diff --git "a/checkpoint-2060640/trainer_state.json" "b/checkpoint-2060640/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2060640/trainer_state.json" @@ -0,0 +1,24385 @@ +{ + "best_metric": 3.848806381225586, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/rel-cl2/transformer/2/checkpoints/checkpoint-992160", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2060640, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9836, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8172, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1904, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.9873, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.827, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.7261, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.6163, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5478, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4726, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.412, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3734, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3286, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989936862987376e-05, + "loss": 5.2826, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989098268236324e-05, + "loss": 5.2333, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988259673485272e-05, + "loss": 5.2069, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.98742107873422e-05, + "loss": 5.1604, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1343, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.1101, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0768, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0456, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983231380739706e-05, + "loss": 5.0296, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.9974, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9807, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9544, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9469, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790384069844466e-05, + "loss": 4.9125, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8982, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.8691, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8618, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756856658606115e-05, + "loss": 4.8367, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748470711095595e-05, + "loss": 4.8312, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740117521192533e-05, + "loss": 4.8185, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731731573682013e-05, + "loss": 4.8007, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7903, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7752, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.761, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.757, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968981821493315e-05, + "loss": 4.7261, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.968143226742263e-05, + "loss": 4.7164, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967304631991211e-05, + "loss": 4.6952, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966466037240159e-05, + "loss": 4.6981, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6834, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6846, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.6621, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6564, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6526, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6467, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6325, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.6173, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.958920322361064e-05, + "loss": 4.6071, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.6255, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.6142, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5923, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5784, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.9547306243665496e-05, + "loss": 4.5873, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.9538920296154976e-05, + "loss": 4.5644, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.9530534348644456e-05, + "loss": 4.5751, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.9522148401133936e-05, + "loss": 4.5425, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5655, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5495, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5293, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948863736869932e-05, + "loss": 4.5227, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5342, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4947, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.5078, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5164, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.5005, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.496, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.4763, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.9421582546222625e-05, + "loss": 4.4754, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4703, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.9404810651201585e-05, + "loss": 4.4878, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396424703691065e-05, + "loss": 4.463, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388038756180545e-05, + "loss": 4.4726, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379652808670025e-05, + "loss": 4.4679, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371266861159505e-05, + "loss": 4.4669, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.9362897292452714e-05, + "loss": 4.4479, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.9354511344942194e-05, + "loss": 4.4468, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.9346125397431674e-05, + "loss": 4.4423, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.9337739449921154e-05, + "loss": 4.4389, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.9329353502410634e-05, + "loss": 4.4327, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.9320967554900114e-05, + "loss": 4.4249, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.9312581607389594e-05, + "loss": 4.4275, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.9304195659879074e-05, + "loss": 4.4254, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929582609117229e-05, + "loss": 4.4049, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4122, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4116, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.4129, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926229867993394e-05, + "loss": 4.3978, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925391273242342e-05, + "loss": 4.3971, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924554316371663e-05, + "loss": 4.3872, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923715721620611e-05, + "loss": 4.3816, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922877126869559e-05, + "loss": 4.3838, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.922038532118507e-05, + "loss": 4.3866, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3787, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920362980496776e-05, + "loss": 4.3861, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919524385745724e-05, + "loss": 4.3761, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918685790994672e-05, + "loss": 4.3614, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.91784719624362e-05, + "loss": 4.3604, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.9170086014925676e-05, + "loss": 4.3672, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.3649, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3638, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3505, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.9136558603687325e-05, + "loss": 4.3409, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.9128172656176805e-05, + "loss": 4.355, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.9119786708666285e-05, + "loss": 4.3334, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3381, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910303119244898e-05, + "loss": 4.3349, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.909464524493846e-05, + "loss": 4.3339, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908625929742794e-05, + "loss": 4.3247, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907787334991742e-05, + "loss": 4.3256, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3179, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.325, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.905273188618959e-05, + "loss": 4.3191, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.904434593867907e-05, + "loss": 4.3115, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903595999116855e-05, + "loss": 4.3216, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902757404365803e-05, + "loss": 4.3277, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.901920447495124e-05, + "loss": 4.3146, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.901081852744072e-05, + "loss": 4.3022, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.90024325799302e-05, + "loss": 4.299, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.8994046632419686e-05, + "loss": 4.298, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985660684909166e-05, + "loss": 4.3032, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977274737398646e-05, + "loss": 4.2983, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968888789888125e-05, + "loss": 4.2871, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960519221181335e-05, + "loss": 4.2974, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952133273670815e-05, + "loss": 4.2875, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943747326160294e-05, + "loss": 4.2855, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935361378649774e-05, + "loss": 4.2823, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.8926991809942984e-05, + "loss": 4.2843, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.8918605862432463e-05, + "loss": 4.2756, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.8910219914921943e-05, + "loss": 4.2864, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.8901833967411423e-05, + "loss": 4.2842, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.88934480199009e-05, + "loss": 4.283, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888506207239038e-05, + "loss": 4.2604, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.88766925036836e-05, + "loss": 4.2746, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886830655617308e-05, + "loss": 4.2688, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885992060866256e-05, + "loss": 4.2727, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885153466115204e-05, + "loss": 4.261, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884314871364151e-05, + "loss": 4.2695, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883477914493473e-05, + "loss": 4.2593, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882639319742421e-05, + "loss": 4.2759, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881800724991369e-05, + "loss": 4.2471, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.880962130240316e-05, + "loss": 4.2634, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880123535489264e-05, + "loss": 4.2486, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.879286578618586e-05, + "loss": 4.2463, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878447983867534e-05, + "loss": 4.2489, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877609389116482e-05, + "loss": 4.2351, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.87677079436543e-05, + "loss": 4.2402, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875932199614378e-05, + "loss": 4.2456, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875093604863326e-05, + "loss": 4.2351, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.202381610870361, + "eval_runtime": 313.8478, + "eval_samples_per_second": 1215.847, + "eval_steps_per_second": 37.996, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.874255010112274e-05, + "loss": 4.2299, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.8734180532415946e-05, + "loss": 4.2254, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.8725794584905426e-05, + "loss": 4.2407, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717408637394906e-05, + "loss": 4.2307, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709022689884386e-05, + "loss": 4.24, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.8700636742373866e-05, + "loss": 4.2184, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.8692250794863346e-05, + "loss": 4.2201, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.8683864847352826e-05, + "loss": 4.2078, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867549527864604e-05, + "loss": 4.2168, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866710933113552e-05, + "loss": 4.2153, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865873976242873e-05, + "loss": 4.2126, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865035381491821e-05, + "loss": 4.2169, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.864196786740769e-05, + "loss": 4.1961, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.863358191989717e-05, + "loss": 4.2095, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862519597238665e-05, + "loss": 4.1935, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861682640367986e-05, + "loss": 4.194, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860844045616934e-05, + "loss": 4.2005, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860005450865882e-05, + "loss": 4.193, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.85916685611483e-05, + "loss": 4.1962, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.2109, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574913044930995e-05, + "loss": 4.1859, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566527097420475e-05, + "loss": 4.1908, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558141149909955e-05, + "loss": 4.1892, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.1938, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.8541385633692644e-05, + "loss": 4.186, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.8532999686182124e-05, + "loss": 4.1872, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.8524613738671604e-05, + "loss": 4.1718, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.8516227791161084e-05, + "loss": 4.1782, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850785822245429e-05, + "loss": 4.1663, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.849947227494377e-05, + "loss": 4.1778, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849108632743325e-05, + "loss": 4.1739, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848270037992273e-05, + "loss": 4.1763, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847431443241221e-05, + "loss": 4.1797, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846592848490169e-05, + "loss": 4.1678, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845755891619491e-05, + "loss": 4.1742, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844917296868439e-05, + "loss": 4.1693, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844078702117387e-05, + "loss": 4.16, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843240107366335e-05, + "loss": 4.1529, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842403150495656e-05, + "loss": 4.1439, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841564555744604e-05, + "loss": 4.1521, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840725960993552e-05, + "loss": 4.1508, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398873662425e-05, + "loss": 4.1599, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.839050409371821e-05, + "loss": 4.1454, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382118146207687e-05, + "loss": 4.1461, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.8373732198697167e-05, + "loss": 4.1521, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.8365346251186646e-05, + "loss": 4.1468, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835697668247986e-05, + "loss": 4.1459, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834859073496934e-05, + "loss": 4.1334, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834020478745882e-05, + "loss": 4.1309, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833183521875203e-05, + "loss": 4.1536, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832344927124151e-05, + "loss": 4.1517, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831506332373099e-05, + "loss": 4.1352, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.830667737622047e-05, + "loss": 4.1361, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.8298291428709944e-05, + "loss": 4.1386, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.8289905481199424e-05, + "loss": 4.1225, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.8281519533688904e-05, + "loss": 4.1422, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273133586178384e-05, + "loss": 4.1148, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.826474763866787e-05, + "loss": 4.142, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.825636169115735e-05, + "loss": 4.1351, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.824799212245056e-05, + "loss": 4.1173, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.823960617494004e-05, + "loss": 4.1162, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.823122022742952e-05, + "loss": 4.1304, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222834279919e-05, + "loss": 4.0958, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.821444833240848e-05, + "loss": 4.1146, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.820607876370169e-05, + "loss": 4.1278, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819769281619117e-05, + "loss": 4.1195, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818930686868065e-05, + "loss": 4.1115, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818092092117013e-05, + "loss": 4.0986, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817255135246334e-05, + "loss": 4.1038, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816416540495282e-05, + "loss": 4.1074, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.8155779457442305e-05, + "loss": 4.1149, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.8147393509931785e-05, + "loss": 4.1037, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.8139023941224994e-05, + "loss": 4.1115, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.8130637993714474e-05, + "loss": 4.1151, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.8122252046203954e-05, + "loss": 4.1135, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.8113866098693434e-05, + "loss": 4.097, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810549652998664e-05, + "loss": 4.1048, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809711058247612e-05, + "loss": 4.1036, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887246349656e-05, + "loss": 4.0989, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808033868745508e-05, + "loss": 4.0994, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807195273994456e-05, + "loss": 4.0928, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806358317123777e-05, + "loss": 4.1019, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805519722372726e-05, + "loss": 4.0981, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804681127621674e-05, + "loss": 4.081, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803842532870622e-05, + "loss": 4.0901, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803005575999943e-05, + "loss": 4.0931, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.802166981248891e-05, + "loss": 4.0978, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801328386497839e-05, + "loss": 4.09, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.8004914296271596e-05, + "loss": 4.0855, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.7996528348761076e-05, + "loss": 4.0804, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.7988142401250556e-05, + "loss": 4.0759, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.7979756453740036e-05, + "loss": 4.0774, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.7971370506229516e-05, + "loss": 4.0886, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.7962984558718996e-05, + "loss": 4.084, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.7954598611208476e-05, + "loss": 4.0909, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.7946212663697956e-05, + "loss": 4.0831, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793784309499117e-05, + "loss": 4.0735, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792945714748065e-05, + "loss": 4.0727, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792107119997013e-05, + "loss": 4.0796, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.7912685252459605e-05, + "loss": 4.0854, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790431568375282e-05, + "loss": 4.0822, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.78959297362423e-05, + "loss": 4.0735, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.7887543788731774e-05, + "loss": 4.0636, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.7879157841221254e-05, + "loss": 4.0832, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.787078827251447e-05, + "loss": 4.0619, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.786241870380768e-05, + "loss": 4.0694, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.7854032756297166e-05, + "loss": 4.0694, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.7845646808786646e-05, + "loss": 4.0675, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.7837260861276126e-05, + "loss": 4.0566, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.7828874913765606e-05, + "loss": 4.0667, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782048896625508e-05, + "loss": 4.0566, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781210301874456e-05, + "loss": 4.064, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.7803733450037775e-05, + "loss": 4.0641, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779534750252725e-05, + "loss": 4.0547, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778696155501673e-05, + "loss": 4.075, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.777857560750621e-05, + "loss": 4.0744, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777018965999569e-05, + "loss": 4.0648, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.776180371248517e-05, + "loss": 4.0559, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775341776497465e-05, + "loss": 4.0499, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.7745031817464134e-05, + "loss": 4.056, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773666224875734e-05, + "loss": 4.0533, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772827630124682e-05, + "loss": 4.0622, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77198903537363e-05, + "loss": 4.0431, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771150440622578e-05, + "loss": 4.053, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.770313483751899e-05, + "loss": 4.0557, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.769474889000847e-05, + "loss": 4.0552, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.768636294249795e-05, + "loss": 4.0445, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.767797699498743e-05, + "loss": 4.0491, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766960742628064e-05, + "loss": 4.049, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766122147877012e-05, + "loss": 4.0527, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528355312596e-05, + "loss": 4.0554, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764444958374909e-05, + "loss": 4.0555, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.76360800150423e-05, + "loss": 4.0334, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762769406753178e-05, + "loss": 4.0472, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761930812002126e-05, + "loss": 4.0505, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761092217251074e-05, + "loss": 4.0471, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.7602552603803946e-05, + "loss": 4.0416, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.7594166656293426e-05, + "loss": 4.0495, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.7585797087586635e-05, + "loss": 4.0432, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.7577411140076115e-05, + "loss": 4.0593, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569025192565595e-05, + "loss": 4.0338, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560639245055075e-05, + "loss": 4.0473, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552253297544555e-05, + "loss": 4.0376, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543867350034035e-05, + "loss": 4.0328, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.753549778132725e-05, + "loss": 4.0392, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.752711183381673e-05, + "loss": 4.0291, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.751872588630621e-05, + "loss": 4.0328, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.751033993879569e-05, + "loss": 4.0343, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.750195399128517e-05, + "loss": 4.0288, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.033535957336426, + "eval_runtime": 333.1084, + "eval_samples_per_second": 1145.546, + "eval_steps_per_second": 35.799, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.749356804377465e-05, + "loss": 4.0263, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748518209626413e-05, + "loss": 4.0209, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.747679614875361e-05, + "loss": 4.0395, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.7468410201243084e-05, + "loss": 4.029, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460024253732563e-05, + "loss": 4.0438, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451638306222043e-05, + "loss": 4.0187, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.744325235871152e-05, + "loss": 4.0257, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434866411201e-05, + "loss": 4.009, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.742649684249422e-05, + "loss": 4.027, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.74181108949837e-05, + "loss": 4.0226, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.740972494747318e-05, + "loss": 4.0177, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740133899996266e-05, + "loss": 4.0293, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739295305245214e-05, + "loss": 4.0042, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738456710494162e-05, + "loss": 4.023, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.73761811574311e-05, + "loss": 4.0054, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.736779520992058e-05, + "loss": 4.0063, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735942564121379e-05, + "loss": 4.0069, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735103969370327e-05, + "loss": 4.0162, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734265374619275e-05, + "loss": 4.0091, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733426779868223e-05, + "loss": 