220621832e-05, + "loss": 3.9668, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.71833862587078e-05, + "loss": 3.977, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9696, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.9687, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158244794979966e-05, + "loss": 3.9724, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149858847469446e-05, + "loss": 3.9813, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9687, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.9645, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.7124717383741615e-05, + "loss": 3.9778, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.7116331436231095e-05, + "loss": 3.97, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9781, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709957592001379e-05, + "loss": 3.9639, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709118997250327e-05, + "loss": 3.9609, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.7082804024992744e-05, + "loss": 3.9711, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707443445628596e-05, + "loss": 3.9637, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706604850877544e-05, + "loss": 3.9671, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9577, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704929299255813e-05, + "loss": 3.9637, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704090704504761e-05, + "loss": 3.9505, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703252109753709e-05, + "loss": 3.9655, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.702413515002657e-05, + "loss": 3.96, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.701574920251605e-05, + "loss": 3.9593, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.700736325500553e-05, + "loss": 3.9683, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.699897730749501e-05, + "loss": 3.9509, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.699060773878822e-05, + "loss": 3.9473, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.69822217912777e-05, + "loss": 3.9686, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.697383584376718e-05, + "loss": 3.9398, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696544989625666e-05, + "loss": 3.939, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.695708032754987e-05, + "loss": 3.9541, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694869438003935e-05, + "loss": 3.9597, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9513, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9421, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9432, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.944, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690679740009422e-05, + "loss": 3.9584, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689841145258369e-05, + "loss": 3.9506, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689002550507317e-05, + "loss": 3.9533, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688163955756265e-05, + "loss": 3.9523, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687325361005213e-05, + "loss": 3.957, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686486766254161e-05, + "loss": 3.9378, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.685648171503109e-05, + "loss": 3.9414, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.684809576752057e-05, + "loss": 3.9504, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9362, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9446, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.9367, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.6814584735085956e-05, + "loss": 3.9553, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806198787575436e-05, + "loss": 3.9401, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797812840064916e-05, + "loss": 3.9304, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789426892554396e-05, + "loss": 3.9352, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781040945043876e-05, + "loss": 3.9419, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9525, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9335, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755899481316045e-05, + "loss": 3.9372, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747513533805525e-05, + "loss": 3.9351, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739127586295005e-05, + "loss": 3.9426, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9304, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9296, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.6713986122567174e-05, + "loss": 3.9414, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670560017505666e-05, + "loss": 3.9424, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9398, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9225, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9294, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9302, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666368681630779e-05, + "loss": 3.9343, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.665530086879727e-05, + "loss": 3.9345, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664693130009048e-05, + "loss": 3.9256, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.9216, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9341, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9076, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.66133875100484e-05, + "loss": 3.9262, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9179, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9324, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9218, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.6579860098810054e-05, + "loss": 3.9266, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657147415129953e-05, + "loss": 3.9184, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656308820378901e-05, + "loss": 3.9211, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9287, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9201, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.6537946740061176e-05, + "loss": 3.9297, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.6529560792550656e-05, + "loss": 3.9314, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.65212076026476e-05, + "loss": 3.9286, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651282165513708e-05, + "loss": 3.9192, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9149, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9276, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648766381260553e-05, + "loss": 3.9112, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9256, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647089191758448e-05, + "loss": 3.9139, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.646250597007396e-05, + "loss": 3.921, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9166, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9148, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9028, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.642897855883561e-05, + "loss": 3.9131, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642059261132509e-05, + "loss": 3.9072, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9176, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.9305, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395451147597266e-05, + "loss": 3.9247, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387065200086746e-05, + "loss": 3.8943, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378679252576226e-05, + "loss": 3.9243, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9136, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.9142, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353537788848395e-05, + "loss": 3.9034, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345151841337874e-05, + "loss": 3.9161, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336765893827354e-05, + "loss": 3.9085, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328379946316834e-05, + "loss": 3.9107, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6319993998806314e-05, + "loss": 3.912, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.6311624430099523e-05, + "loss": 3.9148, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.6303238482589003e-05, + "loss": 3.9099, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9053, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9144, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627809701886118e-05, + "loss": 3.9132, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626971107135066e-05, + "loss": 3.9037, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626132512384014e-05, + "loss": 3.9176, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625293917632962e-05, + "loss": 3.9019, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9672722816467285, + "eval_runtime": 325.6205, + "eval_samples_per_second": 1171.889, + "eval_steps_per_second": 36.622, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.62445532288191e-05, + "loss": 3.894, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623616728130858e-05, + "loss": 3.8961, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622778133379806e-05, + "loss": 3.9129, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.621939538628753e-05, + "loss": 3.9046, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621100943877701e-05, + "loss": 3.9166, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620263987007023e-05, + "loss": 3.8888, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619425392255971e-05, + "loss": 3.9068, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618586797504919e-05, + "loss": 3.8817, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617748202753867e-05, + "loss": 3.9123, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.6169112458831884e-05, + "loss": 3.8929, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.6160726511321364e-05, + "loss": 3.9041, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.615234056381084e-05, + "loss": 3.9026, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614397099510405e-05, + "loss": 3.8895, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613558504759353e-05, + "loss": 3.8939, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.6127199100083006e-05, + "loss": 3.8864, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.6118813152572486e-05, + "loss": 3.8845, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.6110427205061966e-05, + "loss": 3.8955, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.6102041257551446e-05, + "loss": 3.8922, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.6093655310040926e-05, + "loss": 3.8918, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085269362530406e-05, + "loss": 3.9051, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.607689979382362e-05, + "loss": 3.9054, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.60685138463131e-05, + "loss": 3.8967, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.606012789880258e-05, + "loss": 3.8917, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.605174195129206e-05, + "loss": 3.9009, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.604337238258527e-05, + "loss": 3.8846, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603498643507475e-05, + "loss": 3.8982, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602660048756423e-05, + "loss": 3.8931, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.601821454005371e-05, + "loss": 3.8865, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.600984497134692e-05, + "loss": 3.8795, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.60014590238364e-05, + "loss": 3.8827, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.599307307632588e-05, + "loss": 3.8853, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598468712881536e-05, + "loss": 3.893, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.5976317560108575e-05, + "loss": 3.8944, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967931612598055e-05, + "loss": 3.887, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959545665087535e-05, + "loss": 3.8871, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.5951159717577015e-05, + "loss": 3.8875, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.5942773770066495e-05, + "loss": 3.8725, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.5934404201359704e-05, + "loss": 3.8812, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.5926018253849184e-05, + "loss": 3.8721, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.5917632306338664e-05, + "loss": 3.8776, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.5909246358828144e-05, + "loss": 3.8785, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590087679012135e-05, + "loss": 3.8837, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589249084261083e-05, + "loss": 3.8836, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.588410489510031e-05, + "loss": 3.8703, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.58757189475898e-05, + "loss": 3.8834, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586733300007928e-05, + "loss": 3.884, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585896343137249e-05, + "loss": 3.884, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585057748386197e-05, + "loss": 3.8757, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584219153635145e-05, + "loss": 3.8671, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583380558884093e-05, + "loss": 3.8814, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582543602013414e-05, + "loss": 3.8715, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581705007262362e-05, + "loss": 3.877, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.58086641251131e-05, + "loss": 3.8691, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.580027817760258e-05, + "loss": 3.8701, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579189223009206e-05, + "loss": 3.8651, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783522661385267e-05, + "loss": 3.8755, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577513671387475e-05, + "loss": 3.8724, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576675076636423e-05, + "loss": 3.873, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575836481885371e-05, + "loss": 3.8763, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.574999525014692e-05, + "loss": 3.8612, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.57416093026364e-05, + "loss": 3.8626, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573322335512588e-05, + "loss": 3.8834, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572483740761536e-05, + "loss": 3.8524, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571646783890857e-05, + "loss": 3.8507, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570808189139805e-05, + "loss": 3.8635, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569969594388753e-05, + "loss": 3.8745, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569130999637701e-05, + "loss": 3.8643, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.568294042767022e-05, + "loss": 3.8594, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.567455448015971e-05, + "loss": 3.8538, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.566616853264919e-05, + "loss": 3.8587, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.565778258513867e-05, + "loss": 3.8734, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649413016431876e-05, + "loss": 3.8655, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641027068921356e-05, + "loss": 3.8638, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632641121410836e-05, + "loss": 3.8721, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624255173900316e-05, + "loss": 3.8721, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561586922638979e-05, + "loss": 3.8536, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607499657683005e-05, + "loss": 3.86, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599113710172485e-05, + "loss": 3.8673, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590727762661965e-05, + "loss": 3.8492, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582341815151445e-05, + "loss": 3.8622, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.5573955867640925e-05, + "loss": 3.8542, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556558629893414e-05, + "loss": 3.8734, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.5557200351423614e-05, + "loss": 3.8577, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.5548814403913094e-05, + "loss": 3.8496, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.5540428456402574e-05, + "loss": 3.848, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553205888769579e-05, + "loss": 3.8589, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552367294018526e-05, + "loss": 3.8698, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551528699267474e-05, + "loss": 3.855, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550690104516422e-05, + "loss": 3.852, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549853147645744e-05, + "loss": 3.8514, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549014552894691e-05, + "loss": 3.8635, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548175958143639e-05, + "loss": 3.8487, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547337363392588e-05, + "loss": 3.8507, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546500406521909e-05, + "loss": 3.8608, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545661811770857e-05, + "loss": 3.8642, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544823217019805e-05, + "loss": 3.8561, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543984622268753e-05, + "loss": 3.8402, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8513, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.5423090706470216e-05, + "loss": 3.8487, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.5414704758959696e-05, + "loss": 3.8552, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.5406318811449176e-05, + "loss": 3.8549, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397949242742385e-05, + "loss": 3.8464, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.5389563295231865e-05, + "loss": 3.8449, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381177347721345e-05, + "loss": 3.8519, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537279140021083e-05, + "loss": 3.832, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536442183150404e-05, + "loss": 3.8483, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535603588399352e-05, + "loss": 3.8372, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347649936483e-05, + "loss": 3.8548, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533926398897248e-05, + "loss": 3.8441, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533089442026569e-05, + "loss": 3.8458, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.532250847275517e-05, + "loss": 3.8409, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.531412252524465e-05, + "loss": 3.8474, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530573657773413e-05, + "loss": 3.8524, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529736700902734e-05, + "loss": 3.8391, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.528898106151682e-05, + "loss": 3.8509, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.52805951140063e-05, + "loss": 3.8542, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272225545299515e-05, + "loss": 3.8489, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263839597788995e-05, + "loss": 3.8486, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255453650278475e-05, + "loss": 3.8358, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247067702767955e-05, + "loss": 3.8526, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238681755257435e-05, + "loss": 3.841, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230295807746915e-05, + "loss": 3.8461, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221909860236395e-05, + "loss": 3.8355, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.5213523912725875e-05, + "loss": 3.8454, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.5205154344019084e-05, + "loss": 3.8409, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.5196768396508564e-05, + "loss": 3.8375, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.5188382448998044e-05, + "loss": 3.8301, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5179996501487524e-05, + "loss": 3.8345, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517162693278074e-05, + "loss": 3.8357, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516324098527022e-05, + "loss": 3.8417, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.51548550377597e-05, + "loss": 3.8522, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514646909024918e-05, + "loss": 3.8514, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513809952154239e-05, + "loss": 3.8224, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512971357403187e-05, + "loss": 3.8519, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512132762652135e-05, + "loss": 3.8389, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511294167901083e-05, + "loss": 3.8404, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510457211030404e-05, + "loss": 3.8313, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509618616279352e-05, + "loss": 3.842, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087800215283e-05, + "loss": 3.8342, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507941426777248e-05, + "loss": 3.8441, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507104469906569e-05, + "loss": 3.8361, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506265875155517e-05, + "loss": 3.8396, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505427280404465e-05, + "loss": 3.8406, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504588685653413e-05, + "loss": 3.8312, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503751728782734e-05, + "loss": 3.84, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502913134031682e-05, + "loss": 3.8458, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.50207453928063e-05, + "loss": 3.8311, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501235944529578e-05, + "loss": 3.8401, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500397349778526e-05, + "loss": 3.8342, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9272706508636475, + "eval_runtime": 302.1874, + "eval_samples_per_second": 1262.763, + "eval_steps_per_second": 39.462, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499558755027474e-05, + "loss": 3.8199, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987201602764215e-05, + "loss": 3.8236, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978815655253695e-05, + "loss": 3.8368, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970429707743175e-05, + "loss": 3.8359, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496204376023266e-05, + "loss": 3.848, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495365781272214e-05, + "loss": 3.8183, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.494527186521162e-05, + "loss": 3.8324, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.49368859177011e-05, + "loss": 3.8182, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.492851634899431e-05, + "loss": 3.8384, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.492013040148379e-05, + "loss": 3.8232, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.491174445397327e-05, + "loss": 3.8298, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.490335850646275e-05, + "loss": 3.8359, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.489500531655969e-05, + "loss": 3.8188, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.488661936904917e-05, + "loss": 3.8292, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.487823342153865e-05, + "loss": 3.8188, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.486984747402813e-05, + "loss": 3.8148, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486146152651761e-05, + "loss": 3.8223, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853075579007095e-05, + "loss": 3.8259, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.4844689631496575e-05, + "loss": 3.8231, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.4836303683986055e-05, + "loss": 3.8354, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827934115279264e-05, + "loss": 3.8381, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.4819548167768744e-05, + "loss": 3.829, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.4811162220258224e-05, + "loss": 3.8263, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.4802776272747704e-05, + "loss": 3.8342, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479440670404091e-05, + "loss": 3.8144, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478602075653039e-05, + "loss": 3.8315, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477763480901987e-05, + "loss": 3.8272, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476924886150935e-05, + "loss": 3.8178, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476087929280256e-05, + "loss": 3.8149, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475249334529205e-05, + "loss": 3.8122, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474410739778153e-05, + "loss": 3.8191, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473572145027101e-05, + "loss": 3.8248, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472735188156422e-05, + "loss": 3.8281, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.47189659340537e-05, + "loss": 3.8222, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471057998654318e-05, + "loss": 3.8228, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470219403903266e-05, + "loss": 3.8213, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469382447032587e-05, + "loss": 3.8045, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468543852281535e-05, + "loss": 3.8186, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467705257530483e-05, + "loss": 3.8069, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466866662779431e-05, + "loss": 3.8117, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.4660297059087516e-05, + "loss": 3.8107, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.4651911111577e-05, + "loss": 3.8256, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464352516406648e-05, + "loss": 3.8174, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463513921655596e-05, + "loss": 3.8043, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.462676964784917e-05, + "loss": 3.8215, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461838370033865e-05, + "loss": 3.8165, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.460999775282813e-05, + "loss": 3.8197, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460161180531761e-05, + "loss": 3.8123, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459324223661082e-05, + "loss": 3.8021, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.45848562891003e-05, + "loss": 3.8196, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457647034158978e-05, + "loss": 3.8066, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456808439407926e-05, + "loss": 3.8145, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455971482537247e-05, + "loss": 3.8056, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551328877861956e-05, + "loss": 3.8048, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542942930351436e-05, + "loss": 3.8041, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534556982840916e-05, + "loss": 3.8106, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526187414134125e-05, + "loss": 3.8077, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517801466623605e-05, + "loss": 3.8092, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509415519113085e-05, + "loss": 3.8165, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501029571602565e-05, + "loss": 3.7997, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492660002895774e-05, + "loss": 3.7971, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.4484274055385254e-05, + "loss": 3.8236, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.4475888107874734e-05, + "loss": 3.7875, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467502160364214e-05, + "loss": 3.7889, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445913259165742e-05, + "loss": 3.8015, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445074664414691e-05, + "loss": 3.816, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444236069663639e-05, + "loss": 3.7973, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443397474912587e-05, + "loss": 3.8023, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442560518041908e-05, + "loss": 3.7931, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441721923290856e-05, + "loss": 3.7987, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440883328539804e-05, + "loss": 3.808, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440044733788752e-05, + "loss": 3.806, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439207776918073e-05, + "loss": 3.8031, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438369182167021e-05, + "loss": 3.8081, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437530587415969e-05, + "loss": 3.8101, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.436691992664917e-05, + "loss": 3.7962, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435855035794238e-05, + "loss": 3.7975, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.4350164410431864e-05, + "loss": 3.8091, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.4341778462921344e-05, + "loss": 3.7866, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.8009, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432502294670403e-05, + "loss": 3.7934, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431663699919351e-05, + "loss": 3.8139, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430825105168299e-05, + "loss": 3.7983, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.7925, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429149553546568e-05, + "loss": 3.7823, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428310958795516e-05, + "loss": 3.8034, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427472364044464e-05, + "loss": 3.8059, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426633769293412e-05, + "loss": 3.7998, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425796812422733e-05, + "loss": 3.792, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.424958217671682e-05, + "loss": 3.7952, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.42411962292063e-05, + "loss": 3.8023, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.7905, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224440712988986e-05, + "loss": 3.79, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216054765478466e-05, + "loss": 3.8023, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207668817967946e-05, + "loss": 3.8027, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199299249261155e-05, + "loss": 3.7995, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190913301750635e-05, + "loss": 3.7843, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182527354240115e-05, + "loss": 3.7936, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174141406729595e-05, + "loss": 3.7878, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165771838022804e-05, + "loss": 3.7957, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157385890512284e-05, + "loss": 3.7962, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414899994300177e-05, + "loss": 3.7936, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.4140613995491244e-05, + "loss": 3.7868, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.7887, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412385847927394e-05, + "loss": 3.7823, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411547253176342e-05, + "loss": 3.7869, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410708658425289e-05, + "loss": 3.7802, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409871701554611e-05, + "loss": 3.797, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409033106803559e-05, + "loss": 3.789, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408194512052507e-05, + "loss": 3.7876, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407355917301454e-05, + "loss": 3.7825, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406518960430776e-05, + "loss": 3.7937, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405680365679724e-05, + "loss": 3.7929, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404841770928672e-05, + "loss": 3.7819, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40400317617762e-05, + "loss": 3.7948, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.4031662193069414e-05, + "loss": 3.797, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402329262436262e-05, + "loss": 3.7918, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.40149066768521e-05, + "loss": 3.7934, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400652072934158e-05, + "loss": 3.7798, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399813478183106e-05, + "loss": 3.7919, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398974883432054e-05, + "loss": 3.7868, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981362886810016e-05, + "loss": 3.7929, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972976939299496e-05, + "loss": 3.7729, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964590991788976e-05, + "loss": 3.7918, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395622142308219e-05, + "loss": 3.7862, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394783547557167e-05, + "loss": 3.7809, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393944952806115e-05, + "loss": 3.7758, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393106358055063e-05, + "loss": 3.7783, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392269401184384e-05, + "loss": 3.7787, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391430806433332e-05, + "loss": 3.7915, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.39059221168228e-05, + "loss": 3.7927, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389753616931228e-05, + "loss": 3.7976, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388916660060549e-05, + "loss": 3.7693, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388078065309497e-05, + "loss": 3.7923, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387239470558445e-05, + "loss": 3.787, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386400875807393e-05, + "loss": 3.7809, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855639189367145e-05, + "loss": 3.7771, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847253241856625e-05, + "loss": 3.7906, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838867294346105e-05, + "loss": 3.7811, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830481346835585e-05, + "loss": 3.7872, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822111778128794e-05, + "loss": 3.7796, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813725830618274e-05, + "loss": 3.7854, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805339883107754e-05, + "loss": 3.7869, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796953935597234e-05, + "loss": 3.7802, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378858436689044e-05, + "loss": 3.7852, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378019841937992e-05, + "loss": 3.7919, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.37718124718694e-05, + "loss": 3.7802, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376342652435888e-05, + "loss": 3.7825, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.375504057684836e-05, + "loss": 3.7842, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.90229868888855, + "eval_runtime": 304.1721, + "eval_samples_per_second": 1254.523, + "eval_steps_per_second": 39.205, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374665462933785e-05, + "loss": 3.7724, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373826868182733e-05, + "loss": 3.7685, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372989911312054e-05, + "loss": 3.7844, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372151316561002e-05, + "loss": 3.7843, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.37131272180995e-05, + "loss": 3.7905, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370474127058898e-05, + "loss": 3.7715, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369637170188219e-05, + "loss": 3.7777, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368798575437167e-05, + "loss": 3.7655, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367959980686115e-05, + "loss": 3.783, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367121385935063e-05, + "loss": 3.7749, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366284429064384e-05, + "loss": 3.7752, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365445834313332e-05, + "loss": 3.7806, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364608877442653e-05, + "loss": 3.7712, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363770282691601e-05, + "loss": 3.7737, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362931687940549e-05, + "loss": 3.7672, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362093093189497e-05, + "loss": 3.7623, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361254498438445e-05, + "loss": 3.7664, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360415903687393e-05, + "loss": 3.7733, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359577308936341e-05, + "loss": 3.7711, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358738714185289e-05, + "loss": 3.7867, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.35790175731461e-05, + "loss": 3.7854, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357063162563558e-05, + "loss": 3.7783, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356224567812506e-05, + "loss": 3.7753, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355385973061454e-05, + "loss": 3.7806, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354549016190776e-05, + "loss": 3.7649, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353710421439724e-05, + "loss": 3.7782, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352871826688672e-05, + "loss": 3.775, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.35203323193762e-05, + "loss": 3.7656, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511962750669406e-05, + "loss": 3.7639, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503576803158886e-05, + "loss": 3.7647, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495190855648366e-05, + "loss": 3.7695, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486804908137846e-05, + "loss": 3.7734, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478435339431055e-05, + "loss": 3.7813, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470049391920535e-05, + "loss": 3.7707, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461663444410015e-05, + "loss": 3.7712, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453277496899495e-05, + "loss": 3.7722, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344490792819271e-05, + "loss": 3.7599, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343652198068219e-05, + "loss": 3.7612, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342813603317167e-05, + "loss": 3.7556, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341975008566115e-05, + "loss": 3.76, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341138051695436e-05, + "loss": 3.7602, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340299456944384e-05, + "loss": 3.7766, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339460862193332e-05, + "loss": 3.7682, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338622267442279e-05, + "loss": 3.7547, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337785310571601e-05, + "loss": 3.776, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336946715820549e-05, + "loss": 3.7624, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336108121069497e-05, + "loss": 3.7745, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335271164198818e-05, + "loss": 3.7613, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344325694477664e-05, + "loss": 3.7525, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335939746967144e-05, + "loss": 3.7684, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327553799456624e-05, + "loss": 3.7611, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331918423074983e-05, + "loss": 3.7688, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331079828323931e-05, + "loss": 3.7545, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330241233572879e-05, + "loss": 3.7581, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.3294026388218266e-05, + "loss": 3.7528, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328565681951148e-05, + "loss": 3.7628, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327727087200096e-05, + "loss": 3.7632, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326888492449044e-05, + "loss": 3.7581, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.3260498976979915e-05, + "loss": 3.7704, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325212940827313e-05, + "loss": 3.754, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324374346076261e-05, + "loss": 3.7492, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.32353575132521e-05, + "loss": 3.776, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322697156574157e-05, + "loss": 3.7425, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218618375838516e-05, + "loss": 3.7379, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210232428327996e-05, + "loss": 