4.0287, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.7325898229975444e-05, + "loss": 4.0091, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.7317512282464924e-05, + "loss": 4.0116, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.7309126334954404e-05, + "loss": 4.0094, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.7300740387443884e-05, + "loss": 4.0171, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729237081873709e-05, + "loss": 4.0061, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728398487122657e-05, + "loss": 4.0128, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727559892371605e-05, + "loss": 4.0007, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726721297620553e-05, + "loss": 4.0044, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.725884340749874e-05, + "loss": 3.9914, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.725045745998822e-05, + "loss": 4.006, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.72420715124777e-05, + "loss": 4.0053, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723368556496718e-05, + "loss": 4.0058, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.72253159962604e-05, + "loss": 4.01, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.721693004874988e-05, + "loss": 4.0002, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.720854410123936e-05, + "loss": 3.9994, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.720015815372884e-05, + "loss": 4.0053, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191788585022046e-05, + "loss": 3.9966, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183402637511526e-05, + "loss": 3.9875, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175016690001006e-05, + "loss": 3.9792, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.7166630742490486e-05, + "loss": 3.9872, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158261173783695e-05, + "loss": 3.9908, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149875226273175e-05, + "loss": 3.9969, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.7141489278762655e-05, + "loss": 3.9909, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.7133103331252135e-05, + "loss": 3.982, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712473376254535e-05, + "loss": 3.9965, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711634781503483e-05, + "loss": 3.9894, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710796186752431e-05, + "loss": 3.9846, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709957592001379e-05, + "loss": 3.9791, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.7091206351307e-05, + "loss": 3.9728, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.9978, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.9962, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.706606488757917e-05, + "loss": 3.9808, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705767894006865e-05, + "loss": 3.9818, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9883, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9664, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9882, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.9657, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015765581319785e-05, + "loss": 3.9858, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007379633809265e-05, + "loss": 3.9909, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6998993686298745e-05, + "loss": 3.9712, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.9639, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9838, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.9531, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.6965466275060394e-05, + "loss": 3.9692, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9804, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.9755, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9695, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.955, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692358567391899e-05, + "loss": 3.9579, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.691519972640847e-05, + "loss": 3.9621, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690681377889795e-05, + "loss": 3.9739, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9614, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9733, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.9738, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9739, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9578, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9641, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9692, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.96, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831373008910725e-05, + "loss": 3.9634, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822987061400205e-05, + "loss": 3.9605, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9619, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9654, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797829218868645e-05, + "loss": 3.9455, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789443271358125e-05, + "loss": 3.9596, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.678107370265134e-05, + "loss": 3.9557, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772687755140814e-05, + "loss": 3.9647, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764301807630294e-05, + "loss": 3.9542, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.955, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747529912609254e-05, + "loss": 3.9514, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739143965098734e-05, + "loss": 3.9469, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.9435, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.6722372070077694e-05, + "loss": 3.9562, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671401888017464e-05, + "loss": 3.9649, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670563293266412e-05, + "loss": 3.9593, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.66972469851536e-05, + "loss": 3.9521, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668886103764308e-05, + "loss": 3.9453, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668047509013256e-05, + "loss": 3.9472, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667208914262204e-05, + "loss": 3.9507, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666370319511152e-05, + "loss": 3.96, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655317247601e-05, + "loss": 3.9545, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664694767889421e-05, + "loss": 3.9485, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663856173138369e-05, + "loss": 3.9383, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663017578387317e-05, + "loss": 3.9593, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662178983636265e-05, + "loss": 3.9384, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661343664645959e-05, + "loss": 3.9485, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.660505069894907e-05, + "loss": 3.9434, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.659666475143855e-05, + "loss": 3.9471, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.658827880392803e-05, + "loss": 3.936, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657989285641751e-05, + "loss": 3.947, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657150690890699e-05, + "loss": 3.9379, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.65631373402002e-05, + "loss": 3.9379, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655475139268968e-05, + "loss": 3.948, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.654636544517916e-05, + "loss": 3.9314, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653797949766864e-05, + "loss": 3.955, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652959355015812e-05, + "loss": 3.9541, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652122398145134e-05, + "loss": 3.9441, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651283803394082e-05, + "loss": 3.9393, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.65044520864303e-05, + "loss": 3.9341, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649606613891978e-05, + "loss": 3.9343, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648768019140926e-05, + "loss": 3.9357, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479310622702466e-05, + "loss": 3.9446, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.6470924675191946e-05, + "loss": 3.9268, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.6462538727681426e-05, + "loss": 3.9376, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.6454152780170906e-05, + "loss": 3.941, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.6445766832660386e-05, + "loss": 3.9386, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.6437380885149866e-05, + "loss": 3.9311, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6429011316443075e-05, + "loss": 3.934, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.6420625368932555e-05, + "loss": 3.9375, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412239421422035e-05, + "loss": 3.9368, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.640385347391152e-05, + "loss": 3.9395, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.9424, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9207, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9361, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9392, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.636194011516265e-05, + "loss": 3.9324, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.932, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9412, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9329, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9472, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.632002675641377e-05, + "loss": 3.9236, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9328, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9303, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.9244, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.628649934517543e-05, + "loss": 3.9286, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.9234, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9227, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.926, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9259, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.9588358402252197, + "eval_runtime": 307.1405, + "eval_samples_per_second": 1242.399, + "eval_steps_per_second": 38.826, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9232, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.9155, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9304, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9217, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9418, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620265624887396e-05, + "loss": 3.9162, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.92, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.9041, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.9227, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9219, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616074289012509e-05, + "loss": 3.913, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9201, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614398737390778e-05, + "loss": 3.9049, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613560142639726e-05, + "loss": 3.9198, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612721547888674e-05, + "loss": 3.9041, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.904, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.9068, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.9127, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.9102, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.6085318498941607e-05, + "loss": 3.9282, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.9099, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9169, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.9089, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9157, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043388761389006e-05, + "loss": 3.9064, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.603500281387848e-05, + "loss": 3.9134, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.602661686636796e-05, + "loss": 3.9061, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.9027, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009877728954384e-05, + "loss": 3.8998, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001491781443864e-05, + "loss": 3.9055, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993105833933344e-05, + "loss": 3.9106, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9077, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597633393891231e-05, + "loss": 3.9173, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.5967947991401784e-05, + "loss": 3.9062, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959562043891264e-05, + "loss": 3.9019, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.907, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594280652767395e-05, + "loss": 3.9064, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593442058016343e-05, + "loss": 3.8888, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592603463265291e-05, + "loss": 3.8866, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591766506394613e-05, + "loss": 3.8918, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.59092791164356e-05, + "loss": 3.9007, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590089316892508e-05, + "loss": 3.9009, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.589250722141457e-05, + "loss": 3.8994, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.887, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587575170519726e-05, + "loss": 3.9031, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.586736575768674e-05, + "loss": 3.8972, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.585897981017622e-05, + "loss": 3.8924, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.58505938626657e-05, + "loss": 3.8849, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584222429395891e-05, + "loss": 3.8765, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583383834644839e-05, + "loss": 3.9132, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.582545239893787e-05, + "loss": 3.9012, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.581706645142735e-05, + "loss": 3.8909, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808696882720556e-05, + "loss": 3.8954, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800310935210036e-05, + "loss": 3.8924, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579192498769952e-05, + "loss": 3.8775, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.5783539040189e-05, + "loss": 3.8955, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577515309267848e-05, + "loss": 3.8813, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8924, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.575839757646117e-05, + "loss": 3.9049, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575001162895065e-05, + "loss": 3.8836, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574162568144013e-05, + "loss": 3.8716, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.9009, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.8669, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.57164842177123e-05, + "loss": 3.8775, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570809827020178e-05, + "loss": 3.8955, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569971232269126e-05, + "loss": 3.8882, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.569132637518074e-05, + "loss": 3.8812, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682956806473956e-05, + "loss": 3.873, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674570858963436e-05, + "loss": 3.8667, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666184911452916e-05, + "loss": 3.876, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657798963942396e-05, + "loss": 3.8892, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649429395235605e-05, + "loss": 3.873, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641043447725085e-05, + "loss": 3.8901, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632657500214565e-05, + "loss": 3.8832, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624271552704045e-05, + "loss": 3.892, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.5615885605193525e-05, + "loss": 3.8774, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.5607516036486734e-05, + "loss": 3.876, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.5599130088976214e-05, + "loss": 3.886, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.5590744141465694e-05, + "loss": 3.8712, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.5582358193955174e-05, + "loss": 3.886, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557398862524839e-05, + "loss": 3.8771, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.556560267773787e-05, + "loss": 3.8779, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555721673022735e-05, + "loss": 3.8793, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554883078271683e-05, + "loss": 3.8659, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554044483520631e-05, + "loss": 3.872, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553207526649952e-05, + "loss": 3.8764, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.5523689318989e-05, + "loss": 3.8804, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551530337147848e-05, + "loss": 3.8693, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550691742396796e-05, + "loss": 3.8739, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.549853147645744e-05, + "loss": 3.8676, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.549016190775065e-05, + "loss": 3.8636, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548177596024013e-05, + "loss": 3.8647, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547339001272961e-05, + "loss": 3.8713, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546500406521909e-05, + "loss": 3.8818, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.54566344965123e-05, + "loss": 3.8828, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544824854900178e-05, + "loss": 3.8727, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543986260149126e-05, + "loss": 3.8633, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.5431476653980736e-05, + "loss": 3.8666, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542310708527395e-05, + "loss": 3.872, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541472113776343e-05, + "loss": 3.8763, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540633519025291e-05, + "loss": 3.8755, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.5397949242742385e-05, + "loss": 3.8707, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.53895796740356e-05, + "loss": 3.859, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.538119372652508e-05, + "loss": 3.8823, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.537280777901456e-05, + "loss": 3.8554, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.536442183150404e-05, + "loss": 3.8734, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.535605226279726e-05, + "loss": 3.8613, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.534766631528674e-05, + "loss": 3.8682, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.533928036777621e-05, + "loss": 3.8572, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.533089442026569e-05, + "loss": 3.8684, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322524851558906e-05, + "loss": 3.8616, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314138904048386e-05, + "loss": 3.8622, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.530575295653786e-05, + "loss": 3.8683, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.529736700902734e-05, + "loss": 3.8574, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5288997440320555e-05, + "loss": 3.8741, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.5280611492810035e-05, + "loss": 3.8755, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.5272225545299515e-05, + "loss": 3.8701, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.5263839597788995e-05, + "loss": 3.8607, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.5255453650278475e-05, + "loss": 3.8593, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.5247084081571684e-05, + "loss": 3.8573, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.5238698134061164e-05, + "loss": 3.86, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.5230312186550644e-05, + "loss": 3.8684, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.5221926239040124e-05, + "loss": 3.8466, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521355667033333e-05, + "loss": 3.8621, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520517072282281e-05, + "loss": 3.861, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519678477531229e-05, + "loss": 3.8664, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518839882780177e-05, + "loss": 3.8542, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.518002925909499e-05, + "loss": 3.86, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.517164331158447e-05, + "loss": 3.8571, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.516325736407395e-05, + "loss": 3.8698, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.515487141656343e-05, + "loss": 3.8621, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.514650184785664e-05, + "loss": 3.87, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513811590034612e-05, + "loss": 3.8458, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.51297299528356e-05, + "loss": 3.8624, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512134400532508e-05, + "loss": 3.8653, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.5112974436618287e-05, + "loss": 3.8552, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.5104588489107766e-05, + "loss": 3.8561, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.5096202541597246e-05, + "loss": 3.8689, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.5087816594086726e-05, + "loss": 3.8613, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507944702537994e-05, + "loss": 3.8762, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507106107786942e-05, + "loss": 3.8483, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.50626751303589e-05, + "loss": 3.8629, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505428918284838e-05, + "loss": 3.8526, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504591961414159e-05, + "loss": 3.8536, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.503753366663107e-05, + "loss": 3.8576, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.502914771912055e-05, + "loss": 3.8505, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.502076177161003e-05, + "loss": 3.8516, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.501239220290324e-05, + "loss": 3.8504, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500400625539272e-05, + "loss": 3.8543, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.9177722930908203, + "eval_runtime": 307.9626, + "eval_samples_per_second": 1239.082, + "eval_steps_per_second": 38.722, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.49956203078822e-05, + "loss": 3.8468, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.498723436037168e-05, + "loss": 3.8432, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.497884841286116e-05, + "loss": 3.8593, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.497046246535065e-05, + "loss": 3.8503, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.496207651784013e-05, + "loss": 3.8651, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.495369057032961e-05, + "loss": 3.8512, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945304622819087e-05, + "loss": 3.8491, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936918675308567e-05, + "loss": 3.8352, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928549106601776e-05, + "loss": 3.8504, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920163159091256e-05, + "loss": 3.8486, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911777211580736e-05, + "loss": 3.8472, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903407642873945e-05, + "loss": 3.8485, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895021695363425e-05, + "loss": 3.8343, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886635747852905e-05, + "loss": 3.8515, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878249800342385e-05, + "loss": 3.8346, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.4869863852831864e-05, + "loss": 3.8341, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.4861477905321344e-05, + "loss": 3.836, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.4853091957810824e-05, + "loss": 3.8475, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484472238910404e-05, + "loss": 3.8399, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483633644159352e-05, + "loss": 3.8573, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.4827950494082993e-05, + "loss": 3.8435, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481956454657247e-05, + "loss": 3.8516, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481119497786569e-05, + "loss": 3.8399, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.480280903035516e-05, + "loss": 3.8445, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479442308284464e-05, + "loss": 3.8387, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478603713533412e-05, + "loss": 3.8482, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.47776511878236e-05, + "loss": 3.8381, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476926524031308e-05, + "loss": 3.8375, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.47608956716063e-05, + "loss": 3.8304, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475250972409578e-05, + "loss": 3.8348, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474412377658526e-05, + "loss": 3.8466, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473573782907474e-05, + "loss": 3.8431, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472736826036795e-05, + "loss": 3.8463, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471898231285743e-05, + "loss": 3.8354, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471059636534691e-05, + "loss": 3.8369, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470221041783639e-05, + "loss": 3.8463, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.4693840849129596e-05, + "loss": 3.8435, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.4685454901619076e-05, + "loss": 3.8194, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.4677068954108556e-05, + "loss": 3.8252, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.4668683006598036e-05, + "loss": 3.8239, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466031343789125e-05, + "loss": 3.8306, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.465192749038073e-05, + "loss": 3.8391, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464354154287021e-05, + "loss": 3.833, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.463515559535969e-05, + "loss": 3.8288, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.46267860266529e-05, + "loss": 3.8341, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.461840007914238e-05, + "loss": 3.83, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.461001413163186e-05, + "loss": 3.8322, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.460162818412134e-05, + "loss": 3.8236, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.459325861541455e-05, + "loss": 3.8062, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.458487266790403e-05, + "loss": 3.8503, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.457648672039351e-05, + "loss": 3.8351, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456810077288299e-05, + "loss": 3.8332, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.4559731204176205e-05, + "loss": 3.8301, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.4551361635469415e-05, + "loss": 3.8264, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.4542975687958895e-05, + "loss": 3.8158, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.4534589740448374e-05, + "loss": 3.8301, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.4526203792937854e-05, + "loss": 3.8229, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.4517817845427334e-05, + "loss": 3.8256, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.4509431897916814e-05, + "loss": 3.8418, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.4501045950406294e-05, + "loss": 3.821, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.4492660002895774e-05, + "loss": 3.8126, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448429043418898e-05, + "loss": 3.8363, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447590448667846e-05, + "loss": 3.805, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.446751853916794e-05, + "loss": 3.8176, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.445913259165742e-05, + "loss": 3.8292, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.445076302295064e-05, + "loss": 3.826, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.444237707544012e-05, + "loss": 3.8187, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.44339911279296e-05, + "loss": 3.8137, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442563793802654e-05, + "loss": 3.8019, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441725199051602e-05, + "loss": 3.8145, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.44088660430055e-05, + "loss": 3.826, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440048009549498e-05, + "loss": 3.8138, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439209414798446e-05, + "loss": 3.8245, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.438370820047394e-05, + "loss": 3.8255, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437532225296342e-05, + "loss": 3.8334, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669363054529e-05, + "loss": 3.8156, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435856673674611e-05, + "loss": 3.8136, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435018078923559e-05, + "loss": 3.8243, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434179484172507e-05, + "loss": 3.8092, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433340889421455e-05, + "loss": 3.8289, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432503932550776e-05, + "loss": 3.8177, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431665337799724e-05, + "loss": 3.816, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430826743048672e-05, + "loss": 3.8226, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.42998814829762e-05, + "loss": 3.8041, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429149553546568e-05, + "loss": 3.8091, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428312596675889e-05, + "loss": 3.8156, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.427474001924837e-05, + "loss": 3.8224, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.426635407173785e-05, + "loss": 3.8066, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.425796812422733e-05, + "loss": 3.8141, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249598555520546e-05, + "loss": 3.808, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241212608010026e-05, + "loss": 3.8078, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232826660499506e-05, + "loss": 3.8015, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224440712988986e-05, + "loss": 3.8152, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216071144282195e-05, + "loss": 3.8224, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207701575575404e-05, + "loss": 3.8195, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199315628064884e-05, + "loss": 3.8178, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190929680554364e-05, + "loss": 3.8042, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182543733043844e-05, + "loss": 3.8076, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.4174157785533324e-05, + "loss": 3.8119, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.4165771838022804e-05, + "loss": 3.8189, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.4157385890512284e-05, + "loss": 3.8173, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414899994300177e-05, + "loss": 3.8083, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414063037429498e-05, + "loss": 3.8042, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413224442678446e-05, + "loss": 3.8222, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.412385847927394e-05, + "loss": 3.8, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411547253176342e-05, + "loss": 3.814, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410710296305663e-05, + "loss": 3.8042, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409871701554611e-05, + "loss": 3.8123, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409034744683932e-05, + "loss": 3.7985, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.40819614993288e-05, + "loss": 3.8114, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407357555181828e-05, + "loss": 3.8021, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406518960430776e-05, + "loss": 3.8073, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.405680365679724e-05, + "loss": 3.8107, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404841770928672e-05, + "loss": 3.802, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.40400317617762e-05, + "loss": 3.8138, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.403164581426568e-05, + "loss": 3.8199, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.4023276245558894e-05, + "loss": 3.8101, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401489029804837e-05, + "loss": 3.8098, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400650435053785e-05, + "loss": 3.8001, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399811840302733e-05, + "loss": 3.8033, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398974883432054e-05, + "loss": 3.8015, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.3981362886810016e-05, + "loss": 3.8164, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.3972976939299496e-05, + "loss": 3.7876, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.3964590991788976e-05, + "loss": 3.8053, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.395622142308219e-05, + "loss": 3.8025, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.394783547557167e-05, + "loss": 3.8099, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.393944952806115e-05, + "loss": 3.8028, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.393106358055063e-05, + "loss": 3.8047, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.392269401184384e-05, + "loss": 3.7992, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.391430806433332e-05, + "loss": 3.8113, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.39059221168228e-05, + "loss": 3.8096, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.389753616931228e-05, + "loss": 3.8129, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.388916660060549e-05, + "loss": 3.7926, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.388078065309497e-05, + "loss": 3.8066, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387239470558445e-05, + "loss": 3.8102, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386400875807393e-05, + "loss": 3.8014, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.3855639189367145e-05, + "loss": 3.8021, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.3847253241856625e-05, + "loss": 3.8112, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.3838867294346105e-05, + "loss": 3.8049, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.3830481346835585e-05, + "loss": 3.8245, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.3822111778128794e-05, + "loss": 3.795, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.3813725830618274e-05, + "loss": 3.8064, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.3805339883107754e-05, + "loss": 3.7986, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.3796953935597234e-05, + "loss": 3.7994, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378858436689044e-05, + "loss": 3.8051, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378019841937992e-05, + "loss": 3.7958, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.37718124718694e-05, + "loss": 3.8019, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.376342652435888e-05, + "loss": 3.7869, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.37550569556521e-05, + "loss": 3.804, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.892151355743408, + "eval_runtime": 335.6919, + "eval_samples_per_second": 1136.73, + "eval_steps_per_second": 35.524, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.374667100814158e-05, + "loss": 3.7989, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.373828506063106e-05, + "loss": 3.7905, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.372989911312054e-05, + "loss": 3.804, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.372152954441375e-05, + "loss": 3.8023, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371314359690323e-05, + "loss": 3.809, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370475764939271e-05, + "loss": 3.7948, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369637170188219e-05, + "loss": 3.7959, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.36880021331754e-05, + "loss": 3.7832, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.367961618566488e-05, + "loss": 3.7971, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367123023815436e-05, + "loss": 3.7961, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.366284429064384e-05, + "loss": 3.798, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365447472193705e-05, + "loss": 3.7907, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364610515323026e-05, + "loss": 3.7885, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363771920571974e-05, + "loss": 3.7922, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362933325820922e-05, + "loss": 3.7841, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.36209473106987e-05, + "loss": 3.7801, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361256136318818e-05, + "loss": 3.7836, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.360417541567766e-05, + "loss": 3.7922, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.359578946816714e-05, + "loss": 3.7879, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358740352065662e-05, + "loss": 3.8041, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357903395194983e-05, + "loss": 3.7916, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357064800443931e-05, + "loss": 3.8001, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356226205692879e-05, + "loss": 3.7865, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355387610941827e-05, + "loss": 3.7891, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.3545506540711486e-05, + "loss": 3.7864, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.3537120593200966e-05, + "loss": 3.7993, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.3528734645690446e-05, + "loss": 3.7877, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.3520348698179926e-05, + "loss": 3.785, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.3511979129473135e-05, + "loss": 3.781, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.3503593181962615e-05, + "loss": 3.7868, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.3495207234452095e-05, + "loss": 3.7906, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.3486821286941575e-05, + "loss": 3.7933, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.3478451718234784e-05, + "loss": 3.795, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.3470065770724264e-05, + "loss": 3.7888, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.3461679823213744e-05, + "loss": 3.786, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.3453293875703224e-05, + "loss": 3.7947, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.344492430699644e-05, + "loss": 3.7909, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343653835948592e-05, + "loss": 3.7752, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.34281524119754e-05, + "loss": 3.7738, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341976646446488e-05, + "loss": 3.7725, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.341139689575809e-05, + "loss": 3.7772, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340301094824757e-05, + "loss": 3.7908, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339462500073705e-05, + "loss": 3.7838, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338623905322653e-05, + "loss": 3.7767, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337786948451974e-05, + "loss": 3.7849, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336948353700922e-05, + "loss": 3.7797, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.33610975894987e-05, + "loss": 3.7828, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335271164198818e-05, + "loss": 3.773, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.3344342073281393e-05, + "loss": 3.7567, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.3335956125770873e-05, + "loss": 3.8024, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.3327570178260353e-05, + "loss": 3.7835, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331918423074983e-05, + "loss": 3.7881, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331081466204304e-05, + "loss": 3.7767, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330244509333625e-05, + "loss": 3.7826, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329405914582573e-05, + "loss": 3.7657, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328567319831521e-05, + "loss": 3.7772, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327728725080469e-05, + "loss": 3.7772, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.326890130329417e-05, + "loss": 3.7761, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326051535578365e-05, + "loss": 3.7959, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325212940827313e-05, + "loss": 3.7697, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324374346076261e-05, + "loss": 3.7613, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323537389205583e-05, + "loss": 3.7898, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322698794454531e-05, + "loss": 3.7573, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.321860199703479e-05, + "loss": 3.7668, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.321021604952427e-05, + "loss": 3.781, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201846480817476e-05, + "loss": 3.7807, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193460533306956e-05, + "loss": 3.7659, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185074585796436e-05, + "loss": 3.7719, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176688638285916e-05, + "loss": 3.7514, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.3168319069579125e-05, + "loss": 3.7696, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.3159933122068605e-05, + "loss": 3.7764, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151547174558085e-05, + "loss": 3.7645, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.31431776058513e-05, + "loss": 3.7776, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313479165834078e-05, + "loss": 3.7759, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312640571083026e-05, + "loss": 3.7886, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311801976331974e-05, + "loss": 3.7661, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.310965019461295e-05, + "loss": 3.7731, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.310126424710243e-05, + "loss": 3.7776, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.309287829959191e-05, + "loss": 3.7623, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308449235208139e-05, + "loss": 3.7776, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.30761227833746e-05, + "loss": 3.7725, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306773683586408e-05, + "loss": 3.7697, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305935088835356e-05, + "loss": 3.7769, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305096494084304e-05, + "loss": 3.7613, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.3042595372136254e-05, + "loss": 3.7598, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034209424625734e-05, + "loss": 3.7689, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.3025823477115214e-05, + "loss": 3.7732, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301743752960469e-05, + "loss": 3.762, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.3009067960897903e-05, + "loss": 3.7694, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.3000682013387383e-05, + "loss": 3.7575, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299229606587686e-05, + "loss": 3.7651, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.2983910118366337e-05, + "loss": 3.758, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.297554054965955e-05, + "loss": 3.7661, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.296715460214903e-05, + "loss": 3.7791, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.295878503344224e-05, + "loss": 3.7715, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.295039908593173e-05, + "loss": 3.7707, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294201313842121e-05, + "loss": 3.7578, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293362719091069e-05, + "loss": 3.7622, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.292524124340016e-05, + "loss": 3.7657, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291685529588964e-05, + "loss": 3.7743, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290846934837912e-05, + "loss": 3.7679, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.29000834008686e-05, + "loss": 3.7709, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289171383216181e-05, + "loss": 3.7582, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288332788465129e-05, + "loss": 3.7739, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287494193714077e-05, + "loss": 3.758, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286655598963025e-05, + "loss": 3.7686, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858186420923466e-05, + "loss": 3.7549, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.2849800473412946e-05, + "loss": 3.77, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284143090470616e-05, + "loss": 3.7557, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.2833044957195635e-05, + "loss": 3.7633, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.2824659009685115e-05, + "loss": 3.76, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816273062174595e-05, + "loss": 3.763, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807887114664075e-05, + "loss": 3.7625, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799501167153555e-05, + "loss": 3.7597, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791115219643035e-05, + "loss": 3.7675, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782729272132515e-05, + "loss": 3.7753, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774359703425724e-05, + "loss": 3.7668, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765973755915204e-05, + "loss": 3.768, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757587808404684e-05, + "loss": 3.7534, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749201860894164e-05, + "loss": 3.7575, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274083229218738e-05, + "loss": 3.7604, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273244634467686e-05, + "loss": 3.7682, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272406039716634e-05, + "loss": 3.7438, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271567444965582e-05, + "loss": 3.7603, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270730488094903e-05, + "loss": 3.7612, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269891893343851e-05, + "loss": 3.7608, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269053298592799e-05, + "loss": 3.7589, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268214703841747e-05, + "loss": 3.7628, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267377746971068e-05, + "loss": 3.7553, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.266539152220016e-05, + "loss": 3.7678, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265700557468964e-05, + "loss": 3.766, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264861962717912e-05, + "loss": 3.7699, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264025005847233e-05, + "loss": 3.747, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263186411096181e-05, + "loss": 3.7634, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262347816345129e-05, + "loss": 3.7677, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261509221594077e-05, + "loss": 3.7556, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260672264723398e-05, + "loss": 3.7597, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259833669972346e-05, + "loss": 3.7644, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258995075221294e-05, + "loss": 3.7632, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258156480470242e-05, + "loss": 3.7768, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257321161479936e-05, + "loss": 3.7559, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256482566728884e-05, + "loss": 3.7617, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.255643971977833e-05, + "loss": 3.7572, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.254805377226781e-05, + "loss": 3.7574, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.253966782475729e-05, + "loss": 3.7565, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253128187724677e-05, + "loss": 3.7503, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252289592973625e-05, + "loss": 3.7603, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251450998222573e-05, + "loss": 3.7416, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.2506140413518936e-05, + "loss": 3.7641, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.875673294067383, + "eval_runtime": 302.8212, + "eval_samples_per_second": 1260.12, + "eval_steps_per_second": 39.38, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2497754466008416e-05, + "loss": 3.7564, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.2489368518497896e-05, + "loss": 3.7459, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.2480982570987376e-05, + "loss": 3.7598, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.2472596623476856e-05, + "loss": 3.7583, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.2464210675966336e-05, + "loss": 3.7684, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.2455824728455816e-05, + "loss": 3.753, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.2447438780945296e-05, + "loss": 3.7561, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.2439052833434776e-05, + "loss": 3.7409, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243068326472799e-05, + "loss": 3.7539, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.242229731721747e-05, + "loss": 3.7543, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413911369706945e-05, + "loss": 3.7548, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405525422196424e-05, + "loss": 3.748, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.239717223229337e-05, + "loss": 3.7464, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.238878628478285e-05, + "loss": 3.7503, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.238040033727233e-05, + "loss": 3.7481, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.237201438976181e-05, + "loss": 3.7377, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.236362844225129e-05, + "loss": 3.7436, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.235524249474076e-05, + "loss": 3.7496, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.234685654723025e-05, + "loss": 3.7464, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.233847059971973e-05, + "loss": 3.7612, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330101031012945e-05, + "loss": 3.7548, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232171508350242e-05, + "loss": 3.76, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.23133291359919e-05, + "loss": 3.7413, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230494318848138e-05, + "loss": 3.7489, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.229657361977459e-05, + "loss": 3.7455, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228818767226407e-05, + "loss": 3.7569, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227980172475355e-05, + "loss": 3.7458, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227141577724303e-05, + "loss": 3.7476, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.2263046208536236e-05, + "loss": 3.7409, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.2254660261025716e-05, + "loss": 3.7414, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.2246274313515196e-05, + "loss": 3.7475, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223788836600468e-05, + "loss": 3.7572, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.222951879729789e-05, + "loss": 3.7532, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222113284978737e-05, + "loss": 3.7485, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.221274690227685e-05, + "loss": 3.7445, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.220436095476633e-05, + "loss": 3.7491, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.219599138605954e-05, + "loss": 3.7511, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.218760543854902e-05, + "loss": 3.7385, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.21792194910385e-05, + "loss": 3.7311, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217083354352798e-05, + "loss": 3.7314, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216246397482119e-05, + "loss": 3.7401, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.215407802731067e-05, + "loss": 3.7456, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.214569207980015e-05, + "loss": 3.7445, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.2137306132289637e-05, + "loss": 3.7404, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.2128936563582846e-05, + "loss": 3.741, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.2120550616072326e-05, + "loss": 3.7419, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.2112164668561806e-05, + "loss": 3.7441, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.2103795099855015e-05, + "loss": 3.7319, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.2095409152344495e-05, + "loss": 