3.7555, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201846480817476e-05, + "loss": 3.7691, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193460533306956e-05, + "loss": 3.7461, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185074585796436e-05, + "loss": 3.7586, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176688638285916e-05, + "loss": 3.7435, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316830269077539e-05, + "loss": 3.7502, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315991674326487e-05, + "loss": 3.7611, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151547174558085e-05, + "loss": 3.7591, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.3143161227047565e-05, + "loss": 3.7576, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.3134775279537045e-05, + "loss": 3.7567, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.3126389332026525e-05, + "loss": 3.7661, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311801976331974e-05, + "loss": 3.7475, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109633815809214e-05, + "loss": 3.7554, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101247868298694e-05, + "loss": 3.7576, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092861920788174e-05, + "loss": 3.741, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308449235208139e-05, + "loss": 3.7536, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307610640457086e-05, + "loss": 3.7506, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306772045706034e-05, + "loss": 3.7623, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305933450954982e-05, + "loss": 3.7566, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305096494084304e-05, + "loss": 3.7453, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304257899333252e-05, + "loss": 3.737, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034193045822e-05, + "loss": 3.7549, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302580709831148e-05, + "loss": 3.76, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301743752960469e-05, + "loss": 3.7472, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300905158209417e-05, + "loss": 3.7511, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300066563458365e-05, + "loss": 3.7483, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299227968707313e-05, + "loss": 3.7535, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983910118366337e-05, + "loss": 3.7438, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975524170855817e-05, + "loss": 3.7429, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967138223345296e-05, + "loss": 3.7597, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958752275834776e-05, + "loss": 3.7579, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295038270712799e-05, + "loss": 3.7532, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294199675961747e-05, + "loss": 3.7383, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293361081210695e-05, + "loss": 3.7499, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292522486459643e-05, + "loss": 3.7393, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291685529588964e-05, + "loss": 3.7538, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290846934837912e-05, + "loss": 3.7501, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290009977967234e-05, + "loss": 3.748, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289171383216181e-05, + "loss": 3.7417, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288332788465129e-05, + "loss": 3.7396, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287494193714077e-05, + "loss": 3.7443, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286655598963025e-05, + "loss": 3.7383, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.285817004211973e-05, + "loss": 3.7375, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284978409460921e-05, + "loss": 3.7498, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.28413981470987e-05, + "loss": 3.7471, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833028578391906e-05, + "loss": 3.7425, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824642630881386e-05, + "loss": 3.7358, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816256683370866e-05, + "loss": 3.7481, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807887114664075e-05, + "loss": 3.7505, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799501167153555e-05, + "loss": 3.7386, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791115219643035e-05, + "loss": 3.7497, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782729272132515e-05, + "loss": 3.7513, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774343324621995e-05, + "loss": 3.7518, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765973755915204e-05, + "loss": 3.7443, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757587808404684e-05, + "loss": 3.7402, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749201860894164e-05, + "loss": 3.744, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274081591338365e-05, + "loss": 3.743, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273242996587313e-05, + "loss": 3.7479, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272404401836261e-05, + "loss": 3.7325, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271565807085209e-05, + "loss": 3.7444, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.27072885021453e-05, + "loss": 3.743, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269890255463478e-05, + "loss": 3.7368, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269051660712426e-05, + "loss": 3.7296, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268213065961374e-05, + "loss": 3.7388, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267376109090695e-05, + "loss": 3.7316, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266537514339643e-05, + "loss": 3.7453, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265698919588591e-05, + "loss": 3.7474, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264860324837539e-05, + "loss": 3.7551, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.2640233679668604e-05, + "loss": 3.7269, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.2631847732158084e-05, + "loss": 3.7484, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262347816345129e-05, + "loss": 3.7441, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261509221594077e-05, + "loss": 3.738, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260670626843025e-05, + "loss": 3.7334, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259832032091973e-05, + "loss": 3.7487, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258993437340921e-05, + "loss": 3.7332, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258154842589869e-05, + "loss": 3.7479, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257316247838817e-05, + "loss": 3.734, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.2564776530877646e-05, + "loss": 3.745, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255640696217086e-05, + "loss": 3.7417, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254802101466034e-05, + "loss": 3.7374, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253965144595356e-05, + "loss": 3.7466, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253126549844304e-05, + "loss": 3.7423, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252287955093252e-05, + "loss": 3.745, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.2514493603422e-05, + "loss": 3.7306, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250610765591147e-05, + "loss": 3.7453, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.8876891136169434, + "eval_runtime": 303.0714, + "eval_samples_per_second": 1259.079, + "eval_steps_per_second": 39.347, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249772170840095e-05, + "loss": 3.7321, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.248933576089043e-05, + "loss": 3.724, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248094981337991e-05, + "loss": 3.7398, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247256386586939e-05, + "loss": 3.7432, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246417791835887e-05, + "loss": 3.7474, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245579197084835e-05, + "loss": 3.7286, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244742240214156e-05, + "loss": 3.7341, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243903645463104e-05, + "loss": 3.7226, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243065050712052e-05, + "loss": 3.742, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422264559610006e-05, + "loss": 3.7316, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413878612099486e-05, + "loss": 3.7376, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405492664588966e-05, + "loss": 3.7371, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397123095882175e-05, + "loss": 3.7273, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7364, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7217, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7202, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7255, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355193358329575e-05, + "loss": 3.7376, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346807410819055e-05, + "loss": 3.7278, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233842146330853e-05, + "loss": 3.7464, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7416, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.2321665947091224e-05, + "loss": 3.7395, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.2313279999580704e-05, + "loss": 3.7345, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.2304894052070184e-05, + "loss": 3.7353, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.7226, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228813853585288e-05, + "loss": 3.7413, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227975258834236e-05, + "loss": 3.7305, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227136664083183e-05, + "loss": 3.7247, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.7256, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225462750341826e-05, + "loss": 3.7253, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224624155590774e-05, + "loss": 3.7279, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223785560839722e-05, + "loss": 3.7353, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7346, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7362, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221269776586566e-05, + "loss": 3.7235, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220431181835514e-05, + "loss": 3.7322, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219592587084462e-05, + "loss": 3.7252, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7171, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217917035462731e-05, + "loss": 3.7147, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217080078592052e-05, + "loss": 3.7215, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7196, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154028890899476e-05, + "loss": 3.7357, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145642943388956e-05, + "loss": 3.7276, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137256995878436e-05, + "loss": 3.7161, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128871048367915e-05, + "loss": 3.737, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120485100857395e-05, + "loss": 3.7215, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211209915334688e-05, + "loss": 3.7336, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210372958464009e-05, + "loss": 3.7219, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209534363712957e-05, + "loss": 3.7073, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208695768961905e-05, + "loss": 3.7352, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207857174210853e-05, + "loss": 3.7185, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.207020217340174e-05, + "loss": 3.7299, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206181622589122e-05, + "loss": 3.7192, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.20534302783807e-05, + "loss": 3.7183, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204506070967391e-05, + "loss": 3.7077, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203667476216339e-05, + "loss": 3.7196, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.202828881465287e-05, + "loss": 3.7304, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201990286714235e-05, + "loss": 3.7152, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011516919631836e-05, + "loss": 3.7294, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.2003130972121316e-05, + "loss": 3.7196, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994745024610796e-05, + "loss": 3.7114, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986359077100276e-05, + "loss": 3.7338, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1977989508393485e-05, + "loss": 3.7046, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969603560882965e-05, + "loss": 3.7008, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.1961233992176174e-05, + "loss": 3.7183, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.1952848044665654e-05, + "loss": 3.7267, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.1944462097155134e-05, + "loss": 3.7055, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936076149644614e-05, + "loss": 3.7227, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927690202134094e-05, + "loss": 3.7028, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.1919304254623574e-05, + "loss": 3.7155, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.1910918307113054e-05, + "loss": 3.7223, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190254873840627e-05, + "loss": 3.7176, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189417916969948e-05, + "loss": 3.7205, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188579322218896e-05, + "loss": 3.7166, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187740727467844e-05, + "loss": 3.7276, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186902132716792e-05, + "loss": 3.7083, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.18606353796574e-05, + "loss": 3.7194, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185224943214688e-05, + "loss": 3.7143, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184386348463636e-05, + "loss": 3.7038, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183547753712584e-05, + "loss": 3.717, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182710796841905e-05, + "loss": 3.7149, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.1818738399712256e-05, + "loss": 3.724, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181035245220174e-05, + "loss": 3.722, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180196650469122e-05, + "loss": 3.7004, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.17935805571807e-05, + "loss": 3.7016, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178519460967018e-05, + "loss": 3.7177, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177680866215966e-05, + "loss": 3.7241, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768422714649136e-05, + "loss": 3.713, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760036767138616e-05, + "loss": 3.7085, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175166719843183e-05, + "loss": 3.7145, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174328125092131e-05, + "loss": 3.7132, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173491168221452e-05, + "loss": 3.7116, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.1726525734704e-05, + "loss": 3.7021, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171813978719348e-05, + "loss": 3.7202, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170975383968296e-05, + "loss": 3.719, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.170136789217244e-05, + "loss": 3.7189, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169298194466192e-05, + "loss": 3.7035, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.16845959971514e-05, + "loss": 3.7072, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167621004964088e-05, + "loss": 3.7062, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166784048093409e-05, + "loss": 3.7154, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165945453342357e-05, + "loss": 3.711, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651084964716786e-05, + "loss": 3.7073, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164269901720626e-05, + "loss": 3.7103, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163431306969574e-05, + "loss": 3.7028, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162592712218522e-05, + "loss": 3.7063, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.16175411746747e-05, + "loss": 3.701, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.160915522716418e-05, + "loss": 3.7029, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160076927965366e-05, + "loss": 3.7067, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.1592383332143145e-05, + "loss": 3.7142, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.1584013763436354e-05, + "loss": 3.7001, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.1575627815925834e-05, + "loss": 3.7037, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.1567241868415314e-05, + "loss": 3.7052, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.1558872299708523e-05, + "loss": 3.7122, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.1550486352198003e-05, + "loss": 3.7031, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154210040468748e-05, + "loss": 3.7168, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153371445717696e-05, + "loss": 3.7125, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152532850966644e-05, + "loss": 3.7125, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151695894095965e-05, + "loss": 3.7083, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150857299344913e-05, + "loss": 3.7069, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150018704593861e-05, + "loss": 3.7059, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.14918010984281e-05, + "loss": 3.708, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148341515091758e-05, + "loss": 3.7052, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147502920340706e-05, + "loss": 3.7004, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146664325589654e-05, + "loss": 3.711, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145827368718975e-05, + "loss": 3.7077, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144990411848296e-05, + "loss": 3.7015, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144151817097244e-05, + "loss": 3.6924, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143313222346192e-05, + "loss": 3.6987, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.14247462759514e-05, + "loss": 3.6966, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141636032844088e-05, + "loss": 3.7076, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140797438093036e-05, + "loss": 3.7124, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139958843341984e-05, + "loss": 3.7194, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139120248590932e-05, + "loss": 3.6918, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138283291720253e-05, + "loss": 3.7113, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137444696969201e-05, + "loss": 3.7062, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136606102218149e-05, + "loss": 3.7071, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135767507467097e-05, + "loss": 3.6971, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349289127160446e-05, + "loss": 3.7106, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340903179649926e-05, + "loss": 3.6979, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332517232139406e-05, + "loss": 3.7156, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132414766343262e-05, + "loss": 3.695, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.1315761715922095e-05, + "loss": 3.7082, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307375768411575e-05, + "loss": 3.705, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1298989820901055e-05, + "loss": 3.7038, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.129062025219427e-05, + "loss": 3.7084, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128223430468375e-05, + "loss": 3.7072, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.127384835717323e-05, + "loss": 3.7069, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.126546240966271e-05, + "loss": 3.6972, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125707646215219e-05, + "loss": 3.7122, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.8773159980773926, + "eval_runtime": 302.013, + "eval_samples_per_second": 1263.492, + "eval_steps_per_second": 39.485, + "step": 534240 + }, + { + "epoch": 0.0, + "learning_rate": 4.124869051464167e-05, + "loss": 3.695, + "step": 534528 + }, + { + "epoch": 0.0, + "learning_rate": 4.124030456713115e-05, + "loss": 3.6872, + "step": 535040 + }, + { + "epoch": 0.0, + "learning_rate": 4.123191861962063e-05, + "loss": 3.705, + "step": 535552 + }, + { + "epoch": 0.0, + "learning_rate": 4.122353267211011e-05, + "loss": 3.7082, + "step": 536064 + }, + { + "epoch": 0.0, + "learning_rate": 4.121514672459959e-05, + "loss": 3.7095, + "step": 536576 + }, + { + "epoch": 0.0, + "learning_rate": 4.120676077708907e-05, + "loss": 3.6945, + "step": 537088 + }, + { + "epoch": 0.0, + "learning_rate": 4.119839120838228e-05, + "loss": 3.7007, + "step": 537600 + }, + { + "epoch": 0.0, + "learning_rate": 4.119000526087176e-05, + "loss": 3.6884, + "step": 538112 + }, + { + "epoch": 0.0, + "learning_rate": 4.118161931336124e-05, + "loss": 3.706, + "step": 538624 + }, + { + "epoch": 0.0, + "learning_rate": 4.117323336585072e-05, + "loss": 3.6989, + "step": 539136 + }, + { + "epoch": 0.0, + "learning_rate": 4.11648474183402e-05, + "loss": 3.7013, + "step": 539648 + }, + { + "epoch": 0.0, + "learning_rate": 4.1156461470829686e-05, + "loss": 3.7014, + "step": 540160 + }, + { + "epoch": 0.0, + "learning_rate": 4.1148091902122895e-05, + "loss": 3.6973, + "step": 540672 + }, + { + "epoch": 0.0, + "learning_rate": 4.1139705954612375e-05, + "loss": 3.695, + "step": 541184 + }, + { + "epoch": 0.0, + "learning_rate": 4.1131320007101855e-05, + "loss": 3.6902, + "step": 541696 + }, + { + "epoch": 0.0, + "learning_rate": 4.1122934059591335e-05, + "loss": 3.6841, + "step": 542208 + }, + { + "epoch": 0.0, + "learning_rate": 4.111454811208081e-05, + "loss": 3.6926, + "step": 542720 + }, + { + "epoch": 0.0, + "learning_rate": 4.110616216457029e-05, + "loss": 3.7014, + "step": 543232 + }, + { + "epoch": 0.0, + "learning_rate": 4.109777621705977e-05, + "loss": 3.695, + "step": 543744 + }, + { + "epoch": 0.0, + "learning_rate": 4.108939026954925e-05, + "loss": 3.7054, + "step": 544256 + }, + { + "epoch": 0.0, + "learning_rate": 4.108102070084246e-05, + "loss": 3.7104, + "step": 544768 + }, + { + "epoch": 0.0, + "learning_rate": 4.107263475333194e-05, + "loss": 3.7082, + "step": 545280 + }, + { + "epoch": 0.0, + "learning_rate": 4.106426518462515e-05, + "loss": 3.6992, + "step": 545792 + }, + { + "epoch": 0.0, + "learning_rate": 4.105587923711463e-05, + "loss": 3.6972, + "step": 546304 + }, + { + "epoch": 0.0, + "learning_rate": 4.104749328960411e-05, + "loss": 3.6953, + "step": 546816 + }, + { + "epoch": 0.0, + "learning_rate": 4.103910734209359e-05, + "loss": 3.7045, + "step": 547328 + }, + { + "epoch": 0.0, + "learning_rate": 4.103072139458307e-05, + "loss": 3.695, + "step": 547840 + }, + { + "epoch": 0.0, + "learning_rate": 4.102233544707255e-05, + "loss": 3.6939, + "step": 548352 + }, + { + "epoch": 0.0, + "learning_rate": 4.101394949956203e-05, + "loss": 3.6928, + "step": 548864 + }, + { + "epoch": 0.0, + "learning_rate": 4.100556355205151e-05, + "loss": 3.6889, + "step": 549376 + }, + { + "epoch": 0.01, + "learning_rate": 4.099719398334472e-05, + "loss": 3.6888, + "step": 549888 + }, + { + "epoch": 0.01, + "learning_rate": 4.098882441463793e-05, + "loss": 3.7001, + "step": 550400 + }, + { + "epoch": 0.01, + "learning_rate": 4.098043846712741e-05, + "loss": 3.7019, + "step": 550912 + }, + { + "epoch": 0.01, + "learning_rate": 4.097205251961689e-05, + "loss": 3.7015, + "step": 551424 + }, + { + "epoch": 0.01, + "learning_rate": 4.096366657210638e-05, + "loss": 3.687, + "step": 551936 + }, + { + "epoch": 0.01, + "learning_rate": 4.095528062459586e-05, + "loss": 3.7012, + "step": 552448 + }, + { + "epoch": 0.01, + "learning_rate": 4.094689467708534e-05, + "loss": 3.695, + "step": 552960 + }, + { + "epoch": 0.01, + "learning_rate": 4.093850872957482e-05, + "loss": 3.6822, + "step": 553472 + }, + { + "epoch": 0.01, + "learning_rate": 4.0930139160868026e-05, + "loss": 3.6806, + "step": 553984 + }, + { + "epoch": 0.01, + "learning_rate": 4.0921769592161235e-05, + "loss": 3.6865, + "step": 554496 + }, + { + "epoch": 0.01, + "learning_rate": 4.0913383644650715e-05, + "loss": 3.6898, + "step": 555008 + }, + { + "epoch": 0.01, + "learning_rate": 4.0904997697140195e-05, + "loss": 3.6957, + "step": 555520 + }, + { + "epoch": 0.01, + "learning_rate": 4.0896611749629675e-05, + "loss": 3.6966, + "step": 556032 + }, + { + "epoch": 0.01, + "learning_rate": 4.0888225802119155e-05, + "loss": 3.6815, + "step": 556544 + }, + { + "epoch": 0.01, + "learning_rate": 4.0879839854608635e-05, + "loss": 3.703, + "step": 557056 + }, + { + "epoch": 0.01, + "learning_rate": 4.0871453907098115e-05, + "loss": 3.6892, + "step": 557568 + }, + { + "epoch": 0.01, + "learning_rate": 4.0863067959587595e-05, + "loss": 3.7011, + "step": 558080 + }, + { + "epoch": 0.01, + "learning_rate": 4.085469839088081e-05, + "loss": 3.6921, + "step": 558592 + }, + { + "epoch": 0.01, + "learning_rate": 4.084631244337029e-05, + "loss": 3.6686, + "step": 559104 + }, + { + "epoch": 0.01, + "learning_rate": 4.083792649585977e-05, + "loss": 3.7055, + "step": 559616 + }, + { + "epoch": 0.01, + "learning_rate": 4.082954054834925e-05, + "loss": 3.6827, + "step": 560128 + }, + { + "epoch": 0.01, + "learning_rate": 4.082117097964246e-05, + "loss": 3.6951, + "step": 560640 + }, + { + "epoch": 0.01, + "learning_rate": 4.081278503213194e-05, + "loss": 3.6858, + "step": 561152 + }, + { + "epoch": 0.01, + "learning_rate": 4.080439908462142e-05, + "loss": 3.6858, + "step": 561664 + }, + { + "epoch": 0.01, + "learning_rate": 4.079602951591463e-05, + "loss": 3.6796, + "step": 562176 + }, + { + "epoch": 0.01, + "learning_rate": 4.078764356840411e-05, + "loss": 3.6819, + "step": 562688 + }, + { + "epoch": 0.01, + "learning_rate": 4.077925762089359e-05, + "loss": 3.7019, + "step": 563200 + }, + { + "epoch": 0.01, + "learning_rate": 4.077087167338307e-05, + "loss": 3.6762, + "step": 563712 + }, + { + "epoch": 0.01, + "learning_rate": 4.076248572587255e-05, + "loss": 3.6972, + "step": 564224 + }, + { + "epoch": 0.01, + "learning_rate": 4.075409977836203e-05, + "loss": 3.6895, + "step": 564736 + }, + { + "epoch": 0.01, + "learning_rate": 4.0745713830851515e-05, + "loss": 3.6757, + "step": 565248 + }, + { + "epoch": 0.01, + "learning_rate": 4.0737344262144724e-05, + "loss": 3.6975, + "step": 565760 + }, + { + "epoch": 0.01, + "learning_rate": 4.0728958314634204e-05, + "loss": 3.6784, + "step": 566272 + }, + { + "epoch": 0.01, + "learning_rate": 4.0720572367123684e-05, + "loss": 3.6706, + "step": 566784 + }, + { + "epoch": 0.01, + "learning_rate": 4.0712186419613164e-05, + "loss": 3.6825, + "step": 567296 + }, + { + "epoch": 0.01, + "learning_rate": 4.0703800472102644e-05, + "loss": 3.6909, + "step": 567808 + }, + { + "epoch": 0.01, + "learning_rate": 4.069541452459212e-05, + "loss": 3.674, + "step": 568320 + }, + { + "epoch": 0.01, + "learning_rate": 4.06870285770816e-05, + "loss": 3.6897, + "step": 568832 + }, + { + "epoch": 0.01, + "learning_rate": 4.067864262957108e-05, + "loss": 3.672, + "step": 569344 + }, + { + "epoch": 0.01, + "learning_rate": 4.0670273060864286e-05, + "loss": 3.6815, + "step": 569856 + }, + { + "epoch": 0.01, + "learning_rate": 4.0661887113353766e-05, + "loss": 3.6892, + "step": 570368 + }, + { + "epoch": 0.01, + "learning_rate": 4.065350116584325e-05, + "loss": 3.6846, + "step": 570880 + }, + { + "epoch": 0.01, + "learning_rate": 4.064511521833273e-05, + "loss": 3.6928, + "step": 571392 + }, + { + "epoch": 0.01, + "learning_rate": 4.063674564962594e-05, + "loss": 3.6811, + "step": 571904 + }, + { + "epoch": 0.01, + "learning_rate": 4.062835970211542e-05, + "loss": 3.6925, + "step": 572416 + }, + { + "epoch": 0.01, + "learning_rate": 4.06199737546049e-05, + "loss": 3.6798, + "step": 572928 + }, + { + "epoch": 0.01, + "learning_rate": 4.061158780709438e-05, + "loss": 3.6874, + "step": 573440 + }, + { + "epoch": 0.01, + "learning_rate": 4.060320185958386e-05, + "loss": 3.6764, + "step": 573952 + }, + { + "epoch": 0.01, + "learning_rate": 4.059481591207334e-05, + "loss": 3.6759, + "step": 574464 + }, + { + "epoch": 0.01, + "learning_rate": 4.058642996456282e-05, + "loss": 3.6835, + "step": 574976 + }, + { + "epoch": 0.01, + "learning_rate": 4.05780440170523e-05, + "loss": 3.6832, + "step": 575488 + }, + { + "epoch": 0.01, + "learning_rate": 4.056967444834551e-05, + "loss": 3.6895, + "step": 576000 + }, + { + "epoch": 0.01, + "learning_rate": 4.056128850083499e-05, + "loss": 3.6926, + "step": 576512 + }, + { + "epoch": 0.01, + "learning_rate": 4.055290255332447e-05, + "loss": 3.6663, + "step": 577024 + }, + { + "epoch": 0.01, + "learning_rate": 4.054451660581395e-05, + "loss": 3.6712, + "step": 577536 + }, + { + "epoch": 0.01, + "learning_rate": 4.0536147037107167e-05, + "loss": 3.6819, + "step": 578048 + }, + { + "epoch": 0.01, + "learning_rate": 4.0527777468400376e-05, + "loss": 3.6919, + "step": 578560 + }, + { + "epoch": 0.01, + "learning_rate": 4.0519391520889856e-05, + "loss": 3.6817, + "step": 579072 + }, + { + "epoch": 0.01, + "learning_rate": 4.0511005573379336e-05, + "loss": 3.6759, + "step": 579584 + }, + { + "epoch": 0.02, + "learning_rate": 4.0502619625868816e-05, + "loss": 3.6872, + "step": 580096 + }, + { + "epoch": 0.02, + "learning_rate": 4.0494233678358296e-05, + "loss": 3.6814, + "step": 580608 + }, + { + "epoch": 0.02, + "learning_rate": 4.0485864109651505e-05, + "loss": 3.68, + "step": 581120 + }, + { + "epoch": 0.02, + "learning_rate": 4.0477478162140985e-05, + "loss": 3.6721, + "step": 581632 + }, + { + "epoch": 0.02, + "learning_rate": 4.0469092214630465e-05, + "loss": 3.6839, + "step": 582144 + }, + { + "epoch": 0.02, + "learning_rate": 4.0460706267119944e-05, + "loss": 3.6902, + "step": 582656 + }, + { + "epoch": 0.02, + "learning_rate": 4.0452320319609424e-05, + "loss": 3.6867, + "step": 583168 + }, + { + "epoch": 0.02, + "learning_rate": 4.0443934372098904e-05, + "loss": 3.6713, + "step": 583680 + }, + { + "epoch": 0.02, + "learning_rate": 4.0435548424588384e-05, + "loss": 3.673, + "step": 584192 + }, + { + "epoch": 0.02, + "learning_rate": 4.042716247707787e-05, + "loss": 3.6729, + "step": 584704 + }, + { + "epoch": 0.02, + "learning_rate": 4.041879290837108e-05, + "loss": 3.6852, + "step": 585216 + }, + { + "epoch": 0.02, + "learning_rate": 4.041040696086056e-05, + "loss": 3.6804, + "step": 585728 + }, + { + "epoch": 0.02, + "learning_rate": 4.040203739215377e-05, + "loss": 3.6759, + "step": 586240 + }, + { + "epoch": 0.02, + "learning_rate": 4.039365144464325e-05, + "loss": 3.678, + "step": 586752 + }, + { + "epoch": 0.02, + "learning_rate": 4.038526549713273e-05, + "loss": 3.6725, + "step": 587264 + }, + { + "epoch": 0.02, + "learning_rate": 4.037687954962221e-05, + "loss": 3.674, + "step": 587776 + }, + { + "epoch": 0.02, + "learning_rate": 4.036849360211169e-05, + "loss": 3.6675, + "step": 588288 + }, + { + "epoch": 0.02, + "learning_rate": 4.036010765460117e-05, + "loss": 3.6738, + "step": 588800 + }, + { + "epoch": 0.02, + "learning_rate": 4.035172170709065e-05, + "loss": 3.6757, + "step": 589312 + }, + { + "epoch": 0.02, + "learning_rate": 4.034333575958012e-05, + "loss": 3.6812, + "step": 589824 + }, + { + "epoch": 0.02, + "learning_rate": 4.033496619087334e-05, + "loss": 3.671, + "step": 590336 + }, + { + "epoch": 0.02, + "learning_rate": 4.0326580243362825e-05, + "loss": 3.6651, + "step": 590848 + }, + { + "epoch": 0.02, + "learning_rate": 4.0318194295852305e-05, + "loss": 3.6773, + "step": 591360 + }, + { + "epoch": 0.02, + "learning_rate": 4.0309824727145514e-05, + "loss": 3.6791, + "step": 591872 + }, + { + "epoch": 0.02, + "learning_rate": 4.0301438779634994e-05, + "loss": 3.6724, + "step": 592384 + }, + { + "epoch": 0.02, + "learning_rate": 4.0293052832124474e-05, + "loss": 3.6817, + "step": 592896 + }, + { + "epoch": 0.02, + "learning_rate": 4.0284666884613954e-05, + "loss": 3.6802, + "step": 593408 + }, + { + "epoch": 0.02, + "learning_rate": 4.027628093710343e-05, + "loss": 3.687, + "step": 593920 + }, + { + "epoch": 0.02, + "learning_rate": 4.026791136839664e-05, + "loss": 3.6742, + "step": 594432 + }, + { + "epoch": 0.02, + "learning_rate": 4.025952542088612e-05, + "loss": 3.6758, + "step": 594944 + }, + { + "epoch": 0.02, + "learning_rate": 4.0251139473375596e-05, + "loss": 3.6716, + "step": 595456 + }, + { + "epoch": 0.02, + "learning_rate": 4.0242753525865076e-05, + "loss": 3.683, + "step": 595968 + }, + { + "epoch": 0.02, + "learning_rate": 4.023436757835456e-05, + "loss": 3.6747, + "step": 596480 + }, + { + "epoch": 0.02, + "learning_rate": 4.022598163084404e-05, + "loss": 3.6663, + "step": 596992 + }, + { + "epoch": 0.02, + "learning_rate": 4.021759568333352e-05, + "loss": 3.678, + "step": 597504 + }, + { + "epoch": 0.02, + "learning_rate": 4.020922611462673e-05, + "loss": 3.6824, + "step": 598016 + }, + { + "epoch": 0.02, + "learning_rate": 4.020084016711621e-05, + "loss": 3.6672, + "step": 598528 + }, + { + "epoch": 0.02, + "learning_rate": 4.019247059840943e-05, + "loss": 3.6651, + "step": 599040 + }, + { + "epoch": 0.02, + "learning_rate": 4.01840846508989e-05, + "loss": 3.6685, + "step": 599552 + }, + { + "epoch": 0.02, + "learning_rate": 4.017569870338838e-05, + "loss": 3.6673, + "step": 600064 + }, + { + "epoch": 0.02, + "learning_rate": 4.016731275587786e-05, + "loss": 3.6756, + "step": 600576 + }, + { + "epoch": 0.02, + "learning_rate": 4.015892680836734e-05, + "loss": 3.6838, + "step": 601088 + }, + { + "epoch": 0.02, + "learning_rate": 4.015055723966055e-05, + "loss": 3.6867, + "step": 601600 + }, + { + "epoch": 0.02, + "learning_rate": 4.014217129215003e-05, + "loss": 3.6608, + "step": 602112 + }, + { + "epoch": 0.02, + "learning_rate": 4.0133785344639516e-05, + "loss": 3.6826, + "step": 602624 + }, + { + "epoch": 0.02, + "learning_rate": 4.0125399397128996e-05, + "loss": 3.6748, + "step": 603136 + }, + { + "epoch": 0.02, + "learning_rate": 4.0117013449618476e-05, + "loss": 3.6739, + "step": 603648 + }, + { + "epoch": 0.02, + "learning_rate": 4.0108627502107956e-05, + "loss": 3.666, + "step": 604160 + }, + { + "epoch": 0.02, + "learning_rate": 4.0100241554597436e-05, + "loss": 3.6768, + "step": 604672 + }, + { + "epoch": 0.02, + "learning_rate": 4.0091855607086916e-05, + "loss": 3.6666, + "step": 605184 + }, + { + "epoch": 0.02, + "learning_rate": 4.0083486038380125e-05, + "loss": 3.6848, + "step": 605696 + }, + { + "epoch": 0.02, + "learning_rate": 4.0075100090869605e-05, + "loss": 3.6663, + "step": 606208 + }, + { + "epoch": 0.02, + "learning_rate": 4.0066714143359085e-05, + "loss": 3.6766, + "step": 606720 + }, + { + "epoch": 0.02, + "learning_rate": 4.0058328195848565e-05, + "loss": 3.6734, + "step": 607232 + }, + { + "epoch": 0.02, + "learning_rate": 4.0049958627141774e-05, + "loss": 3.677, + "step": 607744 + }, + { + "epoch": 0.02, + "learning_rate": 4.004158905843498e-05, + "loss": 3.6751, + "step": 608256 + }, + { + "epoch": 0.02, + "learning_rate": 4.003320311092447e-05, + "loss": 3.6753, + "step": 608768 + }, + { + "epoch": 0.02, + "learning_rate": 4.002481716341395e-05, + "loss": 3.6787, + "step": 609280 + }, + { + "epoch": 0.02, + "learning_rate": 4.001643121590343e-05, + "loss": 3.6676, + "step": 609792 + }, + { + "epoch": 0.02, + "learning_rate": 4.000804526839291e-05, + "loss": 3.6801, + "step": 610304 + }, + { + "epoch": 0.03, + "eval_loss": 3.8724730014801025, + "eval_runtime": 303.6358, + "eval_samples_per_second": 1256.739, + "eval_steps_per_second": 39.274, + "step": 610560 + }, + { + "epoch": 1.0, + "learning_rate": 3.999965932088239e-05, + "loss": 3.6657, + "step": 610816 + }, + { + "epoch": 1.0, + "learning_rate": 3.999127337337187e-05, + "loss": 3.6596, + "step": 611328 + }, + { + "epoch": 1.0, + "learning_rate": 3.998288742586135e-05, + "loss": 3.6727, + "step": 611840 + }, + { + "epoch": 1.0, + "learning_rate": 3.997451785715456e-05, + "loss": 3.6769, + "step": 612352 + }, + { + "epoch": 1.0, + "learning_rate": 3.996613190964404e-05, + "loss": 3.6815, + "step": 612864 + }, + { + "epoch": 1.0, + "learning_rate": 3.995774596213352e-05, + "loss": 3.6646, + "step": 613376 + }, + { + "epoch": 1.0, + "learning_rate": 3.994937639342673e-05, + "loss": 3.6752, + "step": 613888 + }, + { + "epoch": 1.0, + "learning_rate": 3.994099044591621e-05, + "loss": 3.6612, + "step": 614400 + }, + { + "epoch": 1.0, + "learning_rate": 3.993260449840569e-05, + "loss": 3.6707, + "step": 614912 + }, + { + "epoch": 1.0, + "learning_rate": 3.992421855089517e-05, + "loss": 3.6694, + "step": 615424 + }, + { + "epoch": 1.0, + "learning_rate": 3.991583260338465e-05, + "loss": 3.6718, + "step": 615936 + }, + { + "epoch": 1.0, + "learning_rate": 3.9907446655874134e-05, + "loss": 3.6694, + "step": 616448 + }, + { + "epoch": 1.0, + "learning_rate": 3.989907708716734e-05, + "loss": 3.671, + "step": 616960 + }, + { + "epoch": 1.0, + "learning_rate": 3.989069113965682e-05, + "loss": 3.6632, + "step": 617472 + }, + { + "epoch": 1.0, + "learning_rate": 3.98823051921463e-05, + "loss": 3.6622, + "step": 617984 + }, + { + "epoch": 1.0, + "learning_rate": 3.987391924463578e-05, + "loss": 3.6537, + "step": 618496 + }, + { + "epoch": 1.0, + "learning_rate": 3.9865533297125256e-05, + "loss": 3.6637, + "step": 619008 + }, + { + "epoch": 1.0, + "learning_rate": 3.9857147349614736e-05, + "loss": 3.6737, + "step": 619520 + }, + { + "epoch": 1.0, + "learning_rate": 3.984877778090795e-05, + "loss": 3.6622, + "step": 620032 + }, + { + "epoch": 1.0, + "learning_rate": 3.984039183339743e-05, + "loss": 3.676, + "step": 620544 + }, + { + "epoch": 1.0, + "learning_rate": 3.9832005885886905e-05, + "loss": 3.6796, + "step": 621056 + }, + { + "epoch": 1.0, + "learning_rate": 3.9823619938376385e-05, + "loss": 3.6761, + "step": 621568 + }, + { + "epoch": 1.0, + "learning_rate": 3.981523399086587e-05, + "loss": 3.6746, + "step": 622080 + }, + { + "epoch": 1.0, + "learning_rate": 3.980686442215909e-05, + "loss": 3.6651, + "step": 622592 + }, + { + "epoch": 1.0, + "learning_rate": 3.979847847464856e-05, + "loss": 3.6644, + "step": 623104 + }, + { + "epoch": 1.0, + "learning_rate": 3.979009252713804e-05, + "loss": 3.6727, + "step": 623616 + }, + { + "epoch": 1.0, + "learning_rate": 3.978170657962752e-05, + "loss": 3.6715, + "step": 624128 + }, + { + "epoch": 1.0, + "learning_rate": 3.9773320632117e-05, + "loss": 3.665, + "step": 624640 + }, + { + "epoch": 1.0, + "learning_rate": 3.976493468460648e-05, + "loss": 3.6635, + "step": 625152 + }, + { + "epoch": 1.0, + "learning_rate": 3.975656511589969e-05, + "loss": 3.6598, + "step": 625664 + }, + { + "epoch": 1.01, + "learning_rate": 3.974817916838917e-05, + "loss": 3.6563, + "step": 626176 + }, + { + "epoch": 1.01, + "learning_rate": 3.973979322087865e-05, + "loss": 3.6719, + "step": 626688 + }, + { + "epoch": 1.01, + "learning_rate": 3.973140727336813e-05, + "loss": 3.6736, + "step": 627200 + }, + { + "epoch": 1.01, + "learning_rate": 3.972302132585761e-05, + "loss": 3.6722, + "step": 627712 + }, + { + "epoch": 1.01, + "learning_rate": 3.971463537834709e-05, + "loss": 3.6597, + "step": 628224 + }, + { + "epoch": 1.01, + "learning_rate": 3.970624943083657e-05, + "loss": 3.6689, + "step": 628736 + }, + { + "epoch": 1.01, + "learning_rate": 3.9697879862129786e-05, + "loss": 3.6674, + "step": 629248 + }, + { + "epoch": 1.01, + "learning_rate": 3.9689493914619266e-05, + "loss": 3.6517, + "step": 629760 + }, + { + "epoch": 1.01, + "learning_rate": 3.9681107967108746e-05, + "loss": 3.6561, + "step": 630272 + }, + { + "epoch": 1.01, + "learning_rate": 3.9672722019598225e-05, + "loss": 3.6551, + "step": 630784 + }, + { + "epoch": 1.01, + "learning_rate": 3.9664368829695164e-05, + "loss": 3.6596, + "step": 631296 + }, + { + "epoch": 1.01, + "learning_rate": 3.9655982882184644e-05, + "loss": 3.6709, + "step": 631808 + }, + { + "epoch": 1.01, + "learning_rate": 3.9647596934674124e-05, + "loss": 3.6653, + "step": 632320 + }, + { + "epoch": 1.01, + "learning_rate": 3.9639210987163604e-05, + "loss": 3.6545, + "step": 632832 + }, + { + "epoch": 1.01, + "learning_rate": 3.9630825039653084e-05, + "loss": 3.6705, + "step": 633344 + }, + { + "epoch": 1.01, + "learning_rate": 3.9622439092142564e-05, + "loss": 3.659, + "step": 633856 + }, + { + "epoch": 1.01, + "learning_rate": 3.9614053144632043e-05, + "loss": 3.6734, + "step": 634368 + }, + { + "epoch": 1.01, + "learning_rate": 3.960568357592526e-05, + "loss": 3.6635, + "step": 634880 + }, + { + "epoch": 1.01, + "learning_rate": 3.959729762841474e-05, + "loss": 3.6389, + "step": 635392 + }, + { + "epoch": 1.01, + "learning_rate": 3.958891168090422e-05, + "loss": 3.6764, + "step": 635904 + }, + { + "epoch": 1.01, + "learning_rate": 3.95805257333937e-05, + "loss": 3.656, + "step": 636416 + }, + { + "epoch": 1.01, + "learning_rate": 3.957213978588318e-05, + "loss": 3.6652, + "step": 636928 + }, + { + "epoch": 1.01, + "learning_rate": 3.956375383837266e-05, + "loss": 3.6588, + "step": 637440 + }, + { + "epoch": 1.01, + "learning_rate": 3.955536789086214e-05, + "loss": 3.6551, + "step": 