3.7166, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.2087023204833975e-05, + "loss": 3.759, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.2078637257323454e-05, + "loss": 3.7421, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070267688616664e-05, + "loss": 3.7498, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.2061881741106144e-05, + "loss": 3.7402, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205351217239936e-05, + "loss": 3.739, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204512622488884e-05, + "loss": 3.7283, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.203674027737832e-05, + "loss": 3.7374, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.20283543298678e-05, + "loss": 3.7406, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.201996838235728e-05, + "loss": 3.7322, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.201158243484676e-05, + "loss": 3.7559, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200319648733624e-05, + "loss": 3.7332, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.199481053982572e-05, + "loss": 3.7228, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.198645734992266e-05, + "loss": 3.7482, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.197807140241214e-05, + "loss": 3.7212, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.196968545490162e-05, + "loss": 3.7215, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19612995073911e-05, + "loss": 3.7458, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195291355988058e-05, + "loss": 3.7424, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194452761237006e-05, + "loss": 3.7255, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.1936141664859544e-05, + "loss": 3.7334, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.1927755717349024e-05, + "loss": 3.716, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191938614864223e-05, + "loss": 3.7312, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191100020113171e-05, + "loss": 3.7348, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190261425362119e-05, + "loss": 3.729, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189422830611067e-05, + "loss": 3.7374, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188584235860015e-05, + "loss": 3.7375, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187745641108963e-05, + "loss": 3.7449, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186907046357911e-05, + "loss": 3.7291, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186068451606859e-05, + "loss": 3.7348, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.18523149473618e-05, + "loss": 3.7366, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.184392899985128e-05, + "loss": 3.7245, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.183554305234076e-05, + "loss": 3.7389, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.182717348363398e-05, + "loss": 3.7354, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181878753612346e-05, + "loss": 3.7289, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181040158861294e-05, + "loss": 3.7427, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180201564110242e-05, + "loss": 3.72, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.1793646072395626e-05, + "loss": 3.72, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.1785260124885106e-05, + "loss": 3.7324, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.1776874177374586e-05, + "loss": 3.7356, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.1768488229864066e-05, + "loss": 3.7245, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.1760118661157275e-05, + "loss": 3.7319, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.1751732713646755e-05, + "loss": 3.7163, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.1743346766136235e-05, + "loss": 3.7264, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.1734960818625715e-05, + "loss": 3.721, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172659124991893e-05, + "loss": 3.7291, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171820530240841e-05, + "loss": 3.7391, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170983573370162e-05, + "loss": 3.7319, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.17014497861911e-05, + "loss": 3.7336, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.169306383868058e-05, + "loss": 3.7217, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.168467789117006e-05, + "loss": 3.7242, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.167629194365954e-05, + "loss": 3.7242, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.166790599614902e-05, + "loss": 3.7384, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.165952004863849e-05, + "loss": 3.7314, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.165113410112797e-05, + "loss": 3.7338, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.164276453242119e-05, + "loss": 3.7195, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.163437858491067e-05, + "loss": 3.7331, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.162599263740015e-05, + "loss": 3.7221, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.161760668988963e-05, + "loss": 3.7304, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609237121182845e-05, + "loss": 3.7173, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160085117367232e-05, + "loss": 3.732, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.15924652261618e-05, + "loss": 3.7174, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158407927865128e-05, + "loss": 3.7276, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.157569333114076e-05, + "loss": 3.7194, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156732376243397e-05, + "loss": 3.7326, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155893781492345e-05, + "loss": 3.7242, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155055186741293e-05, + "loss": 3.7212, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154216591990241e-05, + "loss": 3.733, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153377997239189e-05, + "loss": 3.737, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152539402488137e-05, + "loss": 3.7327, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151702445617458e-05, + "loss": 3.7277, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.150863850866406e-05, + "loss": 3.7212, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.150025256115354e-05, + "loss": 3.7202, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149186661364302e-05, + "loss": 3.7254, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.14834806661325e-05, + "loss": 3.7268, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147509471862198e-05, + "loss": 3.7106, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146670877111146e-05, + "loss": 3.7251, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145833920240467e-05, + "loss": 3.7256, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144995325489415e-05, + "loss": 3.7253, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.144156730738363e-05, + "loss": 3.7225, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143318135987311e-05, + "loss": 3.724, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.142481179116632e-05, + "loss": 3.719, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141642584365581e-05, + "loss": 3.7323, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140803989614529e-05, + "loss": 3.7296, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139965394863477e-05, + "loss": 3.731, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.1391284379927976e-05, + "loss": 3.7125, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.1382898432417456e-05, + "loss": 3.7298, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.1374512484906936e-05, + "loss": 3.7273, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.1366142916200145e-05, + "loss": 3.7204, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.1357756968689625e-05, + "loss": 3.7263, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.1349371021179105e-05, + "loss": 3.7261, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340985073668585e-05, + "loss": 3.7271, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.1332599126158065e-05, + "loss": 3.7427, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.1324229557451274e-05, + "loss": 3.7189, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131584360994076e-05, + "loss": 3.725, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.130745766243024e-05, + "loss": 3.7244, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.129907171491972e-05, + "loss": 3.7239, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.12906857674092e-05, + "loss": 3.7157, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.128229981989868e-05, + "loss": 3.7141, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7233, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.7104, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.125715835617085e-05, + "loss": 3.7273, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.864861011505127, + "eval_runtime": 305.1967, + "eval_samples_per_second": 1250.312, + "eval_steps_per_second": 39.073, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.124877240866032e-05, + "loss": 3.7212, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.12403864611498e-05, + "loss": 3.7096, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123200051363928e-05, + "loss": 3.7216, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.12236309449325e-05, + "loss": 3.7232, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.1215261376225714e-05, + "loss": 3.7317, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.1206875428715194e-05, + "loss": 3.7163, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.1198489481204674e-05, + "loss": 3.724, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.1190103533694154e-05, + "loss": 3.7107, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.118171758618363e-05, + "loss": 3.7125, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117333163867311e-05, + "loss": 3.7239, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116494569116259e-05, + "loss": 3.7165, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.7116, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114820655374901e-05, + "loss": 3.7201, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113982060623849e-05, + "loss": 3.7098, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113143465872797e-05, + "loss": 3.7096, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.112304871121745e-05, + "loss": 3.7051, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.111466276370693e-05, + "loss": 3.7072, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110627681619641e-05, + "loss": 3.7169, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109789086868589e-05, + "loss": 3.7056, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108950492117537e-05, + "loss": 3.7292, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108113535246858e-05, + "loss": 3.7181, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107274940495806e-05, + "loss": 3.7255, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106436345744754e-05, + "loss": 3.7091, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105597750993702e-05, + "loss": 3.7127, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.104760794123023e-05, + "loss": 3.717, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103922199371971e-05, + "loss": 3.7196, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103083604620919e-05, + "loss": 3.7101, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102245009869867e-05, + "loss": 3.7165, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.1014080529991886e-05, + "loss": 3.703, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005694582481366e-05, + "loss": 3.71, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997308634970846e-05, + "loss": 3.713, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988922687460326e-05, + "loss": 3.7196, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980553118753535e-05, + "loss": 3.7194, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972167171243015e-05, + "loss": 3.717, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963781223732495e-05, + "loss": 3.7124, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955395276221975e-05, + "loss": 3.7142, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947025707515184e-05, + "loss": 3.7186, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938639760004664e-05, + "loss": 3.704, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930253812494144e-05, + "loss": 3.7001, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.092188424378736e-05, + "loss": 3.6971, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.091349829627684e-05, + "loss": 3.7053, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.090511234876632e-05, + "loss": 3.7052, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.08967264012558e-05, + "loss": 3.7123, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088835683254901e-05, + "loss": 3.7084, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087997088503849e-05, + "loss": 3.7038, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087158493752797e-05, + "loss": 3.7106, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086319899001745e-05, + "loss": 3.7102, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.085482942131066e-05, + "loss": 3.6996, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084644347380014e-05, + "loss": 3.6847, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083805752628962e-05, + "loss": 3.7194, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.08296715787791e-05, + "loss": 3.7116, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082130201007231e-05, + "loss": 3.7169, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081291606256179e-05, + "loss": 3.705, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.0804546493855e-05, + "loss": 3.7061, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.079616054634448e-05, + "loss": 3.6959, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.078777459883396e-05, + "loss": 3.7011, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077938865132344e-05, + "loss": 3.7111, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077100270381292e-05, + "loss": 3.6939, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.07626167563024e-05, + "loss": 3.7247, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075423080879188e-05, + "loss": 3.7055, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6853, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.07374916713783e-05, + "loss": 3.7173, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072910572386778e-05, + "loss": 3.6903, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.072071977635726e-05, + "loss": 3.6883, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071233382884675e-05, + "loss": 3.7145, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070394788133623e-05, + "loss": 3.7054, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069556193382571e-05, + "loss": 3.6949, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068717598631519e-05, + "loss": 3.7006, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.686, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670420470097876e-05, + "loss": 3.6972, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662034522587356e-05, + "loss": 3.7041, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653648575076836e-05, + "loss": 3.6959, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645262627566316e-05, + "loss": 3.7055, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636893058859525e-05, + "loss": 3.7017, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628507111349005e-05, + "loss": 3.7132, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620121163838485e-05, + "loss": 3.6974, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611735216327965e-05, + "loss": 3.7036, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.060336564762118e-05, + "loss": 3.702, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059497970011066e-05, + "loss": 3.6935, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.058659375260014e-05, + "loss": 3.7088, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.057820780508962e-05, + "loss": 3.7042, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.056985461518656e-05, + "loss": 3.6926, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056146866767604e-05, + "loss": 3.7101, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055308272016552e-05, + "loss": 3.6866, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.0544696772655e-05, + "loss": 3.6868, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053631082514448e-05, + "loss": 3.7024, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052792487763396e-05, + "loss": 3.7002, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.051953893012344e-05, + "loss": 3.6936, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051115298261292e-05, + "loss": 3.7017, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.0502783413906134e-05, + "loss": 3.6851, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.0494397466395614e-05, + "loss": 3.6909, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048602789768882e-05, + "loss": 3.6921, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.04776419501783e-05, + "loss": 3.6953, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.046925600266778e-05, + "loss": 3.7095, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046087005515726e-05, + "loss": 3.6996, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045248410764674e-05, + "loss": 3.7058, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044409816013622e-05, + "loss": 3.6887, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.04357122126257e-05, + "loss": 3.6929, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.6941, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.041895669640839e-05, + "loss": 3.7035, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.041057074889787e-05, + "loss": 3.6977, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040218480138735e-05, + "loss": 3.7041, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039379885387683e-05, + "loss": 3.6906, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038542928517005e-05, + "loss": 3.6964, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037704333765953e-05, + "loss": 3.6954, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368657390149e-05, + "loss": 3.6975, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036028782144222e-05, + "loss": 3.6847, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.03519018739317e-05, + "loss": 3.7031, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.0343515926421177e-05, + "loss": 3.6873, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033512997891065e-05, + "loss": 3.6939, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032674403140013e-05, + "loss": 3.6868, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.0318374462693346e-05, + "loss": 3.6987, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.0309988515182826e-05, + "loss": 3.6952, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301602567672305e-05, + "loss": 3.69, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293216620161785e-05, + "loss": 3.6983, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284830672651265e-05, + "loss": 3.7071, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276444725140745e-05, + "loss": 3.706, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268075156433954e-05, + "loss": 3.6951, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259689208923434e-05, + "loss": 3.6903, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251303261412914e-05, + "loss": 3.6896, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242917313902394e-05, + "loss": 3.6948, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234531366391874e-05, + "loss": 3.6954, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.0226145418881354e-05, + "loss": 3.6801, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.0217759471370834e-05, + "loss": 3.6957, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020938990266404e-05, + "loss": 3.6978, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020100395515353e-05, + "loss": 3.6896, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019261800764301e-05, + "loss": 3.6908, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018423206013249e-05, + "loss": 3.696, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.01758624914257e-05, + "loss": 3.6895, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016747654391518e-05, + "loss": 3.7, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015909059640466e-05, + "loss": 3.6977, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015070464889414e-05, + "loss": 3.7023, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014233508018735e-05, + "loss": 3.6821, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013394913267683e-05, + "loss": 3.6973, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012556318516631e-05, + "loss": 3.695, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011719361645952e-05, + "loss": 3.6921, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108807668949e-05, + "loss": 3.693, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.0100421721438484e-05, + "loss": 3.6928, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.0092035773927964e-05, + "loss": 3.6981, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.0083649826417444e-05, + "loss": 3.7154, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007528025771065e-05, + "loss": 3.6835, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006689431020013e-05, + "loss": 3.6966, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005850836268961e-05, + "loss": 3.6938, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005012241517909e-05, + "loss": 3.6922, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.004173646766857e-05, + "loss": 3.6866, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003335052015805e-05, + "loss": 3.6835, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002496457264753e-05, + "loss": 3.695, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.0016578625137006e-05, + "loss": 3.6791, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000820905643022e-05, + "loss": 3.6967, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.8586690425872803, + "eval_runtime": 304.6995, + "eval_samples_per_second": 1252.352, + "eval_steps_per_second": 39.137, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.99998231089197e-05, + "loss": 3.6897, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.999143716140918e-05, + "loss": 3.6831, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.998305121389866e-05, + "loss": 3.6914, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.997466526638814e-05, + "loss": 3.6925, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.996629569768136e-05, + "loss": 3.6987, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.995790975017084e-05, + "loss": 3.6865, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.994952380266031e-05, + "loss": 3.6954, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.994113785514979e-05, + "loss": 3.6779, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.993275190763927e-05, + "loss": 3.6808, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.992436596012875e-05, + "loss": 3.6958, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.991598001261823e-05, + "loss": 3.6869, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.990759406510771e-05, + "loss": 3.6794, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.9899240875204655e-05, + "loss": 3.6917, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.9890854927694135e-05, + "loss": 3.677, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.9882468980183615e-05, + "loss": 3.6807, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.9874083032673095e-05, + "loss": 3.6697, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.9865697085162575e-05, + "loss": 3.6801, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.9857311137652055e-05, + "loss": 3.6896, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.9848925190141535e-05, + "loss": 3.6744, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.9840539242631015e-05, + "loss": 3.6972, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.9832169673924224e-05, + "loss": 3.6911, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.9823783726413704e-05, + "loss": 3.6917, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.9815397778903184e-05, + "loss": 3.6833, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.9807011831392664e-05, + "loss": 3.6843, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979864226268587e-05, + "loss": 3.6837, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.979025631517535e-05, + "loss": 3.6891, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.978187036766484e-05, + "loss": 3.6803, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.977348442015432e-05, + "loss": 3.6882, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.976511485144753e-05, + "loss": 3.6745, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.975672890393701e-05, + "loss": 3.6803, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974834295642649e-05, + "loss": 3.6837, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.973995700891597e-05, + "loss": 3.6878, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973158744020918e-05, + "loss": 3.6925, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972320149269866e-05, + "loss": 3.6923, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971481554518814e-05, + "loss": 3.676, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970642959767762e-05, + "loss": 3.6858, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.9698060028970827e-05, + "loss": 3.6899, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.9689674081460306e-05, + "loss": 3.6733, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968128813394979e-05, + "loss": 3.6748, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.9672918565243e-05, + "loss": 3.6698, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966453261773248e-05, + "loss": 3.6718, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.965614667022196e-05, + "loss": 3.6783, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.964776072271144e-05, + "loss": 3.6848, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.963939115400465e-05, + "loss": 3.6803, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.963100520649413e-05, + "loss": 3.6764, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.962261925898361e-05, + "loss": 3.6767, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.961423331147309e-05, + "loss": 3.6841, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.96058637427663e-05, + "loss": 3.669, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.959747779525578e-05, + "loss": 3.659, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958909184774526e-05, + "loss": 3.6883, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958070590023475e-05, + "loss": 3.6814, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.9572336331527956e-05, + "loss": 3.6882, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.9563950384017436e-05, + "loss": 3.6763, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.9555580815310645e-05, + "loss": 3.6765, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.9547194867800125e-05, + "loss": 