637952 + }, + { + "epoch": 1.01, + "learning_rate": 3.954699832215535e-05, + "loss": 3.6507, + "step": 638464 + }, + { + "epoch": 1.01, + "learning_rate": 3.953861237464483e-05, + "loss": 3.6562, + "step": 638976 + }, + { + "epoch": 1.01, + "learning_rate": 3.953022642713431e-05, + "loss": 3.6739, + "step": 639488 + }, + { + "epoch": 1.01, + "learning_rate": 3.952184047962379e-05, + "loss": 3.6466, + "step": 640000 + }, + { + "epoch": 1.01, + "learning_rate": 3.951345453211327e-05, + "loss": 3.6713, + "step": 640512 + }, + { + "epoch": 1.01, + "learning_rate": 3.950506858460275e-05, + "loss": 3.6599, + "step": 641024 + }, + { + "epoch": 1.01, + "learning_rate": 3.949668263709223e-05, + "loss": 3.6439, + "step": 641536 + }, + { + "epoch": 1.01, + "learning_rate": 3.9488313068385444e-05, + "loss": 3.6697, + "step": 642048 + }, + { + "epoch": 1.01, + "learning_rate": 3.947992712087492e-05, + "loss": 3.6512, + "step": 642560 + }, + { + "epoch": 1.01, + "learning_rate": 3.94715411733644e-05, + "loss": 3.6395, + "step": 643072 + }, + { + "epoch": 1.01, + "learning_rate": 3.946315522585388e-05, + "loss": 3.6543, + "step": 643584 + }, + { + "epoch": 1.01, + "learning_rate": 3.945476927834336e-05, + "loss": 3.6624, + "step": 644096 + }, + { + "epoch": 1.01, + "learning_rate": 3.944638333083284e-05, + "loss": 3.6482, + "step": 644608 + }, + { + "epoch": 1.01, + "learning_rate": 3.943799738332232e-05, + "loss": 3.6599, + "step": 645120 + }, + { + "epoch": 1.01, + "learning_rate": 3.94296114358118e-05, + "loss": 3.646, + "step": 645632 + }, + { + "epoch": 1.01, + "learning_rate": 3.9421241867105006e-05, + "loss": 3.6498, + "step": 646144 + }, + { + "epoch": 1.01, + "learning_rate": 3.9412855919594486e-05, + "loss": 3.6615, + "step": 646656 + }, + { + "epoch": 1.01, + "learning_rate": 3.94044863508877e-05, + "loss": 3.6581, + "step": 647168 + }, + { + "epoch": 1.01, + "learning_rate": 3.939610040337718e-05, + "loss": 3.6605, + "step": 647680 + }, + { + "epoch": 1.01, + "learning_rate": 3.938771445586666e-05, + "loss": 3.6556, + "step": 648192 + }, + { + "epoch": 1.01, + "learning_rate": 3.937932850835614e-05, + "loss": 3.6682, + "step": 648704 + }, + { + "epoch": 1.01, + "learning_rate": 3.937094256084562e-05, + "loss": 3.6492, + "step": 649216 + }, + { + "epoch": 1.01, + "learning_rate": 3.93625566133351e-05, + "loss": 3.6592, + "step": 649728 + }, + { + "epoch": 1.01, + "learning_rate": 3.935418704462831e-05, + "loss": 3.6472, + "step": 650240 + }, + { + "epoch": 1.01, + "learning_rate": 3.934580109711779e-05, + "loss": 3.6485, + "step": 650752 + }, + { + "epoch": 1.01, + "learning_rate": 3.933741514960727e-05, + "loss": 3.6579, + "step": 651264 + }, + { + "epoch": 1.01, + "learning_rate": 3.932902920209675e-05, + "loss": 3.6518, + "step": 651776 + }, + { + "epoch": 1.01, + "learning_rate": 3.932064325458623e-05, + "loss": 3.6615, + "step": 652288 + }, + { + "epoch": 1.01, + "learning_rate": 3.931225730707571e-05, + "loss": 3.667, + "step": 652800 + }, + { + "epoch": 1.01, + "learning_rate": 3.930388773836892e-05, + "loss": 3.6384, + "step": 653312 + }, + { + "epoch": 1.01, + "learning_rate": 3.92955017908584e-05, + "loss": 3.642, + "step": 653824 + }, + { + "epoch": 1.01, + "learning_rate": 3.928711584334788e-05, + "loss": 3.6562, + "step": 654336 + }, + { + "epoch": 1.01, + "learning_rate": 3.9278729895837366e-05, + "loss": 3.6589, + "step": 654848 + }, + { + "epoch": 1.01, + "learning_rate": 3.9270343948326846e-05, + "loss": 3.657, + "step": 655360 + }, + { + "epoch": 1.01, + "learning_rate": 3.9261958000816326e-05, + "loss": 3.6492, + "step": 655872 + }, + { + "epoch": 1.02, + "learning_rate": 3.9253588432109535e-05, + "loss": 3.657, + "step": 656384 + }, + { + "epoch": 1.02, + "learning_rate": 3.9245202484599015e-05, + "loss": 3.6528, + "step": 656896 + }, + { + "epoch": 1.02, + "learning_rate": 3.9236816537088495e-05, + "loss": 3.6489, + "step": 657408 + }, + { + "epoch": 1.02, + "learning_rate": 3.9228430589577975e-05, + "loss": 3.6487, + "step": 657920 + }, + { + "epoch": 1.02, + "learning_rate": 3.9220044642067455e-05, + "loss": 3.6575, + "step": 658432 + }, + { + "epoch": 1.02, + "learning_rate": 3.9211675073360664e-05, + "loss": 3.6641, + "step": 658944 + }, + { + "epoch": 1.02, + "learning_rate": 3.9203289125850144e-05, + "loss": 3.6579, + "step": 659456 + }, + { + "epoch": 1.02, + "learning_rate": 3.9194903178339624e-05, + "loss": 3.6421, + "step": 659968 + }, + { + "epoch": 1.02, + "learning_rate": 3.9186517230829104e-05, + "loss": 3.6476, + "step": 660480 + }, + { + "epoch": 1.02, + "learning_rate": 3.917814766212232e-05, + "loss": 3.6462, + "step": 660992 + }, + { + "epoch": 1.02, + "learning_rate": 3.91697617146118e-05, + "loss": 3.6554, + "step": 661504 + }, + { + "epoch": 1.02, + "learning_rate": 3.916137576710128e-05, + "loss": 3.6537, + "step": 662016 + }, + { + "epoch": 1.02, + "learning_rate": 3.915298981959075e-05, + "loss": 3.6467, + "step": 662528 + }, + { + "epoch": 1.02, + "learning_rate": 3.914460387208023e-05, + "loss": 3.6508, + "step": 663040 + }, + { + "epoch": 1.02, + "learning_rate": 3.913621792456971e-05, + "loss": 3.6428, + "step": 663552 + }, + { + "epoch": 1.02, + "learning_rate": 3.912783197705919e-05, + "loss": 3.6473, + "step": 664064 + }, + { + "epoch": 1.02, + "learning_rate": 3.911944602954867e-05, + "loss": 3.6411, + "step": 664576 + }, + { + "epoch": 1.02, + "learning_rate": 3.911107646084188e-05, + "loss": 3.6486, + "step": 665088 + }, + { + "epoch": 1.02, + "learning_rate": 3.910269051333136e-05, + "loss": 3.65, + "step": 665600 + }, + { + "epoch": 1.02, + "learning_rate": 3.909430456582084e-05, + "loss": 3.653, + "step": 666112 + }, + { + "epoch": 1.02, + "learning_rate": 3.908591861831032e-05, + "loss": 3.6419, + "step": 666624 + }, + { + "epoch": 1.02, + "learning_rate": 3.90775326707998e-05, + "loss": 3.6441, + "step": 667136 + }, + { + "epoch": 1.02, + "learning_rate": 3.906914672328929e-05, + "loss": 3.6465, + "step": 667648 + }, + { + "epoch": 1.02, + "learning_rate": 3.90607771545825e-05, + "loss": 3.657, + "step": 668160 + }, + { + "epoch": 1.02, + "learning_rate": 3.905239120707198e-05, + "loss": 3.6461, + "step": 668672 + }, + { + "epoch": 1.02, + "learning_rate": 3.904400525956146e-05, + "loss": 3.6495, + "step": 669184 + }, + { + "epoch": 1.02, + "learning_rate": 3.903561931205094e-05, + "loss": 3.652, + "step": 669696 + }, + { + "epoch": 1.02, + "learning_rate": 3.902723336454042e-05, + "loss": 3.6645, + "step": 670208 + }, + { + "epoch": 1.02, + "learning_rate": 3.90188474170299e-05, + "loss": 3.6473, + "step": 670720 + }, + { + "epoch": 1.02, + "learning_rate": 3.901046146951938e-05, + "loss": 3.6489, + "step": 671232 + }, + { + "epoch": 1.02, + "learning_rate": 3.9002091900812586e-05, + "loss": 3.6483, + "step": 671744 + }, + { + "epoch": 1.02, + "learning_rate": 3.8993705953302066e-05, + "loss": 3.653, + "step": 672256 + }, + { + "epoch": 1.02, + "learning_rate": 3.8985320005791546e-05, + "loss": 3.6476, + "step": 672768 + }, + { + "epoch": 1.02, + "learning_rate": 3.8976934058281026e-05, + "loss": 3.641, + "step": 673280 + }, + { + "epoch": 1.02, + "learning_rate": 3.8968548110770506e-05, + "loss": 3.65, + "step": 673792 + }, + { + "epoch": 1.02, + "learning_rate": 3.8960162163259986e-05, + "loss": 3.6541, + "step": 674304 + }, + { + "epoch": 1.02, + "learning_rate": 3.8951776215749466e-05, + "loss": 3.6431, + "step": 674816 + }, + { + "epoch": 1.02, + "learning_rate": 3.894340664704268e-05, + "loss": 3.6391, + "step": 675328 + }, + { + "epoch": 1.02, + "learning_rate": 3.893502069953216e-05, + "loss": 3.6416, + "step": 675840 + }, + { + "epoch": 1.02, + "learning_rate": 3.892663475202164e-05, + "loss": 3.6376, + "step": 676352 + }, + { + "epoch": 1.02, + "learning_rate": 3.8918248804511115e-05, + "loss": 3.6522, + "step": 676864 + }, + { + "epoch": 1.02, + "learning_rate": 3.890987923580433e-05, + "loss": 3.6528, + "step": 677376 + }, + { + "epoch": 1.02, + "learning_rate": 3.890149328829381e-05, + "loss": 3.6601, + "step": 677888 + }, + { + "epoch": 1.02, + "learning_rate": 3.889310734078329e-05, + "loss": 3.6357, + "step": 678400 + }, + { + "epoch": 1.02, + "learning_rate": 3.8884721393272764e-05, + "loss": 3.6566, + "step": 678912 + }, + { + "epoch": 1.02, + "learning_rate": 3.887635182456598e-05, + "loss": 3.6496, + "step": 679424 + }, + { + "epoch": 1.02, + "learning_rate": 3.886796587705546e-05, + "loss": 3.6486, + "step": 679936 + }, + { + "epoch": 1.02, + "learning_rate": 3.885957992954494e-05, + "loss": 3.6423, + "step": 680448 + }, + { + "epoch": 1.02, + "learning_rate": 3.885119398203442e-05, + "loss": 3.6439, + "step": 680960 + }, + { + "epoch": 1.02, + "learning_rate": 3.88428080345239e-05, + "loss": 3.6419, + "step": 681472 + }, + { + "epoch": 1.02, + "learning_rate": 3.883442208701338e-05, + "loss": 3.6585, + "step": 681984 + }, + { + "epoch": 1.02, + "learning_rate": 3.882603613950286e-05, + "loss": 3.6369, + "step": 682496 + }, + { + "epoch": 1.02, + "learning_rate": 3.881765019199234e-05, + "loss": 3.6514, + "step": 683008 + }, + { + "epoch": 1.02, + "learning_rate": 3.880928062328555e-05, + "loss": 3.6503, + "step": 683520 + }, + { + "epoch": 1.02, + "learning_rate": 3.880089467577503e-05, + "loss": 3.6529, + "step": 684032 + }, + { + "epoch": 1.02, + "learning_rate": 3.879252510706824e-05, + "loss": 3.6408, + "step": 684544 + }, + { + "epoch": 1.02, + "learning_rate": 3.878413915955772e-05, + "loss": 3.6497, + "step": 685056 + }, + { + "epoch": 1.02, + "learning_rate": 3.87757532120472e-05, + "loss": 3.6518, + "step": 685568 + }, + { + "epoch": 1.02, + "learning_rate": 3.876736726453668e-05, + "loss": 3.6417, + "step": 686080 + }, + { + "epoch": 1.02, + "learning_rate": 3.875899769582989e-05, + "loss": 3.6523, + "step": 686592 + }, + { + "epoch": 1.03, + "eval_loss": 3.868178129196167, + "eval_runtime": 303.4461, + "eval_samples_per_second": 1257.525, + "eval_steps_per_second": 39.299, + "step": 686880 + }, + { + "epoch": 0.0, + "learning_rate": 3.875061174831937e-05, + "loss": 3.6419, + "step": 687104 + }, + { + "epoch": 0.0, + "learning_rate": 3.874222580080885e-05, + "loss": 3.6286, + "step": 687616 + }, + { + "epoch": 0.0, + "learning_rate": 3.873383985329833e-05, + "loss": 3.6444, + "step": 688128 + }, + { + "epoch": 0.0, + "learning_rate": 3.872545390578781e-05, + "loss": 3.652, + "step": 688640 + }, + { + "epoch": 0.0, + "learning_rate": 3.871706795827729e-05, + "loss": 3.6539, + "step": 689152 + }, + { + "epoch": 0.0, + "learning_rate": 3.870868201076677e-05, + "loss": 3.6381, + "step": 689664 + }, + { + "epoch": 0.0, + "learning_rate": 3.870031244205998e-05, + "loss": 3.649, + "step": 690176 + }, + { + "epoch": 0.0, + "learning_rate": 3.869192649454946e-05, + "loss": 3.6337, + "step": 690688 + }, + { + "epoch": 0.0, + "learning_rate": 3.868354054703894e-05, + "loss": 3.6422, + "step": 691200 + }, + { + "epoch": 0.0, + "learning_rate": 3.867515459952842e-05, + "loss": 3.6442, + "step": 691712 + }, + { + "epoch": 0.0, + "learning_rate": 3.86667686520179e-05, + "loss": 3.6447, + "step": 692224 + }, + { + "epoch": 0.0, + "learning_rate": 3.865838270450738e-05, + "loss": 3.6442, + "step": 692736 + }, + { + "epoch": 0.0, + "learning_rate": 3.86500131358006e-05, + "loss": 3.6498, + "step": 693248 + }, + { + "epoch": 0.0, + "learning_rate": 3.864162718829008e-05, + "loss": 3.6365, + "step": 693760 + }, + { + "epoch": 0.0, + "learning_rate": 3.863324124077956e-05, + "loss": 3.6353, + "step": 694272 + }, + { + "epoch": 0.0, + "learning_rate": 3.862485529326904e-05, + "loss": 3.6247, + "step": 694784 + }, + { + "epoch": 0.0, + "learning_rate": 3.861646934575852e-05, + "loss": 3.6402, + "step": 695296 + }, + { + "epoch": 0.0, + "learning_rate": 3.8608083398248e-05, + "loss": 3.6473, + "step": 695808 + }, + { + "epoch": 0.0, + "learning_rate": 3.859969745073748e-05, + "loss": 3.6325, + "step": 696320 + }, + { + "epoch": 0.0, + "learning_rate": 3.8591327882030687e-05, + "loss": 3.6482, + "step": 696832 + }, + { + "epoch": 0.0, + "learning_rate": 3.8582941934520167e-05, + "loss": 3.6572, + "step": 697344 + }, + { + "epoch": 0.0, + "learning_rate": 3.8574555987009646e-05, + "loss": 3.65, + "step": 697856 + }, + { + "epoch": 0.0, + "learning_rate": 3.8566170039499126e-05, + "loss": 3.6474, + "step": 698368 + }, + { + "epoch": 0.0, + "learning_rate": 3.8557800470792336e-05, + "loss": 3.6403, + "step": 698880 + }, + { + "epoch": 0.0, + "learning_rate": 3.8549414523281816e-05, + "loss": 3.6413, + "step": 699392 + }, + { + "epoch": 0.0, + "learning_rate": 3.8541028575771295e-05, + "loss": 3.6438, + "step": 699904 + }, + { + "epoch": 0.0, + "learning_rate": 3.8532642628260775e-05, + "loss": 3.6459, + "step": 700416 + }, + { + "epoch": 0.0, + "learning_rate": 3.852427305955399e-05, + "loss": 3.6462, + "step": 700928 + }, + { + "epoch": 0.0, + "learning_rate": 3.851588711204347e-05, + "loss": 3.6339, + "step": 701440 + }, + { + "epoch": 0.0, + "learning_rate": 3.850750116453295e-05, + "loss": 3.6295, + "step": 701952 + }, + { + "epoch": 0.01, + "learning_rate": 3.8499115217022424e-05, + "loss": 3.6319, + "step": 702464 + }, + { + "epoch": 0.01, + "learning_rate": 3.8490729269511904e-05, + "loss": 3.648, + "step": 702976 + }, + { + "epoch": 0.01, + "learning_rate": 3.848235970080512e-05, + "loss": 3.6488, + "step": 703488 + }, + { + "epoch": 0.01, + "learning_rate": 3.84739737532946e-05, + "loss": 3.6445, + "step": 704000 + }, + { + "epoch": 0.01, + "learning_rate": 3.846558780578407e-05, + "loss": 3.6368, + "step": 704512 + }, + { + "epoch": 0.01, + "learning_rate": 3.845720185827355e-05, + "loss": 3.6376, + "step": 705024 + }, + { + "epoch": 0.01, + "learning_rate": 3.844881591076303e-05, + "loss": 3.6437, + "step": 705536 + }, + { + "epoch": 0.01, + "learning_rate": 3.844042996325252e-05, + "loss": 3.6274, + "step": 706048 + }, + { + "epoch": 0.01, + "learning_rate": 3.8432044015742e-05, + "loss": 3.6299, + "step": 706560 + }, + { + "epoch": 0.01, + "learning_rate": 3.842367444703521e-05, + "loss": 3.6309, + "step": 707072 + }, + { + "epoch": 0.01, + "learning_rate": 3.841528849952469e-05, + "loss": 3.6323, + "step": 707584 + }, + { + "epoch": 0.01, + "learning_rate": 3.840690255201417e-05, + "loss": 3.6447, + "step": 708096 + }, + { + "epoch": 0.01, + "learning_rate": 3.839851660450365e-05, + "loss": 3.6416, + "step": 708608 + }, + { + "epoch": 0.01, + "learning_rate": 3.839013065699313e-05, + "loss": 3.6306, + "step": 709120 + }, + { + "epoch": 0.01, + "learning_rate": 3.838176108828634e-05, + "loss": 3.6445, + "step": 709632 + }, + { + "epoch": 0.01, + "learning_rate": 3.837337514077582e-05, + "loss": 3.6316, + "step": 710144 + }, + { + "epoch": 0.01, + "learning_rate": 3.83649891932653e-05, + "loss": 3.6428, + "step": 710656 + }, + { + "epoch": 0.01, + "learning_rate": 3.835660324575478e-05, + "loss": 3.6465, + "step": 711168 + }, + { + "epoch": 0.01, + "learning_rate": 3.834821729824426e-05, + "loss": 3.6119, + "step": 711680 + }, + { + "epoch": 0.01, + "learning_rate": 3.833983135073374e-05, + "loss": 3.6442, + "step": 712192 + }, + { + "epoch": 0.01, + "learning_rate": 3.833144540322322e-05, + "loss": 3.6342, + "step": 712704 + }, + { + "epoch": 0.01, + "learning_rate": 3.8323075834516434e-05, + "loss": 3.6401, + "step": 713216 + }, + { + "epoch": 0.01, + "learning_rate": 3.8314689887005914e-05, + "loss": 3.6347, + "step": 713728 + }, + { + "epoch": 0.01, + "learning_rate": 3.8306303939495393e-05, + "loss": 3.629, + "step": 714240 + }, + { + "epoch": 0.01, + "learning_rate": 3.8297917991984873e-05, + "loss": 3.6266, + "step": 714752 + }, + { + "epoch": 0.01, + "learning_rate": 3.828953204447435e-05, + "loss": 3.6281, + "step": 715264 + }, + { + "epoch": 0.01, + "learning_rate": 3.828114609696383e-05, + "loss": 3.651, + "step": 715776 + }, + { + "epoch": 0.01, + "learning_rate": 3.827276014945331e-05, + "loss": 3.6232, + "step": 716288 + }, + { + "epoch": 0.01, + "learning_rate": 3.8264374201942786e-05, + "loss": 3.6464, + "step": 716800 + }, + { + "epoch": 0.01, + "learning_rate": 3.8256004633236e-05, + "loss": 3.6365, + "step": 717312 + }, + { + "epoch": 0.01, + "learning_rate": 3.824761868572548e-05, + "loss": 3.6203, + "step": 717824 + }, + { + "epoch": 0.01, + "learning_rate": 3.8239232738214955e-05, + "loss": 3.6447, + "step": 718336 + }, + { + "epoch": 0.01, + "learning_rate": 3.823086316950817e-05, + "loss": 3.6257, + "step": 718848 + }, + { + "epoch": 0.01, + "learning_rate": 3.822247722199765e-05, + "loss": 3.6169, + "step": 719360 + }, + { + "epoch": 0.01, + "learning_rate": 3.821409127448714e-05, + "loss": 3.6252, + "step": 719872 + }, + { + "epoch": 0.01, + "learning_rate": 3.820570532697661e-05, + "loss": 3.6406, + "step": 720384 + }, + { + "epoch": 0.01, + "learning_rate": 3.819731937946609e-05, + "loss": 3.6191, + "step": 720896 + }, + { + "epoch": 0.01, + "learning_rate": 3.818893343195557e-05, + "loss": 3.6392, + "step": 721408 + }, + { + "epoch": 0.01, + "learning_rate": 3.818054748444505e-05, + "loss": 3.6234, + "step": 721920 + }, + { + "epoch": 0.01, + "learning_rate": 3.817217791573826e-05, + "loss": 3.6215, + "step": 722432 + }, + { + "epoch": 0.01, + "learning_rate": 3.816379196822774e-05, + "loss": 3.6357, + "step": 722944 + }, + { + "epoch": 0.01, + "learning_rate": 3.8155422399520956e-05, + "loss": 3.6336, + "step": 723456 + }, + { + "epoch": 0.01, + "learning_rate": 3.814703645201043e-05, + "loss": 3.6371, + "step": 723968 + }, + { + "epoch": 0.01, + "learning_rate": 3.813865050449991e-05, + "loss": 3.6326, + "step": 724480 + }, + { + "epoch": 0.01, + "learning_rate": 3.813026455698939e-05, + "loss": 3.6409, + "step": 724992 + }, + { + "epoch": 0.01, + "learning_rate": 3.8121878609478876e-05, + "loss": 3.6283, + "step": 725504 + }, + { + "epoch": 0.01, + "learning_rate": 3.8113492661968356e-05, + "loss": 3.6359, + "step": 726016 + }, + { + "epoch": 0.01, + "learning_rate": 3.8105123093261565e-05, + "loss": 3.6175, + "step": 726528 + }, + { + "epoch": 0.01, + "learning_rate": 3.8096737145751045e-05, + "loss": 3.6249, + "step": 727040 + }, + { + "epoch": 0.01, + "learning_rate": 3.8088351198240525e-05, + "loss": 3.6332, + "step": 727552 + }, + { + "epoch": 0.01, + "learning_rate": 3.8079965250730005e-05, + "loss": 3.6244, + "step": 728064 + }, + { + "epoch": 0.01, + "learning_rate": 3.8071595682023214e-05, + "loss": 3.6369, + "step": 728576 + }, + { + "epoch": 0.01, + "learning_rate": 3.8063209734512694e-05, + "loss": 3.6399, + "step": 729088 + }, + { + "epoch": 0.01, + "learning_rate": 3.8054823787002174e-05, + "loss": 3.6199, + "step": 729600 + }, + { + "epoch": 0.01, + "learning_rate": 3.8046437839491654e-05, + "loss": 3.6168, + "step": 730112 + }, + { + "epoch": 0.01, + "learning_rate": 3.8038051891981134e-05, + "loss": 3.6317, + "step": 730624 + }, + { + "epoch": 0.01, + "learning_rate": 3.802968232327434e-05, + "loss": 3.6329, + "step": 731136 + }, + { + "epoch": 0.01, + "learning_rate": 3.802129637576383e-05, + "loss": 3.633, + "step": 731648 + }, + { + "epoch": 0.01, + "learning_rate": 3.801291042825331e-05, + "loss": 3.6236, + "step": 732160 + }, + { + "epoch": 0.02, + "learning_rate": 3.800452448074279e-05, + "loss": 3.6358, + "step": 732672 + }, + { + "epoch": 0.02, + "learning_rate": 3.799613853323227e-05, + "loss": 3.6274, + "step": 733184 + }, + { + "epoch": 0.02, + "learning_rate": 3.798775258572175e-05, + "loss": 3.6253, + "step": 733696 + }, + { + "epoch": 0.02, + "learning_rate": 3.797938301701496e-05, + "loss": 3.624, + "step": 734208 + }, + { + "epoch": 0.02, + "learning_rate": 3.797099706950444e-05, + "loss": 3.6314, + "step": 734720 + }, + { + "epoch": 0.02, + "learning_rate": 3.796261112199392e-05, + "loss": 3.6385, + "step": 735232 + }, + { + "epoch": 0.02, + "learning_rate": 3.79542251744834e-05, + "loss": 3.6349, + "step": 735744 + }, + { + "epoch": 0.02, + "learning_rate": 3.794583922697288e-05, + "loss": 3.617, + "step": 736256 + }, + { + "epoch": 0.02, + "learning_rate": 3.793746965826609e-05, + "loss": 3.6279, + "step": 736768 + }, + { + "epoch": 0.02, + "learning_rate": 3.792908371075557e-05, + "loss": 3.618, + "step": 737280 + }, + { + "epoch": 0.02, + "learning_rate": 3.792069776324505e-05, + "loss": 3.6326, + "step": 737792 + }, + { + "epoch": 0.02, + "learning_rate": 3.791231181573453e-05, + "loss": 3.6281, + "step": 738304 + }, + { + "epoch": 0.02, + "learning_rate": 3.790394224702774e-05, + "loss": 3.6252, + "step": 738816 + }, + { + "epoch": 0.02, + "learning_rate": 3.789555629951722e-05, + "loss": 3.6254, + "step": 739328 + }, + { + "epoch": 0.02, + "learning_rate": 3.78871703520067e-05, + "loss": 3.618, + "step": 739840 + }, + { + "epoch": 0.02, + "learning_rate": 3.787878440449618e-05, + "loss": 3.6226, + "step": 740352 + }, + { + "epoch": 0.02, + "learning_rate": 3.787039845698566e-05, + "loss": 3.6154, + "step": 740864 + }, + { + "epoch": 0.02, + "learning_rate": 3.786202888827887e-05, + "loss": 3.6237, + "step": 741376 + }, + { + "epoch": 0.02, + "learning_rate": 3.785364294076835e-05, + "loss": 3.6264, + "step": 741888 + }, + { + "epoch": 0.02, + "learning_rate": 3.784525699325783e-05, + "loss": 3.6254, + "step": 742400 + }, + { + "epoch": 0.02, + "learning_rate": 3.783687104574731e-05, + "loss": 3.618, + "step": 742912 + }, + { + "epoch": 0.02, + "learning_rate": 3.782850147704052e-05, + "loss": 3.6181, + "step": 743424 + }, + { + "epoch": 0.02, + "learning_rate": 3.782011552953e-05, + "loss": 3.621, + "step": 743936 + }, + { + "epoch": 0.02, + "learning_rate": 3.781172958201948e-05, + "loss": 3.6323, + "step": 744448 + }, + { + "epoch": 0.02, + "learning_rate": 3.780334363450896e-05, + "loss": 3.6241, + "step": 744960 + }, + { + "epoch": 0.02, + "learning_rate": 3.779497406580218e-05, + "loss": 3.6229, + "step": 745472 + }, + { + "epoch": 0.02, + "learning_rate": 3.778658811829166e-05, + "loss": 3.6276, + "step": 745984 + }, + { + "epoch": 0.02, + "learning_rate": 3.777820217078114e-05, + "loss": 3.6389, + "step": 746496 + }, + { + "epoch": 0.02, + "learning_rate": 3.7769816223270617e-05, + "loss": 3.6233, + "step": 747008 + }, + { + "epoch": 0.02, + "learning_rate": 3.776143027576009e-05, + "loss": 3.6242, + "step": 747520 + }, + { + "epoch": 0.02, + "learning_rate": 3.775304432824957e-05, + "loss": 3.625, + "step": 748032 + }, + { + "epoch": 0.02, + "learning_rate": 3.774465838073905e-05, + "loss": 3.6291, + "step": 748544 + }, + { + "epoch": 0.02, + "learning_rate": 3.7736288812032266e-05, + "loss": 3.6257, + "step": 749056 + }, + { + "epoch": 0.02, + "learning_rate": 3.772790286452174e-05, + "loss": 3.6186, + "step": 749568 + }, + { + "epoch": 0.02, + "learning_rate": 3.771951691701122e-05, + "loss": 3.6214, + "step": 750080 + }, + { + "epoch": 0.02, + "learning_rate": 3.7711130969500705e-05, + "loss": 3.6309, + "step": 750592 + }, + { + "epoch": 0.02, + "learning_rate": 3.7702745021990185e-05, + "loss": 3.6186, + "step": 751104 + }, + { + "epoch": 0.02, + "learning_rate": 3.7694375453283394e-05, + "loss": 3.615, + "step": 751616 + }, + { + "epoch": 0.02, + "learning_rate": 3.7685989505772874e-05, + "loss": 3.6176, + "step": 752128 + }, + { + "epoch": 0.02, + "learning_rate": 3.7677603558262354e-05, + "loss": 3.6102, + "step": 752640 + }, + { + "epoch": 0.02, + "learning_rate": 3.7669217610751834e-05, + "loss": 3.6332, + "step": 753152 + }, + { + "epoch": 0.02, + "learning_rate": 3.7660848042045043e-05, + "loss": 3.6239, + "step": 753664 + }, + { + "epoch": 0.02, + "learning_rate": 3.765246209453452e-05, + "loss": 3.6388, + "step": 754176 + }, + { + "epoch": 0.02, + "learning_rate": 3.7644076147024e-05, + "loss": 3.6171, + "step": 754688 + }, + { + "epoch": 0.02, + "learning_rate": 3.763569019951348e-05, + "loss": 3.6293, + "step": 755200 + }, + { + "epoch": 0.02, + "learning_rate": 3.762732063080669e-05, + "loss": 3.6225, + "step": 755712 + }, + { + "epoch": 0.02, + "learning_rate": 3.761893468329617e-05, + "loss": 3.6251, + "step": 756224 + }, + { + "epoch": 0.02, + "learning_rate": 3.761054873578565e-05, + "loss": 3.6176, + "step": 756736 + }, + { + "epoch": 0.02, + "learning_rate": 3.760216278827514e-05, + "loss": 3.6181, + "step": 757248 + }, + { + "epoch": 0.02, + "learning_rate": 3.759377684076462e-05, + "loss": 3.6187, + "step": 757760 + }, + { + "epoch": 0.02, + "learning_rate": 3.758540727205783e-05, + "loss": 3.6388, + "step": 758272 + }, + { + "epoch": 0.02, + "learning_rate": 3.757702132454731e-05, + "loss": 3.613, + "step": 758784 + }, + { + "epoch": 0.02, + "learning_rate": 3.756863537703679e-05, + "loss": 3.6269, + "step": 759296 + }, + { + "epoch": 0.02, + "learning_rate": 3.756024942952627e-05, + "loss": 3.6295, + "step": 759808 + }, + { + "epoch": 0.02, + "learning_rate": 3.755187986081948e-05, + "loss": 3.6231, + "step": 760320 + }, + { + "epoch": 0.02, + "learning_rate": 3.754349391330896e-05, + "loss": 3.6189, + "step": 760832 + }, + { + "epoch": 0.02, + "learning_rate": 3.753510796579844e-05, + "loss": 3.6264, + "step": 761344 + }, + { + "epoch": 0.02, + "learning_rate": 3.752672201828792e-05, + "loss": 3.6299, + "step": 761856 + }, + { + "epoch": 0.02, + "learning_rate": 3.7518352449581126e-05, + "loss": 3.6221, + "step": 762368 + }, + { + "epoch": 0.02, + "learning_rate": 3.7509966502070606e-05, + "loss": 3.6281, + "step": 762880 + }, + { + "epoch": 0.03, + "eval_loss": 3.865046739578247, + "eval_runtime": 302.2535, + "eval_samples_per_second": 1262.486, + "eval_steps_per_second": 39.454, + "step": 763200 + }, + { + "epoch": 1.0, + "learning_rate": 3.750158055456009e-05, + "loss": 3.6133, + "step": 763392 + }, + { + "epoch": 1.0, + "learning_rate": 3.749319460704957e-05, + "loss": 3.609, + "step": 763904 + }, + { + "epoch": 1.0, + "learning_rate": 3.748480865953905e-05, + "loss": 3.6202, + "step": 764416 + }, + { + "epoch": 1.0, + "learning_rate": 3.747643909083226e-05, + "loss": 3.6289, + "step": 764928 + }, + { + "epoch": 1.0, + "learning_rate": 3.746805314332174e-05, + "loss": 3.6337, + "step": 765440 + }, + { + "epoch": 1.0, + "learning_rate": 3.745966719581122e-05, + "loss": 3.6159, + "step": 765952 + }, + { + "epoch": 1.0, + "learning_rate": 3.74512812483007e-05, + "loss": 3.6225, + "step": 766464 + }, + { + "epoch": 1.0, + "learning_rate": 3.744289530079018e-05, + "loss": 3.6141, + "step": 766976 + }, + { + "epoch": 1.0, + "learning_rate": 3.743452573208339e-05, + "loss": 3.6197, + "step": 767488 + }, + { + "epoch": 1.0, + "learning_rate": 3.742613978457287e-05, + "loss": 3.6204, + "step": 768000 + }, + { + "epoch": 1.0, + "learning_rate": 3.741775383706235e-05, + "loss": 3.6173, + "step": 768512 + }, + { + "epoch": 1.0, + "learning_rate": 3.740936788955183e-05, + "loss": 3.6252, + "step": 769024 + }, + { + "epoch": 1.0, + "learning_rate": 3.7400998320845046e-05, + "loss": 3.6236, + "step": 769536 + }, + { + "epoch": 1.0, + "learning_rate": 3.7392612373334526e-05, + "loss": 3.6118, + "step": 770048 + }, + { + "epoch": 1.0, + "learning_rate": 3.7384226425824006e-05, + "loss": 3.6136, + "step": 770560 + }, + { + "epoch": 1.0, + "learning_rate": 3.7375840478313486e-05, + "loss": 3.6049, + "step": 771072 + }, + { + "epoch": 1.0, + "learning_rate": 3.7367454530802966e-05, + "loss": 3.6198, + "step": 771584 + }, + { + "epoch": 1.0, + "learning_rate": 3.7359084962096175e-05, + "loss": 3.6196, + "step": 772096 + }, + { + "epoch": 1.0, + "learning_rate": 3.7350699014585655e-05, + "loss": 3.6119, + "step": 772608 + }, + { + "epoch": 1.0, + "learning_rate": 3.7342313067075135e-05, + "loss": 3.6214, + "step": 773120 + }, + { + "epoch": 1.0, + "learning_rate": 3.7333927119564615e-05, + "loss": 3.6376, + "step": 773632 + }, + { + "epoch": 1.0, + "learning_rate": 3.7325541172054095e-05, + "loss": 3.6283, + "step": 774144 + }, + { + "epoch": 1.0, + "learning_rate": 3.7317171603347304e-05, + "loss": 3.6231, + "step": 774656 + }, + { + "epoch": 1.0, + "learning_rate": 3.7308785655836784e-05, + "loss": 3.6169, + "step": 775168 + }, + { + "epoch": 1.0, + "learning_rate": 3.7300399708326264e-05, + "loss": 3.6231, + "step": 775680 + }, + { + "epoch": 1.0, + "learning_rate": 3.7292013760815744e-05, + "loss": 3.6183, + "step": 776192 + }, + { + "epoch": 1.0, + "learning_rate": 3.728362781330523e-05, + "loss": 3.6208, + "step": 776704 + }, + { + "epoch": 1.0, + "learning_rate": 3.7275241865794704e-05, + "loss": 3.6232, + "step": 777216 + }, + { + "epoch": 1.0, + "learning_rate": 3.7266855918284184e-05, + "loss": 3.6138, + "step": 777728 + }, + { + "epoch": 1.0, + "learning_rate": 3.72584863495774e-05, + "loss": 3.6088, + "step": 778240 + }, + { + "epoch": 1.01, + "learning_rate": 3.725010040206687e-05, + "loss": 3.6125, + "step": 778752 + }, + { + "epoch": 1.01, + "learning_rate": 3.724171445455635e-05, + "loss": 3.6233, + "step": 779264 + }, + { + "epoch": 1.01, + "learning_rate": 3.723332850704583e-05, + "loss": 3.6215, + "step": 779776 + }, + { + "epoch": 1.01, + "learning_rate": 3.722494255953531e-05, + "loss": 3.6248, + "step": 780288 + }, + { + "epoch": 1.01, + "learning_rate": 3.721655661202479e-05, + "loss": 3.6157, + "step": 780800 + }, + { + "epoch": 1.01, + "learning_rate": 3.7208187043318e-05, + "loss": 3.6148, + "step": 781312 + }, + { + "epoch": 1.01, + "learning_rate": 3.719980109580748e-05, + "loss": 3.6196, + "step": 781824 + }, + { + "epoch": 1.01, + "learning_rate": 3.719141514829697e-05, + "loss": 3.6069, + "step": 782336 + }, + { + "epoch": 1.01, + "learning_rate": 3.718302920078645e-05, + "loss": 3.6074, + "step": 782848 + }, + { + "epoch": 1.01, + "learning_rate": 3.717464325327593e-05, + "loss": 3.6093, + "step": 783360 + }, + { + "epoch": 1.01, + "learning_rate": 3.716625730576541e-05, + "loss": 3.6058, + "step": 783872 + }, + { + "epoch": 1.01, + "learning_rate": 3.715788773705862e-05, + "loss": 3.6213, + "step": 784384 + }, + { + "epoch": 1.01, + "learning_rate": 3.71495017895481e-05, + "loss": 3.6166, + "step": 784896 + }, + { + "epoch": 1.01, + "learning_rate": 3.714111584203758e-05, + "loss": 3.6137, + "step": 785408 + }, + { + "epoch": 1.01, + "learning_rate": 3.713272989452706e-05, + "loss": 3.6153, + "step": 785920 + }, + { + "epoch": 1.01, + "learning_rate": 3.712434394701654e-05, + "loss": 3.6118, + "step": 786432 + }, + { + "epoch": 1.01, + "learning_rate": 3.7115974378309746e-05, + "loss": 3.6224, + "step": 786944 + }, + { + "epoch": 1.01, + "learning_rate": 3.7107588430799226e-05, + "loss": 3.6241, + "step": 787456 + }, + { + "epoch": 1.01, + "learning_rate": 3.7099202483288706e-05, + "loss": 3.5893, + "step": 787968 + }, + { + "epoch": 1.01, + "learning_rate": 3.7090816535778186e-05, + "loss": 3.6239, + "step": 788480 + }, + { + "epoch": 1.01, + "learning_rate": 3.70824469670714e-05, + "loss": 3.6092, + "step": 788992 + }, + { + "epoch": 1.01, + "learning_rate": 3.707406101956088e-05, + "loss": 3.6194, + "step": 789504 + }, + { + "epoch": 1.01, + "learning_rate": 3.706567507205036e-05, + "loss": 3.6144, + "step": 790016 + }, + { + "epoch": 1.01, + "learning_rate": 3.705728912453984e-05, + "loss": 3.6043, + "step": 790528 + }, + { + "epoch": 1.01, + "learning_rate": 3.704891955583305e-05, + "loss": 3.6096, + "step": 791040 + }, + { + "epoch": 1.01, + "learning_rate": 3.704053360832253e-05, + "loss": 3.6024, + "step": 791552 + }, + { + "epoch": 1.01, + "learning_rate": 3.703214766081201e-05, + "loss": 3.6224, + "step": 792064 + }, + { + "epoch": 1.01, + "learning_rate": 3.702376171330149e-05, + "loss": 3.604, + "step": 792576 + }, + { + "epoch": 1.01, + "learning_rate": 3.701537576579097e-05, + "loss": 3.6195, + "step": 793088 + }, + { + "epoch": 1.01, + "learning_rate": 3.700698981828045e-05, + "loss": 3.6146, + "step": 793600 + }, + { + "epoch": 1.01, + "learning_rate": 3.699862024957366e-05, + "loss": 3.6024, + "step": 794112 + }, + { + "epoch": 1.01, + "learning_rate": 3.699023430206314e-05, + "loss": 3.6184, + "step": 794624 + }, + { + "epoch": 1.01, + "learning_rate": 3.698184835455262e-05, + "loss": 3.6004, + "step": 795136 + }, + { + "epoch": 1.01, + "learning_rate": 3.69734624070421e-05, + "loss": 3.5986, + "step": 795648 + }, + { + "epoch": 1.01, + "learning_rate": 3.6965092838335316e-05, + "loss": 3.6023, + "step": 796160 + }, + { + "epoch": 1.01, + "learning_rate": 3.6956706890824796e-05, + "loss": 3.6178, + "step": 796672 + }, + { + "epoch": 1.01, + "learning_rate": 3.6948320943314276e-05, + "loss": 3.5977, + "step": 797184 + }, + { + "epoch": 1.01, + "learning_rate": 3.6939934995803756e-05, + "loss": 3.6195, + "step": 797696 + }, + { + "epoch": 1.01, + "learning_rate": 3.6931549048293236e-05, + "loss": 3.5956, + "step": 798208 + }, + { + "epoch": 1.01, + "learning_rate": 3.6923179479586445e-05, + "loss": 3.6036, + "step": 798720 + }, + { + "epoch": 1.01, + "learning_rate": 3.6914793532075925e-05, + "loss": 3.6107, + "step": 799232 + }, + { + "epoch": 1.01, + "learning_rate": 3.6906407584565405e-05, + "loss": 3.6099, + "step": 799744 + }, + { + "epoch": 1.01, + "learning_rate": 3.6898021637054885e-05, + "loss": 3.617, + "step": 800256 + }, + { + "epoch": 1.01, + "learning_rate": 3.688963568954436e-05, + "loss": 3.6115, + "step": 800768 + }, + { + "epoch": 1.01, + "learning_rate": 3.6881266120837574e-05, + "loss": 3.6198, + "step": 801280 + }, + { + "epoch": 1.01, + "learning_rate": 3.6872880173327054e-05, + "loss": 3.6023, + "step": 801792 + }, + { + "epoch": 1.01, + "learning_rate": 3.6864494225816534e-05, + "loss": 3.6132, + "step": 802304 + }, + { + "epoch": 1.01, + "learning_rate": 3.6856108278306013e-05, + "loss": 3.5998, + "step": 802816 + }, + { + "epoch": 1.01, + "learning_rate": 3.6847722330795493e-05, + "loss": 3.6053, + "step": 803328 + }, + { + "epoch": 1.01, + "learning_rate": 3.683935276208871e-05, + "loss": 3.6074, + "step": 803840 + }, + { + "epoch": 1.01, + "learning_rate": 3.683096681457818e-05, + "loss": 3.6008, + "step": 804352 + }, + { + "epoch": 1.01, + "learning_rate": 3.682258086706766e-05, + "loss": 3.6137, + "step": 804864 + }, + { + "epoch": 1.01, + "learning_rate": 3.681419491955714e-05, + "loss": 3.6181, + "step": 805376 + }, + { + "epoch": 1.01, + "learning_rate": 3.680582535085036e-05, + "loss": 3.6035, + "step": 805888 + }, + { + "epoch": 1.01, + "learning_rate": 3.679743940333983e-05, + "loss": 3.5901, + "step": 806400 + }, + { + "epoch": 1.01, + "learning_rate": 3.678905345582931e-05, + "loss": 3.6115, + "step": 806912 + }, + { + "epoch": 1.01, + "learning_rate": 3.678066750831879e-05, + "loss": 3.6071, + "step": 807424 + }, + { + "epoch": 1.01, + "learning_rate": 3.677228156080828e-05, + "loss": 3.6141, + "step": 807936 + }, + { + "epoch": 1.01, + "learning_rate": 3.676391199210149e-05, + "loss": 3.5957, + "step": 808448 + }, + { + "epoch": 1.01, + "learning_rate": 3.675552604459097e-05, + "loss": 3.6134, + "step": 808960 + }, + { + "epoch": 1.02, + "learning_rate": 3.674714009708045e-05, + "loss": 3.6074, + "step": 809472 + }, + { + "epoch": 1.02, + "learning_rate": 3.673875414956993e-05, + "loss": 3.6014, + "step": 809984 + }, + { + "epoch": 1.02, + "learning_rate": 3.673036820205941e-05, + "loss": 3.6016, + "step": 810496 + }, + { + "epoch": 1.02, + "learning_rate": 3.672198225454889e-05, + "loss": 3.6094, + "step": 811008 + }, + { + "epoch": 1.02, + "learning_rate": 3.671359630703837e-05, + "loss": 3.614, + "step": 811520 + }, + { + "epoch": 1.02, + "learning_rate": 3.6705226738331576e-05, + "loss": 3.6136, + "step": 812032 + }, + { + "epoch": 1.02, + "learning_rate": 3.6696840790821056e-05, + "loss": 3.5942, + "step": 812544 + }, + { + "epoch": 1.02, + "learning_rate": 3.6688454843310536e-05, + "loss": 3.6043, + "step": 813056 + }, + { + "epoch": 1.02, + "learning_rate": 3.6680068895800016e-05, + "loss": 3.598, + "step": 813568 + }, + { + "epoch": 1.02, + "learning_rate": 3.6671682948289496e-05, + "loss": 3.6092, + "step": 814080 + }, + { + "epoch": 1.02, + "learning_rate": 3.666331337958271e-05, + "loss": 3.6054, + "step": 814592 + }, + { + "epoch": 1.02, + "learning_rate": 3.665492743207219e-05, + "loss": 3.6066, + "step": 815104 + }, + { + "epoch": 1.02, + "learning_rate": 3.664654148456167e-05, + "loss": 3.6023, + "step": 815616 + }, + { + "epoch": 1.02, + "learning_rate": 3.663815553705115e-05, + "loss": 3.5972, + "step": 816128 + }, + { + "epoch": 1.02, + "learning_rate": 3.662976958954063e-05, + "loss": 3.6053, + "step": 816640 + }, + { + "epoch": 1.02, + "learning_rate": 3.662138364203011e-05, + "loss": 3.5919, + "step": 817152 + }, + { + "epoch": 1.02, + "learning_rate": 3.661301407332332e-05, + "loss": 3.6016, + "step": 817664 + }, + { + "epoch": 1.02, + "learning_rate": 3.66046281258128e-05, + "loss": 3.6017, + "step": 818176 + }, + { + "epoch": 1.02, + "learning_rate": 3.659624217830228e-05, + "loss": 3.6092, + "step": 818688 + }, + { + "epoch": 1.02, + "learning_rate": 3.658785623079176e-05, + "loss": 3.5938, + "step": 819200 + }, + { + "epoch": 1.02, + "learning_rate": 3.657948666208497e-05, + "loss": 3.5974, + "step": 819712 + }, + { + "epoch": 1.02, + "learning_rate": 3.657110071457445e-05, + "loss": 3.5965, + "step": 820224 + }, + { + "epoch": 1.02, + "learning_rate": 3.656271476706393e-05, + "loss": 3.6106, + "step": 820736 + }, + { + "epoch": 1.02, + "learning_rate": 3.6554328819553416e-05, + "loss": 3.6033, + "step": 821248 + }, + { + "epoch": 1.02, + "learning_rate": 3.6545942872042896e-05, + "loss": 3.6021, + "step": 821760 + }, + { + "epoch": 1.02, + "learning_rate": 3.6537573303336105e-05, + "loss": 3.6091, + "step": 822272 + }, + { + "epoch": 1.02, + "learning_rate": 3.6529187355825585e-05, + "loss": 3.6178, + "step": 822784 + }, + { + "epoch": 1.02, + "learning_rate": 3.6520801408315065e-05, + "loss": 3.6019, + "step": 823296 + }, + { + "epoch": 1.02, + "learning_rate": 3.6512415460804545e-05, + "loss": 3.6039, + "step": 823808 + }, + { + "epoch": 1.02, + "learning_rate": 3.6504045892097754e-05, + "loss": 3.6025, + "step": 824320 + }, + { + "epoch": 1.02, + "learning_rate": 3.6495659944587234e-05, + "loss": 3.6077, + "step": 824832 + }, + { + "epoch": 1.02, + "learning_rate": 3.6487273997076714e-05, + "loss": 3.6, + "step": 825344 + }, + { + "epoch": 1.02, + "learning_rate": 3.647888804956619e-05, + "loss": 3.6005, + "step": 825856 + }, + { + "epoch": 1.02, + "learning_rate": 3.647050210205567e-05, + "loss": 3.5998, + "step": 826368 + }, + { + "epoch": 1.02, + "learning_rate": 3.646213253334888e-05, + "loss": 3.6091, + "step": 826880 + }, + { + "epoch": 1.02, + "learning_rate": 3.645374658583836e-05, + "loss": 3.596, + "step": 827392 + }, + { + "epoch": 1.02, + "learning_rate": 3.644536063832784e-05, + "loss": 3.5985, + "step": 827904 + }, + { + "epoch": 1.02, + "learning_rate": 3.643697469081732e-05, + "loss": 3.5903, + "step": 828416 + }, + { + "epoch": 1.02, + "learning_rate": 3.64285887433068e-05, + "loss": 3.5929, + "step": 828928 + }, + { + "epoch": 1.02, + "learning_rate": 3.642021917460002e-05, + "loss": 3.6083, + "step": 829440 + }, + { + "epoch": 1.02, + "learning_rate": 3.641183322708949e-05, + "loss": 3.6049, + "step": 829952 + }, + { + "epoch": 1.02, + "learning_rate": 3.640344727957897e-05, + "loss": 3.621, + "step": 830464 + }, + { + "epoch": 1.02, + "learning_rate": 3.639506133206845e-05, + "loss": 3.5931, + "step": 830976 + }, + { + "epoch": 1.02, + "learning_rate": 3.638667538455793e-05, + "loss": 3.6067, + "step": 831488 + }, + { + "epoch": 1.02, + "learning_rate": 3.637830581585114e-05, + "loss": 3.6016, + "step": 832000 + }, + { + "epoch": 1.02, + "learning_rate": 3.636991986834062e-05, + "loss": 3.6048, + "step": 832512 + }, + { + "epoch": 1.02, + "learning_rate": 3.63615339208301e-05, + "loss": 3.5961, + "step": 833024 + }, + { + "epoch": 1.02, + "learning_rate": 3.635314797331959e-05, + "loss": 3.5963, + "step": 833536 + }, + { + "epoch": 1.02, + "learning_rate": 3.63447784046128e-05, + "loss": 3.6015, + "step": 834048 + }, + { + "epoch": 1.02, + "learning_rate": 3.633639245710228e-05, + "loss": 3.6172, + "step": 834560 + }, + { + "epoch": 1.02, + "learning_rate": 3.632800650959176e-05, + "loss": 3.5877, + "step": 835072 + }, + { + "epoch": 1.02, + "learning_rate": 3.6319620562081237e-05, + "loss": 3.6071, + "step": 835584 + }, + { + "epoch": 1.02, + "learning_rate": 3.6311234614570717e-05, + "loss": 3.6058, + "step": 836096 + }, + { + "epoch": 1.02, + "learning_rate": 3.6302865045863926e-05, + "loss": 3.6019, + "step": 836608 + }, + { + "epoch": 1.02, + "learning_rate": 3.6294479098353406e-05, + "loss": 3.6002, + "step": 837120 + }, + { + "epoch": 1.02, + "learning_rate": 3.6286093150842886e-05, + "loss": 3.6078, + "step": 837632 + }, + { + "epoch": 1.02, + "learning_rate": 3.6277707203332366e-05, + "loss": 3.6042, + "step": 838144 + }, + { + "epoch": 1.02, + "learning_rate": 3.6269337634625575e-05, + "loss": 3.6052, + "step": 838656 + }, + { + "epoch": 1.02, + "learning_rate": 3.6260951687115055e-05, + "loss": 3.6022, + "step": 839168 + }, + { + "epoch": 1.03, + "eval_loss": 3.865051031112671, + "eval_runtime": 302.0792, + "eval_samples_per_second": 1263.215, + "eval_steps_per_second": 39.476, + "step": 839520 + }, + { + "epoch": 0.0, + "learning_rate": 3.625256573960454e-05, + "loss": 3.5814, + "step": 839680 + }, + { + "epoch": 0.0, + "learning_rate": 3.624417979209402e-05, + "loss": 3.5882, + "step": 840192 + }, + { + "epoch": 0.0, + "learning_rate": 3.62357938445835e-05, + "loss": 3.601, + "step": 840704 + }, + { + "epoch": 0.0, + "learning_rate": 3.622740789707298e-05, + "loss": 3.6053, + "step": 841216 + }, + { + "epoch": 0.0, + "learning_rate": 3.621902194956246e-05, + "loss": 3.6126, + "step": 841728 + }, + { + "epoch": 0.0, + "learning_rate": 3.621063600205194e-05, + "loss": 3.5974, + "step": 842240 + }, + { + "epoch": 0.0, + "learning_rate": 3.620226643334515e-05, + "loss": 3.6043, + "step": 842752 + }, + { + "epoch": 0.0, + "learning_rate": 3.619388048583463e-05, + "loss": 3.5953, + "step": 843264 + }, + { + "epoch": 0.0, + "learning_rate": 3.618549453832411e-05, + "loss": 3.5958, + "step": 843776 + }, + { + "epoch": 0.0, + "learning_rate": 3.617710859081359e-05, + "loss": 3.5963, + "step": 844288 + }, + { + "epoch": 0.0, + "learning_rate": 3.616872264330307e-05, + "loss": 3.6009, + "step": 844800 + }, + { + "epoch": 0.0, + "learning_rate": 3.616033669579255e-05, + "loss": 3.601, + "step": 845312 + }, + { + "epoch": 0.0, + "learning_rate": 3.615196712708576e-05, + "loss": 3.6041, + "step": 845824 + }, + { + "epoch": 0.0, + "learning_rate": 3.614358117957524e-05, + "loss": 3.5903, + "step": 846336 + }, + { + "epoch": 0.0, + "learning_rate": 3.6135195232064726e-05, + "loss": 3.5925, + "step": 846848 + }, + { + "epoch": 0.0, + "learning_rate": 3.6126809284554206e-05, + "loss": 3.5793, + "step": 847360 + }, + { + "epoch": 0.0, + "learning_rate": 3.6118439715847415e-05, + "loss": 3.5996, + "step": 847872 + }, + { + "epoch": 0.0, + "learning_rate": 3.6110053768336895e-05, + "loss": 3.5981, + "step": 848384 + }, + { + "epoch": 0.0, + "learning_rate": 3.6101667820826375e-05, + "loss": 3.5895, + "step": 848896 + }, + { + "epoch": 0.0, + "learning_rate": 3.6093281873315855e-05, + "loss": 3.6011, + "step": 849408 + }, + { + "epoch": 0.0, + "learning_rate": 3.608489592580533e-05, + "loss": 3.6177, + "step": 849920 + }, + { + "epoch": 0.0, + "learning_rate": 3.6076526357098544e-05, + "loss": 3.6058, + "step": 850432 + }, + { + "epoch": 0.0, + "learning_rate": 3.6068140409588024e-05, + "loss": 3.6007, + "step": 850944 + }, + { + "epoch": 0.0, + "learning_rate": 3.60597544620775e-05, + "loss": 3.6, + "step": 851456 + }, + { + "epoch": 0.0, + "learning_rate": 3.605136851456698e-05, + "loss": 3.602, + "step": 851968 + }, + { + "epoch": 0.0, + "learning_rate": 3.6042982567056464e-05, + "loss": 3.5985, + "step": 852480 + }, + { + "epoch": 0.0, + "learning_rate": 3.6034596619545943e-05, + "loss": 3.5994, + "step": 852992 + }, + { + "epoch": 0.0, + "learning_rate": 3.602622705083915e-05, + "loss": 3.6005, + "step": 853504 + }, + { + "epoch": 0.0, + "learning_rate": 3.601784110332863e-05, + "loss": 3.5925, + "step": 854016 + }, + { + "epoch": 0.0, + "learning_rate": 3.600945515581811e-05, + "loss": 3.5865, + "step": 854528 + }, + { + "epoch": 0.01, + "learning_rate": 3.600106920830759e-05, + "loss": 3.5949, + "step": 855040 + }, + { + "epoch": 0.01, + "learning_rate": 3.59926996396008e-05, + "loss": 3.5965, + "step": 855552 + }, + { + "epoch": 0.01, + "learning_rate": 3.598431369209028e-05, + "loss": 3.6009, + "step": 856064 + }, + { + "epoch": 0.01, + "learning_rate": 3.597592774457976e-05, + "loss": 3.6058, + "step": 856576 + }, + { + "epoch": 0.01, + "learning_rate": 3.596754179706924e-05, + "loss": 3.5959, + "step": 857088 + }, + { + "epoch": 0.01, + "learning_rate": 3.595917222836245e-05, + "loss": 3.5913, + "step": 857600 + }, + { + "epoch": 0.01, + "learning_rate": 3.595078628085193e-05, + "loss": 3.6013, + "step": 858112 + }, + { + "epoch": 0.01, + "learning_rate": 3.594240033334142e-05, + "loss": 3.586, + "step": 858624 + }, + { + "epoch": 0.01, + "learning_rate": 3.59340143858309e-05, + "loss": 3.588, + "step": 859136 + }, + { + "epoch": 0.01, + "learning_rate": 3.592562843832038e-05, + "loss": 3.5863, + "step": 859648 + }, + { + "epoch": 0.01, + "learning_rate": 3.591724249080986e-05, + "loss": 3.5903, + "step": 860160 + }, + { + "epoch": 0.01, + "learning_rate": 3.5908872922103066e-05, + "loss": 3.5946, + "step": 860672 + }, + { + "epoch": 0.01, + "learning_rate": 3.5900486974592546e-05, + "loss": 3.5968, + "step": 861184 + }, + { + "epoch": 0.01, + "learning_rate": 3.5892101027082026e-05, + "loss": 3.5972, + "step": 861696 + }, + { + "epoch": 0.01, + "learning_rate": 3.5883715079571506e-05, + "loss": 3.5919, + "step": 862208 + }, + { + "epoch": 0.01, + "learning_rate": 3.5875345510864715e-05, + "loss": 3.5951, + "step": 862720 + }, + { + "epoch": 0.01, + "learning_rate": 3.5866959563354195e-05, + "loss": 3.598, + "step": 863232 + }, + { + "epoch": 0.01, + "learning_rate": 3.5858573615843675e-05, + "loss": 3.6048, + "step": 863744 + }, + { + "epoch": 0.01, + "learning_rate": 3.5850187668333155e-05, + "loss": 3.5714, + "step": 864256 + }, + { + "epoch": 0.01, + "learning_rate": 3.5841801720822635e-05, + "loss": 3.6011, + "step": 864768 + }, + { + "epoch": 0.01, + "learning_rate": 3.5833415773312115e-05, + "loss": 3.5878, + "step": 865280 + }, + { + "epoch": 0.01, + "learning_rate": 3.582504620460533e-05, + "loss": 3.5978, + "step": 865792 + }, + { + "epoch": 0.01, + "learning_rate": 3.581666025709481e-05, + "loss": 3.5929, + "step": 866304 + }, + { + "epoch": 0.01, + "learning_rate": 3.580827430958429e-05, + "loss": 3.5881, + "step": 866816 + }, + { + "epoch": 0.01, + "learning_rate": 3.579988836207377e-05, + "loss": 3.5824, + "step": 867328 + }, + { + "epoch": 0.01, + "learning_rate": 3.579150241456325e-05, + "loss": 3.5832, + "step": 867840 + }, + { + "epoch": 0.01, + "learning_rate": 3.578311646705273e-05, + "loss": 3.6066, + "step": 868352 + }, + { + "epoch": 0.01, + "learning_rate": 3.577474689834594e-05, + "loss": 3.5809, + "step": 868864 + }, + { + "epoch": 0.01, + "learning_rate": 3.576636095083542e-05, + "loss": 3.602, + "step": 869376 + }, + { + "epoch": 0.01, + "learning_rate": 3.57579750033249e-05, + "loss": 3.5911, + "step": 869888 + }, + { + "epoch": 0.01, + "learning_rate": 3.574958905581438e-05, + "loss": 3.5832, + "step": 870400 + }, + { + "epoch": 0.01, + "learning_rate": 3.574121948710759e-05, + "loss": 3.5983, + "step": 870912 + }, + { + "epoch": 0.01, + "learning_rate": 3.573283353959707e-05, + "loss": 3.5827, + "step": 871424 + }, + { + "epoch": 0.01, + "learning_rate": 3.572444759208655e-05, + "loss": 3.5737, + "step": 871936 + }, + { + "epoch": 0.01, + "learning_rate": 3.5716061644576035e-05, + "loss": 3.5821, + "step": 872448 + }, + { + "epoch": 0.01, + "learning_rate": 3.5707675697065515e-05, + "loss": 3.598, + "step": 872960 + }, + { + "epoch": 0.01, + "learning_rate": 3.5699306128358724e-05, + "loss": 3.5801, + "step": 873472 + }, + { + "epoch": 0.01, + "learning_rate": 3.5690920180848204e-05, + "loss": 3.5992, + "step": 873984 + }, + { + "epoch": 0.01, + "learning_rate": 3.5682534233337684e-05, + "loss": 3.5728, + "step": 874496 + }, + { + "epoch": 0.01, + "learning_rate": 3.567414828582716e-05, + "loss": 3.5854, + "step": 875008 + }, + { + "epoch": 0.01, + "learning_rate": 3.566576233831664e-05, + "loss": 3.591, + "step": 875520 + }, + { + "epoch": 0.01, + "learning_rate": 3.565739276960985e-05, + "loss": 3.5922, + "step": 876032 + }, + { + "epoch": 0.01, + "learning_rate": 3.564900682209933e-05, + "loss": 3.5925, + "step": 876544 + }, + { + "epoch": 0.01, + "learning_rate": 3.5640620874588806e-05, + "loss": 3.5931, + "step": 877056 + }, + { + "epoch": 0.01, + "learning_rate": 3.5632234927078286e-05, + "loss": 3.5995, + "step": 877568 + }, + { + "epoch": 0.01, + "learning_rate": 3.56238653583715e-05, + "loss": 3.5807, + "step": 878080 + }, + { + "epoch": 0.01, + "learning_rate": 3.561547941086099e-05, + "loss": 3.5893, + "step": 878592 + }, + { + "epoch": 0.01, + "learning_rate": 3.560709346335046e-05, + "loss": 3.5811, + "step": 879104 + }, + { + "epoch": 0.01, + "learning_rate": 3.559870751583994e-05, + "loss": 3.5876, + "step": 879616 + }, + { + "epoch": 0.01, + "learning_rate": 3.559032156832942e-05, + "loss": 3.5851, + "step": 880128 + }, + { + "epoch": 0.01, + "learning_rate": 3.558195199962263e-05, + "loss": 3.5837, + "step": 880640 + }, + { + "epoch": 0.01, + "learning_rate": 3.557356605211211e-05, + "loss": 3.5945, + "step": 881152 + }, + { + "epoch": 0.01, + "learning_rate": 3.556518010460159e-05, + "loss": 3.5959, + "step": 881664 + }, + { + "epoch": 0.01, + "learning_rate": 3.555679415709107e-05, + "loss": 3.5846, + "step": 882176 + }, + { + "epoch": 0.01, + "learning_rate": 3.554840820958055e-05, + "loss": 3.568, + "step": 882688 + }, + { + "epoch": 0.01, + "learning_rate": 3.554002226207003e-05, + "loss": 3.5908, + "step": 883200 + }, + { + "epoch": 0.01, + "learning_rate": 3.553165269336324e-05, + "loss": 3.5883, + "step": 883712 + }, + { + "epoch": 0.01, + "learning_rate": 3.552326674585273e-05, + "loss": 3.5957, + "step": 884224 + }, + { + "epoch": 0.01, + "learning_rate": 3.551488079834221e-05, + "loss": 3.5783, + "step": 884736 + }, + { + "epoch": 0.01, + "learning_rate": 3.550649485083169e-05, + "loss": 3.5904, + "step": 885248 + }, + { + "epoch": 0.02, + "learning_rate": 3.5498125282124896e-05, + "loss": 3.5927, + "step": 885760 + }, + { + "epoch": 0.02, + "learning_rate": 3.5489739334614376e-05, + "loss": 3.5789, + "step": 886272 + }, + { + "epoch": 0.02, + "learning_rate": 3.5481353387103856e-05, + "loss": 3.578, + "step": 886784 + }, + { + "epoch": 0.02, + "learning_rate": 3.5472967439593336e-05, + "loss": 3.591, + "step": 887296 + }, + { + "epoch": 0.02, + "learning_rate": 3.5464597870886545e-05, + "loss": 3.5904, + "step": 887808 + }, + { + "epoch": 0.02, + "learning_rate": 3.5456211923376025e-05, + "loss": 3.5951, + "step": 888320 + }, + { + "epoch": 0.02, + "learning_rate": 3.5447825975865505e-05, + "loss": 3.5782, + "step": 888832 + }, + { + "epoch": 0.02, + "learning_rate": 3.5439440028354985e-05, + "loss": 3.5812, + "step": 889344 + }, + { + "epoch": 0.02, + "learning_rate": 3.5431054080844464e-05, + "loss": 3.5781, + "step": 889856 + }, + { + "epoch": 0.02, + "learning_rate": 3.542268451213768e-05, + "loss": 3.592, + "step": 890368 + }, + { + "epoch": 0.02, + "learning_rate": 3.541429856462716e-05, + "loss": 3.5861, + "step": 890880 + }, + { + "epoch": 0.02, + "learning_rate": 3.540591261711664e-05, + "loss": 3.5837, + "step": 891392 + }, + { + "epoch": 0.02, + "learning_rate": 3.539752666960612e-05, + "loss": 3.5834, + "step": 891904 + }, + { + "epoch": 0.02, + "learning_rate": 3.538915710089933e-05, + "loss": 3.5802, + "step": 892416 + }, + { + "epoch": 0.02, + "learning_rate": 3.538077115338881e-05, + "loss": 3.5854, + "step": 892928 + }, + { + "epoch": 0.02, + "learning_rate": 3.537238520587829e-05, + "loss": 3.5693, + "step": 893440 + }, + { + "epoch": 0.02, + "learning_rate": 3.536399925836777e-05, + "loss": 3.5818, + "step": 893952 + }, + { + "epoch": 0.02, + "learning_rate": 3.535562968966098e-05, + "loss": 3.5804, + "step": 894464 + }, + { + "epoch": 0.02, + "learning_rate": 3.534724374215046e-05, + "loss": 3.5868, + "step": 894976 + }, + { + "epoch": 0.02, + "learning_rate": 3.533885779463994e-05, + "loss": 3.5779, + "step": 895488 + }, + { + "epoch": 0.02, + "learning_rate": 3.533047184712942e-05, + "loss": 3.5848, + "step": 896000 + }, + { + "epoch": 0.02, + "learning_rate": 3.53220858996189e-05, + "loss": 3.5756, + "step": 896512 + }, + { + "epoch": 0.02, + "learning_rate": 3.5313716330912114e-05, + "loss": 3.5917, + "step": 897024 + }, + { + "epoch": 0.02, + "learning_rate": 3.5305330383401594e-05, + "loss": 3.5801, + "step": 897536 + }, + { + "epoch": 0.02, + "learning_rate": 3.5296944435891074e-05, + "loss": 3.5826, + "step": 898048 + }, + { + "epoch": 0.02, + "learning_rate": 3.5288558488380554e-05, + "loss": 3.5855, + "step": 898560 + }, + { + "epoch": 0.02, + "learning_rate": 3.528018891967376e-05, + "loss": 3.6027, + "step": 899072 + }, + { + "epoch": 0.02, + "learning_rate": 3.527180297216324e-05, + "loss": 3.5801, + "step": 899584 + }, + { + "epoch": 0.02, + "learning_rate": 3.526341702465272e-05, + "loss": 3.5836, + "step": 900096 + }, + { + "epoch": 0.02, + "learning_rate": 3.52550310771422e-05, + "loss": 3.5871, + "step": 900608 + }, + { + "epoch": 0.02, + "learning_rate": 3.524664512963168e-05, + "loss": 3.589, + "step": 901120 + }, + { + "epoch": 0.02, + "learning_rate": 3.523825918212116e-05, + "loss": 3.5806, + "step": 901632 + }, + { + "epoch": 0.02, + "learning_rate": 3.522988961341437e-05, + "loss": 3.5836, + "step": 902144 + }, + { + "epoch": 0.02, + "learning_rate": 3.522150366590385e-05, + "loss": 3.5786, + "step": 902656 + }, + { + "epoch": 0.02, + "learning_rate": 3.521311771839333e-05, + "loss": 3.5869, + "step": 903168 + }, + { + "epoch": 0.02, + "learning_rate": 3.520473177088281e-05, + "loss": 3.5746, + "step": 903680 + }, + { + "epoch": 0.02, + "learning_rate": 3.519636220217603e-05, + "loss": 3.5787, + "step": 904192 + }, + { + "epoch": 0.02, + "learning_rate": 3.518797625466551e-05, + "loss": 3.5714, + "step": 904704 + }, + { + "epoch": 0.02, + "learning_rate": 3.517959030715499e-05, + "loss": 3.5795, + "step": 905216 + }, + { + "epoch": 0.02, + "learning_rate": 3.517120435964447e-05, + "loss": 3.5859, + "step": 905728 + }, + { + "epoch": 0.02, + "learning_rate": 3.5162834790937677e-05, + "loss": 3.5865, + "step": 906240 + }, + { + "epoch": 0.02, + "learning_rate": 3.5154448843427156e-05, + "loss": 3.5995, + "step": 906752 + }, + { + "epoch": 0.02, + "learning_rate": 3.5146062895916636e-05, + "loss": 3.5769, + "step": 907264 + }, + { + "epoch": 0.02, + "learning_rate": 3.5137676948406116e-05, + "loss": 3.582, + "step": 907776 + }, + { + "epoch": 0.02, + "learning_rate": 3.5129307379699325e-05, + "loss": 3.5863, + "step": 908288 + }, + { + "epoch": 0.02, + "learning_rate": 3.5120921432188805e-05, + "loss": 3.5832, + "step": 908800 + }, + { + "epoch": 0.02, + "learning_rate": 3.5112535484678285e-05, + "loss": 3.5767, + "step": 909312 + }, + { + "epoch": 0.02, + "learning_rate": 3.5104149537167765e-05, + "loss": 3.5718, + "step": 909824 + }, + { + "epoch": 0.02, + "learning_rate": 3.5095763589657245e-05, + "loss": 3.5831, + "step": 910336 + }, + { + "epoch": 0.02, + "learning_rate": 3.508739402095046e-05, + "loss": 3.5895, + "step": 910848 + }, + { + "epoch": 0.02, + "learning_rate": 3.507900807343994e-05, + "loss": 3.577, + "step": 911360 + }, + { + "epoch": 0.02, + "learning_rate": 3.5070622125929414e-05, + "loss": 3.5864, + "step": 911872 + }, + { + "epoch": 0.02, + "learning_rate": 3.5062236178418894e-05, + "loss": 3.5869, + "step": 912384 + }, + { + "epoch": 0.02, + "learning_rate": 3.505386660971211e-05, + "loss": 3.5831, + "step": 912896 + }, + { + "epoch": 0.02, + "learning_rate": 3.504548066220159e-05, + "loss": 3.58, + "step": 913408 + }, + { + "epoch": 0.02, + "learning_rate": 3.503709471469106e-05, + "loss": 3.5852, + "step": 913920 + }, + { + "epoch": 0.02, + "learning_rate": 3.502870876718054e-05, + "loss": 3.5851, + "step": 914432 + }, + { + "epoch": 0.02, + "learning_rate": 3.502032281967002e-05, + "loss": 3.5825, + "step": 914944 + }, + { + "epoch": 0.02, + "learning_rate": 3.50119368721595e-05, + "loss": 3.5871, + "step": 915456 + }, + { + "epoch": 0.03, + "eval_loss": 3.8636531829833984, + "eval_runtime": 305.2434, + "eval_samples_per_second": 1250.12, + "eval_steps_per_second": 39.067, + "step": 915840 + }, + { + "epoch": 1.0, + "learning_rate": 3.500356730345272e-05, + "loss": 3.5772, + "step": 915968 + }, + { + "epoch": 1.0, + "learning_rate": 3.49951813559422e-05, + "loss": 3.5637, + "step": 916480 + }, + { + "epoch": 1.0, + "learning_rate": 3.498679540843168e-05, + "loss": 3.5795, + "step": 916992 + }, + { + "epoch": 1.0, + "learning_rate": 3.497840946092116e-05, + "loss": 3.5888, + "step": 917504 + }, + { + "epoch": 1.0, + "learning_rate": 3.497003989221437e-05, + "loss": 3.5889, + "step": 918016 + }, + { + "epoch": 1.0, + "learning_rate": 3.496165394470385e-05, + "loss": 3.5804, + "step": 918528 + }, + { + "epoch": 1.0, + "learning_rate": 3.495326799719333e-05, + "loss": 3.582, + "step": 919040 + }, + { + "epoch": 1.0, + "learning_rate": 3.494488204968281e-05, + "loss": 3.5783, + "step": 919552 + }, + { + "epoch": 1.0, + "learning_rate": 3.493649610217229e-05, + "loss": 3.5745, + "step": 920064 + }, + { + "epoch": 1.0, + "learning_rate": 3.49281265334655e-05, + "loss": 3.5784, + "step": 920576 + }, + { + "epoch": 1.0, + "learning_rate": 3.491974058595498e-05, + "loss": 3.5821, + "step": 921088 + }, + { + "epoch": 1.0, + "learning_rate": 3.491135463844446e-05, + "loss": 3.5807, + "step": 921600 + }, + { + "epoch": 1.0, + "learning_rate": 3.490298506973767e-05, + "loss": 3.5863, + "step": 922112 + }, + { + "epoch": 1.0, + "learning_rate": 3.489459912222715e-05, + "loss": 3.5682, + "step": 922624 + }, + { + "epoch": 1.0, + "learning_rate": 3.488621317471663e-05, + "loss": 3.5726, + "step": 923136 + }, + { + "epoch": 1.0, + "learning_rate": 3.487782722720611e-05, + "loss": 3.5622, + "step": 923648 + }, + { + "epoch": 1.0, + "learning_rate": 3.486944127969559e-05, + "loss": 3.5807, + "step": 924160 + }, + { + "epoch": 1.0, + "learning_rate": 3.486105533218507e-05, + "loss": 3.5776, + "step": 924672 + }, + { + "epoch": 1.0, + "learning_rate": 3.485266938467455e-05, + "loss": 3.5764, + "step": 925184 + }, + { + "epoch": 1.0, + "learning_rate": 3.484428343716403e-05, + "loss": 3.5782, + "step": 925696 + }, + { + "epoch": 1.0, + "learning_rate": 3.483589748965351e-05, + "loss": 3.5964, + "step": 926208 + }, + { + "epoch": 1.0, + "learning_rate": 3.482752792094672e-05, + "loss": 3.5854, + "step": 926720 + }, + { + "epoch": 1.0, + "learning_rate": 3.48191419734362e-05, + "loss": 3.5834, + "step": 927232 + }, + { + "epoch": 1.0, + "learning_rate": 3.481075602592568e-05, + "loss": 3.579, + "step": 927744 + }, + { + "epoch": 1.0, + "learning_rate": 3.480237007841516e-05, + "loss": 3.5885, + "step": 928256 + }, + { + "epoch": 1.0, + "learning_rate": 3.479400050970838e-05, + "loss": 3.578, + "step": 928768 + }, + { + "epoch": 1.0, + "learning_rate": 3.478561456219786e-05, + "loss": 3.5762, + "step": 929280 + }, + { + "epoch": 1.0, + "learning_rate": 3.477722861468734e-05, + "loss": 3.5873, + "step": 929792 + }, + { + "epoch": 1.0, + "learning_rate": 3.476884266717682e-05, + "loss": 3.5682, + "step": 930304 + }, + { + "epoch": 1.0, + "learning_rate": 3.47604567196663e-05, + "loss": 3.5715, + "step": 930816 + }, + { + "epoch": 1.01, + "learning_rate": 3.475207077215578e-05, + "loss": 3.5754, + "step": 931328 + }, + { + "epoch": 1.01, + "learning_rate": 3.4743701203448986e-05, + "loss": 3.5749, + "step": 931840 + }, + { + "epoch": 1.01, + "learning_rate": 3.4735315255938466e-05, + "loss": 3.583, + "step": 932352 + }, + { + "epoch": 1.01, + "learning_rate": 3.4726929308427946e-05, + "loss": 3.5882, + "step": 932864 + }, + { + "epoch": 1.01, + "learning_rate": 3.471854336091742e-05, + "loss": 3.5746, + "step": 933376 + }, + { + "epoch": 1.01, + "learning_rate": 3.4710173792210635e-05, + "loss": 3.5756, + "step": 933888 + }, + { + "epoch": 1.01, + "learning_rate": 3.4701787844700115e-05, + "loss": 3.5836, + "step": 934400 + }, + { + "epoch": 1.01, + "learning_rate": 3.4693401897189595e-05, + "loss": 3.5666, + "step": 934912 + }, + { + "epoch": 1.01, + "learning_rate": 3.4685015949679075e-05, + "loss": 3.5681, + "step": 935424 + }, + { + "epoch": 1.01, + "learning_rate": 3.467664638097229e-05, + "loss": 3.5718, + "step": 935936 + }, + { + "epoch": 1.01, + "learning_rate": 3.466826043346177e-05, + "loss": 3.5681, + "step": 936448 + }, + { + "epoch": 1.01, + "learning_rate": 3.465987448595125e-05, + "loss": 3.574, + "step": 936960 + }, + { + "epoch": 1.01, + "learning_rate": 3.4651488538440724e-05, + "loss": 3.5821, + "step": 937472 + }, + { + "epoch": 1.01, + "learning_rate": 3.4643102590930204e-05, + "loss": 3.5772, + "step": 937984 + }, + { + "epoch": 1.01, + "learning_rate": 3.463473302222342e-05, + "loss": 3.5749, + "step": 938496 + }, + { + "epoch": 1.01, + "learning_rate": 3.462634707471289e-05, + "loss": 3.5744, + "step": 939008 + }, + { + "epoch": 1.01, + "learning_rate": 3.461796112720237e-05, + "loss": 3.5809, + "step": 939520 + }, + { + "epoch": 1.01, + "learning_rate": 3.460957517969185e-05, + "loss": 3.5817, + "step": 940032 + }, + { + "epoch": 1.01, + "learning_rate": 3.460118923218133e-05, + "loss": 3.5579, + "step": 940544 + }, + { + "epoch": 1.01, + "learning_rate": 3.459281966347455e-05, + "loss": 3.5813, + "step": 941056 + }, + { + "epoch": 1.01, + "learning_rate": 3.458443371596403e-05, + "loss": 3.5695, + "step": 941568 + }, + { + "epoch": 1.01, + "learning_rate": 3.457604776845351e-05, + "loss": 3.5776, + "step": 942080 + }, + { + "epoch": 1.01, + "learning_rate": 3.456766182094299e-05, + "loss": 3.5765, + "step": 942592 + }, + { + "epoch": 1.01, + "learning_rate": 3.45592922522362e-05, + "loss": 3.5682, + "step": 943104 + }, + { + "epoch": 1.01, + "learning_rate": 3.455090630472568e-05, + "loss": 3.565, + "step": 943616 + }, + { + "epoch": 1.01, + "learning_rate": 3.454252035721516e-05, + "loss": 3.5615, + "step": 944128 + }, + { + "epoch": 1.01, + "learning_rate": 3.453413440970464e-05, + "loss": 3.5919, + "step": 944640 + }, + { + "epoch": 1.01, + "learning_rate": 3.452574846219412e-05, + "loss": 3.5634, + "step": 945152 + }, + { + "epoch": 1.01, + "learning_rate": 3.4517378893487326e-05, + "loss": 3.5793, + "step": 945664 + }, + { + "epoch": 1.01, + "learning_rate": 3.4508992945976806e-05, + "loss": 3.5729, + "step": 946176 + }, + { + "epoch": 1.01, + "learning_rate": 3.4500606998466286e-05, + "loss": 3.5639, + "step": 946688 + }, + { + "epoch": 1.01, + "learning_rate": 3.4492221050955766e-05, + "loss": 3.5753, + "step": 947200 + }, + { + "epoch": 1.01, + "learning_rate": 3.448385148224898e-05, + "loss": 3.5661, + "step": 947712 + }, + { + "epoch": 1.01, + "learning_rate": 3.447546553473846e-05, + "loss": 3.5609, + "step": 948224 + }, + { + "epoch": 1.01, + "learning_rate": 3.446707958722794e-05, + "loss": 3.5576, + "step": 948736 + }, + { + "epoch": 1.01, + "learning_rate": 3.445869363971742e-05, + "loss": 3.5845, + "step": 949248 + }, + { + "epoch": 1.01, + "learning_rate": 3.445032407101063e-05, + "loss": 3.561, + "step": 949760 + }, + { + "epoch": 1.01, + "learning_rate": 3.444193812350011e-05, + "loss": 3.5732, + "step": 950272 + }, + { + "epoch": 1.01, + "learning_rate": 3.443355217598959e-05, + "loss": 3.5566, + "step": 950784 + }, + { + "epoch": 1.01, + "learning_rate": 3.442516622847907e-05, + "loss": 3.5678, + "step": 951296 + }, + { + "epoch": 1.01, + "learning_rate": 3.441678028096855e-05, + "loss": 3.5678, + "step": 951808 + }, + { + "epoch": 1.01, + "learning_rate": 3.440841071226176e-05, + "loss": 3.5769, + "step": 952320 + }, + { + "epoch": 1.01, + "learning_rate": 3.440002476475124e-05, + "loss": 3.5738, + "step": 952832 + }, + { + "epoch": 1.01, + "learning_rate": 3.439163881724072e-05, + "loss": 3.5733, + "step": 953344 + }, + { + "epoch": 1.01, + "learning_rate": 3.438325286973021e-05, + "loss": 3.5795, + "step": 953856 + }, + { + "epoch": 1.01, + "learning_rate": 3.4374883301023416e-05, + "loss": 3.5651, + "step": 954368 + }, + { + "epoch": 1.01, + "learning_rate": 3.4366497353512896e-05, + "loss": 3.5705, + "step": 954880 + }, + { + "epoch": 1.01, + "learning_rate": 3.4358111406002376e-05, + "loss": 3.562, + "step": 955392 + }, + { + "epoch": 1.01, + "learning_rate": 3.4349725458491856e-05, + "loss": 3.5681, + "step": 955904 + }, + { + "epoch": 1.01, + "learning_rate": 3.4341339510981336e-05, + "loss": 3.569, + "step": 956416 + }, + { + "epoch": 1.01, + "learning_rate": 3.4332969942274545e-05, + "loss": 3.5624, + "step": 956928 + }, + { + "epoch": 1.01, + "learning_rate": 3.4324583994764025e-05, + "loss": 3.5783, + "step": 957440 + }, + { + "epoch": 1.01, + "learning_rate": 3.4316198047253505e-05, + "loss": 3.579, + "step": 957952 + }, + { + "epoch": 1.01, + "learning_rate": 3.4307812099742985e-05, + "loss": 3.5676, + "step": 958464 + }, + { + "epoch": 1.01, + "learning_rate": 3.4299442531036194e-05, + "loss": 3.5485, + "step": 958976 + }, + { + "epoch": 1.01, + "learning_rate": 3.4291056583525674e-05, + "loss": 3.5678, + "step": 959488 + }, + { + "epoch": 1.01, + "learning_rate": 3.428267063601516e-05, + "loss": 3.5717, + "step": 960000 + }, + { + "epoch": 1.01, + "learning_rate": 3.427428468850464e-05, + "loss": 3.5782, + "step": 960512 + }, + { + "epoch": 1.01, + "learning_rate": 3.426589874099412e-05, + "loss": 3.5656, + "step": 961024 + }, + { + "epoch": 1.01, + "learning_rate": 3.425752917228733e-05, + "loss": 3.5687, + "step": 961536 + }, + { + "epoch": 1.02, + "learning_rate": 3.424914322477681e-05, + "loss": 3.5756, + "step": 962048 + }, + { + "epoch": 1.02, + "learning_rate": 3.424075727726629e-05, + "loss": 3.5585, + "step": 962560 + }, + { + "epoch": 1.02, + "learning_rate": 3.423237132975577e-05, + "loss": 3.5611, + "step": 963072 + }, + { + "epoch": 1.02, + "learning_rate": 3.422398538224525e-05, + "loss": 3.5734, + "step": 963584 + }, + { + "epoch": 1.02, + "learning_rate": 3.421561581353846e-05, + "loss": 3.5701, + "step": 964096 + }, + { + "epoch": 1.02, + "learning_rate": 3.420722986602794e-05, + "loss": 3.5789, + "step": 964608 + }, + { + "epoch": 1.02, + "learning_rate": 3.419884391851742e-05, + "loss": 3.563, + "step": 965120 + }, + { + "epoch": 1.02, + "learning_rate": 3.41904579710069e-05, + "loss": 3.5625, + "step": 965632 + }, + { + "epoch": 1.02, + "learning_rate": 3.418207202349638e-05, + "loss": 3.56, + "step": 966144 + }, + { + "epoch": 1.02, + "learning_rate": 3.4173702454789594e-05, + "loss": 3.5731, + "step": 966656 + }, + { + "epoch": 1.02, + "learning_rate": 3.4165316507279074e-05, + "loss": 3.5699, + "step": 967168 + }, + { + "epoch": 1.02, + "learning_rate": 3.4156930559768554e-05, + "loss": 3.5654, + "step": 967680 + }, + { + "epoch": 1.02, + "learning_rate": 3.4148544612258034e-05, + "loss": 3.5627, + "step": 968192 + }, + { + "epoch": 1.02, + "learning_rate": 3.414017504355124e-05, + "loss": 3.5589, + "step": 968704 + }, + { + "epoch": 1.02, + "learning_rate": 3.413178909604072e-05, + "loss": 3.5714, + "step": 969216 + }, + { + "epoch": 1.02, + "learning_rate": 3.41234031485302e-05, + "loss": 3.5486, + "step": 969728 + }, + { + "epoch": 1.02, + "learning_rate": 3.4115017201019676e-05, + "loss": 3.5623, + "step": 970240 + }, + { + "epoch": 1.02, + "learning_rate": 3.4106631253509156e-05, + "loss": 3.5671, + "step": 970752 + }, + { + "epoch": 1.02, + "learning_rate": 3.409826168480237e-05, + "loss": 3.5692, + "step": 971264 + }, + { + "epoch": 1.02, + "learning_rate": 3.408987573729185e-05, + "loss": 3.5546, + "step": 971776 + }, + { + "epoch": 1.02, + "learning_rate": 3.408148978978133e-05, + "loss": 3.5693, + "step": 972288 + }, + { + "epoch": 1.02, + "learning_rate": 3.407310384227081e-05, + "loss": 3.5587, + "step": 972800 + }, + { + "epoch": 1.02, + "learning_rate": 3.406473427356403e-05, + "loss": 3.5716, + "step": 973312 + }, + { + "epoch": 1.02, + "learning_rate": 3.40563483260535e-05, + "loss": 3.5619, + "step": 973824 + }, + { + "epoch": 1.02, + "learning_rate": 3.404796237854298e-05, + "loss": 3.5655, + "step": 974336 + }, + { + "epoch": 1.02, + "learning_rate": 3.403957643103246e-05, + "loss": 3.5663, + "step": 974848 + }, + { + "epoch": 1.02, + "learning_rate": 3.403119048352194e-05, + "loss": 3.583, + "step": 975360 + }, + { + "epoch": 1.02, + "learning_rate": 3.402280453601142e-05, + "loss": 3.5627, + "step": 975872 + }, + { + "epoch": 1.02, + "learning_rate": 3.401443496730463e-05, + "loss": 3.5657, + "step": 976384 + }, + { + "epoch": 1.02, + "learning_rate": 3.400604901979411e-05, + "loss": 3.5706, + "step": 976896 + }, + { + "epoch": 1.02, + "learning_rate": 3.399766307228359e-05, + "loss": 3.5668, + "step": 977408 + }, + { + "epoch": 1.02, + "learning_rate": 3.398927712477307e-05, + "loss": 3.5606, + "step": 977920 + }, + { + "epoch": 1.02, + "learning_rate": 3.3980907556066285e-05, + "loss": 3.565, + "step": 978432 + }, + { + "epoch": 1.02, + "learning_rate": 3.3972521608555765e-05, + "loss": 3.5602, + "step": 978944 + }, + { + "epoch": 1.02, + "learning_rate": 3.3964135661045245e-05, + "loss": 3.5676, + "step": 979456 + }, + { + "epoch": 1.02, + "learning_rate": 3.3955749713534725e-05, + "loss": 3.5549, + "step": 979968 + }, + { + "epoch": 1.02, + "learning_rate": 3.3947380144827934e-05, + "loss": 3.5647, + "step": 980480 + }, + { + "epoch": 1.02, + "learning_rate": 3.3938994197317414e-05, + "loss": 3.5555, + "step": 980992 + }, + { + "epoch": 1.02, + "learning_rate": 3.3930608249806894e-05, + "loss": 3.5623, + "step": 981504 + }, + { + "epoch": 1.02, + "learning_rate": 3.3922222302296374e-05, + "loss": 3.5621, + "step": 982016 + }, + { + "epoch": 1.02, + "learning_rate": 3.3913852733589583e-05, + "loss": 3.5692, + "step": 982528 + }, + { + "epoch": 1.02, + "learning_rate": 3.390546678607906e-05, + "loss": 3.5814, + "step": 983040 + }, + { + "epoch": 1.02, + "learning_rate": 3.389708083856854e-05, + "loss": 3.5619, + "step": 983552 + }, + { + "epoch": 1.02, + "learning_rate": 3.388869489105802e-05, + "loss": 3.5652, + "step": 984064 + }, + { + "epoch": 1.02, + "learning_rate": 3.388032532235124e-05, + "loss": 3.5646, + "step": 984576 + }, + { + "epoch": 1.02, + "learning_rate": 3.387193937484072e-05, + "loss": 3.5646, + "step": 985088 + }, + { + "epoch": 1.02, + "learning_rate": 3.38635534273302e-05, + "loss": 3.5628, + "step": 985600 + }, + { + "epoch": 1.02, + "learning_rate": 3.385516747981968e-05, + "loss": 3.5528, + "step": 986112 + }, + { + "epoch": 1.02, + "learning_rate": 3.384678153230916e-05, + "loss": 3.5689, + "step": 986624 + }, + { + "epoch": 1.02, + "learning_rate": 3.383841196360237e-05, + "loss": 3.5738, + "step": 987136 + }, + { + "epoch": 1.02, + "learning_rate": 3.383002601609185e-05, + "loss": 3.5569, + "step": 987648 + }, + { + "epoch": 1.02, + "learning_rate": 3.382164006858133e-05, + "loss": 3.5687, + "step": 988160 + }, + { + "epoch": 1.02, + "learning_rate": 3.381325412107081e-05, + "loss": 3.5707, + "step": 988672 + }, + { + "epoch": 1.02, + "learning_rate": 3.380486817356029e-05, + "loss": 3.5609, + "step": 989184 + }, + { + "epoch": 1.02, + "learning_rate": 3.37964986048535e-05, + "loss": 3.5627, + "step": 989696 + }, + { + "epoch": 1.02, + "learning_rate": 3.378811265734298e-05, + "loss": 3.5716, + "step": 990208 + }, + { + "epoch": 1.02, + "learning_rate": 3.377972670983246e-05, + "loss": 3.5652, + "step": 990720 + }, + { + "epoch": 1.02, + "learning_rate": 3.377134076232194e-05, + "loss": 3.564, + "step": 991232 + }, + { + "epoch": 1.02, + "learning_rate": 3.376297119361515e-05, + "loss": 3.5709, + "step": 991744 + }, + { + "epoch": 1.03, + "eval_loss": 3.8647313117980957, + "eval_runtime": 304.9956, + "eval_samples_per_second": 1251.136, + "eval_steps_per_second": 39.099, + "step": 992160 + }, + { + "epoch": 0.0, + "learning_rate": 3.375458524610463e-05, + "loss": 3.5687, + "step": 992256 + }, + { + "epoch": 0.0, + "learning_rate": 3.374619929859411e-05, + "loss": 3.5444, + "step": 992768 + }, + { + "epoch": 0.0, + "learning_rate": 3.373781335108359e-05, + "loss": 3.5597, + "step": 993280 + }, + { + "epoch": 0.0, + "learning_rate": 3.372942740357307e-05, + "loss": 3.5747, + "step": 993792 + }, + { + "epoch": 0.0, + "learning_rate": 3.372105783486628e-05, + "loss": 3.5682, + "step": 994304 + }, + { + "epoch": 0.0, + "learning_rate": 3.371267188735576e-05, + "loss": 3.5657, + "step": 994816 + }, + { + "epoch": 0.0, + "learning_rate": 3.370428593984524e-05, + "loss": 3.5623, + "step": 995328 + }, + { + "epoch": 0.0, + "learning_rate": 3.369589999233472e-05, + "loss": 3.5633, + "step": 995840 + }, + { + "epoch": 0.0, + "learning_rate": 3.36875140448242e-05, + "loss": 3.5534, + "step": 996352 + }, + { + "epoch": 0.0, + "learning_rate": 3.367912809731368e-05, + "loss": 3.5634, + "step": 996864 + }, + { + "epoch": 0.0, + "learning_rate": 3.367075852860689e-05, + "loss": 3.5616, + "step": 997376 + }, + { + "epoch": 0.0, + "learning_rate": 3.366237258109638e-05, + "loss": 3.563, + "step": 997888 + }, + { + "epoch": 0.0, + "learning_rate": 3.3654003012389586e-05, + "loss": 3.5694, + "step": 998400 + }, + { + "epoch": 0.0, + "learning_rate": 3.3645617064879066e-05, + "loss": 3.5509, + "step": 998912 + }, + { + "epoch": 0.0, + "learning_rate": 3.3637231117368546e-05, + "loss": 3.5528, + "step": 999424 + }, + { + "epoch": 0.0, + "learning_rate": 3.3628845169858026e-05, + "loss": 3.5443, + "step": 999936 + }, + { + "epoch": 0.0, + "learning_rate": 3.3620459222347506e-05, + "loss": 3.5656, + "step": 1000448 + }, + { + "epoch": 0.0, + "learning_rate": 3.3612073274836986e-05, + "loss": 3.5594, + "step": 1000960 + }, + { + "epoch": 0.0, + "learning_rate": 3.360368732732646e-05, + "loss": 3.5613, + "step": 1001472 + }, + { + "epoch": 0.0, + "learning_rate": 3.359530137981594e-05, + "loss": 3.5575, + "step": 1001984 + }, + { + "epoch": 0.0, + "learning_rate": 3.358691543230542e-05, + "loss": 3.578, + "step": 1002496 + }, + { + "epoch": 0.0, + "learning_rate": 3.3578545863598635e-05, + "loss": 3.5667, + "step": 1003008 + }, + { + "epoch": 0.0, + "learning_rate": 3.3570159916088115e-05, + "loss": 3.5648, + "step": 1003520 + }, + { + "epoch": 0.0, + "learning_rate": 3.3561773968577595e-05, + "loss": 3.5612, + "step": 1004032 + }, + { + "epoch": 0.0, + "learning_rate": 3.3553388021067075e-05, + "loss": 3.5745, + "step": 1004544 + }, + { + "epoch": 0.0, + "learning_rate": 3.3545018452360284e-05, + "loss": 3.5549, + "step": 1005056 + }, + { + "epoch": 0.0, + "learning_rate": 3.3536632504849764e-05, + "loss": 3.5619, + "step": 1005568 + }, + { + "epoch": 0.0, + "learning_rate": 3.3528246557339244e-05, + "loss": 3.5702, + "step": 1006080 + }, + { + "epoch": 0.0, + "learning_rate": 3.3519860609828724e-05, + "loss": 3.5508, + "step": 1006592 + }, + { + "epoch": 0.0, + "learning_rate": 3.3511474662318204e-05, + "loss": 3.555, + "step": 1007104 + }, + { + "epoch": 0.01, + "learning_rate": 3.3503088714807684e-05, + "loss": 3.5557, + "step": 1007616 + }, + { + "epoch": 0.01, + "learning_rate": 3.349471914610089e-05, + "loss": 3.5562, + "step": 1008128 + }, + { + "epoch": 0.01, + "learning_rate": 3.348633319859037e-05, + "loss": 3.5675, + "step": 1008640 + }, + { + "epoch": 0.01, + "learning_rate": 3.347794725107985e-05, + "loss": 3.5695, + "step": 1009152 + }, + { + "epoch": 0.01, + "learning_rate": 3.346956130356933e-05, + "loss": 3.5599, + "step": 1009664 + }, + { + "epoch": 0.01, + "learning_rate": 3.346119173486255e-05, + "loss": 3.5572, + "step": 1010176 + }, + { + "epoch": 0.01, + "learning_rate": 3.345280578735203e-05, + "loss": 3.5698, + "step": 1010688 + }, + { + "epoch": 0.01, + "learning_rate": 3.344441983984151e-05, + "loss": 3.5434, + "step": 1011200 + }, + { + "epoch": 0.01, + "learning_rate": 3.343603389233099e-05, + "loss": 3.5559, + "step": 1011712 + }, + { + "epoch": 0.01, + "learning_rate": 3.34276643236242e-05, + "loss": 3.5547, + "step": 1012224 + }, + { + "epoch": 0.01, + "learning_rate": 3.341927837611368e-05, + "loss": 3.5482, + "step": 1012736 + }, + { + "epoch": 0.01, + "learning_rate": 3.341089242860316e-05, + "loss": 3.5579, + "step": 1013248 + }, + { + "epoch": 0.01, + "learning_rate": 3.340250648109264e-05, + "loss": 3.5658, + "step": 1013760 + }, + { + "epoch": 0.01, + "learning_rate": 3.339412053358212e-05, + "loss": 3.5594, + "step": 1014272 + }, + { + "epoch": 0.01, + "learning_rate": 3.3385750964875327e-05, + "loss": 3.5558, + "step": 1014784 + }, + { + "epoch": 0.01, + "learning_rate": 3.3377365017364807e-05, + "loss": 3.5543, + "step": 1015296 + }, + { + "epoch": 0.01, + "learning_rate": 3.3368979069854286e-05, + "loss": 3.5598, + "step": 1015808 + }, + { + "epoch": 0.01, + "learning_rate": 3.3360593122343766e-05, + "loss": 3.566, + "step": 1016320 + }, + { + "epoch": 0.01, + "learning_rate": 3.335220717483325e-05, + "loss": 3.542, + "step": 1016832 + }, + { + "epoch": 0.01, + "learning_rate": 3.334383760612646e-05, + "loss": 3.5641, + "step": 1017344 + }, + { + "epoch": 0.01, + "learning_rate": 3.333545165861594e-05, + "loss": 3.5565, + "step": 1017856 + }, + { + "epoch": 0.01, + "learning_rate": 3.332706571110542e-05, + "loss": 3.5579, + "step": 1018368 + }, + { + "epoch": 0.01, + "learning_rate": 3.33186797635949e-05, + "loss": 3.5603, + "step": 1018880 + }, + { + "epoch": 0.01, + "learning_rate": 3.331031019488811e-05, + "loss": 3.5448, + "step": 1019392 + }, + { + "epoch": 0.01, + "learning_rate": 3.330192424737759e-05, + "loss": 3.5531, + "step": 1019904 + }, + { + "epoch": 0.01, + "learning_rate": 3.329353829986707e-05, + "loss": 3.5423, + "step": 1020416 + }, + { + "epoch": 0.01, + "learning_rate": 3.328515235235655e-05, + "loss": 3.5734, + "step": 1020928 + }, + { + "epoch": 0.01, + "learning_rate": 3.327678278364976e-05, + "loss": 3.5461, + "step": 1021440 + }, + { + "epoch": 0.01, + "learning_rate": 3.326839683613924e-05, + "loss": 3.5667, + "step": 1021952 + }, + { + "epoch": 0.01, + "learning_rate": 3.326001088862872e-05, + "loss": 3.5524, + "step": 1022464 + }, + { + "epoch": 0.01, + "learning_rate": 3.325162494111821e-05, + "loss": 3.5481, + "step": 1022976 + }, + { + "epoch": 0.01, + "learning_rate": 3.324323899360769e-05, + "loss": 3.5562, + "step": 1023488 + }, + { + "epoch": 0.01, + "learning_rate": 3.3234869424900896e-05, + "loss": 3.5515, + "step": 1024000 + }, + { + "epoch": 0.01, + "learning_rate": 3.3226483477390376e-05, + "loss": 3.5464, + "step": 1024512 + }, + { + "epoch": 0.01, + "learning_rate": 3.3218097529879856e-05, + "loss": 3.5372, + "step": 1025024 + }, + { + "epoch": 0.01, + "learning_rate": 3.3209711582369336e-05, + "loss": 3.5636, + "step": 1025536 + }, + { + "epoch": 0.01, + "learning_rate": 3.3201342013662545e-05, + "loss": 3.5511, + "step": 1026048 + }, + { + "epoch": 0.01, + "learning_rate": 3.3192956066152025e-05, + "loss": 3.555, + "step": 1026560 + }, + { + "epoch": 0.01, + "learning_rate": 3.3184570118641505e-05, + "loss": 3.5409, + "step": 1027072 + }, + { + "epoch": 0.01, + "learning_rate": 3.3176184171130985e-05, + "loss": 3.5476, + "step": 1027584 + }, + { + "epoch": 0.01, + "learning_rate": 3.3167798223620465e-05, + "loss": 3.5535, + "step": 1028096 + }, + { + "epoch": 0.01, + "learning_rate": 3.3159428654913674e-05, + "loss": 3.5575, + "step": 1028608 + }, + { + "epoch": 0.01, + "learning_rate": 3.3151042707403154e-05, + "loss": 3.5552, + "step": 1029120 + }, + { + "epoch": 0.01, + "learning_rate": 3.314265675989264e-05, + "loss": 3.5574, + "step": 1029632 + }, + { + "epoch": 0.01, + "learning_rate": 3.313427081238212e-05, + "loss": 3.5616, + "step": 1030144 + }, + { + "epoch": 0.01, + "learning_rate": 3.312590124367533e-05, + "loss": 3.5479, + "step": 1030656 + }, + { + "epoch": 0.01, + "learning_rate": 3.311751529616481e-05, + "loss": 3.5523, + "step": 1031168 + }, + { + "epoch": 0.01, + "learning_rate": 3.310912934865429e-05, + "loss": 3.5469, + "step": 1031680 + }, + { + "epoch": 0.01, + "learning_rate": 3.310074340114377e-05, + "loss": 3.5519, + "step": 1032192 + }, + { + "epoch": 0.01, + "learning_rate": 3.309235745363324e-05, + "loss": 3.5532, + "step": 1032704 + }, + { + "epoch": 0.01, + "learning_rate": 3.308397150612272e-05, + "loss": 3.5457, + "step": 1033216 + }, + { + "epoch": 0.01, + "learning_rate": 3.307560193741594e-05, + "loss": 3.5609, + "step": 1033728 + }, + { + "epoch": 0.01, + "learning_rate": 3.306721598990541e-05, + "loss": 3.5618, + "step": 1034240 + }, + { + "epoch": 0.01, + "learning_rate": 3.305883004239489e-05, + "loss": 3.5476, + "step": 1034752 + }, + { + "epoch": 0.01, + "learning_rate": 3.305044409488438e-05, + "loss": 3.5357, + "step": 1035264 + }, + { + "epoch": 0.01, + "learning_rate": 3.3042074526177594e-05, + "loss": 3.5526, + "step": 1035776 + }, + { + "epoch": 0.01, + "learning_rate": 3.303368857866707e-05, + "loss": 3.557, + "step": 1036288 + }, + { + "epoch": 0.01, + "learning_rate": 3.302530263115655e-05, + "loss": 3.5595, + "step": 1036800 + }, + { + "epoch": 0.01, + "learning_rate": 3.301691668364603e-05, + "loss": 3.5474, + "step": 1037312 + }, + { + "epoch": 0.01, + "learning_rate": 3.300854711493924e-05, + "loss": 3.5506, + "step": 1037824 + }, + { + "epoch": 0.02, + "learning_rate": 3.3000161167428716e-05, + "loss": 3.56, + "step": 1038336 + }, + { + "epoch": 0.02, + "learning_rate": 3.2991775219918196e-05, + "loss": 3.5402, + "step": 1038848 + }, + { + "epoch": 0.02, + "learning_rate": 3.2983389272407676e-05, + "loss": 3.5462, + "step": 1039360 + }, + { + "epoch": 0.02, + "learning_rate": 3.2975003324897156e-05, + "loss": 3.5526, + "step": 1039872 + }, + { + "epoch": 0.02, + "learning_rate": 3.2966633756190365e-05, + "loss": 3.5528, + "step": 1040384 + }, + { + "epoch": 0.02, + "learning_rate": 3.2958247808679845e-05, + "loss": 3.5616, + "step": 1040896 + }, + { + "epoch": 0.02, + "learning_rate": 3.294986186116933e-05, + "loss": 3.5525, + "step": 1041408 + }, + { + "epoch": 0.02, + "learning_rate": 3.294147591365881e-05, + "loss": 3.5416, + "step": 1041920 + }, + { + "epoch": 0.02, + "learning_rate": 3.293310634495202e-05, + "loss": 3.5439, + "step": 1042432 + }, + { + "epoch": 0.02, + "learning_rate": 3.29247203974415e-05, + "loss": 3.5522, + "step": 1042944 + }, + { + "epoch": 0.02, + "learning_rate": 3.291633444993098e-05, + "loss": 3.5541, + "step": 1043456 + }, + { + "epoch": 0.02, + "learning_rate": 3.290794850242046e-05, + "loss": 3.5487, + "step": 1043968 + }, + { + "epoch": 0.02, + "learning_rate": 3.289956255490994e-05, + "loss": 3.5448, + "step": 1044480 + }, + { + "epoch": 0.02, + "learning_rate": 3.289119298620315e-05, + "loss": 3.5422, + "step": 1044992 + }, + { + "epoch": 0.02, + "learning_rate": 3.288280703869263e-05, + "loss": 3.5567, + "step": 1045504 + }, + { + "epoch": 0.02, + "learning_rate": 3.287442109118211e-05, + "loss": 3.5316, + "step": 1046016 + }, + { + "epoch": 0.02, + "learning_rate": 3.286603514367159e-05, + "loss": 3.5423, + "step": 1046528 + }, + { + "epoch": 0.02, + "learning_rate": 3.28576655749648e-05, + "loss": 3.5494, + "step": 1047040 + }, + { + "epoch": 0.02, + "learning_rate": 3.2849279627454286e-05, + "loss": 3.5548, + "step": 1047552 + }, + { + "epoch": 0.02, + "learning_rate": 3.2840893679943766e-05, + "loss": 3.5399, + "step": 1048064 + }, + { + "epoch": 0.02, + "learning_rate": 3.2832507732433245e-05, + "loss": 3.5511, + "step": 1048576 + }, + { + "epoch": 0.02, + "learning_rate": 3.2824121784922725e-05, + "loss": 3.5415, + "step": 1049088 + }, + { + "epoch": 0.02, + "learning_rate": 3.2815752216215935e-05, + "loss": 3.5527, + "step": 1049600 + }, + { + "epoch": 0.02, + "learning_rate": 3.2807366268705414e-05, + "loss": 3.5502, + "step": 1050112 + }, + { + "epoch": 0.02, + "learning_rate": 3.2798980321194894e-05, + "loss": 3.5445, + "step": 1050624 + }, + { + "epoch": 0.02, + "learning_rate": 3.2790594373684374e-05, + "loss": 3.549, + "step": 1051136 + }, + { + "epoch": 0.02, + "learning_rate": 3.2782208426173854e-05, + "loss": 3.5662, + "step": 1051648 + }, + { + "epoch": 0.02, + "learning_rate": 3.2773822478663334e-05, + "loss": 3.5453, + "step": 1052160 + }, + { + "epoch": 0.02, + "learning_rate": 3.2765452909956543e-05, + "loss": 3.5501, + "step": 1052672 + }, + { + "epoch": 0.02, + "learning_rate": 3.275706696244602e-05, + "loss": 3.5495, + "step": 1053184 + }, + { + "epoch": 0.02, + "learning_rate": 3.27486810149355e-05, + "loss": 3.548, + "step": 1053696 + }, + { + "epoch": 0.02, + "learning_rate": 3.274029506742498e-05, + "loss": 3.5452, + "step": 1054208 + }, + { + "epoch": 0.02, + "learning_rate": 3.27319254987182e-05, + "loss": 3.5471, + "step": 1054720 + }, + { + "epoch": 0.02, + "learning_rate": 3.272353955120768e-05, + "loss": 3.5464, + "step": 1055232 + }, + { + "epoch": 0.02, + "learning_rate": 3.271515360369716e-05, + "loss": 3.5514, + "step": 1055744 + }, + { + "epoch": 0.02, + "learning_rate": 3.270676765618664e-05, + "loss": 3.5408, + "step": 1056256 + }, + { + "epoch": 0.02, + "learning_rate": 3.269839808747985e-05, + "loss": 3.546, + "step": 1056768 + }, + { + "epoch": 0.02, + "learning_rate": 3.269001213996933e-05, + "loss": 3.5404, + "step": 1057280 + }, + { + "epoch": 0.02, + "learning_rate": 3.268162619245881e-05, + "loss": 3.546, + "step": 1057792 + }, + { + "epoch": 0.02, + "learning_rate": 3.267324024494829e-05, + "loss": 3.5409, + "step": 1058304 + }, + { + "epoch": 0.02, + "learning_rate": 3.26648706762415e-05, + "loss": 3.5568, + "step": 1058816 + }, + { + "epoch": 0.02, + "learning_rate": 3.265648472873098e-05, + "loss": 3.5631, + "step": 1059328 + }, + { + "epoch": 0.02, + "learning_rate": 3.264809878122046e-05, + "loss": 3.5407, + "step": 1059840 + }, + { + "epoch": 0.02, + "learning_rate": 3.263971283370994e-05, + "loss": 3.5486, + "step": 1060352 + }, + { + "epoch": 0.02, + "learning_rate": 3.2631326886199424e-05, + "loss": 3.5519, + "step": 1060864 + }, + { + "epoch": 0.02, + "learning_rate": 3.262295731749263e-05, + "loss": 3.5509, + "step": 1061376 + }, + { + "epoch": 0.02, + "learning_rate": 3.261457136998211e-05, + "loss": 3.5382, + "step": 1061888 + }, + { + "epoch": 0.02, + "learning_rate": 3.260618542247159e-05, + "loss": 3.5379, + "step": 1062400 + }, + { + "epoch": 0.02, + "learning_rate": 3.259779947496107e-05, + "loss": 3.5559, + "step": 1062912 + }, + { + "epoch": 0.02, + "learning_rate": 3.2589413527450546e-05, + "loss": 3.5547, + "step": 1063424 + }, + { + "epoch": 0.02, + "learning_rate": 3.258104395874376e-05, + "loss": 3.5394, + "step": 1063936 + }, + { + "epoch": 0.02, + "learning_rate": 3.257265801123324e-05, + "loss": 3.5518, + "step": 1064448 + }, + { + "epoch": 0.02, + "learning_rate": 3.256427206372272e-05, + "loss": 3.5558, + "step": 1064960 + }, + { + "epoch": 0.02, + "learning_rate": 3.2555886116212195e-05, + "loss": 3.5473, + "step": 1065472 + }, + { + "epoch": 0.02, + "learning_rate": 3.254751654750541e-05, + "loss": 3.5411, + "step": 1065984 + }, + { + "epoch": 0.02, + "learning_rate": 3.253913059999489e-05, + "loss": 3.5544, + "step": 1066496 + }, + { + "epoch": 0.02, + "learning_rate": 3.253074465248438e-05, + "loss": 3.5465, + "step": 1067008 + }, + { + "epoch": 0.02, + "learning_rate": 3.252235870497385e-05, + "loss": 3.5526, + "step": 1067520 + }, + { + "epoch": 0.02, + "learning_rate": 3.2513989136267066e-05, + "loss": 3.5497, + "step": 1068032 + }, + { + "epoch": 0.03, + "eval_loss": 3.8658111095428467, + "eval_runtime": 302.2352, + "eval_samples_per_second": 1262.563, + "eval_steps_per_second": 39.456, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.2505603188756546e-05, + "loss": 3.5558, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249721724124602e-05, + "loss": 3.5292, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.24888312937355e-05, + "loss": 3.5409, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248044534622498e-05, + "loss": 3.5594, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247205939871446e-05, + "loss": 3.5511, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246367345120394e-05, + "loss": 3.5493, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245530388249715e-05, + "loss": 3.5411, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244691793498663e-05, + "loss": 3.5463, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2438531987476115e-05, + "loss": 3.5388, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2430146039965595e-05, + "loss": 3.5488, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2421776471258804e-05, + "loss": 3.5407, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2413390523748284e-05, + "loss": 3.5522, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240502095504149e-05, + "loss": 3.5515, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239663500753097e-05, + "loss": 3.5342, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.238824906002045e-05, + "loss": 3.5378, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.237986311250993e-05, + "loss": 3.5257, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237147716499941e-05, + "loss": 3.5479, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236309121748889e-05, + "loss": 3.5439, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235470526997837e-05, + "loss": 3.5471, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234631932246785e-05, + "loss": 3.5372, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233793337495733e-05, + "loss": 3.5654, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232956380625055e-05, + "loss": 3.553, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.232117785874003e-05, + "loss": 3.5458, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231279191122951e-05, + "loss": 3.5466, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230440596371899e-05, + "loss": 3.5591, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229602001620847e-05, + "loss": 3.5393, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228765044750168e-05, + "loss": 3.5429, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227926449999116e-05, + "loss": 3.555, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227087855248064e-05, + "loss": 3.5325, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226249260497012e-05, + "loss": 3.537, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.225412303626333e-05, + "loss": 3.5354, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2245737088752807e-05, + "loss": 3.5401, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2237351141242287e-05, + "loss": 3.5508, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2228965193731767e-05, + "loss": 3.552, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2220579246221246e-05, + "loss": 3.5402, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221220967751446e-05, + "loss": 3.5479, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220382373000394e-05, + "loss": 3.5489, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219543778249342e-05, + "loss": 3.5285, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21870518349829e-05, + "loss": 3.5368, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217868226627611e-05, + "loss": 3.5411, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217029631876559e-05, + "loss": 3.5294, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216191037125507e-05, + "loss": 3.5448, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215352442374455e-05, + "loss": 3.5493, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214513847623403e-05, + "loss": 3.5405, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213676890752724e-05, + "loss": 3.5387, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212838296001672e-05, + "loss": 3.5415, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.21199970125062e-05, + "loss": 3.5395, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211161106499568e-05, + "loss": 3.5513, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210322511748516e-05, + "loss": 3.5237, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.2094855548778376e-05, + "loss": 3.5456, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.2086469601267856e-05, + "loss": 3.5433, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207808365375733e-05, + "loss": 3.5403, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.206969770624681e-05, + "loss": 3.5432, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061328137540025e-05, + "loss": 3.5269, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2052942190029505e-05, + "loss": 3.542, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.204455624251898e-05, + "loss": 3.5232, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.203617029500846e-05, + "loss": 3.5569, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2027800726301674e-05, + "loss": 3.5299, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.2019414778791154e-05, + "loss": 3.5463, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011028831280634e-05, + "loss": 3.5412, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.2002642883770114e-05, + "loss": 3.534, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.1994256936259594e-05, + "loss": 3.5384, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.19858873675528e-05, + "loss": 3.5381, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197750142004228e-05, + "loss": 3.5267, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196911547253176e-05, + "loss": 3.5237, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196072952502124e-05, + "loss": 3.5468, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195235995631445e-05, + "loss": 3.5358, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.194397400880393e-05, + "loss": 3.5369, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193558806129341e-05, + "loss": 3.5249, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.192720211378289e-05, + "loss": 3.5354, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191881616627238e-05, + "loss": 3.5371, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191044659756559e-05, + "loss": 3.5416, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190206065005507e-05, + "loss": 3.5414, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189367470254455e-05, + "loss": 3.5425, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188528875503403e-05, + "loss": 3.5439, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.1876919186327236e-05, + "loss": 3.5329, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.1868533238816716e-05, + "loss": 3.5353, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860147291306196e-05, + "loss": 3.5303, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1851761343795676e-05, + "loss": 3.5385, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843375396285156e-05, + "loss": 3.536, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1834989448774636e-05, + "loss": 3.5298, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.1826619880067845e-05, + "loss": 3.5406, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181823393255733e-05, + "loss": 3.5444, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.180984798504681e-05, + "loss": 3.5332, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180146203753629e-05, + "loss": 3.5249, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.17930924688295e-05, + "loss": 3.5313, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178470652131898e-05, + "loss": 3.5373, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177632057380846e-05, + "loss": 3.5467, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176793462629794e-05, + "loss": 3.5322, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175956505759115e-05, + "loss": 3.5345, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175117911008063e-05, + "loss": 3.5411, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174279316257011e-05, + "loss": 3.5289, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173440721505959e-05, + "loss": 3.5291, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172602126754907e-05, + "loss": 3.5347, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171763532003855e-05, + "loss": 3.5402, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1709265751331766e-05, + "loss": 3.5423, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1700879803821246e-05, + "loss": 3.5403, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1692493856310726e-05, + "loss": 3.5239, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684107908800205e-05, + "loss": 3.5319, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1675738340093415e-05, + "loss": 3.5344, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667352392582895e-05, + "loss": 3.5408, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1658966445072374e-05, + "loss": 3.5318, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1650580497561854e-05, + "loss": 3.531, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642210928855064e-05, + "loss": 3.5251, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1633824981344543e-05, + "loss": 3.5398, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.1625439033834023e-05, + "loss": 3.5186, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.1617053086323503e-05, + "loss": 3.5284, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160866713881298e-05, + "loss": 3.5348, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.16002975701062e-05, + "loss": 3.5331, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159191162259568e-05, + "loss": 3.5244, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158352567508516e-05, + "loss": 3.5345, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157513972757464e-05, + "loss": 3.5249, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156677015886785e-05, + "loss": 3.5353, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.155838421135733e-05, + "loss": 3.537, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.154999826384681e-05, + "loss": 3.527, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154162869514002e-05, + "loss": 3.5362, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.15332427476295e-05, + "loss": 3.5472, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152485680011898e-05, + "loss": 3.5362, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.151647085260846e-05, + "loss": 3.5264, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.150808490509794e-05, + "loss": 3.5395, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.149969895758742e-05, + "loss": 3.5334, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.14913130100769e-05, + "loss": 3.5278, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148292706256638e-05, + "loss": 3.5336, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147454111505586e-05, + "loss": 3.5294, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.1466171546349066e-05, + "loss": 3.5353, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.1457785598838546e-05, + "loss": 3.5269, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.1449399651328026e-05, + "loss": 3.5289, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.1441013703817506e-05, + "loss": 3.5251, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.1432644135110715e-05, + "loss": 3.5284, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.1424258187600195e-05, + "loss": 3.5211, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.1415872240089675e-05, + "loss": 3.5427, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.1407486292579155e-05, + "loss": 3.5482, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139910034506864e-05, + "loss": 3.5315, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139073077636185e-05, + "loss": 3.5296, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138234482885133e-05, + "loss": 3.5395, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137395888134081e-05, + "loss": 3.5337, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.136557293383029e-05, + "loss": 3.5244, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.13572033651235e-05, + "loss": 3.5232, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134881741761298e-05, + "loss": 3.5408, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134043147010246e-05, + "loss": 3.5369, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133204552259194e-05, + "loss": 3.5276, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132367595388515e-05, + "loss": 3.5347, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131529000637463e-05, + "loss": 3.5411, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130690405886411e-05, + "loss": 3.5284, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298518111353595e-05, + "loss": 3.5296, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.1290148542646804e-05, + "loss": 3.5406, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1281762595136284e-05, + "loss": 3.5304, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273376647625764e-05, + "loss": 3.5384, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1264990700115244e-05, + "loss": 3.5332, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.866710662841797, + "eval_runtime": 302.6303, + "eval_samples_per_second": 1260.915, + "eval_steps_per_second": 39.405, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125662113140845e-05, + "loss": 3.5312, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124823518389793e-05, + "loss": 3.5167, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.123984923638741e-05, + "loss": 3.5252, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123146328887689e-05, + "loss": 3.5413, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122307734136637e-05, + "loss": 3.5358, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121469139385585e-05, + "loss": 3.5375, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120632182514906e-05, + "loss": 3.5253, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119793587763855e-05, + "loss": 3.5344, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118954993012803e-05, + "loss": 3.5206, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118116398261751e-05, + "loss": 3.5368, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117277803510699e-05, + "loss": 3.5242, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.116439208759647e-05, + "loss": 3.5383, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115603889769341e-05, + "loss": 3.537, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114765295018289e-05, + "loss": 3.5189, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.113926700267237e-05, + "loss": 3.5217, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113088105516185e-05, + "loss": 3.5144, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112249510765133e-05, + "loss": 3.5237, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111410916014081e-05, + "loss": 3.5278, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110572321263029e-05, + "loss": 3.5347, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.1097337265119767e-05, + "loss": 3.5212, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.1088951317609247e-05, + "loss": 3.5531, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108058174890246e-05, + "loss": 3.535, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107219580139194e-05, + "loss": 3.5332, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106380985388142e-05, + "loss": 3.529, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.1055423906370896e-05, + "loss": 3.5447, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047037958860375e-05, + "loss": 3.5255, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103866839015359e-05, + "loss": 3.5297, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.1030282442643065e-05, + "loss": 3.5367, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.1021896495132544e-05, + "loss": 3.5142, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1013510547622024e-05, + "loss": 3.5261, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1005124600111504e-05, + "loss": 3.5207, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.099675503140472e-05, + "loss": 3.5272, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.09883690838942e-05, + "loss": 3.5331, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.097998313638368e-05, + "loss": 3.5369, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097159718887316e-05, + "loss": 3.527, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096322762016637e-05, + "loss": 3.5338, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095484167265585e-05, + "loss": 3.5326, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094645572514533e-05, + "loss": 3.5119, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093806977763481e-05, + "loss": 3.5252, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.092970020892802e-05, + "loss": 3.5264, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.09213142614175e-05, + "loss": 3.5113, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091292831390698e-05, + "loss": 3.5301, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090454236639646e-05, + "loss": 3.5326, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089615641888594e-05, + "loss": 3.5304, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088777047137542e-05, + "loss": 3.5171, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0879400902668634e-05, + "loss": 3.53, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871014955158114e-05, + "loss": 3.5226, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0862629007647594e-05, + "loss": 3.5374, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0854243060137074e-05, + "loss": 3.5088, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084587349143028e-05, + "loss": 3.5271, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.083748754391976e-05, + "loss": 3.5325, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082910159640924e-05, + "loss": 3.5239, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082071564889872e-05, + "loss": 3.5314, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081234608019193e-05, + "loss": 3.5103, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080396013268141e-05, + "loss": 3.5279, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079557418517089e-05, + "loss": 3.5089, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078718823766037e-05, + "loss": 3.54, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077881866895359e-05, + "loss": 3.5191, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.077043272144307e-05, + "loss": 3.5285, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076204677393255e-05, + "loss": 3.5281, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075366082642203e-05, + "loss": 3.5168, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074527487891151e-05, + "loss": 3.5226, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.0736905310204716e-05, + "loss": 3.5234, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.0728519362694196e-05, + "loss": 3.5125, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.0720133415183676e-05, + "loss": 3.5085, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.0711747467673156e-05, + "loss": 3.5289, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.0703377898966365e-05, + "loss": 3.5224, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.0694991951455845e-05, + "loss": 3.5251, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0686606003945325e-05, + "loss": 3.5099, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067822005643481e-05, + "loss": 3.5151, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.066985048772802e-05, + "loss": 3.5221, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.06614645402175e-05, + "loss": 3.5243, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065307859270698e-05, + "loss": 3.5269, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064469264519646e-05, + "loss": 3.5269, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.063632307648967e-05, + "loss": 3.5307, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062793712897915e-05, + "loss": 3.5201, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061955118146863e-05, + "loss": 3.5186, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061116523395811e-05, + "loss": 3.5185, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060277928644759e-05, + "loss": 3.5182, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.05944097177408e-05, + "loss": 3.5237, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058602377023028e-05, + "loss": 3.5196, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0577637822719766e-05, + "loss": 3.521, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0569251875209246e-05, + "loss": 3.5358, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0560882306502455e-05, + "loss": 3.5154, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0552496358991935e-05, + "loss": 3.5108, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544110411481415e-05, + "loss": 3.5169, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0535724463970895e-05, + "loss": 3.5233, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0527338516460375e-05, + "loss": 3.529, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0518968947753584e-05, + "loss": 3.5167, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510583000243064e-05, + "loss": 3.5192, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502197052732544e-05, + "loss": 3.5278, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0493811105222027e-05, + "loss": 3.5167, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.04854251577115e-05, + "loss": 3.5124, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477055589004716e-05, + "loss": 3.5188, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0468669641494196e-05, + "loss": 3.5256, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460283693983673e-05, + "loss": 3.5284, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0451897746473152e-05, + "loss": 3.5241, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443511798962632e-05, + "loss": 3.5104, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.0435142230255848e-05, + "loss": 3.5151, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042675628274532e-05, + "loss": 3.5172, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.04183703352348e-05, + "loss": 3.5282, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.040998438772428e-05, + "loss": 3.5165, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.0401598440213765e-05, + "loss": 3.5146, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.0393228871506974e-05, + "loss": 3.5135, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0384842923996454e-05, + "loss": 3.5217, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376456976485934e-05, + "loss": 3.5039, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.0368071028975414e-05, + "loss": 3.517, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.0359685081464894e-05, + "loss": 3.5147, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.0351299133954374e-05, + "loss": 3.5202, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.0342929565247586e-05, + "loss": 3.5096, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334543617737066e-05, + "loss": 3.5225, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326157670226546e-05, + "loss": 3.5084, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0317771722716026e-05, + "loss": 3.5208, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309385775205506e-05, + "loss": 3.5213, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030101620649872e-05, + "loss": 3.5117, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0292646637791927e-05, + "loss": 3.5227, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284260690281407e-05, + "loss": 3.5321, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0275874742770887e-05, + "loss": 3.5223, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267488795260367e-05, + "loss": 3.5149, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259102847749847e-05, + "loss": 3.5186, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0250716900239327e-05, + "loss": 3.5199, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.024233095272881e-05, + "loss": 3.5111, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.023394500521829e-05, + "loss": 3.5221, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.022555905770777e-05, + "loss": 3.5136, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.021718948900098e-05, + "loss": 3.5233, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.020880354149046e-05, + "loss": 3.5101, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.020041759397994e-05, + "loss": 3.5148, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019203164646942e-05, + "loss": 3.5095, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0183645698958903e-05, + "loss": 3.5119, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.0175276130252112e-05, + "loss": 3.5076, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0166890182741592e-05, + "loss": 3.5261, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0158504235231072e-05, + "loss": 3.5362, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0150118287720552e-05, + "loss": 3.5169, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0141748719013764e-05, + "loss": 3.5092, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.0133362771503244e-05, + "loss": 3.5255, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.0124976823992724e-05, + "loss": 3.5213, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.0116590876482204e-05, + "loss": 3.5128, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0108221307775413e-05, + "loss": 3.5059, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.0099835360264893e-05, + "loss": 3.5266, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091449412754373e-05, + "loss": 3.5176, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0083063465243853e-05, + "loss": 3.5154, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0074693896537066e-05, + "loss": 3.5167, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066307949026546e-05, + "loss": 3.524, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0057922001516025e-05, + "loss": 3.5149, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049536054005505e-05, + "loss": 3.5149, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041166485298718e-05, + "loss": 3.528, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0032780537788198e-05, + "loss": 3.5165, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024394590277678e-05, + "loss": 3.5207, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016008642767158e-05, + "loss": 3.5217, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0007639074060367e-05, + "loss": 3.5166, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8686678409576416, + "eval_runtime": 302.0591, + "eval_samples_per_second": 1263.299, + "eval_steps_per_second": 39.479, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999253126549847e-05, + "loss": 3.5016, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9990867179039327e-05, + "loss": 3.5089, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982481231528803e-05, + "loss": 3.5267, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974095284018283e-05, + "loss": 3.5229, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9965709336507763e-05, + "loss": 3.5228, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.995733976780098e-05, + "loss": 3.5077, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9948953820290456e-05, + "loss": 3.5218, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940567872779936e-05, + "loss": 3.5025, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932181925269416e-05, + "loss": 3.525, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992381235656263e-05, + "loss": 3.5063, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.9915426409052105e-05, + "loss": 3.5259, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.9907040461541585e-05, + "loss": 3.5197, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.98986708928348e-05, + "loss": 3.509, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890284945324277e-05, + "loss": 3.5079, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9881898997813757e-05, + "loss": 3.5024, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9873513050303237e-05, + "loss": 3.5037, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9865127102792717e-05, + "loss": 3.5144, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9856741155282197e-05, + "loss": 3.5178, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9848355207771677e-05, + "loss": 3.5079, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9839969260261157e-05, + "loss": 3.5364, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9831583312750637e-05, + "loss": 3.5204, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982321374404385e-05, + "loss": 3.5208, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.981482779653333e-05, + "loss": 3.5141, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.980644184902281e-05, + "loss": 3.5276, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.979805590151229e-05, + "loss": 3.5084, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9789686332805498e-05, + "loss": 3.5217, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.978130038529498e-05, + "loss": 3.5209, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977291443778446e-05, + "loss": 3.5066, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976452849027394e-05, + "loss": 3.506, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.975614254276342e-05, + "loss": 3.5044, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.974777297405663e-05, + "loss": 3.5145, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.973938702654611e-05, + "loss": 3.5189, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.973100107903559e-05, + "loss": 3.5205, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9722615131525074e-05, + "loss": 3.5153, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714245562818283e-05, + "loss": 3.5178, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.9705859615307763e-05, + "loss": 3.5153, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9697473667797243e-05, + "loss": 3.5022, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689087720286723e-05, + "loss": 3.5107, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9680718151579935e-05, + "loss": 3.5087, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672332204069415e-05, + "loss": 3.5031, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9663946256558895e-05, + "loss": 3.5118, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655560309048375e-05, + "loss": 3.5232, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.9647174361537855e-05, + "loss": 3.514, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.9638788414027335e-05, + "loss": 3.5059, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9630418845320544e-05, + "loss": 3.5146, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622032897810027e-05, + "loss": 3.5153, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9613646950299507e-05, + "loss": 3.5175, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605261002788987e-05, + "loss": 3.5004, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9596891434082196e-05, + "loss": 3.5088, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588505486571676e-05, + "loss": 3.5162, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580119539061156e-05, + "loss": 3.511, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9571733591550636e-05, + "loss": 3.5131, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.956336402284385e-05, + "loss": 3.4991, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.955497807533333e-05, + "loss": 3.5142, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.954659212782281e-05, + "loss": 3.4936, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.953820618031229e-05, + "loss": 3.5214, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9529836611605498e-05, + "loss": 3.5063, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.952145066409498e-05, + "loss": 3.5127, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.951306471658446e-05, + "loss": 3.5107, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9504678769073934e-05, + "loss": 3.5082, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496292821563414e-05, + "loss": 3.5039, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.948792325285663e-05, + "loss": 3.5112, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.947953730534611e-05, + "loss": 3.4985, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471151357835587e-05, + "loss": 3.4955, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9462765410325067e-05, + "loss": 3.5124, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9454379462814547e-05, + "loss": 3.5112, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.9446009894107762e-05, + "loss": 3.5075, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9437623946597236e-05, + "loss": 3.4948, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942923799908672e-05, + "loss": 3.5013, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.94208520515762e-05, + "loss": 3.5105, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9412482482869408e-05, + "loss": 3.5125, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.9404096535358888e-05, + "loss": 3.5096, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.9395710587848368e-05, + "loss": 3.5139, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9387324640337848e-05, + "loss": 3.5171, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937895507163106e-05, + "loss": 3.5126, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937056912412054e-05, + "loss": 3.4976, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936218317661002e-05, + "loss": 3.503, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.93537972290995e-05, + "loss": 3.5091, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934542766039271e-05, + "loss": 3.506, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933704171288219e-05, + "loss": 3.506, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9328655765371673e-05, + "loss": 3.5058, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320269817861153e-05, + "loss": 3.5235, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9311883870350632e-05, + "loss": 3.5, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.930351430164384e-05, + "loss": 3.4937, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.929512835413332e-05, + "loss": 3.5054, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.92867424066228e-05, + "loss": 3.509, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927835645911228e-05, + "loss": 3.5151, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9269986890405494e-05, + "loss": 3.5007, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9261600942894974e-05, + "loss": 3.5075, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253214995384454e-05, + "loss": 3.5098, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9244829047873934e-05, + "loss": 3.5048, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236443100363414e-05, + "loss": 3.4972, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228073531656623e-05, + "loss": 3.5048, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9219687584146106e-05, + "loss": 3.5136, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211301636635586e-05, + "loss": 3.5217, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.9202915689125066e-05, + "loss": 3.5024, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.9194546120418275e-05, + "loss": 3.4968, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186160172907755e-05, + "loss": 3.5054, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9177774225397235e-05, + "loss": 3.501, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169388277886715e-05, + "loss": 3.5128, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.91610023303762e-05, + "loss": 3.5019, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9152632761669408e-05, + "loss": 3.5022, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9144246814158887e-05, + "loss": 3.4987, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9135860866648367e-05, + "loss": 3.5099, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9127474919137847e-05, + "loss": 3.4851, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911910535043106e-05, + "loss": 3.5037, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.911071940292054e-05, + "loss": 3.4981, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.910233345541002e-05, + "loss": 3.5083, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.90939475078995e-05, + "loss": 3.4956, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.908557793919271e-05, + "loss": 3.5084, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907719199168219e-05, + "loss": 3.4977, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906880604417167e-05, + "loss": 3.5035, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9060420096661152e-05, + "loss": 3.5058, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.905205052795436e-05, + "loss": 3.4992, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.904368095924757e-05, + "loss": 3.5116, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.903529501173705e-05, + "loss": 3.5188, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.902690906422653e-05, + "loss": 3.5066, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.9018523116716014e-05, + "loss": 3.5019, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010137169205493e-05, + "loss": 3.5037, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9001751221694973e-05, + "loss": 3.5042, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993365274184453e-05, + "loss": 3.4998, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8984979326673933e-05, + "loss": 3.5053, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8976593379163413e-05, + "loss": 3.5031, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968207431652893e-05, + "loss": 3.5064, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.895982148414237e-05, + "loss": 3.4961, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951451915435586e-05, + "loss": 3.5025, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943065967925066e-05, + "loss": 