3.6709, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.9538808920289605e-05, + "loss": 3.6734, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.9530422972779085e-05, + "loss": 3.683, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.9522037025268565e-05, + "loss": 3.6633, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.9513651077758045e-05, + "loss": 3.6978, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.9505265130247525e-05, + "loss": 3.674, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.9496879182737005e-05, + "loss": 3.6553, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.948852599283395e-05, + "loss": 3.6887, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.948014004532343e-05, + "loss": 3.6686, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.947175409781291e-05, + "loss": 3.6567, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946336815030239e-05, + "loss": 3.6821, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.94549985815956e-05, + "loss": 3.6795, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.944661263408508e-05, + "loss": 3.6674, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.943822668657456e-05, + "loss": 3.6697, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.942984073906404e-05, + "loss": 3.6561, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942145479155352e-05, + "loss": 3.6672, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.9413068844043e-05, + "loss": 3.6777, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940468289653248e-05, + "loss": 3.6677, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939629694902196e-05, + "loss": 3.6757, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938792738031517e-05, + "loss": 3.6714, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937954143280465e-05, + "loss": 3.686, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937117186409786e-05, + "loss": 3.6713, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.936278591658734e-05, + "loss": 3.6755, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935439996907682e-05, + "loss": 3.671, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.93460140215663e-05, + "loss": 3.666, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933762807405578e-05, + "loss": 3.681, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932924212654526e-05, + "loss": 3.6755, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932087255783847e-05, + "loss": 3.6688, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.931248661032795e-05, + "loss": 3.6816, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.930410066281743e-05, + "loss": 3.6575, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.929571471530691e-05, + "loss": 3.6632, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287328767796385e-05, + "loss": 3.6706, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.927894282028587e-05, + "loss": 3.6743, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.927055687277535e-05, + "loss": 3.6615, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.926217092526483e-05, + "loss": 3.675, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.925380135655804e-05, + "loss": 3.6622, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.924541540904752e-05, + "loss": 3.6643, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.923704584034074e-05, + "loss": 3.661, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.922865989283021e-05, + "loss": 3.668, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.922027394531969e-05, + "loss": 3.6816, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.921188799780917e-05, + "loss": 3.6719, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920350205029865e-05, + "loss": 3.6773, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919511610278813e-05, + "loss": 3.6631, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918673015527761e-05, + "loss": 3.6651, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917834420776709e-05, + "loss": 3.6667, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.9169991017864035e-05, + "loss": 3.6783, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.9161605070353515e-05, + "loss": 3.6719, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.9153219122842995e-05, + "loss": 3.6741, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.9144833175332475e-05, + "loss": 3.6703, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.9136447227821955e-05, + "loss": 3.6692, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.9128061280311434e-05, + "loss": 3.6685, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.9119675332800914e-05, + "loss": 3.6688, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.9111305764094124e-05, + "loss": 3.6572, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102919816583604e-05, + "loss": 3.6729, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094533869073083e-05, + "loss": 3.66, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086147921562563e-05, + "loss": 3.6661, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.907776197405204e-05, + "loss": 3.6633, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906939240534526e-05, + "loss": 3.6644, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906100645783474e-05, + "loss": 3.6701, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905262051032422e-05, + "loss": 3.6629, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.90442345628137e-05, + "loss": 3.6753, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903584861530318e-05, + "loss": 3.6795, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902746266779266e-05, + "loss": 3.6771, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901907672028214e-05, + "loss": 3.6655, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901069077277162e-05, + "loss": 3.6666, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900233758286856e-05, + "loss": 3.6585, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899395163535804e-05, + "loss": 3.6683, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898556568784752e-05, + "loss": 3.6695, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.8977179740337e-05, + "loss": 3.6542, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.896879379282648e-05, + "loss": 3.6661, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960407845315964e-05, + "loss": 3.6691, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952021897805444e-05, + "loss": 3.667, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943635950294924e-05, + "loss": 3.6617, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.893528276039186e-05, + "loss": 3.6679, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.892689681288134e-05, + "loss": 3.661, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.891851086537082e-05, + "loss": 3.6756, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.89101249178603e-05, + "loss": 3.6664, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890173897034978e-05, + "loss": 3.6792, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889335302283926e-05, + "loss": 3.6562, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.888496707532874e-05, + "loss": 3.667, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887658112781822e-05, + "loss": 3.6721, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.8868227937915167e-05, + "loss": 3.666, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.8859841990404647e-05, + "loss": 3.6647, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.8851456042894126e-05, + "loss": 3.6681, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.8843070095383606e-05, + "loss": 3.6698, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.8834684147873086e-05, + "loss": 3.6851, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.8826314579166295e-05, + "loss": 3.6627, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.8817928631655775e-05, + "loss": 3.669, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.8809542684145255e-05, + "loss": 3.6682, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801156736634735e-05, + "loss": 3.6638, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792770789124215e-05, + "loss": 3.6609, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784401220417424e-05, + "loss": 3.657, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8776015272906904e-05, + "loss": 3.665, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767629325396384e-05, + "loss": 3.6587, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.875924337788587e-05, + "loss": 3.6658, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8542556762695312, + "eval_runtime": 308.0052, + "eval_samples_per_second": 1238.911, + "eval_steps_per_second": 38.717, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750857430375344e-05, + "loss": 3.6634, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742471482864824e-05, + "loss": 3.6554, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.8734085535354304e-05, + "loss": 3.6598, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872571596664752e-05, + "loss": 3.6708, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871733001913699e-05, + "loss": 3.6766, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870894407162647e-05, + "loss": 3.6608, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870055812411595e-05, + "loss": 3.6635, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869218855540916e-05, + "loss": 3.6548, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868380260789864e-05, + "loss": 3.6549, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867541666038812e-05, + "loss": 3.6657, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.866703071287761e-05, + "loss": 3.6635, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865864476536709e-05, + "loss": 3.6573, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.86502751966603e-05, + "loss": 3.6652, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864188924914978e-05, + "loss": 3.6507, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.863350330163926e-05, + "loss": 3.6536, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.862511735412874e-05, + "loss": 3.6421, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.861673140661822e-05, + "loss": 3.6586, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.86083454591077e-05, + "loss": 3.6613, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.859995951159718e-05, + "loss": 3.6488, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859157356408666e-05, + "loss": 3.67, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858320399537987e-05, + "loss": 3.6644, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857481804786935e-05, + "loss": 3.6686, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.8566432100358827e-05, + "loss": 3.6581, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.8558046152848307e-05, + "loss": 3.6563, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854967658414152e-05, + "loss": 3.6579, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.8541290636631e-05, + "loss": 3.6667, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.853290468912048e-05, + "loss": 3.6485, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852451874160996e-05, + "loss": 3.6639, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851614917290317e-05, + "loss": 3.6478, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850776322539265e-05, + "loss": 3.6536, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.849937727788213e-05, + "loss": 3.6602, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.849099133037161e-05, + "loss": 3.664, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.848262176166482e-05, + "loss": 3.6577, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.84742358141543e-05, + "loss": 3.6698, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.846584986664378e-05, + "loss": 3.6535, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.845746391913326e-05, + "loss": 3.6582, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449094350426476e-05, + "loss": 3.6634, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440708402915956e-05, + "loss": 3.6456, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432322455405436e-05, + "loss": 3.648, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8423936507894916e-05, + "loss": 3.6479, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415566939188125e-05, + "loss": 3.6467, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407180991677605e-05, + "loss": 3.65, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.8398795044167085e-05, + "loss": 3.6636, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.8390409096656565e-05, + "loss": 3.6525, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.8382039527949774e-05, + "loss": 3.6518, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837366995924298e-05, + "loss": 3.6511, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836528401173246e-05, + "loss": 3.657, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835689806422195e-05, + "loss": 3.6422, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834851211671143e-05, + "loss": 3.6345, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834012616920091e-05, + "loss": 3.6637, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833174022169039e-05, + "loss": 3.657, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832335427417987e-05, + "loss": 3.6653, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831496832666935e-05, + "loss": 3.6486, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830661513676629e-05, + "loss": 3.6506, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829822918925577e-05, + "loss": 3.6448, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828984324174525e-05, + "loss": 3.6461, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.828145729423473e-05, + "loss": 3.6613, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.827307134672421e-05, + "loss": 3.6338, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826468539921369e-05, + "loss": 3.6751, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825629945170317e-05, + "loss": 3.6531, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.824791350419265e-05, + "loss": 3.6277, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.823956031428959e-05, + "loss": 3.6586, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.823117436677907e-05, + "loss": 3.645, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822278841926855e-05, + "loss": 3.6328, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.821440247175803e-05, + "loss": 3.6541, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.820603290305124e-05, + "loss": 3.6581, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819764695554072e-05, + "loss": 3.6399, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.81892610080302e-05, + "loss": 3.6473, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818087506051968e-05, + "loss": 3.6298, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817248911300916e-05, + "loss": 3.6436, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816410316549864e-05, + "loss": 3.6509, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815573359679186e-05, + "loss": 3.6416, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814734764928134e-05, + "loss": 3.6533, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.813896170177082e-05, + "loss": 3.6439, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.81305757542603e-05, + "loss": 3.6637, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812218980674977e-05, + "loss": 3.6441, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811380385923925e-05, + "loss": 3.6537, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810541791172873e-05, + "loss": 3.647, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.809703196421821e-05, + "loss": 3.6408, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.808866239551142e-05, + "loss": 3.654, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.80802764480009e-05, + "loss": 3.6469, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.8071906879294115e-05, + "loss": 3.6513, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.8063520931783595e-05, + "loss": 3.6521, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.8055134984273075e-05, + "loss": 3.6398, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.8046749036762555e-05, + "loss": 3.6302, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.8038363089252035e-05, + "loss": 3.6455, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.8029993520545244e-05, + "loss": 3.6527, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.8021607573034724e-05, + "loss": 3.6385, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.8013221625524204e-05, + "loss": 3.649, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.8004835678013684e-05, + "loss": 3.6368, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.7996449730503164e-05, + "loss": 3.6402, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.798808016179637e-05, + "loss": 3.6389, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797969421428585e-05, + "loss": 3.6429, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797130826677533e-05, + "loss": 3.6562, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796292231926481e-05, + "loss": 3.6484, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.795453637175429e-05, + "loss": 3.6532, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.794616680304751e-05, + "loss": 3.6378, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.793778085553699e-05, + "loss": 3.6404, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.792939490802647e-05, + "loss": 3.6427, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.792100896051595e-05, + "loss": 3.6515, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.791263939180916e-05, + "loss": 3.6465, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.790425344429864e-05, + "loss": 3.6507, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789586749678812e-05, + "loss": 3.6453, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.78874815492776e-05, + "loss": 3.6414, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787909560176708e-05, + "loss": 3.6467, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787070965425656e-05, + "loss": 3.6429, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.7862340085549766e-05, + "loss": 3.6377, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.7853954138039246e-05, + "loss": 3.6465, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.7845568190528726e-05, + "loss": 3.6377, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783718224301821e-05, + "loss": 3.6407, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782879629550769e-05, + "loss": 3.6389, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.78204267268009e-05, + "loss": 3.6395, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781204077929038e-05, + "loss": 3.6495, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780365483177986e-05, + "loss": 3.6394, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.779526888426934e-05, + "loss": 3.6473, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.778688293675882e-05, + "loss": 3.6519, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.77784969892483e-05, + "loss": 3.6532, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.777012742054151e-05, + "loss": 3.6433, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.776174147303099e-05, + "loss": 3.6436, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.775335552552047e-05, + "loss": 3.6347, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.774496957800995e-05, + "loss": 3.6481, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773658363049943e-05, + "loss": 3.6436, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772819768298891e-05, + "loss": 3.6285, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.771981173547839e-05, + "loss": 3.6412, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.7711442166771607e-05, + "loss": 3.6429, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770305621926108e-05, + "loss": 3.6461, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.7694686650554296e-05, + "loss": 3.6401, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.7686300703043776e-05, + "loss": 3.6422, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.7677914755533255e-05, + "loss": 3.636, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766952880802273e-05, + "loss": 3.6515, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766114286051221e-05, + "loss": 3.6438, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.7652773291805424e-05, + "loss": 3.655, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.7644387344294904e-05, + "loss": 3.6332, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.7636001396784384e-05, + "loss": 3.6435, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627615449273864e-05, + "loss": 3.6487, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.761924588056708e-05, + "loss": 3.6378, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7610859933056553e-05, + "loss": 3.643, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.760247398554603e-05, + "loss": 3.642, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759408803803551e-05, + "loss": 3.6496, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758570209052499e-05, + "loss": 3.6552, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.75773325218182e-05, + "loss": 3.6437, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756894657430768e-05, + "loss": 3.6422, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756056062679716e-05, + "loss": 3.6459, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755217467928664e-05, + "loss": 3.6412, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754378873177612e-05, + "loss": 3.6378, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753541916306934e-05, + "loss": 3.6345, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752703321555882e-05, + "loss": 3.6406, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.75186472680483e-05, + "loss": 3.6352, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751026132053778e-05, + "loss": 3.6407, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8511030673980713, + "eval_runtime": 320.7121, + "eval_samples_per_second": 1189.824, + "eval_steps_per_second": 37.183, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750187537302726e-05, + "loss": 3.6437, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.749348942551674e-05, + "loss": 3.6315, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.748510347800622e-05, + "loss": 3.6363, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.74767175304957e-05, + "loss": 3.6453, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.746834796178891e-05, + "loss": 3.6526, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.745996201427839e-05, + "loss": 3.6388, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.745157606676787e-05, + "loss": 3.645, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.744319011925735e-05, + "loss": 3.6325, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.743480417174683e-05, + "loss": 3.6302, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.742641822423631e-05, + "loss": 3.6386, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418032276725787e-05, + "loss": 3.6434, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409646329215267e-05, + "loss": 3.6347, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740129313931221e-05, + "loss": 3.6404, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.739290719180169e-05, + "loss": 3.6253, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738452124429117e-05, + "loss": 3.6313, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737613529678065e-05, + "loss": 3.6165, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736774934927013e-05, + "loss": 3.6369, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735936340175961e-05, + "loss": 3.6365, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735099383305282e-05, + "loss": 3.6262, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.73426078855423e-05, + "loss": 3.6447, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733422193803178e-05, + "loss": 3.644, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732583599052126e-05, + "loss": 3.6445, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731745004301074e-05, + "loss": 3.6338, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730906409550022e-05, + "loss": 3.6342, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.73006781479897e-05, + "loss": 3.6381, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729229220047918e-05, + "loss": 3.642, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728392263177239e-05, + "loss": 3.6272, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727553668426187e-05, + "loss": 3.64, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.7267167115555085e-05, + "loss": 3.6295, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.7258781168044565e-05, + "loss": 3.6267, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.725039522053404e-05, + "loss": 3.6353, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.724200927302352e-05, + "loss": 3.6416, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.7233623325513e-05, + "loss": 3.6367, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722523737800248e-05, + "loss": 3.645, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.721685143049196e-05, + "loss": 3.6296, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208465482981445e-05, + "loss": 3.6376, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.7200095914274654e-05, + "loss": 3.6433, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.7191709966764134e-05, + "loss": 3.6223, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.7183324019253614e-05, + "loss": 3.6242, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.7174938071743094e-05, + "loss": 3.6263, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.71665685030363e-05, + "loss": 3.6199, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715818255552578e-05, + "loss": 3.6294, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714979660801526e-05, + "loss": 3.6423, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714141066050474e-05, + "loss": 3.6275, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.713305747060168e-05, + "loss": 3.6306, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712467152309117e-05, + "loss": 3.6316, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711628557558065e-05, + "loss": 3.6343, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710789962807013e-05, + "loss": 3.6207, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.709951368055961e-05, + "loss": 3.6117, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.709112773304909e-05, + "loss": 3.638, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.708274178553857e-05, + "loss": 3.6357, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.707435583802805e-05, + "loss": 3.6444, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.7065986269321256e-05, + "loss": 3.6277, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.7057616700614466e-05, + "loss": 3.6267, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.7049230753103946e-05, + "loss": 3.6235, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.7040844805593425e-05, + "loss": 3.6236, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.7032458858082905e-05, + "loss": 