3.4948, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.893468002041454e-05, + "loss": 3.4965, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892629407290402e-05, + "loss": 3.4932, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8917924504197235e-05, + "loss": 3.5136, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8909538556686715e-05, + "loss": 3.5209, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890115260917619e-05, + "loss": 3.5096, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.889276666166567e-05, + "loss": 3.4896, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884397092958887e-05, + "loss": 3.5131, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876011145448367e-05, + "loss": 3.506, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8867625197937844e-05, + "loss": 3.4982, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859239250427324e-05, + "loss": 3.4932, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8850853302916803e-05, + "loss": 3.5126, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8842483734210013e-05, + "loss": 3.5033, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834097786699493e-05, + "loss": 3.5019, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8825711839188972e-05, + "loss": 3.5072, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817325891678452e-05, + "loss": 3.5074, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8808956322971665e-05, + "loss": 3.5011, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8800570375461145e-05, + "loss": 3.5006, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792184427950625e-05, + "loss": 3.5144, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8783798480440105e-05, + "loss": 3.5034, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8775412532929585e-05, + "loss": 3.5042, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.8767026585419065e-05, + "loss": 3.5112, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.8758657016712277e-05, + "loss": 3.4988, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.868619918823242, + "eval_runtime": 302.3829, + "eval_samples_per_second": 1261.946, + "eval_steps_per_second": 39.437, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8750271069201757e-05, + "loss": 3.4894, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8741885121691237e-05, + "loss": 3.4978, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733499174180717e-05, + "loss": 3.5126, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725113226670197e-05, + "loss": 3.5058, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.8716743657963406e-05, + "loss": 3.5111, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870835771045289e-05, + "loss": 3.493, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.869997176294237e-05, + "loss": 3.5052, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869158581543185e-05, + "loss": 3.4895, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868321624672506e-05, + "loss": 3.5102, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867483029921454e-05, + "loss": 3.4963, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.866644435170402e-05, + "loss": 3.5113, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.86580584041935e-05, + "loss": 3.5015, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.864968883548671e-05, + "loss": 3.4982, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864130288797619e-05, + "loss": 3.493, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863291694046567e-05, + "loss": 3.4908, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.862453099295515e-05, + "loss": 3.4916, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.861614504544463e-05, + "loss": 3.5004, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.860775909793411e-05, + "loss": 3.506, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.859937315042359e-05, + "loss": 3.4923, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.859098720291307e-05, + "loss": 3.5196, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8582601255402554e-05, + "loss": 3.5103, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574231686695763e-05, + "loss": 3.5044, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8565845739185243e-05, + "loss": 3.5007, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557459791674723e-05, + "loss": 3.515, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549073844164203e-05, + "loss": 3.4922, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8540704275457415e-05, + "loss": 3.5065, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532318327946895e-05, + "loss": 3.5061, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8523932380436375e-05, + "loss": 3.4984, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.851554643292585e-05, + "loss": 3.4902, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.8507176864219064e-05, + "loss": 3.4915, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.8498790916708544e-05, + "loss": 3.5029, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.8490404969198024e-05, + "loss": 3.5037, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.84820190216875e-05, + "loss": 3.5056, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8473649452980717e-05, + "loss": 3.5058, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465263505470197e-05, + "loss": 3.5041, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.845687755795967e-05, + "loss": 3.502, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.8448491610449153e-05, + "loss": 3.4876, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844012204174237e-05, + "loss": 3.5003, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843173609423185e-05, + "loss": 3.4908, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8423350146721322e-05, + "loss": 3.4896, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8414964199210802e-05, + "loss": 3.4978, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8406578251700282e-05, + "loss": 3.5083, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398192304189762e-05, + "loss": 3.5009, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8389806356679245e-05, + "loss": 3.4931, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381436787972454e-05, + "loss": 3.4986, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8373050840461934e-05, + "loss": 3.5012, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8364664892951414e-05, + "loss": 3.5053, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8356278945440894e-05, + "loss": 3.4897, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8347909376734107e-05, + "loss": 3.4963, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8339523429223587e-05, + "loss": 3.5002, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331137481713067e-05, + "loss": 3.4955, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8322751534202547e-05, + "loss": 3.4981, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314365586692027e-05, + "loss": 3.4911, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8305996017985236e-05, + "loss": 3.5029, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8297610070474716e-05, + "loss": 3.4785, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.82892241229642e-05, + "loss": 3.5055, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.828083817545368e-05, + "loss": 3.4955, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272468606746888e-05, + "loss": 3.495, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264082659236368e-05, + "loss": 3.5048, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8255696711725848e-05, + "loss": 3.4937, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247310764215328e-05, + "loss": 3.4901, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823894119550854e-05, + "loss": 3.5019, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823055524799802e-05, + "loss": 3.4823, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.82221693004875e-05, + "loss": 3.4821, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.821378335297698e-05, + "loss": 3.497, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820541378427019e-05, + "loss": 3.5001, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819702783675967e-05, + "loss": 3.4955, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8188641889249153e-05, + "loss": 3.4835, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8180255941738633e-05, + "loss": 3.485, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.817188637303184e-05, + "loss": 3.4924, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.816350042552132e-05, + "loss": 3.5001, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.81551144780108e-05, + "loss": 3.4959, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.814672853050028e-05, + "loss": 3.5038, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.813834258298976e-05, + "loss": 3.4984, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8129973014282974e-05, + "loss": 3.5022, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8121587066772454e-05, + "loss": 3.484, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113201119261934e-05, + "loss": 3.4901, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8104815171751414e-05, + "loss": 3.5001, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096445603044623e-05, + "loss": 3.4894, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088059655534106e-05, + "loss": 3.4948, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8079673708023586e-05, + "loss": 3.4893, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071287760513066e-05, + "loss": 3.5085, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8062918191806275e-05, + "loss": 3.4882, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8054532244295755e-05, + "loss": 3.4805, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8046146296785235e-05, + "loss": 3.4918, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8037760349274715e-05, + "loss": 3.4975, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.80293744017642e-05, + "loss": 3.5021, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802098845425368e-05, + "loss": 3.4891, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8012618885546888e-05, + "loss": 3.4904, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8004232938036368e-05, + "loss": 3.4986, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7995846990525847e-05, + "loss": 3.4882, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7987461043015327e-05, + "loss": 3.4858, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7979075095504807e-05, + "loss": 3.4884, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797070552679802e-05, + "loss": 3.5019, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.79623195792875e-05, + "loss": 3.5015, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.795393363177698e-05, + "loss": 3.4957, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7945547684266453e-05, + "loss": 3.4809, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.793717811555967e-05, + "loss": 3.4907, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.792879216804915e-05, + "loss": 3.4899, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920406220538632e-05, + "loss": 3.4955, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912020273028105e-05, + "loss": 3.4906, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7903634325517585e-05, + "loss": 3.4902, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.78952647568108e-05, + "loss": 3.4833, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788687880930028e-05, + "loss": 3.4981, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7878492861789758e-05, + "loss": 3.4684, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870106914279238e-05, + "loss": 3.4905, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7861737345572453e-05, + "loss": 3.4849, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853351398061927e-05, + "loss": 3.4963, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7844965450551407e-05, + "loss": 3.4801, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7836579503040887e-05, + "loss": 3.4968, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828209934334102e-05, + "loss": 3.4855, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.781982398682358e-05, + "loss": 3.4885, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781143803931306e-05, + "loss": 3.4956, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780305209180254e-05, + "loss": 3.4861, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779466614429202e-05, + "loss": 3.4956, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778629657558523e-05, + "loss": 3.5062, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777791062807471e-05, + "loss": 3.4935, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.776952468056419e-05, + "loss": 3.4877, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776113873305367e-05, + "loss": 3.4932, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.775276916434688e-05, + "loss": 3.493, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774438321683636e-05, + "loss": 3.479, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773599726932584e-05, + "loss": 3.498, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7727611321815324e-05, + "loss": 3.4872, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7719241753108533e-05, + "loss": 3.4953, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7710855805598013e-05, + "loss": 3.4883, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7702469858087493e-05, + "loss": 3.4873, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694083910576973e-05, + "loss": 3.48, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7685697963066453e-05, + "loss": 3.4824, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677312015555932e-05, + "loss": 3.4811, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7668942446849145e-05, + "loss": 3.4986, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7660556499338625e-05, + "loss": 3.5121, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7652170551828105e-05, + "loss": 3.4954, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7643784604317585e-05, + "loss": 3.4785, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635398656807065e-05, + "loss": 3.4984, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627012709296545e-05, + "loss": 3.4889, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7618643140589757e-05, + "loss": 3.4882, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610257193079237e-05, + "loss": 3.4855, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7601871245568717e-05, + "loss": 3.4948, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7593485298058197e-05, + "loss": 3.4874, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585099350547677e-05, + "loss": 3.4906, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7576729781840886e-05, + "loss": 3.4938, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756834383433037e-05, + "loss": 3.494, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.755995788681985e-05, + "loss": 3.4929, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755157193930933e-05, + "loss": 3.4827, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754320237060254e-05, + "loss": 3.5016, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753481642309202e-05, + "loss": 3.4944, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.75264304755815e-05, + "loss": 3.4892, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751804452807098e-05, + "loss": 3.4988, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.750967495936419e-05, + "loss": 3.484, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.869220018386841, + "eval_runtime": 302.9661, + "eval_samples_per_second": 1259.517, + "eval_steps_per_second": 39.361, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.750128901185367e-05, + "loss": 3.4771, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.749290306434315e-05, + "loss": 3.4812, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748451711683263e-05, + "loss": 3.4994, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.747613116932211e-05, + "loss": 3.4911, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7467761600615323e-05, + "loss": 3.4988, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7459375653104803e-05, + "loss": 3.4817, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7450989705594283e-05, + "loss": 3.4926, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7442603758083763e-05, + "loss": 3.4717, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7434234189376972e-05, + "loss": 3.502, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7425848241866452e-05, + "loss": 3.4808, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417462294355932e-05, + "loss": 3.4962, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409076346845415e-05, + "loss": 3.489, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7400706778138624e-05, + "loss": 3.4852, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392320830628104e-05, + "loss": 3.4814, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7383934883117584e-05, + "loss": 3.48, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.737554893560706e-05, + "loss": 3.48, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.736716298809654e-05, + "loss": 3.4864, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.735877704058602e-05, + "loss": 3.489, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.73503910930755e-05, + "loss": 3.4863, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734200514556498e-05, + "loss": 3.5024, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.733361919805446e-05, + "loss": 3.4993, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732524962934767e-05, + "loss": 3.4932, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7316863681837153e-05, + "loss": 3.487, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7308477734326633e-05, + "loss": 3.4986, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300091786816113e-05, + "loss": 3.4814, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.7291722218109322e-05, + "loss": 3.4926, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.7283336270598802e-05, + "loss": 3.4914, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.7274950323088282e-05, + "loss": 3.4868, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.7266564375577762e-05, + "loss": 3.4751, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.7258178428067242e-05, + "loss": 3.4794, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7249808859360454e-05, + "loss": 3.4881, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7241422911849934e-05, + "loss": 3.4907, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233036964339414e-05, + "loss": 3.4939, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7224651016828894e-05, + "loss": 3.4912, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216281448122103e-05, + "loss": 3.4889, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7207895500611587e-05, + "loss": 3.4887, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199509553101067e-05, + "loss": 3.4743, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191123605590547e-05, + "loss": 3.4887, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7182754036883756e-05, + "loss": 3.4762, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174368089373236e-05, + "loss": 3.4805, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7165982141862716e-05, + "loss": 3.4827, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7157596194352196e-05, + "loss": 3.4978, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.714921024684168e-05, + "loss": 3.4845, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7140840678134888e-05, + "loss": 3.4775, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132454730624368e-05, + "loss": 3.4914, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124068783113848e-05, + "loss": 3.4854, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7115682835603328e-05, + "loss": 3.4949, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107296888092808e-05, + "loss": 3.4735, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.709892731938602e-05, + "loss": 3.4761, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.70905413718755e-05, + "loss": 3.4911, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708215542436498e-05, + "loss": 3.4822, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707376947685446e-05, + "loss": 3.4865, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706538352934394e-05, + "loss": 3.4777, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705701396063715e-05, + "loss": 3.4836, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7048628013126633e-05, + "loss": 3.4715, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7040242065616113e-05, + "loss": 3.4872, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7031856118105593e-05, + "loss": 3.4838, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.70234865493988e-05, + "loss": 3.4831, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701510060188828e-05, + "loss": 3.4923, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700671465437776e-05, + "loss": 3.4774, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.699832870686724e-05, + "loss": 3.475, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6989959138160454e-05, + "loss": 3.4942, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6981573190649934e-05, + "loss": 3.468, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973187243139414e-05, + "loss": 3.4698, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6964801295628894e-05, + "loss": 3.4828, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6956431726922103e-05, + "loss": 3.4913, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948045779411586e-05, + "loss": 3.4813, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6939659831901066e-05, + "loss": 3.4708, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931273884390546e-05, + "loss": 3.4743, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6922904315683755e-05, + "loss": 3.4754, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6914518368173235e-05, + "loss": 3.4884, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906132420662715e-05, + "loss": 3.4817, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6897746473152192e-05, + "loss": 3.4882, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889360525641672e-05, + "loss": 3.4834, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6880990956934888e-05, + "loss": 3.49, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6872605009424368e-05, + "loss": 3.4728, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686421906191384e-05, + "loss": 3.477, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6855833114403324e-05, + "loss": 3.4853, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684746354569654e-05, + "loss": 3.4739, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.683907759818602e-05, + "loss": 3.484, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6830691650675493e-05, + "loss": 3.4778, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822305703164973e-05, + "loss": 3.493, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6813919755654453e-05, + "loss": 3.4776, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6805533808143933e-05, + "loss": 3.4699, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.6797164239437145e-05, + "loss": 3.4749, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.6788778291926625e-05, + "loss": 3.4818, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6780392344416105e-05, + "loss": 3.493, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6772006396905585e-05, + "loss": 3.4751, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6763636828198794e-05, + "loss": 3.4808, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755250880688278e-05, + "loss": 3.4753, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6746864933177758e-05, + "loss": 3.4847, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6738478985667238e-05, + "loss": 3.4733, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.6730093038156718e-05, + "loss": 3.4728, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6721723469449927e-05, + "loss": 3.4883, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6713337521939407e-05, + "loss": 3.4894, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6704951574428887e-05, + "loss": 3.4828, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.669656562691837e-05, + "loss": 3.47, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668819605821158e-05, + "loss": 3.478, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.667981011070106e-05, + "loss": 3.478, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667142416319054e-05, + "loss": 3.4801, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666303821568002e-05, + "loss": 3.481, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.66546522681695e-05, + "loss": 3.4756, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664628269946271e-05, + "loss": 3.4737, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663789675195219e-05, + "loss": 3.4847, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.662951080444167e-05, + "loss": 3.4621, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.662112485693115e-05, + "loss": 3.4747, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.661275528822436e-05, + "loss": 3.469, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.660436934071384e-05, + "loss": 3.4863, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6595983393203324e-05, + "loss": 3.4717, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6587597445692804e-05, + "loss": 3.4805, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579211498182284e-05, + "loss": 3.4735, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6570841929475493e-05, + "loss": 3.477, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6562455981964973e-05, + "loss": 3.4823, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554070034454453e-05, + "loss": 3.4761, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6545684086943933e-05, + "loss": 3.4837, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6537314518237145e-05, + "loss": 3.4893, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6528928570726625e-05, + "loss": 3.4836, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6520542623216105e-05, + "loss": 3.4757, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512156675705585e-05, + "loss": 3.4761, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6503770728195065e-05, + "loss": 3.4851, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495384780684545e-05, + "loss": 3.4671, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6486998833174025e-05, + "loss": 3.4814, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.64786128856635e-05, + "loss": 3.4727, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.6470243316956717e-05, + "loss": 3.4786, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.6461857369446197e-05, + "loss": 3.4768, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.6453471421935677e-05, + "loss": 3.4763, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644508547442515e-05, + "loss": 3.4646, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6436699526914634e-05, + "loss": 3.4728, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642832995820785e-05, + "loss": 3.4716, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.6419944010697323e-05, + "loss": 3.4789, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.6411558063186803e-05, + "loss": 3.4964, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.6403172115676283e-05, + "loss": 3.4876, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.63948025469695e-05, + "loss": 3.4615, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6386416599458975e-05, + "loss": 3.4874, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378030651948455e-05, + "loss": 3.4763, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6369644704437935e-05, + "loss": 3.4741, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.636127513573115e-05, + "loss": 3.4655, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6352889188220624e-05, + "loss": 3.4858, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6344503240710104e-05, + "loss": 3.4741, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336117293199587e-05, + "loss": 3.4767, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6327747724492796e-05, + "loss": 3.4823, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6319361776982276e-05, + "loss": 3.4807, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6310975829471756e-05, + "loss": 3.4793, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6302589881961236e-05, + "loss": 3.4736, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629422031325445e-05, + "loss": 3.4848, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.628583436574393e-05, + "loss": 3.4826, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.627744841823341e-05, + "loss": 3.4753, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.626906247072289e-05, + "loss": 3.4857, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6260692902016098e-05, + "loss": 3.4711, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.872420310974121, + "eval_runtime": 302.5381, + "eval_samples_per_second": 1261.299, + "eval_steps_per_second": 39.417, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252306954505578e-05, + "loss": 3.4668, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6243921006995058e-05, + "loss": 3.4712, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.623553505948454e-05, + "loss": 3.4848, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.622714911197402e-05, + "loss": 3.477, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621877954326723e-05, + "loss": 3.4896, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621039359575671e-05, + "loss": 3.4676, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.620200764824619e-05, + "loss": 3.4802, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.619362170073567e-05, + "loss": 3.4586, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6185252132028882e-05, + "loss": 3.4891, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6176866184518362e-05, + "loss": 3.4728, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6168480237007842e-05, + "loss": 3.4816, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160094289497322e-05, + "loss": 3.4775, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615172472079053e-05, + "loss": 3.467, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.614333877328001e-05, + "loss": 3.4742, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6134952825769495e-05, + "loss": 3.4688, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6126566878258975e-05, + "loss": 3.4642, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118197309552184e-05, + "loss": 3.4743, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6109811362041664e-05, + "loss": 3.4757, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101425414531144e-05, + "loss": 3.4745, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093039467020624e-05, + "loss": 3.4889, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6084653519510104e-05, + "loss": 3.4887, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6076283950803316e-05, + "loss": 3.4777, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.6067898003292796e-05, + "loss": 3.4777, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6059512055782276e-05, + "loss": 3.4841, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051126108271756e-05, + "loss": 3.4696, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6042756539564965e-05, + "loss": 3.4845, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603437059205445e-05, + "loss": 3.477, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6025984644543928e-05, + "loss": 3.4714, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6017598697033408e-05, + "loss": 3.4636, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.6009229128326617e-05, + "loss": 3.4681, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.6000843180816097e-05, + "loss": 3.4739, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.5992457233305577e-05, + "loss": 3.4795, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984071285795057e-05, + "loss": 3.4812, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597568533828454e-05, + "loss": 3.4782, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.596731576957775e-05, + "loss": 3.4765, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595892982206723e-05, + "loss": 3.4767, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595054387455671e-05, + "loss": 3.4612, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594215792704619e-05, + "loss": 3.4747, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5933788358339402e-05, + "loss": 3.4625, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925402410828882e-05, + "loss": 3.4691, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917016463318362e-05, + "loss": 3.4718, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5908630515807842e-05, + "loss": 3.4784, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900244568297322e-05, + "loss": 3.4787, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.589187499959053e-05, + "loss": 3.4622, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.588348905208001e-05, + "loss": 3.4774, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.587510310456949e-05, + "loss": 3.4765, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5866717157058974e-05, + "loss": 3.4799, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858331209548454e-05, + "loss": 3.4664, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5849961640841663e-05, + "loss": 3.4598, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5841575693331143e-05, + "loss": 3.4816, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5833189745820623e-05, + "loss": 3.4696, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5824803798310103e-05, + "loss": 3.4748, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.581641785079958e-05, + "loss": 3.4684, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808048282092796e-05, + "loss": 3.4678, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5799662334582275e-05, + "loss": 3.46, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5791276387071755e-05, + "loss": 3.4746, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578289043956123e-05, + "loss": 3.4743, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5774520870854444e-05, + "loss": 3.4736, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.5766134923343928e-05, + "loss": 3.4773, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.57577489758334e-05, + "loss": 3.4639, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.574936302832288e-05, + "loss": 3.4647, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.5740993459616097e-05, + "loss": 3.485, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5732607512105577e-05, + "loss": 3.4578, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724221564595053e-05, + "loss": 3.4561, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.5715835617084533e-05, + "loss": 3.4667, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570746604837775e-05, + "loss": 3.4771, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569908010086723e-05, + "loss": 3.466, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.5690694153356702e-05, + "loss": 3.4629, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682308205846182e-05, + "loss": 3.4578, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5673922258335666e-05, + "loss": 3.4622, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5665552689628875e-05, + "loss": 3.4779, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657166742118355e-05, + "loss": 3.4681, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5648780794607835e-05, + "loss": 3.4699, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5640394847097315e-05, + "loss": 3.4775, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632025278390527e-05, + "loss": 3.478, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5623639330880007e-05, + "loss": 3.4595, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615253383369487e-05, + "loss": 3.4662, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5606867435858967e-05, + "loss": 3.4729, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5598481488348447e-05, + "loss": 3.4579, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590111919641656e-05, + "loss": 3.4741, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5581725972131136e-05, + "loss": 3.4641, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.557334002462062e-05, + "loss": 3.48, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.55649540771101e-05, + "loss": 3.4652, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555658450840331e-05, + "loss": 3.4581, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548198560892788e-05, + "loss": 3.4609, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5539812613382268e-05, + "loss": 3.4702, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.5531426665871748e-05, + "loss": 3.4801, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552305709716496e-05, + "loss": 3.4665, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551467114965444e-05, + "loss": 3.4678, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.550628520214392e-05, + "loss": 3.4614, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.54978992546334e-05, + "loss": 3.4744, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.548952968592661e-05, + "loss": 3.4595, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.548114373841609e-05, + "loss": 3.4628, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5472757790905573e-05, + "loss": 3.4755, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5464371843395053e-05, + "loss": 3.4775, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5456002274688262e-05, + "loss": 3.4698, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5447616327177742e-05, + "loss": 3.4556, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5439230379667222e-05, + "loss": 3.4672, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5430844432156702e-05, + "loss": 3.4627, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5422474863449914e-05, + "loss": 3.4702, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414088915939394e-05, + "loss": 3.4695, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5405702968428874e-05, + "loss": 3.4628, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397317020918354e-05, + "loss": 3.4623, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5388947452211563e-05, + "loss": 3.469, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5380561504701043e-05, + "loss": 3.452, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372175557190527e-05, + "loss": 3.4639, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5363789609680007e-05, + "loss": 3.4534, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5355420040973216e-05, + "loss": 3.4721, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347034093462696e-05, + "loss": 3.4607, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5338648145952176e-05, + "loss": 3.4648, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5330262198441656e-05, + "loss": 3.4589, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5321876250931135e-05, + "loss": 3.469, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5313506682224348e-05, + "loss": 3.4713, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305120734713828e-05, + "loss": 3.4602, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5296734787203308e-05, + "loss": 3.4696, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288365218496517e-05, + "loss": 3.4752, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5279979270985997e-05, + "loss": 3.4692, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527159332347548e-05, + "loss": 3.4699, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526320737596496e-05, + "loss": 3.4586, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525482142845444e-05, + "loss": 3.4753, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524643548094392e-05, + "loss": 3.4587, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.52380495334334e-05, + "loss": 3.4665, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.522966358592288e-05, + "loss": 3.4608, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522129401721609e-05, + "loss": 3.4685, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5212908069705572e-05, + "loss": 3.4652, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5204522122195052e-05, + "loss": 3.4606, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196136174684532e-05, + "loss": 3.4546, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.518776660597774e-05, + "loss": 3.4587, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.517938065846722e-05, + "loss": 3.4626, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.51709947109567e-05, + "loss": 3.4658, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.516260876344618e-05, + "loss": 3.4783, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154239194739394e-05, + "loss": 3.4771, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5145853247228874e-05, + "loss": 3.4516, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5137467299718354e-05, + "loss": 3.4773, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129081352207834e-05, + "loss": 3.464, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5120711783501043e-05, + "loss": 3.4627, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5112325835990523e-05, + "loss": 3.4559, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5103939888480006e-05, + "loss": 3.4689, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.509555394096948e-05, + "loss": 3.4605, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5087184372262695e-05, + "loss": 3.4713, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5078798424752175e-05, + "loss": 3.4679, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5070412477241655e-05, + "loss": 3.466, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506202652973113e-05, + "loss": 3.471, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.5053656961024348e-05, + "loss": 3.4593, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.5045271013513827e-05, + "loss": 3.4692, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.5036885066003307e-05, + "loss": 3.4759, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502849911849278e-05, + "loss": 3.4638, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502011317098226e-05, + "loss": 3.4682, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.5011743602275476e-05, + "loss": 3.463, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8741793632507324, + "eval_runtime": 303.349, + "eval_samples_per_second": 1257.927, + "eval_steps_per_second": 39.311, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.5003357654764953e-05, + "loss": 3.4528, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.4994971707254436e-05, + "loss": 3.4582, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.4986585759743916e-05, + "loss": 3.4693, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.4978199812233396e-05, + "loss": 3.4676, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4969830243526605e-05, + "loss": 3.4795, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496144429601609e-05, + "loss": 3.4554, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495305834850557e-05, + "loss": 3.4646, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4944672400995045e-05, + "loss": 3.4505, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936302832288258e-05, + "loss": 3.4714, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4927916884777738e-05, + "loss": 3.4596, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4919530937267218e-05, + "loss": 3.463, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911144989756698e-05, + "loss": 3.4689, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490277542104991e-05, + "loss": 3.4525, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.489438947353939e-05, + "loss": 3.4658, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.488600352602887e-05, + "loss": 3.4543, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4877617578518347e-05, + "loss": 3.4529, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869231631007827e-05, + "loss": 3.4582, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4860845683497306e-05, + "loss": 3.4657, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485245973598679e-05, + "loss": 3.4602, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.484407378847627e-05, + "loss": 3.4761, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483570421976948e-05, + "loss": 3.477, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482731827225896e-05, + "loss": 3.4668, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481893232474844e-05, + "loss": 3.4654, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.481054637723792e-05, + "loss": 3.4744, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480217680853113e-05, + "loss": 3.4554, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.479379086102061e-05, + "loss": 3.472, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.478540491351009e-05, + "loss": 3.4666, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477701896599957e-05, + "loss": 3.4568, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476864939729278e-05, + "loss": 3.4542, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476026344978226e-05, + "loss": 3.4548, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4751877502271743e-05, + "loss": 3.4621, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4743491554761223e-05, + "loss": 3.4664, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4735121986054433e-05, + "loss": 3.4708, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4726736038543912e-05, + "loss": 3.4666, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4718350091033392e-05, + "loss": 3.4651, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4709964143522872e-05, + "loss": 3.4667, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4701578196012352e-05, + "loss": 3.4462, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.4693208627305565e-05, + "loss": 3.4646, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4684822679795045e-05, + "loss": 3.4496, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.467643673228452e-05, + "loss": 3.4584, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668050784774e-05, + "loss": 3.4572, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4659681216067214e-05, + "loss": 3.4716, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4651295268556697e-05, + "loss": 3.4642, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4642909321046174e-05, + "loss": 3.4495, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4634523373535654e-05, + "loss": 3.4684, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626153804828866e-05, + "loss": 3.4605, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4617767857318346e-05, + "loss": 3.4656, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609381909807823e-05, + "loss": 3.4582, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4600995962297306e-05, + "loss": 3.4475, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4592610014786786e-05, + "loss": 3.4697, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584240446079995e-05, + "loss": 3.4558, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4575854498569475e-05, + "loss": 3.4645, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4567468551058955e-05, + "loss": 3.4553, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559082603548435e-05, + "loss": 3.4532, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4550713034841647e-05, + "loss": 3.4502, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542327087331127e-05, + "loss": 3.4627, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4533941139820607e-05, + "loss": 3.4613, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4525555192310087e-05, + "loss": 3.4607, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517185623603296e-05, + "loss": 3.4684, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4508799676092776e-05, + "loss": 3.4538, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450041372858226e-05, + "loss": 3.4511, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449202778107174e-05, + "loss": 3.4748, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.448365821236495e-05, + "loss": 3.4413, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447527226485443e-05, + "loss": 3.4433, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446688631734391e-05, + "loss": 3.4543, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.445850036983339e-05, + "loss": 3.4694, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.44501308011266e-05, + "loss": 3.4513, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.444174485361608e-05, + "loss": 3.4561, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.443335890610556e-05, + "loss": 3.4467, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442497295859504e-05, + "loss": 3.4502, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441660338988825e-05, + "loss": 3.4621, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440821744237773e-05, + "loss": 3.4588, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4399831494867213e-05, + "loss": 3.4612, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4391445547356693e-05, + "loss": 3.4644, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4383075978649902e-05, + "loss": 3.4637, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4374690031139382e-05, + "loss": 3.4518, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366304083628862e-05, + "loss": 3.456, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4357918136118342e-05, + "loss": 3.4625, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4349548567411555e-05, + "loss": 3.4437, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341162619901035e-05, + "loss": 3.4636, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4332776672390515e-05, + "loss": 3.4529, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324390724879995e-05, + "loss": 3.4692, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316004777369475e-05, + "loss": 3.4538, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4307635208662684e-05, + "loss": 3.4496, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299249261152167e-05, + "loss": 3.4404, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4290863313641647e-05, + "loss": 3.4607, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4282477366131124e-05, + "loss": 3.4629, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274107797424336e-05, + "loss": 3.4589, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4265721849913816e-05, + "loss": 3.4531, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257335902403296e-05, + "loss": 3.4513, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4248949954892776e-05, + "loss": 3.463, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.424058038618599e-05, + "loss": 3.4487, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.423219443867547e-05, + "loss": 3.4491, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4223808491164948e-05, + "loss": 3.464, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215422543654425e-05, + "loss": 3.4611, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207052974947637e-05, + "loss": 3.4592, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.419866702743712e-05, + "loss": 3.445, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190281079926597e-05, + "loss": 3.454, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4181895132416077e-05, + "loss": 3.4512, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417352556370929e-05, + "loss": 3.4572, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416513961619877e-05, + "loss": 3.4552, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.4156753668688246e-05, + "loss": 3.4564, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414836772117773e-05, + "loss": 3.4496, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4139998152470942e-05, + "loss": 3.4535, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.4131612204960422e-05, + "loss": 3.4478, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.41232262574499e-05, + "loss": 3.4466, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.411484030993938e-05, + "loss": 3.4411, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.410647074123259e-05, + "loss": 3.4613, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409808479372207e-05, + "loss": 3.4516, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.408969884621155e-05, + "loss": 3.4528, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408131289870103e-05, + "loss": 3.4483, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4072943329994243e-05, + "loss": 3.4587, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.406455738248372e-05, + "loss": 3.4564, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.40561714349732e-05, + "loss": 3.4485, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4047785487462683e-05, + "loss": 3.458, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4039415918755892e-05, + "loss": 3.4661, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031029971245372e-05, + "loss": 3.4576, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4022644023734852e-05, + "loss": 3.4565, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014258076224332e-05, + "loss": 3.4473, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4005872128713812e-05, + "loss": 3.4584, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3997486181203292e-05, + "loss": 3.4513, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3989100233692775e-05, + "loss": 3.4576, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3980714286182252e-05, + "loss": 3.4426, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972344717475464e-05, + "loss": 3.457, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3963958769964944e-05, + "loss": 3.4527, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3955572822454424e-05, + "loss": 3.4504, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947186874943904e-05, + "loss": 3.4437, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3938817306237117e-05, + "loss": 3.4471, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930431358726597e-05, + "loss": 3.4501, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922045411216073e-05, + "loss": 3.4564, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3913659463705553e-05, + "loss": 3.4626, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905289894998766e-05, + "loss": 3.4703, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3896903947488246e-05, + "loss": 3.4397, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3888517999977726e-05, + "loss": 3.4627, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880148431270938e-05, + "loss": 3.4548, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3871762483760418e-05, + "loss": 3.4497, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863376536249898e-05, + "loss": 3.4453, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3854990588739375e-05, + "loss": 3.4594, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.384662102003259e-05, + "loss": 3.4506, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.383823507252207e-05, + "loss": 3.4558, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3829849125011547e-05, + "loss": 3.4533, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.3821463177501027e-05, + "loss": 3.4534, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381309360879424e-05, + "loss": 3.4588, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380470766128372e-05, + "loss": 3.4511, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.37963217137732e-05, + "loss": 3.457, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.378793576626268e-05, + "loss": 3.4643, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.3779566197555892e-05, + "loss": 3.4524, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.3771180250045372e-05, + "loss": 3.4524, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376279430253485e-05, + "loss": 3.4548, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.875269889831543, + "eval_runtime": 304.7139, + "eval_samples_per_second": 1252.293, + "eval_steps_per_second": 39.135, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.375440835502433e-05, + "loss": 3.4465, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.3746038786317544e-05, + "loss": 3.4453, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.373765283880702e-05, + "loss": 3.4563, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.37292668912965e-05, + "loss": 3.4585, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.372088094378598e-05, + "loss": 3.4661, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3712511375079193e-05, + "loss": 3.4485, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.370412542756867e-05, + "loss": 3.4535, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3695739480058153e-05, + "loss": 3.4405, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3687353532547633e-05, + "loss": 3.4581, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3678983963840846e-05, + "loss": 3.4512, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3670598016330322e-05, + "loss": 3.4522, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662212068819802e-05, + "loss": 3.4544, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3653842500113015e-05, + "loss": 3.4445, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3645456552602494e-05, + "loss": 3.4515, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637070605091974e-05, + "loss": 3.4464, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3628684657581454e-05, + "loss": 3.4394, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620315088874667e-05, + "loss": 3.4459, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3611929141364143e-05, + "loss": 3.4551, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3603543193853623e-05, + "loss": 3.4482, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595157246343107e-05, + "loss": 3.4649, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3586771298832587e-05, + "loss": 3.4635, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.3578385351322067e-05, + "loss": 3.4559, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3569999403811547e-05, + "loss": 3.4543, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3561613456301027e-05, + "loss": 3.4593, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553243887594236e-05, + "loss": 3.4471, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3544857940083716e-05, + "loss": 3.4609, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.35364719925732e-05, + "loss": 3.4552, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528086045062676e-05, + "loss": 3.4435, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.3519716476355888e-05, + "loss": 3.4429, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511330528845368e-05, + "loss": 3.447, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3502944581334848e-05, + "loss": 3.4497, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3494558633824328e-05, + "loss": 3.4541, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.348618906511754e-05, + "loss": 3.4605, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.347780311760702e-05, + "loss": 3.4544, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.3469417170096497e-05, + "loss": 3.4526, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.3461031222585977e-05, + "loss": 3.456, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.345266165387919e-05, + "loss": 3.4409, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.344427570636867e-05, + "loss": 3.4476, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.343588975885815e-05, + "loss": 3.4381, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.342750381134763e-05, + "loss": 3.4453, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.3419134242640842e-05, + "loss": 3.4438, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341074829513032e-05, + "loss": 3.4608, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.3402362347619798e-05, + "loss": 3.454, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3393976400109278e-05, + "loss": 3.436, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3385606831402494e-05, + "loss": 3.4606, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.337722088389197e-05, + "loss": 3.4463, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.336883493638145e-05, + "loss": 3.4584, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.336044898887093e-05, + "loss": 3.4449, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352079420164143e-05, + "loss": 3.4343, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3343693472653623e-05, + "loss": 3.4561, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.3335307525143103e-05, + "loss": 3.4468, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3326921577632583e-05, + "loss": 3.4527, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3318552008925795e-05, + "loss": 3.4399, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310182440219004e-05, + "loss": 3.4441, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3301796492708484e-05, + "loss": 3.4357, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3293410545197968e-05, + "loss": 3.4482, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285024597687444e-05, + "loss": 3.4538, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3276638650176924e-05, + "loss": 3.4458, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268252702666404e-05, + "loss": 3.4569, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3259866755155884e-05, + "loss": 3.443, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3251480807645364e-05, + "loss": 3.4373, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243111238938577e-05, + "loss": 3.4641, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3234725291428057e-05, + "loss": 3.4314, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.3226339343917537e-05, + "loss": 3.4287, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.3217953396407017e-05, + "loss": 3.4451, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.3209583827700226e-05, + "loss": 3.4578, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201197880189706e-05, + "loss": 3.4365, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3192811932679186e-05, + "loss": 3.4459, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318442598516867e-05, + "loss": 3.4344, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.3176056416461878e-05, + "loss": 3.4382, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.3167670468951358e-05, + "loss": 3.4522, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.3159284521440838e-05, + "loss": 3.4475, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.3150898573930318e-05, + "loss": 3.4495, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.314252900522353e-05, + "loss": 3.4477, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.313414305771301e-05, + "loss": 3.4551, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.312575711020249e-05, + "loss": 3.4381, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311737116269197e-05, + "loss": 3.4464, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310900159398518e-05, + "loss": 3.4485, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310061564647466e-05, + "loss": 3.4333, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309222969896414e-05, + "loss": 3.4486, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.308386013025735e-05, + "loss": 3.4456, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.307547418274683e-05, + "loss": 3.4523, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.306708823523631e-05, + "loss": 3.4481, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305870228772579e-05, + "loss": 3.4373, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3050332719019e-05, + "loss": 3.4312, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3041946771508484e-05, + "loss": 3.446, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3033560823997964e-05, + "loss": 3.4504, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025174876487444e-05, + "loss": 3.4428, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3016805307780653e-05, + "loss": 3.4485, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3008419360270133e-05, + "loss": 3.4415, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000033412759613e-05, + "loss": 3.4475, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.2991647465249093e-05, + "loss": 3.4386, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983277896542305e-05, + "loss": 3.4363, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2974891949031785e-05, + "loss": 3.4554, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2966506001521265e-05, + "loss": 3.4514, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958120054010745e-05, + "loss": 3.4466, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2949750485303954e-05, + "loss": 3.4335, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2941364537793438e-05, + "loss": 3.4464, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2932978590282918e-05, + "loss": 3.4356, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2924592642772398e-05, + "loss": 3.4478, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.2916223074065607e-05, + "loss": 3.4413, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2907837126555087e-05, + "loss": 3.4471, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2899451179044567e-05, + "loss": 3.4381, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891065231534047e-05, + "loss": 3.4378, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.288269566282726e-05, + "loss": 3.4409, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.287430971531674e-05, + "loss": 3.4347, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.286592376780622e-05, + "loss": 3.4334, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2857537820295695e-05, + "loss": 3.4466, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.2849168251588908e-05, + "loss": 3.4439, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.284078230407839e-05, + "loss": 3.4396, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283239635656787e-05, + "loss": 3.4362, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.2824010409057348e-05, + "loss": 3.4449, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281564084035056e-05, + "loss": 3.4484, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280725489284004e-05, + "loss": 3.4403, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.2798868945329517e-05, + "loss": 3.4457, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.2790499376622733e-05, + "loss": 3.452, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.2782113429112213e-05, + "loss": 3.4504, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.2773727481601693e-05, + "loss": 3.4441, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276534153409117e-05, + "loss": 3.4399, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275695558658065e-05, + "loss": 3.443, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274856963907013e-05, + "loss": 3.4391, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274018369155961e-05, + "loss": 3.4479, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2731797744049092e-05, + "loss": 3.4349, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.27234281753423e-05, + "loss": 3.4439, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.271504222783178e-05, + "loss": 3.443, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.270665628032126e-05, + "loss": 3.4391, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.269827033281074e-05, + "loss": 3.4315, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2689900764103954e-05, + "loss": 3.4404, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2681514816593434e-05, + "loss": 3.4364, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673128869082914e-05, + "loss": 3.4452, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2664742921572394e-05, + "loss": 3.4495, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2656373352865603e-05, + "loss": 3.4573, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2647987405355083e-05, + "loss": 3.4296, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2639601457844563e-05, + "loss": 3.4526, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631215510334046e-05, + "loss": 3.4441, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2622845941627255e-05, + "loss": 3.4379, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2614459994116735e-05, + "loss": 3.4331, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606074046606215e-05, + "loss": 3.4499, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2597688099095695e-05, + "loss": 3.4358, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589318530388908e-05, + "loss": 3.4481, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.2580932582878387e-05, + "loss": 3.439, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.2572546635367867e-05, + "loss": 3.4456, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.2564177066661077e-05, + "loss": 3.4447, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.2555791119150556e-05, + "loss": 3.442, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2547405171640036e-05, + "loss": 3.449, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539019224129516e-05, + "loss": 3.4469, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.253064965542273e-05, + "loss": 3.4482, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252226370791221e-05, + "loss": 3.4339, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251387776040169e-05, + "loss": 3.4478, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.8769257068634033, + "eval_runtime": 305.306, + "eval_samples_per_second": 1249.864, + "eval_steps_per_second": 39.059, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250549181289117e-05, + "loss": 3.4364, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.2497105865380645e-05, + "loss": 3.4325, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.2488719917870125e-05, + "loss": 3.4407, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248033397035961e-05, + "loss": 3.4474, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.247196440165282e-05, + "loss": 3.4545, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2463578454142298e-05, + "loss": 3.4348, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2455192506631778e-05, + "loss": 3.4383, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.2446806559121258e-05, + "loss": 3.4282, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243843699041447e-05, + "loss": 3.4496, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243005104290395e-05, + "loss": 3.4393, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242166509539343e-05, + "loss": 3.4458, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.241327914788291e-05, + "loss": 3.4416, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.240490957917612e-05, + "loss": 3.4321, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.23965236316656e-05, + "loss": 3.4424, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.238813768415508e-05, + "loss": 3.4308, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2379751736644562e-05, + "loss": 3.4285, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.237138216793777e-05, + "loss": 3.4341, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.236299622042725e-05, + "loss": 3.4466, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.235461027291673e-05, + "loss": 3.4362, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.234622432540621e-05, + "loss": 3.4554, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.233783837789569e-05, + "loss": 3.4497, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.232945243038517e-05, + "loss": 3.4462, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.232106648287465e-05, + "loss": 3.4442, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.231268053536413e-05, + "loss": 3.4466, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304310966657344e-05, + "loss": 3.433, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2295925019146823e-05, + "loss": 3.4546, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.22875390716363e-05, + "loss": 3.4389, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.227915312412578e-05, + "loss": 3.4339, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2270783555418996e-05, + "loss": 3.4346, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2262397607908476e-05, + "loss": 3.4367, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254011660397952e-05, + "loss": 3.4377, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2245625712887432e-05, + "loss": 3.4471, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.2237256144180645e-05, + "loss": 3.4449, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.2228870196670125e-05, + "loss": 3.4468, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.2220484249159605e-05, + "loss": 3.4354, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.2212098301649085e-05, + "loss": 3.4437, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2203728732942297e-05, + "loss": 3.4363, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2195342785431774e-05, + "loss": 3.4304, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2186956837921254e-05, + "loss": 3.4254, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.2178570890410734e-05, + "loss": 3.4341, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.2170201321703946e-05, + "loss": 3.4321, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.2161815374193426e-05, + "loss": 3.4505, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.2153429426682906e-05, + "loss": 3.4395, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214505985797612e-05, + "loss": 3.4264, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2136673910465595e-05, + "loss": 3.4506, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.212828796295508e-05, + "loss": 3.4342, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.211990201544456e-05, + "loss": 3.4462, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.211153244673777e-05, + "loss": 3.433, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.2103146499227247e-05, + "loss": 3.4205, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.2094760551716727e-05, + "loss": 3.4507, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.2086374604206207e-05, + "loss": 3.4337, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.207800503549942e-05, + "loss": 3.4437, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.20696190879889e-05, + "loss": 3.4324, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061249519282112e-05, + "loss": 3.4324, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2052863571771592e-05, + "loss": 3.4196, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.204447762426107e-05, + "loss": 3.4345, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.203609167675055e-05, + "loss": 3.4451, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2027705729240032e-05, + "loss": 3.4307, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019319781729512e-05, + "loss": 3.4459, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2010933834218992e-05, + "loss": 3.4349, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2002547886708472e-05, + "loss": 3.4271, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.199417831800168e-05, + "loss": 3.4482, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.198579237049116e-05, + "loss": 3.4221, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.197740642298064e-05, + "loss": 3.4176, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969020475470124e-05, + "loss": 3.4365, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1960650906763333e-05, + "loss": 3.4416, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952264959252813e-05, + "loss": 3.4246, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1943879011742293e-05, + "loss": 3.4385, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1935493064231773e-05, + "loss": 3.4212, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.1927123495524986e-05, + "loss": 3.4318, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.1918737548014466e-05, + "loss": 3.4412, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.1910351600503946e-05, + "loss": 3.4338, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.1901965652993426e-05, + "loss": 3.4416, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.1893596084286635e-05, + "loss": 3.4357, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.1885210136776115e-05, + "loss": 3.4457, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.1876824189265595e-05, + "loss": 3.4238, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.1868438241755075e-05, + "loss": 3.4386, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.1860068673048287e-05, + "loss": 3.4313, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.1851682725537767e-05, + "loss": 3.4238, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.1843296778027247e-05, + "loss": 3.4379, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.1834910830516724e-05, + "loss": 3.4365, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.182654126180994e-05, + "loss": 3.4425, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.181815531429942e-05, + "loss": 3.4402, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.18097693667889e-05, + "loss": 3.4209, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.180139979808211e-05, + "loss": 3.4222, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.179301385057159e-05, + "loss": 3.4365, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.178462790306107e-05, + "loss": 3.4414, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.177624195555055e-05, + "loss": 3.4314, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.176787238684376e-05, + "loss": 3.4307, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.175948643933324e-05, + "loss": 3.4351, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175110049182272e-05, + "loss": 3.4339, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1742714544312197e-05, + "loss": 3.4289, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.173434497560541e-05, + "loss": 3.4256, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1725959028094893e-05, + "loss": 3.4425, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1717573080584373e-05, + "loss": 3.4406, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.170918713307385e-05, + "loss": 3.4381, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1700817564367062e-05, + "loss": 3.424, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1692431616856542e-05, + "loss": 3.4309, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.168404566934602e-05, + "loss": 3.4299, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.1675659721835502e-05, + "loss": 3.4364, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.1667290153128715e-05, + "loss": 3.4308, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1658904205618194e-05, + "loss": 3.4321, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.165051825810767e-05, + "loss": 3.4322, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.164213231059715e-05, + "loss": 3.4258, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1633762741890363e-05, + "loss": 3.4286, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1625376794379847e-05, + "loss": 3.4234, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1616990846869323e-05, + "loss": 3.4251, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.1608604899358803e-05, + "loss": 3.4278, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600235330652016e-05, + "loss": 3.4377, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1591849383141492e-05, + "loss": 3.4224, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1583463435630972e-05, + "loss": 3.4275, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575077488120456e-05, + "loss": 3.4292, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1566707919413668e-05, + "loss": 3.4358, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.1558321971903145e-05, + "loss": 3.4282, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.1549936024392625e-05, + "loss": 3.4385, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.1541566455685837e-05, + "loss": 3.4374, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.1533180508175317e-05, + "loss": 3.4403, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.1524794560664797e-05, + "loss": 3.4312, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.1516408613154277e-05, + "loss": 3.4317, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.1508022665643757e-05, + "loss": 3.4316, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.1499636718133237e-05, + "loss": 3.4318, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.1491250770622717e-05, + "loss": 3.4287, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1482864823112197e-05, + "loss": 3.426, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.147449525440541e-05, + "loss": 3.4354, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.146610930689489e-05, + "loss": 3.433, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.145772335938437e-05, + "loss": 3.4268, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144933741187385e-05, + "loss": 3.4187, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.144096784316706e-05, + "loss": 3.4256, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1432581895656538e-05, + "loss": 3.4244, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424195948146018e-05, + "loss": 3.4332, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.141582637943923e-05, + "loss": 3.4399, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.140744043192871e-05, + "loss": 3.4456, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.139905448441819e-05, + "loss": 3.4203, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.139066853690767e-05, + "loss": 3.4395, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.1382282589397147e-05, + "loss": 3.431, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1373896641886627e-05, + "loss": 3.4303, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.136551069437611e-05, + "loss": 3.4222, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357141125669323e-05, + "loss": 3.4362, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.13487551781588e-05, + "loss": 3.4234, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.134036923064828e-05, + "loss": 3.4415, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.133198328313776e-05, + "loss": 3.4244, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1323613714430972e-05, + "loss": 3.4338, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315227766920452e-05, + "loss": 3.4326, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1306841819409932e-05, + "loss": 3.4325, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1298455871899412e-05, + "loss": 