3.6374, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.7024072910572385e-05, + "loss": 3.6095, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.7015686963061865e-05, + "loss": 3.6516, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700730101555135e-05, + "loss": 3.6321, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699891506804083e-05, + "loss": 3.6086, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699056187813777e-05, + "loss": 3.6345, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.698217593062725e-05, + "loss": 3.6222, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697378998311673e-05, + "loss": 3.6104, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696540403560621e-05, + "loss": 3.6324, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695703446689942e-05, + "loss": 3.6347, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.69486485193889e-05, + "loss": 3.6154, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694026257187838e-05, + "loss": 3.63, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.693187662436786e-05, + "loss": 3.6051, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.692349067685734e-05, + "loss": 3.6215, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.691510472934682e-05, + "loss": 3.6234, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906735160640035e-05, + "loss": 3.6215, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.6898349213129515e-05, + "loss": 3.6274, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.6889963265618995e-05, + "loss": 3.6231, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.6881577318108475e-05, + "loss": 3.6426, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.6873207749401684e-05, + "loss": 3.6243, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.6864821801891164e-05, + "loss": 3.6326, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.6856435854380644e-05, + "loss": 3.6215, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.6848049906870124e-05, + "loss": 3.6197, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.6839663959359604e-05, + "loss": 3.6348, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.6831278011849084e-05, + "loss": 3.6247, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682290844314229e-05, + "loss": 3.6259, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681452249563177e-05, + "loss": 3.6334, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680613654812126e-05, + "loss": 3.6193, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679775060061074e-05, + "loss": 3.6086, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.678936465310022e-05, + "loss": 3.622, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.678099508439343e-05, + "loss": 3.6317, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.677260913688291e-05, + "loss": 3.6131, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.676422318937239e-05, + "loss": 3.6287, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.675583724186187e-05, + "loss": 3.6198, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.674745129435134e-05, + "loss": 3.6128, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.673908172564456e-05, + "loss": 3.6179, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.673069577813404e-05, + "loss": 3.6207, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.672230983062352e-05, + "loss": 3.6385, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6713923883113e-05, + "loss": 3.6247, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670553793560248e-05, + "loss": 3.6296, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669715198809196e-05, + "loss": 3.619, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668876604058144e-05, + "loss": 3.6164, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.6680396471874646e-05, + "loss": 3.6192, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.6672010524364126e-05, + "loss": 3.6301, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.6663624576853606e-05, + "loss": 3.6281, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.6655238629343086e-05, + "loss": 3.6274, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.6646852681832566e-05, + "loss": 3.6241, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.6638466734322046e-05, + "loss": 3.6166, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.6630080786811526e-05, + "loss": 3.6287, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.6621711218104735e-05, + "loss": 3.6215, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.6613325270594215e-05, + "loss": 3.6167, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.6604939323083695e-05, + "loss": 3.622, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.6596553375573175e-05, + "loss": 3.6196, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.658816742806266e-05, + "loss": 3.6193, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.657979785935587e-05, + "loss": 3.6154, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657141191184535e-05, + "loss": 3.6164, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656302596433483e-05, + "loss": 3.6257, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655464001682431e-05, + "loss": 3.6237, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654625406931379e-05, + "loss": 3.6205, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653786812180327e-05, + "loss": 3.6299, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652948217429275e-05, + "loss": 3.6348, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652111260558596e-05, + "loss": 3.6189, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651272665807544e-05, + "loss": 3.6237, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650434071056492e-05, + "loss": 3.6128, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.64959547630544e-05, + "loss": 3.6248, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648756881554388e-05, + "loss": 3.6216, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.6479199246837095e-05, + "loss": 3.6129, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6470813299326575e-05, + "loss": 3.6148, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462427351816055e-05, + "loss": 3.6235, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454041404305535e-05, + "loss": 3.6248, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.644565545679501e-05, + "loss": 3.6145, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.643726950928449e-05, + "loss": 3.6196, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6428899940577704e-05, + "loss": 3.6188, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.642051399306718e-05, + "loss": 3.6262, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.641212804555666e-05, + "loss": 3.6239, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.640374209804614e-05, + "loss": 3.6337, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.639537252933935e-05, + "loss": 3.611, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.638698658182883e-05, + "loss": 3.6247, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637860063431831e-05, + "loss": 3.6254, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.637021468680779e-05, + "loss": 3.6142, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636182873929727e-05, + "loss": 3.6218, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635345917059048e-05, + "loss": 3.6238, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634507322307996e-05, + "loss": 3.6302, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633668727556944e-05, + "loss": 3.6329, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632830132805892e-05, + "loss": 3.6209, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.631993175935213e-05, + "loss": 3.6212, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631154581184161e-05, + "loss": 3.6252, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.630315986433109e-05, + "loss": 3.6186, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629477391682057e-05, + "loss": 3.6168, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628640434811379e-05, + "loss": 3.6144, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627801840060327e-05, + "loss": 3.6151, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269632453092747e-05, + "loss": 3.6187, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261246505582227e-05, + "loss": 3.614, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.849750280380249, + "eval_runtime": 302.9113, + "eval_samples_per_second": 1259.745, + "eval_steps_per_second": 39.368, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.6252860558071707e-05, + "loss": 3.6213, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244474610561186e-05, + "loss": 3.611, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.6236088663050666e-05, + "loss": 3.6176, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.6227719094343876e-05, + "loss": 3.624, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219333146833355e-05, + "loss": 3.6296, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.6210947199322835e-05, + "loss": 3.618, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.6202561251812315e-05, + "loss": 3.6251, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.6194175304301795e-05, + "loss": 3.6143, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.6185789356791275e-05, + "loss": 3.6087, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.6177403409280755e-05, + "loss": 3.6146, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.6169017461770235e-05, + "loss": 3.6261, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616066427186718e-05, + "loss": 3.6096, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615229470316039e-05, + "loss": 3.6237, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.614390875564987e-05, + "loss": 3.6026, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.613552280813935e-05, + "loss": 3.6075, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612713686062883e-05, + "loss": 3.5979, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611875091311831e-05, + "loss": 3.6179, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.611036496560779e-05, + "loss": 3.6138, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.610197901809727e-05, + "loss": 3.6093, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.609359307058675e-05, + "loss": 3.6151, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.608520712307623e-05, + "loss": 3.6275, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607682117556571e-05, + "loss": 3.6208, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.606843522805519e-05, + "loss": 3.6159, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.606004928054467e-05, + "loss": 3.6116, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051679711837885e-05, + "loss": 3.6213, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.6043293764327365e-05, + "loss": 3.616, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.603490781681684e-05, + "loss": 3.6109, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602652186930632e-05, + "loss": 3.6171, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601816867940326e-05, + "loss": 3.6068, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.600978273189274e-05, + "loss": 3.6039, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600139678438222e-05, + "loss": 3.6191, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.59930108368717e-05, + "loss": 3.6153, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598462488936118e-05, + "loss": 3.6214, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597623894185066e-05, + "loss": 3.6218, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596785299434014e-05, + "loss": 3.6086, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595948342563336e-05, + "loss": 3.6169, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595109747812284e-05, + "loss": 3.6204, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594271153061231e-05, + "loss": 3.6059, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593432558310179e-05, + "loss": 3.6074, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592593963559127e-05, + "loss": 3.5995, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591755368808075e-05, + "loss": 3.6021, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.590916774057023e-05, + "loss": 3.6096, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590078179305971e-05, + "loss": 3.622, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589241222435292e-05, + "loss": 3.6085, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.5884042655646136e-05, + "loss": 3.6064, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.5875656708135616e-05, + "loss": 3.6119, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.5867270760625096e-05, + "loss": 3.6121, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.5858884813114576e-05, + "loss": 3.603, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.5850498865604056e-05, + "loss": 3.5921, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.5842129296897265e-05, + "loss": 3.615, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.5833743349386745e-05, + "loss": 3.62, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.5825357401876225e-05, + "loss": 3.6185, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.5816971454365705e-05, + "loss": 3.6075, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.5808601885658914e-05, + "loss": 3.604, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800215938148394e-05, + "loss": 3.6018, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5791829990637874e-05, + "loss": 3.6009, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783444043127354e-05, + "loss": 3.6176, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775058095616834e-05, + "loss": 3.594, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766672148106314e-05, + "loss": 3.6288, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.57582862005958e-05, + "loss": 3.6105, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.574990025308528e-05, + "loss": 3.5925, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.574154706318222e-05, + "loss": 3.6103, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.57331611156717e-05, + "loss": 3.6034, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.572477516816118e-05, + "loss": 3.592, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.571638922065066e-05, + "loss": 3.6075, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570801965194387e-05, + "loss": 3.6162, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569963370443335e-05, + "loss": 3.5967, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569124775692283e-05, + "loss": 3.6098, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568286180941231e-05, + "loss": 3.5863, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567447586190179e-05, + "loss": 3.6017, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566608991439127e-05, + "loss": 3.6047, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.5657720345684483e-05, + "loss": 3.6039, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.5649334398173963e-05, + "loss": 3.6042, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.5640948450663443e-05, + "loss": 3.604, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563256250315292e-05, + "loss": 3.6188, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.562419293444613e-05, + "loss": 3.6061, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561580698693561e-05, + "loss": 3.6096, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560742103942509e-05, + "loss": 3.6037, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.559903509191457e-05, + "loss": 3.5992, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.559064914440405e-05, + "loss": 3.6153, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558226319689353e-05, + "loss": 3.6042, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557389362818674e-05, + "loss": 3.6037, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556550768067622e-05, + "loss": 3.6146, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.555712173316571e-05, + "loss": 3.6019, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554873578565519e-05, + "loss": 3.5858, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554034983814467e-05, + "loss": 3.6035, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553198026943788e-05, + "loss": 3.6079, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552359432192736e-05, + "loss": 3.5963, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551520837441684e-05, + "loss": 3.6052, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550682242690632e-05, + "loss": 3.6021, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.54984364793958e-05, + "loss": 3.5928, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.5490066910689006e-05, + "loss": 3.6003, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.5481680963178486e-05, + "loss": 3.5977, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473295015667966e-05, + "loss": 3.6142, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5464909068157446e-05, + "loss": 3.6077, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456523120646926e-05, + "loss": 3.61, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448137173136406e-05, + "loss": 3.597, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5439751225625886e-05, + "loss": 3.5962, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431365278115366e-05, + "loss": 3.602, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5422995709408575e-05, + "loss": 3.6101, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414609761898055e-05, + "loss": 3.6062, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406223814387535e-05, + "loss": 3.6077, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5397837866877015e-05, + "loss": 3.6016, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.5389451919366495e-05, + "loss": 3.5957, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.5381065971855975e-05, + "loss": 3.6083, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.5372696403149184e-05, + "loss": 3.6004, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.5364310455638664e-05, + "loss": 3.6016, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.5355924508128144e-05, + "loss": 3.5997, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.5347538560617623e-05, + "loss": 3.5977, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.533915261310711e-05, + "loss": 3.5984, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533076666559659e-05, + "loss": 3.5946, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.53223970968898e-05, + "loss": 3.5949, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531401114937928e-05, + "loss": 3.6087, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530562520186876e-05, + "loss": 3.6041, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529723925435824e-05, + "loss": 3.5983, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.528885330684772e-05, + "loss": 3.609, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.52804673593372e-05, + "loss": 3.6184, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.527209779063041e-05, + "loss": 3.5979, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.526371184311989e-05, + "loss": 3.5999, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525532589560937e-05, + "loss": 3.5975, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524693994809885e-05, + "loss": 3.6042, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523855400058833e-05, + "loss": 3.5994, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.5230184431881544e-05, + "loss": 3.5962, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.5221798484371024e-05, + "loss": 3.5963, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.5213412536860504e-05, + "loss": 3.6059, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.5205026589349984e-05, + "loss": 3.5991, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519665702064319e-05, + "loss": 3.5969, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518827107313267e-05, + "loss": 3.6054, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.517988512562215e-05, + "loss": 3.6008, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517149917811163e-05, + "loss": 3.6018, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.5163113230601106e-05, + "loss": 3.6062, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515474366189432e-05, + "loss": 3.6117, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.51463577143838e-05, + "loss": 3.5965, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.513797176687328e-05, + "loss": 3.6041, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.512958581936276e-05, + "loss": 3.6045, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.512121625065598e-05, + "loss": 3.5965, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.511283030314546e-05, + "loss": 3.5984, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.510444435563493e-05, + "loss": 3.6037, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.509605840812441e-05, + "loss": 3.6135, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508767246061389e-05, + "loss": 3.6124, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.50793028919071e-05, + "loss": 3.603, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507091694439658e-05, + "loss": 3.6019, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506253099688606e-05, + "loss": 3.6062, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505414504937554e-05, + "loss": 3.6023, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504575910186502e-05, + "loss": 3.5946, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.5037389533158235e-05, + "loss": 3.5996, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.5029003585647715e-05, + "loss": 3.5912, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.5020617638137195e-05, + "loss": 3.6, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.5012231690626675e-05, + "loss": 3.5939, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.8499250411987305, + "eval_runtime": 302.7141, + "eval_samples_per_second": 1260.566, + "eval_steps_per_second": 39.394, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.5003845743116155e-05, + "loss": 3.615, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.4995459795605635e-05, + "loss": 3.5872, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987073848095115e-05, + "loss": 3.595, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.4978687900584595e-05, + "loss": 3.6095, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970318331877804e-05, + "loss": 3.6043, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4961932384367284e-05, + "loss": 3.6059, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953546436856764e-05, + "loss": 3.6048, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.4945160489346244e-05, + "loss": 3.5918, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4936774541835724e-05, + "loss": 3.5872, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.4928388594325204e-05, + "loss": 3.6011, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.4920002646814684e-05, + "loss": 3.5985, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.49116330781079e-05, + "loss": 3.5952, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490326350940111e-05, + "loss": 3.6031, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489487756189059e-05, + "loss": 3.5836, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488649161438007e-05, + "loss": 3.5923, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.487810566686955e-05, + "loss": 3.5761, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.486971971935903e-05, + "loss": 3.6004, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.486133377184851e-05, + "loss": 3.591, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485294782433799e-05, + "loss": 3.5948, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484456187682746e-05, + "loss": 3.5968, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483617592931694e-05, + "loss": 3.6045, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482778998180642e-05, + "loss": 3.6042, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.48194040342959e-05, + "loss": 3.5949, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.481101808678539e-05, + "loss": 3.5927, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.48026485180786e-05, + "loss": 3.6039, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.479427894937181e-05, + "loss": 3.5949, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.478589300186129e-05, + "loss": 3.5904, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777507054350766e-05, + "loss": 3.5999, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.4769121106840246e-05, + "loss": 3.5852, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4760735159329726e-05, + "loss": 3.5911, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752349211819206e-05, + "loss": 3.6002, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4743963264308686e-05, + "loss": 3.5963, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4735593695601895e-05, + "loss": 3.5994, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727207748091375e-05, + "loss": 3.6041, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4718821800580855e-05, + "loss": 3.592, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.471043585307034e-05, + "loss": 3.5986, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470204990555982e-05, + "loss": 3.601, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.46936639580493e-05, + "loss": 3.5826, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468527801053878e-05, + "loss": 3.5883, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467690844183199e-05, + "loss": 3.5808, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466852249432147e-05, + "loss": 3.5858, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.466013654681095e-05, + "loss": 3.5905, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465175059930043e-05, + "loss": 3.601, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464336465178991e-05, + "loss": 3.5873, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463499508308312e-05, + "loss": 3.5908, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.46266091355726e-05, + "loss": 3.5921, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461822318806208e-05, + "loss": 3.5941, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.460983724055156e-05, + "loss": 3.5861, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460145129304104e-05, + "loss": 3.5714, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593065345530526e-05, + "loss": 3.5931, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.4584679398020006e-05, + "loss": 3.6041, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457629345050948e-05, + "loss": 3.6009, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.4567923881802695e-05, + "loss": 3.5861, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.4559554313095904e-05, + "loss": 3.5868, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.4551168365585384e-05, + "loss": 3.5846, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.4542782418074864e-05, + "loss": 3.578, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.4534396470564344e-05, + "loss": 3.6052, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.4526010523053824e-05, + "loss": 3.5726, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.45176245755433e-05, + "loss": 3.6087, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.450923862803278e-05, + "loss": 3.5925, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.4500852680522264e-05, + "loss": 3.5759, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449249949061921e-05, + "loss": 3.5935, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448411354310869e-05, + "loss": 3.5859, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.447572759559817e-05, + "loss": 3.5736, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.446734164808765e-05, + "loss": 3.5896, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.445897207938086e-05, + "loss": 3.5964, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.445058613187034e-05, + "loss": 3.5794, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.444220018435982e-05, + "loss": 3.5885, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.44338142368493e-05, + "loss": 3.5681, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.442544466814251e-05, + "loss": 3.5846, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.441705872063199e-05, + "loss": 3.5834, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.440867277312147e-05, + "loss": 3.5875, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440028682561095e-05, + "loss": 3.5843, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439190087810043e-05, + "loss": 3.587, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438351493058991e-05, + "loss": 3.6023, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.437514536188312e-05, + "loss": 3.5879, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.4366759414372596e-05, + "loss": 3.5899, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.4358373466862076e-05, + "loss": 3.5861, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.4349987519351556e-05, + "loss": 3.58, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.4341601571841036e-05, + "loss": 3.5946, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.4333215624330516e-05, + "loss": 3.5845, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.4324846055623725e-05, + "loss": 3.5907, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.4316460108113205e-05, + "loss": 3.5927, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.4308074160602685e-05, + "loss": 3.5889, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.429968821309217e-05, + "loss": 3.5639, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429130226558165e-05, + "loss": 3.5879, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.428293269687486e-05, + "loss": 3.5871, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.427454674936434e-05, + "loss": 3.5779, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.426616080185382e-05, + "loss": 3.586, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.42577748543433e-05, + "loss": 3.5831, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.424940528563651e-05, + "loss": 3.5773, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424101933812599e-05, + "loss": 3.5811, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423263339061547e-05, + "loss": 3.5824, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422424744310495e-05, + "loss": 3.592, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421586149559443e-05, + "loss": 3.5909, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420747554808391e-05, + "loss": 3.5923, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.419908960057339e-05, + "loss": 3.5792, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419070365306287e-05, + "loss": 3.5779, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.4182334084356085e-05, + "loss": 3.5846, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.4173948136845565e-05, + "loss": 3.5935, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.4165562189335045e-05, + "loss": 3.5869, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157176241824525e-05, + "loss": 3.588, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.4148790294314005e-05, + "loss": 3.5845, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.4140420725607214e-05, + "loss": 3.5778, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.4132034778096694e-05, + "loss": 3.5873, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.4123648830586174e-05, + "loss": 3.5835, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115262883075654e-05, + "loss": 3.5823, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.4106876935565134e-05, + "loss": 3.58, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409850736685834e-05, + "loss": 3.5805, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409012141934782e-05, + "loss": 3.578, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.40817354718373e-05, + "loss": 3.5804, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.407334952432679e-05, + "loss": 3.5729, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.406496357681626e-05, + "loss": 3.5898, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.405659400810948e-05, + "loss": 3.5896, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404820806059896e-05, + "loss": 3.5769, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.403982211308843e-05, + "loss": 3.5908, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.403143616557791e-05, + "loss": 3.5992, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.402306659687113e-05, + "loss": 3.5813, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401468064936061e-05, + "loss": 3.5821, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.400629470185008e-05, + "loss": 3.5799, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.399790875433956e-05, + "loss": 3.5837, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398952280682904e-05, + "loss": 3.5808, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.3981153238122257e-05, + "loss": 3.5777, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.3972767290611736e-05, + "loss": 3.5783, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.3964381343101216e-05, + "loss": 3.5854, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3955995395590696e-05, + "loss": 3.5804, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.3947625826883905e-05, + "loss": 3.5847, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.3939239879373385e-05, + "loss": 3.5842, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.3930853931862865e-05, + "loss": 3.5826, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922467984352345e-05, + "loss": 3.5801, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.3914082036841825e-05, + "loss": 3.5944, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.3905712468135034e-05, + "loss": 3.5923, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.3897326520624514e-05, + "loss": 3.5782, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.3888940573113994e-05, + "loss": 3.5816, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388055462560348e-05, + "loss": 3.5894, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.387216867809296e-05, + "loss": 3.5759, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386379910938617e-05, + "loss": 3.5841, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385541316187565e-05, + "loss": 3.5852, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384702721436513e-05, + "loss": 3.5955, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383864126685461e-05, + "loss": 3.5907, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383027169814782e-05, + "loss": 3.5906, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.38218857506373e-05, + "loss": 3.5801, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381349980312678e-05, + "loss": 3.5932, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.380511385561626e-05, + "loss": 3.5806, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379672790810574e-05, + "loss": 3.576, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.378835833939895e-05, + "loss": 3.582, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.3779972391888435e-05, + "loss": 3.5731, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.3771586444377915e-05, + "loss": 3.5846, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.3763200496867395e-05, + "loss": 3.5759, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.848806381225586, + "eval_runtime": 303.0858, + "eval_samples_per_second": 1259.02, + "eval_steps_per_second": 39.345, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3754814549356875e-05, + "loss": 3.5867, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746444980650084e-05, + "loss": 3.5739, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738059033139564e-05, + "loss": 3.5793, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3729673085629044e-05, + "loss": 3.5921, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721287138118524e-05, + "loss": 3.5855, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.371291756941173e-05, + "loss": 3.5932, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.370453162190121e-05, + "loss": 3.5819, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.369614567439069e-05, + "loss": 3.5763, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368775972688017e-05, + "loss": 3.5653, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367937377936965e-05, + "loss": 3.5841, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367100421066287e-05, + "loss": 3.5806, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366261826315235e-05, + "loss": 3.5788, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.365424869444556e-05, + "loss": 3.5908, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364586274693504e-05, + "loss": 3.5632, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363747679942452e-05, + "loss": 3.5709, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.3629090851914e-05, + "loss": 3.5659, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362070490440348e-05, + "loss": 3.5775, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361231895689296e-05, + "loss": 3.5754, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360393300938244e-05, + "loss": 3.5742, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359554706187192e-05, + "loss": 3.5817, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.358716111436139e-05, + "loss": 3.5846, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.357877516685087e-05, + "loss": 3.5852, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570405598144086e-05, + "loss": 3.5814, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562019650633566e-05, + "loss": 3.5744, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.3553633703123046e-05, + "loss": 3.5889, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.3545247755612526e-05, + "loss": 3.5743, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.3536861808102006e-05, + "loss": 3.5756, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.3528475860591486e-05, + "loss": 3.5823, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.3520106291884695e-05, + "loss": 3.5661, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.3511720344374175e-05, + "loss": 3.574, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.3503334396863655e-05, + "loss": 3.5763, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.3494948449353135e-05, + "loss": 3.5804, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.3486578880646344e-05, + "loss": 3.5828, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.3478192933135824e-05, + "loss": 3.5854, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.3469806985625304e-05, + "loss": 3.5742, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.346142103811479e-05, + "loss": 3.5805, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345303509060427e-05, + "loss": 3.5876, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344466552189748e-05, + "loss": 3.5649, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343627957438696e-05, + "loss": 3.5721, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.342789362687644e-05, + "loss": 3.5603, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.341950767936592e-05, + "loss": 3.571, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.34111217318554e-05, + "loss": 3.5682, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.340275216314861e-05, + "loss": 3.589, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.339436621563809e-05, + "loss": 3.5678, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338598026812757e-05, + "loss": 3.5726, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337759432061705e-05, + "loss": 3.5747, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336922475191026e-05, + "loss": 3.5759, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.3360838804399744e-05, + "loss": 3.5703, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.3352452856889224e-05, + "loss": 3.5556, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.3344066909378704e-05, + "loss": 3.5763, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.3335680961868184e-05, + "loss": 3.5833, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.332731139316139e-05, + "loss": 3.5782, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331892544565087e-05, + "loss": 3.5724, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331053949814035e-05, + "loss": 3.5652, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330215355062983e-05, + "loss": 3.5749, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329378398192304e-05, + "loss": 3.5603, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.328539803441252e-05, + "loss": 3.5862, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277012086902e-05, + "loss": 3.5575, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.326862613939148e-05, + "loss": 3.5883, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.326024019188096e-05, + "loss": 3.577, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.325185424437044e-05, + "loss": 3.554, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.324348467566366e-05, + "loss": 3.5754, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.323509872815314e-05, + "loss": 3.5731, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322671278064262e-05, + "loss": 3.5569, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.32183268331321e-05, + "loss": 3.5635, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.320995726442531e-05, + "loss": 3.584, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320157131691479e-05, + "loss": 3.5641, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319318536940427e-05, + "loss": 3.5689, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318479942189375e-05, + "loss": 3.5535, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.317641347438322e-05, + "loss": 3.5687, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.3168043905676436e-05, + "loss": 3.5629, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.3159657958165916e-05, + "loss": 3.5699, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.3151272010655396e-05, + "loss": 3.5673, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.3142886063144876e-05, + "loss": 3.5702, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.3134500115634355e-05, + "loss": 3.5803, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312613054692757e-05, + "loss": 3.5695, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311774459941705e-05, + "loss": 3.5709, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.3109358651906525e-05, + "loss": 3.5724, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3100972704396004e-05, + "loss": 3.5673, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309260313568922e-05, + "loss": 3.5759, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.3084217188178694e-05, + "loss": 3.5686, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.3075831240668173e-05, + "loss": 3.5707, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.3067445293157653e-05, + "loss": 3.5779, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305907572445087e-05, + "loss": 3.5695, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305068977694035e-05, + "loss": 3.5525, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.304230382942983e-05, + "loss": 3.5694, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.303391788191931e-05, + "loss": 3.5676, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.3025548313212525e-05, + "loss": 3.5676, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.3017162365702e-05, + "loss": 3.5648, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.300877641819148e-05, + "loss": 3.5712, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.300039047068096e-05, + "loss": 3.5556, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299202090197417e-05, + "loss": 3.5628, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298363495446365e-05, + "loss": 3.5628, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297524900695313e-05, + "loss": 3.5775, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296686305944261e-05, + "loss": 3.5686, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.295849349073582e-05, + "loss": 3.5791, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.29501075432253e-05, + "loss": 3.5593, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294172159571478e-05, + "loss": 3.563, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.293333564820426e-05, + "loss": 3.567, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.292496607949747e-05, + "loss": 3.5744, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291658013198695e-05, + "loss": 3.5694, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290819418447643e-05, + "loss": 3.5718, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.289980823696591e-05, + "loss": 3.5671, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.289142228945539e-05, + "loss": 3.5616, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.288303634194487e-05, + "loss": 3.5758, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.287466677323808e-05, + "loss": 3.5599, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.286628082572756e-05, + "loss": 3.5643, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285789487821704e-05, + "loss": 3.5655, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.284950893070652e-05, + "loss": 3.5645, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.2841139361999737e-05, + "loss": 3.5627, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.2832753414489216e-05, + "loss": 3.5669, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.2824367466978696e-05, + "loss": 3.5554, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.2815981519468176e-05, + "loss": 3.5713, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.2807611950761386e-05, + "loss": 3.5734, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799226003250865e-05, + "loss": 3.561, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.2790840055740345e-05, + "loss": 3.5763, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.2782454108229825e-05, + "loss": 3.5831, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.2774084539523034e-05, + "loss": 3.5652, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2765698592012514e-05, + "loss": 3.5675, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757312644501994e-05, + "loss": 3.5613, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2748926696991474e-05, + "loss": 3.5667, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.274054074948096e-05, + "loss": 3.5615, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.273217118077417e-05, + "loss": 3.564, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.272378523326365e-05, + "loss": 3.5606, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.271539928575313e-05, + "loss": 3.5709, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.270701333824261e-05, + "loss": 3.5667, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.269864376953582e-05, + "loss": 3.565, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.26902578220253e-05, + "loss": 3.5663, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268187187451478e-05, + "loss": 3.5659, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267348592700426e-05, + "loss": 3.5602, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266509997949374e-05, + "loss": 3.5769, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265673041078695e-05, + "loss": 3.5784, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.264834446327643e-05, + "loss": 3.5658, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.2639958515765915e-05, + "loss": 3.5625, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.2631572568255395e-05, + "loss": 3.5703, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.2623202999548604e-05, + "loss": 3.5621, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.2614817052038084e-05, + "loss": 3.5672, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.2606431104527564e-05, + "loss": 3.5659, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.2598045157017044e-05, + "loss": 3.5846, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.258967558831025e-05, + "loss": 3.5665, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.258128964079973e-05, + "loss": 3.5738, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.257290369328921e-05, + "loss": 3.5621, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256451774577869e-05, + "loss": 3.5767, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.25561481770719e-05, + "loss": 3.5636, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254776222956138e-05, + "loss": 3.5594, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253937628205087e-05, + "loss": 3.5673, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253099033454035e-05, + "loss": 3.5559, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252262076583356e-05, + "loss": 3.568, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.251423481832304e-05, + "loss": 3.5578, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.850602388381958, + "eval_runtime": 303.4645, + "eval_samples_per_second": 1257.449, + "eval_steps_per_second": 39.296, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250584887081252e-05, + "loss": 3.5689, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.2497462923302e-05, + "loss": 3.5609, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248907697579148e-05, + "loss": 3.5594, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248069102828095e-05, + "loss": 3.5757, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.2472321459574166e-05, + "loss": 3.5692, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.2463935512063646e-05, + "loss": 3.5772, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.2455549564553126e-05, + "loss": 3.5617, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.2447163617042606e-05, + "loss": 3.5596, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.2438777669532086e-05, + "loss": 3.5542, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.2430391722021566e-05, + "loss": 3.5667, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.2422022153314775e-05, + "loss": 3.5638, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.2413636205804255e-05, + "loss": 3.5619, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.240526663709747e-05, + "loss": 3.5749, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.239688068958695e-05, + "loss": 3.5474, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2388494742076424e-05, + "loss": 3.5517, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380108794565904e-05, + "loss": 3.552, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.2371722847055384e-05, + "loss": 3.5584, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.2363336899544864e-05, + "loss": 3.5594, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.2354950952034344e-05, + "loss": 3.5607, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.2346565004523824e-05, + "loss": 3.5628, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.2338179057013304e-05, + "loss": 3.5718, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.232980948830652e-05, + "loss": 3.5634, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.2321423540796e-05, + "loss": 3.5663, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231303759328548e-05, + "loss": 3.5587, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230465164577496e-05, + "loss": 3.573, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229628207706817e-05, + "loss": 3.5579, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228789612955765e-05, + "loss": 3.5615, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.227951018204713e-05, + "loss": 3.5613, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.227112423453661e-05, + "loss": 3.5533, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.226275466582982e-05, + "loss": 3.5568, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.22543687183193e-05, + "loss": 3.5591, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.224598277080878e-05, + "loss": 3.5622, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.223759682329826e-05, + "loss": 3.5667, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229227254591473e-05, + "loss": 3.569, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2220841307080953e-05, + "loss": 3.5578, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.221245535957043e-05, + "loss": 3.5637, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.220406941205991e-05, + "loss": 3.5651, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.219568346454939e-05, + "loss": 3.5508, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.21873138958426e-05, + "loss": 3.5548, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.217892794833208e-05, + "loss": 3.5431, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.217054200082156e-05, + "loss": 3.5569, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216215605331104e-05, + "loss": 3.5539, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215377010580052e-05, + "loss": 3.5722, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214540053709373e-05, + "loss": 3.5513, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213701458958321e-05, + "loss": 3.5556, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212862864207269e-05, + "loss": 3.56, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212024269456218e-05, + "loss": 3.5571, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211187312585539e-05, + "loss": 3.5567, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.210348717834487e-05, + "loss": 3.5358, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209510123083435e-05, + "loss": 3.5585, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208671528332383e-05, + "loss": 3.5663, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207832933581331e-05, + "loss": 3.5656, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.2069959767106516e-05, + "loss": 3.5555, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.2061573819595996e-05, + "loss": 3.5479, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.2053187872085476e-05, + "loss": 3.559, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2044801924574956e-05, + "loss": 3.5474, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.2036432355868165e-05, + "loss": 3.5678, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.2028046408357645e-05, + "loss": 3.5405, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.201966046084713e-05, + "loss": 3.575, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.201127451333661e-05, + "loss": 3.5599, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200290494462982e-05, + "loss": 3.539, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.19945189971193e-05, + "loss": 