3.4356, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.129008630319262e-05, + "loss": 3.4343, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.12817003556821e-05, + "loss": 3.436, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.127331440817158e-05, + "loss": 3.4248, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1264928460661064e-05, + "loss": 3.4397, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.878614664077759, + "eval_runtime": 304.5266, + "eval_samples_per_second": 1253.063, + "eval_steps_per_second": 39.159, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1256558891954273e-05, + "loss": 3.4274, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248172944443753e-05, + "loss": 3.4199, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1239786996933233e-05, + "loss": 3.4318, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1231401049422713e-05, + "loss": 3.4376, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223031480715926e-05, + "loss": 3.4398, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.1214645533205406e-05, + "loss": 3.4256, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.1206259585694885e-05, + "loss": 3.4292, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.1197873638184365e-05, + "loss": 3.4169, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.1189504069477575e-05, + "loss": 3.4337, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181118121967054e-05, + "loss": 3.4304, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1172732174456534e-05, + "loss": 3.4324, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.1164346226946018e-05, + "loss": 3.4291, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.1155976658239227e-05, + "loss": 3.4242, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.1147590710728707e-05, + "loss": 3.4264, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.1139204763218187e-05, + "loss": 3.4226, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1130818815707667e-05, + "loss": 3.4175, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112244924700088e-05, + "loss": 3.425, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111406329949036e-05, + "loss": 3.4347, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110567735197984e-05, + "loss": 3.4268, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109729140446932e-05, + "loss": 3.4372, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.10889054569588e-05, + "loss": 3.44, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.1080519509448276e-05, + "loss": 3.4389, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.1072133561937756e-05, + "loss": 3.4292, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1063747614427236e-05, + "loss": 3.4318, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.105537804572045e-05, + "loss": 3.4274, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1046992098209928e-05, + "loss": 3.4392, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1038606150699408e-05, + "loss": 3.4265, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030220203188888e-05, + "loss": 3.4272, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.10218506344821e-05, + "loss": 3.4259, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.101346468697158e-05, + "loss": 3.4229, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.100507873946106e-05, + "loss": 3.4234, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.099669279195054e-05, + "loss": 3.4345, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.098832322324375e-05, + "loss": 3.4333, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.097993727573323e-05, + "loss": 3.4329, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.097155132822271e-05, + "loss": 3.4209, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.096316538071219e-05, + "loss": 3.4371, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.09547958120054e-05, + "loss": 3.4296, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.094640986449488e-05, + "loss": 3.4162, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.093802391698436e-05, + "loss": 3.4181, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.092963796947384e-05, + "loss": 3.4226, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.092126840076705e-05, + "loss": 3.4262, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0912882453256534e-05, + "loss": 3.4334, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0904496505746014e-05, + "loss": 3.4346, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896110558235494e-05, + "loss": 3.4166, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0887740989528703e-05, + "loss": 3.4407, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0879355042018183e-05, + "loss": 3.4251, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0870969094507663e-05, + "loss": 3.4363, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.0862599525800875e-05, + "loss": 3.4288, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.0854213578290355e-05, + "loss": 3.4015, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.0845827630779835e-05, + "loss": 3.445, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.0837441683269315e-05, + "loss": 3.4193, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0829072114562524e-05, + "loss": 3.4324, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0820686167052004e-05, + "loss": 3.4229, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081231659834522e-05, + "loss": 3.4216, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.0803930650834697e-05, + "loss": 3.4133, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.0795544703324177e-05, + "loss": 3.4216, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.0787158755813657e-05, + "loss": 3.4398, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.0778772808303137e-05, + "loss": 3.415, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.0770386860792617e-05, + "loss": 3.4354, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762000913282097e-05, + "loss": 3.4283, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.075363134457531e-05, + "loss": 3.4146, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.074524539706479e-05, + "loss": 3.4346, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.073685944955427e-05, + "loss": 3.4154, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.072847350204375e-05, + "loss": 3.4087, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0720087554533225e-05, + "loss": 3.4231, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.071170160702271e-05, + "loss": 3.4296, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.070331565951219e-05, + "loss": 3.4146, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.069492971200167e-05, + "loss": 3.429, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0686560143294878e-05, + "loss": 3.4109, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678174195784358e-05, + "loss": 3.4189, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0669788248273838e-05, + "loss": 3.4302, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0661402300763318e-05, + "loss": 3.4223, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.065303273205653e-05, + "loss": 3.4323, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.064464678454601e-05, + "loss": 3.4229, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.063626083703549e-05, + "loss": 3.4331, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.062787488952497e-05, + "loss": 3.4182, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.061950532081818e-05, + "loss": 3.4294, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061111937330766e-05, + "loss": 3.4169, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0602733425797142e-05, + "loss": 3.4153, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0594347478286622e-05, + "loss": 3.4237, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.058597790957983e-05, + "loss": 3.427, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.057759196206931e-05, + "loss": 3.4298, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.056920601455879e-05, + "loss": 3.4318, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056082006704827e-05, + "loss": 3.4069, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.0552450498341484e-05, + "loss": 3.4119, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544064550830964e-05, + "loss": 3.4232, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0535678603320444e-05, + "loss": 3.4305, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.0527292655809924e-05, + "loss": 3.4228, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.0518923087103133e-05, + "loss": 3.4185, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.0510537139592613e-05, + "loss": 3.4259, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.0502151192082096e-05, + "loss": 3.4219, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.0493765244571576e-05, + "loss": 3.4184, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0485395675864785e-05, + "loss": 3.4159, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477009728354265e-05, + "loss": 3.4281, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.0468623780843745e-05, + "loss": 3.4318, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460237833333225e-05, + "loss": 3.4284, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.0451868264626437e-05, + "loss": 3.4149, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.0443482317115917e-05, + "loss": 3.418, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.0435096369605397e-05, + "loss": 3.4162, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0426710422094877e-05, + "loss": 3.4262, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0418340853388086e-05, + "loss": 3.4202, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0409954905877566e-05, + "loss": 3.4198, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.040156895836705e-05, + "loss": 3.4205, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.039319938966026e-05, + "loss": 3.4162, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.038481344214974e-05, + "loss": 3.418, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.037642749463922e-05, + "loss": 3.4115, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.03680415471287e-05, + "loss": 3.4155, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.035967197842191e-05, + "loss": 3.4178, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.035128603091139e-05, + "loss": 3.4257, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.034290008340087e-05, + "loss": 3.4158, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.033451413589035e-05, + "loss": 3.4098, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.032614456718356e-05, + "loss": 3.4226, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.031775861967304e-05, + "loss": 3.4246, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.030937267216252e-05, + "loss": 3.4192, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0300986724652003e-05, + "loss": 3.4227, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0292617155945213e-05, + "loss": 3.4253, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0284231208434692e-05, + "loss": 3.4337, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0275845260924172e-05, + "loss": 3.4213, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.026745931341365e-05, + "loss": 3.4214, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0259073365903132e-05, + "loss": 3.4177, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0250687418392612e-05, + "loss": 3.4262, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0242301470882092e-05, + "loss": 3.4168, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0233915523371572e-05, + "loss": 3.4138, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.022554595466478e-05, + "loss": 3.422, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.021716000715426e-05, + "loss": 3.4292, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.020877405964374e-05, + "loss": 3.413, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.020038811213322e-05, + "loss": 3.4108, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.0192018543426434e-05, + "loss": 3.4135, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0183632595915914e-05, + "loss": 3.4125, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175246648405394e-05, + "loss": 3.4231, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.0166877079698603e-05, + "loss": 3.4287, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0158491132188083e-05, + "loss": 3.433, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.0150105184677566e-05, + "loss": 3.4102, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.0141719237167046e-05, + "loss": 3.4314, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.0133333289656526e-05, + "loss": 3.4213, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0124947342146006e-05, + "loss": 3.4175, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.0116561394635482e-05, + "loss": 3.4115, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.0108191825928695e-05, + "loss": 3.4245, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0099805878418175e-05, + "loss": 3.4127, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0091419930907655e-05, + "loss": 3.4324, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083033983397135e-05, + "loss": 3.4153, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0074664414690347e-05, + "loss": 3.4238, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0066278467179827e-05, + "loss": 3.4188, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0057892519669304e-05, + "loss": 3.4251, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0049506572158787e-05, + "loss": 3.422, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041137003452e-05, + "loss": 3.4241, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.003275105594148e-05, + "loss": 3.4288, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.0024365108430956e-05, + "loss": 3.4157, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0015979160920436e-05, + "loss": 3.4264, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8801841735839844, + "eval_runtime": 331.3434, + "eval_samples_per_second": 1151.648, + "eval_steps_per_second": 35.99, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0007593213409916e-05, + "loss": 3.4138, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999207265899396e-05, + "loss": 3.4106, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9990821318388876e-05, + "loss": 3.4171, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.998243537087836e-05, + "loss": 3.4259, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.997406580217157e-05, + "loss": 3.4307, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.996567985466105e-05, + "loss": 3.4142, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9957293907150528e-05, + "loss": 3.4222, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9948907959640008e-05, + "loss": 3.4097, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.994053839093322e-05, + "loss": 3.418, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.99321524434227e-05, + "loss": 3.4195, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.992376649591218e-05, + "loss": 3.4203, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.991538054840166e-05, + "loss": 3.4183, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907027358498602e-05, + "loss": 3.4181, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9898641410988082e-05, + "loss": 3.4119, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890255463477562e-05, + "loss": 3.4138, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9881869515967042e-05, + "loss": 3.4044, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.987349994726025e-05, + "loss": 3.4146, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.986511399974973e-05, + "loss": 3.4249, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.985672805223921e-05, + "loss": 3.4142, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.984834210472869e-05, + "loss": 3.4275, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.9839956157218174e-05, + "loss": 3.4286, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.9831570209707654e-05, + "loss": 3.4265, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823184262197134e-05, + "loss": 3.4255, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.981479831468661e-05, + "loss": 3.4174, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9806428745979823e-05, + "loss": 3.4167, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798042798469303e-05, + "loss": 3.4246, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.9789656850958783e-05, + "loss": 3.4205, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.9781270903448263e-05, + "loss": 3.4175, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.9772901334741476e-05, + "loss": 3.416, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.9764515387230956e-05, + "loss": 3.4137, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.9756129439720432e-05, + "loss": 3.412, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.9747743492209912e-05, + "loss": 3.423, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9739373923503128e-05, + "loss": 3.4218, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.9730987975992608e-05, + "loss": 3.4215, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.9722602028482085e-05, + "loss": 3.4142, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.9714216080971565e-05, + "loss": 3.4242, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9705846512264777e-05, + "loss": 3.4186, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9697460564754257e-05, + "loss": 3.4045, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689074617243737e-05, + "loss": 3.4127, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9680688669733217e-05, + "loss": 3.4076, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967231910102643e-05, + "loss": 3.4131, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9663933153515906e-05, + "loss": 3.4269, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9655547206005386e-05, + "loss": 3.4208, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.96471776372986e-05, + "loss": 3.4086, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9638791689788082e-05, + "loss": 3.423, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9630405742277558e-05, + "loss": 3.4136, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622019794767038e-05, + "loss": 3.4255, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.961365022606025e-05, + "loss": 3.4158, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605264278549727e-05, + "loss": 3.3916, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.959687833103921e-05, + "loss": 3.4318, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.958849238352869e-05, + "loss": 3.4119, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580122814821903e-05, + "loss": 3.4212, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.957173686731138e-05, + "loss": 3.4118, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.9563367298604592e-05, + "loss": 3.4119, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.9554981351094072e-05, + "loss": 3.4023, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9546595403583552e-05, + "loss": 3.4126, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538209456073032e-05, + "loss": 3.4303, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9529823508562512e-05, + "loss": 3.4017, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9521437561051992e-05, + "loss": 3.4274, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513051613541472e-05, + "loss": 3.4156, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.950468204483468e-05, + "loss": 3.3999, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.9496296097324164e-05, + "loss": 3.427, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9487910149813644e-05, + "loss": 3.4073, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.9479524202303124e-05, + "loss": 3.3965, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.9471138254792604e-05, + "loss": 3.4115, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.9462752307282084e-05, + "loss": 3.418, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.945436635977156e-05, + "loss": 3.406, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.944598041226104e-05, + "loss": 3.4167, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9437610843554253e-05, + "loss": 3.403, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.9429224896043733e-05, + "loss": 3.4042, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.9420838948533213e-05, + "loss": 3.4176, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.9412453001022693e-05, + "loss": 3.4147, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.9404083432315905e-05, + "loss": 3.4184, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9395697484805382e-05, + "loss": 3.4117, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387311537294865e-05, + "loss": 3.4258, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9378925589784345e-05, + "loss": 3.4063, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.9370539642273825e-05, + "loss": 3.4171, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362153694763305e-05, + "loss": 3.4055, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9353767747252785e-05, + "loss": 3.4045, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9345381799742265e-05, + "loss": 3.4169, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337012231035474e-05, + "loss": 3.412, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9328626283524958e-05, + "loss": 3.4189, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9320240336014438e-05, + "loss": 3.4234, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9311854388503914e-05, + "loss": 3.3971, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9303484819797127e-05, + "loss": 3.4026, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295098872286607e-05, + "loss": 3.4131, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9286712924776087e-05, + "loss": 3.4152, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.92783433560693e-05, + "loss": 3.4161, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.926995740855878e-05, + "loss": 3.4105, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9261587839851988e-05, + "loss": 3.4135, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9253201892341468e-05, + "loss": 3.4119, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9244815944830948e-05, + "loss": 3.4074, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.9236429997320428e-05, + "loss": 3.4075, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.9228044049809908e-05, + "loss": 3.4171, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.9219658102299388e-05, + "loss": 3.4221, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.9211272154788868e-05, + "loss": 3.4181, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.9202886207278348e-05, + "loss": 3.3999, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919451663857156e-05, + "loss": 3.4116, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186130691061037e-05, + "loss": 3.4055, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.917774474355052e-05, + "loss": 3.4128, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.9169375174843733e-05, + "loss": 3.4127, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.9160989227333213e-05, + "loss": 3.4072, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915260327982269e-05, + "loss": 3.4091, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914421733231217e-05, + "loss": 3.4047, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.913584776360538e-05, + "loss": 3.4088, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912746181609486e-05, + "loss": 3.4, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911907586858434e-05, + "loss": 3.4078, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.911068992107382e-05, + "loss": 3.407, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102320352367034e-05, + "loss": 3.4133, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909393440485651e-05, + "loss": 3.4022, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908554845734599e-05, + "loss": 3.4025, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077162509835474e-05, + "loss": 3.4076, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9068792941128686e-05, + "loss": 3.4182, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9060406993618163e-05, + "loss": 3.4092, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052021046107643e-05, + "loss": 3.4101, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9043651477400855e-05, + "loss": 3.4137, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9035265529890335e-05, + "loss": 3.4261, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9026879582379815e-05, + "loss": 3.4102, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9018493634869295e-05, + "loss": 3.4105, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010107687358775e-05, + "loss": 3.4104, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9001721739848255e-05, + "loss": 3.4123, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8993335792337735e-05, + "loss": 3.4074, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8984949844827215e-05, + "loss": 3.4051, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8976580276120427e-05, + "loss": 3.4109, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8968194328609907e-05, + "loss": 3.4166, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8959808381099387e-05, + "loss": 3.4044, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8951422433588864e-05, + "loss": 3.3982, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943069243685806e-05, + "loss": 3.4031, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.893468329617529e-05, + "loss": 3.4009, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.892629734866477e-05, + "loss": 3.4156, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.891791140115425e-05, + "loss": 3.4171, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.890952545364373e-05, + "loss": 3.4213, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890113950613321e-05, + "loss": 3.4005, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889275355862269e-05, + "loss": 3.4198, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.8884367611112165e-05, + "loss": 3.411, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887599804240538e-05, + "loss": 3.4093, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.886761209489486e-05, + "loss": 3.4013, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8859226147384338e-05, + "loss": 3.4055, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.8850840199873818e-05, + "loss": 3.4054, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884247063116703e-05, + "loss": 3.4211, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.883408468365651e-05, + "loss": 3.4026, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882569873614599e-05, + "loss": 3.4135, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.881731278863547e-05, + "loss": 3.4123, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.8808943219928682e-05, + "loss": 3.4161, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8800557272418162e-05, + "loss": 3.405, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.879217132490764e-05, + "loss": 3.4156, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.878378537739712e-05, + "loss": 3.4159, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.877541580869033e-05, + "loss": 3.4047, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.876702986117981e-05, + "loss": 3.4143, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.8824093341827393, + "eval_runtime": 312.2796, + "eval_samples_per_second": 1221.953, + "eval_steps_per_second": 38.187, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.875864391366929e-05, + "loss": 3.4061, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.875025796615877e-05, + "loss": 3.3973, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8741888397451984e-05, + "loss": 3.4069, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873350244994146e-05, + "loss": 3.4164, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.8725116502430944e-05, + "loss": 3.4211, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8716730554920424e-05, + "loss": 3.4053, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8708360986213636e-05, + "loss": 3.4108, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8699975038703113e-05, + "loss": 3.3969, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8691589091192593e-05, + "loss": 3.4086, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683203143682073e-05, + "loss": 3.4104, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8674833574975285e-05, + "loss": 3.4089, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8666447627464765e-05, + "loss": 3.4091, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658078058757978e-05, + "loss": 3.4128, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8649692111247458e-05, + "loss": 3.3997, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8641306163736934e-05, + "loss": 3.4004, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8632920216226414e-05, + "loss": 3.3896, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.862455064751963e-05, + "loss": 3.4089, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.861616470000911e-05, + "loss": 3.4158, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8607778752498586e-05, + "loss": 3.4006, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8599392804988066e-05, + "loss": 3.4133, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591006857477546e-05, + "loss": 3.4213, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8582620909967026e-05, + "loss": 3.417, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8574234962456506e-05, + "loss": 3.4127, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.856584901494599e-05, + "loss": 3.4078, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.85574794462392e-05, + "loss": 3.4101, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854909349872868e-05, + "loss": 3.4135, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.854070755121816e-05, + "loss": 3.4105, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.853232160370764e-05, + "loss": 3.4125, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.852395203500085e-05, + "loss": 3.4009, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.851556608749033e-05, + "loss": 3.3978, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.850718013997981e-05, + "loss": 3.4014, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.849879419246929e-05, + "loss": 3.4158, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.84904246237625e-05, + "loss": 3.4138, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848203867625198e-05, + "loss": 3.4114, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847365272874146e-05, + "loss": 3.4043, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.846526678123094e-05, + "loss": 3.4065, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8456897212524152e-05, + "loss": 3.4123, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.8448511265013632e-05, + "loss": 3.3949, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440125317503112e-05, + "loss": 3.3985, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843173936999259e-05, + "loss": 3.3986, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.8423369801285805e-05, + "loss": 3.4014, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.8414983853775285e-05, + "loss": 3.4141, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8406597906264765e-05, + "loss": 3.4102, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.839821195875424e-05, + "loss": 3.3993, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.8389842390047454e-05, + "loss": 3.4139, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.8381456442536934e-05, + "loss": 3.4022, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.8373070495026414e-05, + "loss": 3.4097, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.8364700926319626e-05, + "loss": 3.4131, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.8356314978809106e-05, + "loss": 3.3809, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.8347929031298586e-05, + "loss": 3.4148, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8339543083788063e-05, + "loss": 3.402, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331173515081275e-05, + "loss": 3.412, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8322787567570755e-05, + "loss": 3.4018, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8314417998863967e-05, + "loss": 3.3997, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306032051353447e-05, + "loss": 3.3939, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8297646103842927e-05, + "loss": 3.3987, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8289260156332407e-05, + "loss": 3.4191, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8280874208821884e-05, + "loss": 3.3929, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8272488261311367e-05, + "loss": 3.4178, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264102313800847e-05, + "loss": 3.4055, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.825573274509406e-05, + "loss": 3.3909, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8247346797583536e-05, + "loss": 3.4175, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8238960850073016e-05, + "loss": 3.395, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8230574902562496e-05, + "loss": 3.3898, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222188955051976e-05, + "loss": 3.3946, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.821380300754146e-05, + "loss": 3.4126, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.820541706003094e-05, + "loss": 3.3907, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197031112520416e-05, + "loss": 3.4104, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.818866154381363e-05, + "loss": 3.3923, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818027559630311e-05, + "loss": 3.3927, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.817188964879259e-05, + "loss": 3.406, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.816350370128207e-05, + "loss": 3.4048, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.815513413257528e-05, + "loss": 3.4079, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814674818506476e-05, + "loss": 3.4044, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813836223755424e-05, + "loss": 3.4104, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.8129976290043717e-05, + "loss": 3.3971, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.8121590342533197e-05, + "loss": 3.4069, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.8113204395022677e-05, + "loss": 3.3913, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810481844751216e-05, + "loss": 3.3966, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809643250000164e-05, + "loss": 3.4062, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.808806293129485e-05, + "loss": 3.3967, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.807967698378433e-05, + "loss": 3.4102, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.807129103627381e-05, + "loss": 3.4097, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806290508876329e-05, + "loss": 3.3937, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.8054535520056502e-05, + "loss": 3.39, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.8046149572545982e-05, + "loss": 3.4033, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.8037763625035462e-05, + "loss": 3.406, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.8029377677524942e-05, + "loss": 3.4037, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.802100810881815e-05, + "loss": 3.3973, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8012638540111363e-05, + "loss": 3.4087, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.8004252592600843e-05, + "loss": 3.4004, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7995866645090323e-05, + "loss": 3.3953, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7987480697579803e-05, + "loss": 3.3989, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979094750069283e-05, + "loss": 3.4053, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7970725181362492e-05, + "loss": 3.4114, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7962339233851976e-05, + "loss": 3.4076, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7953953286341456e-05, + "loss": 3.3874, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7945567338830936e-05, + "loss": 3.4031, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7937181391320416e-05, + "loss": 3.3926, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7928795443809895e-05, + "loss": 3.4051, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7920425875103105e-05, + "loss": 3.3996, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912039927592585e-05, + "loss": 3.4008, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7903653980082068e-05, + "loss": 3.4006, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7895268032571544e-05, + "loss": 3.3942, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7886882085061024e-05, + "loss": 3.3963, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7878512516354237e-05, + "loss": 3.3902, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870126568843717e-05, + "loss": 3.3961, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7861740621333193e-05, + "loss": 3.3991, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7853354673822677e-05, + "loss": 3.4019, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7844968726312157e-05, + "loss": 3.391, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7836582778801637e-05, + "loss": 3.3937, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.7828196831291117e-05, + "loss": 3.3951, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.7819810883780597e-05, + "loss": 3.4062, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.7811441315073806e-05, + "loss": 3.3995, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803055367563286e-05, + "loss": 3.398, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7794685798856498e-05, + "loss": 3.4021, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.7786299851345978e-05, + "loss": 3.4152, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.7777913903835458e-05, + "loss": 3.3989, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.7769527956324938e-05, + "loss": 3.4005, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.7761158387618147e-05, + "loss": 3.3983, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.775277244010763e-05, + "loss": 3.4029, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.774438649259711e-05, + "loss": 3.3976, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773600054508659e-05, + "loss": 3.395, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772761459757607e-05, + "loss": 3.3975, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.7719228650065547e-05, + "loss": 3.4064, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.7710842702555027e-05, + "loss": 3.3928, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.7702456755044507e-05, + "loss": 3.3897, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.7694087186337723e-05, + "loss": 3.3912, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.76857012388272e-05, + "loss": 3.3884, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.767731529131668e-05, + "loss": 3.4109, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.766894572260989e-05, + "loss": 3.4001, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766055977509937e-05, + "loss": 3.416, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.7652173827588848e-05, + "loss": 3.3951, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.764378788007833e-05, + "loss": 3.4057, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.763540193256781e-05, + "loss": 3.3983, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.762701598505729e-05, + "loss": 3.3995, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.761863003754677e-05, + "loss": 3.3933, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.761024409003625e-05, + "loss": 3.3942, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.760187452132946e-05, + "loss": 3.3948, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.759348857381894e-05, + "loss": 3.4135, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7585102626308424e-05, + "loss": 3.3912, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7576716678797904e-05, + "loss": 3.402, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7568347110091113e-05, + "loss": 3.4051, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7559961162580593e-05, + "loss": 3.4019, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7551575215070073e-05, + "loss": 3.3977, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543205646363285e-05, + "loss": 3.4038, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7534819698852765e-05, + "loss": 3.4067, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7526433751342245e-05, + "loss": 3.3975, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518047803831725e-05, + "loss": 3.4034, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.8830504417419434, + "eval_runtime": 310.4872, + "eval_samples_per_second": 1229.007, + "eval_steps_per_second": 38.407, + "step": 1984320 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.338486415714087e+18, + "trial_name": null, + "trial_params": null +}