3.556, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198613304960878e-05, + "loss": 3.5621, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197774710209826e-05, + "loss": 3.54, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.1969361154587734e-05, + "loss": 3.5462, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196099158588095e-05, + "loss": 3.5701, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195260563837043e-05, + "loss": 3.5516, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.19442196908599e-05, + "loss": 3.55, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.193583374334938e-05, + "loss": 3.5356, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.19274641746426e-05, + "loss": 3.5525, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.1919078227132085e-05, + "loss": 3.5481, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.191069227962156e-05, + "loss": 3.559, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.190230633211104e-05, + "loss": 3.5479, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.189392038460052e-05, + "loss": 3.5562, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.188553443709e-05, + "loss": 3.5623, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187716486838321e-05, + "loss": 3.5585, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186877892087269e-05, + "loss": 3.5534, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.186039297336217e-05, + "loss": 3.5519, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.185200702585165e-05, + "loss": 3.5553, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.1843637457144856e-05, + "loss": 3.5593, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.1835251509634336e-05, + "loss": 3.5528, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182686556212382e-05, + "loss": 3.5572, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.18184796146133e-05, + "loss": 3.5572, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181011004590651e-05, + "loss": 3.5538, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180172409839599e-05, + "loss": 3.5367, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.179333815088547e-05, + "loss": 3.5537, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178495220337495e-05, + "loss": 3.5519, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.177658263466816e-05, + "loss": 3.5527, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176819668715764e-05, + "loss": 3.552, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.175981073964712e-05, + "loss": 3.5543, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.17514247921366e-05, + "loss": 3.5433, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174303884462608e-05, + "loss": 3.5443, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173466927591929e-05, + "loss": 3.5458, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172628332840878e-05, + "loss": 3.5602, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.171789738089826e-05, + "loss": 3.5545, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.170951143338774e-05, + "loss": 3.5602, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701141864680946e-05, + "loss": 3.5488, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1692755917170426e-05, + "loss": 3.5503, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684369969659906e-05, + "loss": 3.5472, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1675984022149386e-05, + "loss": 3.5611, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.1667614453442595e-05, + "loss": 3.5507, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.1659228505932075e-05, + "loss": 3.5586, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.1650842558421555e-05, + "loss": 3.5511, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.1642456610911035e-05, + "loss": 3.5456, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.1634070663400515e-05, + "loss": 3.563, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162570109469373e-05, + "loss": 3.5425, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161731514718321e-05, + "loss": 3.5471, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160892919967269e-05, + "loss": 3.5526, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.160054325216217e-05, + "loss": 3.5461, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159215730465165e-05, + "loss": 3.546, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158378773594486e-05, + "loss": 3.5504, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157540178843434e-05, + "loss": 3.5413, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.156701584092382e-05, + "loss": 3.5562, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.15586298934133e-05, + "loss": 3.552, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.155026032470651e-05, + "loss": 3.5496, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.154187437719599e-05, + "loss": 3.5603, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.153348842968547e-05, + "loss": 3.5637, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.152510248217495e-05, + "loss": 3.5526, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1516732913468164e-05, + "loss": 3.5525, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508346965957644e-05, + "loss": 3.547, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1499961018447124e-05, + "loss": 3.5488, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1491575070936604e-05, + "loss": 3.5468, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.148320550222981e-05, + "loss": 3.5512, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147481955471929e-05, + "loss": 3.5416, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146643360720877e-05, + "loss": 3.5561, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145804765969825e-05, + "loss": 3.5494, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.144966171218773e-05, + "loss": 3.5522, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144129214348094e-05, + "loss": 3.5514, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143290619597042e-05, + "loss": 3.5466, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.14245202484599e-05, + "loss": 3.5442, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141613430094938e-05, + "loss": 3.5619, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.14077647322426e-05, + "loss": 3.5619, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139937878473208e-05, + "loss": 3.5548, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139099283722156e-05, + "loss": 3.5437, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.138260688971104e-05, + "loss": 3.5507, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137422094220051e-05, + "loss": 3.5489, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1365851373493727e-05, + "loss": 3.5526, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.1357465425983207e-05, + "loss": 3.5554, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.1349079478472686e-05, + "loss": 3.564, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134069353096216e-05, + "loss": 3.5537, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.1332323962255376e-05, + "loss": 3.5614, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.1323938014744855e-05, + "loss": 3.5483, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.1315552067234335e-05, + "loss": 3.5577, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.1307166119723815e-05, + "loss": 3.5453, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.1298780172213295e-05, + "loss": 3.5481, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129041060350651e-05, + "loss": 3.5531, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.1282024655995984e-05, + "loss": 3.5377, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.1273638708485464e-05, + "loss": 3.5541, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.1265252760974944e-05, + "loss": 3.5451, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.8509738445281982, + "eval_runtime": 302.9299, + "eval_samples_per_second": 1259.668, + "eval_steps_per_second": 39.366, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125688319226816e-05, + "loss": 3.5512, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.124849724475763e-05, + "loss": 3.5464, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.124011129724711e-05, + "loss": 3.5435, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.123172534973659e-05, + "loss": 3.5605, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122335578102981e-05, + "loss": 3.5551, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.121496983351929e-05, + "loss": 3.5625, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.120658388600877e-05, + "loss": 3.5481, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119819793849825e-05, + "loss": 3.5467, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.118982836979146e-05, + "loss": 3.5351, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.118144242228094e-05, + "loss": 3.5528, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.117305647477042e-05, + "loss": 3.5476, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.11646705272599e-05, + "loss": 3.547, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.115630095855311e-05, + "loss": 3.5501, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114793138984632e-05, + "loss": 3.5385, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.11395454423358e-05, + "loss": 3.5411, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113115949482528e-05, + "loss": 3.5382, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112277354731476e-05, + "loss": 3.5364, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111438759980424e-05, + "loss": 3.5432, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110600165229372e-05, + "loss": 3.5465, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.10976157047832e-05, + "loss": 3.5443, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108922975727268e-05, + "loss": 3.5576, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108084380976216e-05, + "loss": 3.548, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107247424105537e-05, + "loss": 3.5489, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106408829354485e-05, + "loss": 3.5465, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.105570234603433e-05, + "loss": 3.5557, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.104731639852381e-05, + "loss": 3.5404, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103894682981702e-05, + "loss": 3.5475, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.10305608823065e-05, + "loss": 3.544, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102217493479598e-05, + "loss": 3.5439, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.101378898728546e-05, + "loss": 3.5439, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.100540303977495e-05, + "loss": 3.5415, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997033471068156e-05, + "loss": 3.5518, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.0988647523557636e-05, + "loss": 3.5524, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.0980261576047116e-05, + "loss": 3.5476, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.0971875628536596e-05, + "loss": 3.5465, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.0963506059829805e-05, + "loss": 3.5496, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.0955120112319285e-05, + "loss": 3.5519, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.0946734164808765e-05, + "loss": 3.5344, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.0938348217298245e-05, + "loss": 3.543, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.0929962269787725e-05, + "loss": 3.5274, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.0921592701080934e-05, + "loss": 3.5407, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.0913206753570414e-05, + "loss": 3.5352, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.09048208060599e-05, + "loss": 3.5567, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089643485854938e-05, + "loss": 3.5397, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088804891103886e-05, + "loss": 3.5368, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.087967934233207e-05, + "loss": 3.5454, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.087129339482155e-05, + "loss": 3.5477, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.086290744731103e-05, + "loss": 3.5425, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.085452149980051e-05, + "loss": 3.5235, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.084615193109372e-05, + "loss": 3.5404, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.08377659835832e-05, + "loss": 3.554, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.082938003607268e-05, + "loss": 3.5488, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082099408856216e-05, + "loss": 3.5425, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081262451985537e-05, + "loss": 3.5355, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.0804238572344855e-05, + "loss": 3.5461, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.0795852624834335e-05, + "loss": 3.5285, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.0787466677323814e-05, + "loss": 3.5526, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.0779097108617024e-05, + "loss": 3.5242, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.0770711161106504e-05, + "loss": 3.5549, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.0762325213595983e-05, + "loss": 3.5515, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.0753939266085463e-05, + "loss": 3.5249, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074556969737867e-05, + "loss": 3.5414, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073718374986815e-05, + "loss": 3.5457, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072879780235763e-05, + "loss": 3.5222, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072041185484711e-05, + "loss": 3.5312, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071204228614032e-05, + "loss": 3.5537, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.07036563386298e-05, + "loss": 3.5368, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069527039111929e-05, + "loss": 3.5328, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.068688444360877e-05, + "loss": 3.5271, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067851487490198e-05, + "loss": 3.5362, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067012892739146e-05, + "loss": 3.5301, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066174297988094e-05, + "loss": 3.5445, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065335703237042e-05, + "loss": 3.531, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.0644987463663626e-05, + "loss": 3.5438, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.0636601516153106e-05, + "loss": 3.5451, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.0628215568642586e-05, + "loss": 3.5416, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.061982962113206e-05, + "loss": 3.538, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061144367362154e-05, + "loss": 3.5366, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.0603074104914755e-05, + "loss": 3.5431, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059468815740424e-05, + "loss": 3.5432, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.0586302209893715e-05, + "loss": 3.5386, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0577916262383195e-05, + "loss": 3.5395, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.056954669367641e-05, + "loss": 3.5426, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.056116074616589e-05, + "loss": 3.5389, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0552774798655364e-05, + "loss": 3.5224, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0544388851144844e-05, + "loss": 3.5349, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.053601928243806e-05, + "loss": 3.5379, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.052763333492753e-05, + "loss": 3.5384, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.051924738741701e-05, + "loss": 3.5377, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0510861439906496e-05, + "loss": 3.5362, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0502491871199712e-05, + "loss": 3.5304, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494105923689185e-05, + "loss": 3.5268, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.048571997617867e-05, + "loss": 3.5318, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.047733402866815e-05, + "loss": 3.5441, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0468964459961365e-05, + "loss": 3.5402, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0460578512450838e-05, + "loss": 3.5462, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452192564940318e-05, + "loss": 3.5364, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0443806617429798e-05, + "loss": 3.5329, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043543704872301e-05, + "loss": 3.532, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042705110121249e-05, + "loss": 3.5474, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041866515370197e-05, + "loss": 3.537, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.041027920619145e-05, + "loss": 3.546, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040190963748466e-05, + "loss": 3.5338, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039352368997414e-05, + "loss": 3.5293, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.0385137742463622e-05, + "loss": 3.5498, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.0376751794953102e-05, + "loss": 3.5304, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036838222624631e-05, + "loss": 3.5325, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.035999627873579e-05, + "loss": 3.5355, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035161033122527e-05, + "loss": 3.5368, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034322438371475e-05, + "loss": 3.5286, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0334854815007964e-05, + "loss": 3.5339, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0326468867497444e-05, + "loss": 3.5289, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318082919986924e-05, + "loss": 3.5373, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0309696972476404e-05, + "loss": 3.5399, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.0301327403769613e-05, + "loss": 3.5339, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0292941456259093e-05, + "loss": 3.5416, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0284555508748576e-05, + "loss": 3.5544, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276169561238056e-05, + "loss": 3.5379, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0267799992531265e-05, + "loss": 3.5365, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0259414045020745e-05, + "loss": 3.5302, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251028097510225e-05, + "loss": 3.5332, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0242642149999705e-05, + "loss": 3.5313, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234272581292917e-05, + "loss": 3.5335, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0225886633782397e-05, + "loss": 3.529, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0217500686271877e-05, + "loss": 3.5403, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209114738761357e-05, + "loss": 3.5333, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0200745170054566e-05, + "loss": 3.537, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.0192359222544046e-05, + "loss": 3.5337, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.0183973275033526e-05, + "loss": 3.533, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017558732752301e-05, + "loss": 3.5279, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.016721775881622e-05, + "loss": 3.5452, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.01588318113057e-05, + "loss": 3.5498, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.015044586379518e-05, + "loss": 3.5402, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.014205991628466e-05, + "loss": 3.532, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013367396877414e-05, + "loss": 3.5348, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012530440006735e-05, + "loss": 3.5371, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011691845255683e-05, + "loss": 3.5387, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.010853250504631e-05, + "loss": 3.5382, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010014655753579e-05, + "loss": 3.5474, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0091776988829e-05, + "loss": 3.5369, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.008339104131848e-05, + "loss": 3.5481, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075005093807963e-05, + "loss": 3.5311, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.0066619146297443e-05, + "loss": 3.5414, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.0058249577590652e-05, + "loss": 3.5351, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0049863630080132e-05, + "loss": 3.5291, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0041477682569612e-05, + "loss": 3.5424, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033091735059092e-05, + "loss": 3.5272, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0024705787548572e-05, + "loss": 3.5329, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016336218841785e-05, + "loss": 3.531, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0007950271331265e-05, + "loss": 3.534, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8517770767211914, + "eval_runtime": 302.8223, + "eval_samples_per_second": 1260.115, + "eval_steps_per_second": 39.38, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 2.9999564323820745e-05, + "loss": 3.5287, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.9991178376310225e-05, + "loss": 3.5314, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.9982792428799705e-05, + "loss": 3.543, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.9974422860092917e-05, + "loss": 3.5402, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.9966036912582397e-05, + "loss": 3.5492, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9957650965071877e-05, + "loss": 3.5305, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.9949265017561357e-05, + "loss": 3.529, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.9940895448854566e-05, + "loss": 3.5246, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.9932509501344046e-05, + "loss": 3.5381, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.9924123553833526e-05, + "loss": 3.5334, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.991573760632301e-05, + "loss": 3.5341, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990736803761622e-05, + "loss": 3.5328, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.9898998468909427e-05, + "loss": 3.5247, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9890612521398907e-05, + "loss": 3.5288, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882226573888387e-05, + "loss": 3.5238, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.987384062637787e-05, + "loss": 3.5213, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.986545467886735e-05, + "loss": 3.5301, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.985706873135683e-05, + "loss": 3.5318, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.984868278384631e-05, + "loss": 3.529, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.984029683633579e-05, + "loss": 3.544, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9831910888825264e-05, + "loss": 3.5322, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.982354132011848e-05, + "loss": 3.5359, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815155372607963e-05, + "loss": 3.5307, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9806769425097443e-05, + "loss": 3.5391, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9798383477586916e-05, + "loss": 3.5294, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790013908880132e-05, + "loss": 3.5344, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9781627961369612e-05, + "loss": 3.5292, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.977324201385909e-05, + "loss": 3.5317, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.976485606634857e-05, + "loss": 3.5227, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9756486497641784e-05, + "loss": 3.5288, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748100550131264e-05, + "loss": 3.5395, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9739714602620737e-05, + "loss": 3.533, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.9731328655110217e-05, + "loss": 3.5365, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.9722959086403433e-05, + "loss": 3.5349, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.9714573138892917e-05, + "loss": 3.5289, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970618719138239e-05, + "loss": 3.5407, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.969780124387187e-05, + "loss": 3.5219, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.9689431675165086e-05, + "loss": 3.5296, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.9681045727654562e-05, + "loss": 3.5149, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.9672659780144042e-05, + "loss": 3.5239, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.9664273832633522e-05, + "loss": 3.5222, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.9655887885123002e-05, + "loss": 3.5381, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964751831641621e-05, + "loss": 3.5274, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963913236890569e-05, + "loss": 3.5243, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.963074642139517e-05, + "loss": 3.5318, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622360473884654e-05, + "loss": 3.5297, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9613974526374134e-05, + "loss": 3.5249, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9605604957667343e-05, + "loss": 3.5134, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597219010156823e-05, + "loss": 3.5215, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9588833062646303e-05, + "loss": 3.5413, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9580447115135783e-05, + "loss": 3.5365, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572077546428996e-05, + "loss": 3.5248, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9563691598918476e-05, + "loss": 3.5227, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555305651407956e-05, + "loss": 3.5324, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9546919703897436e-05, + "loss": 3.5155, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9538550135190645e-05, + "loss": 3.5324, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530164187680125e-05, + "loss": 3.5119, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9521778240169608e-05, + "loss": 3.5415, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9513392292659088e-05, + "loss": 3.5316, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505022723952297e-05, + "loss": 3.5174, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9496636776441777e-05, + "loss": 3.5218, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488250828931257e-05, + "loss": 3.537, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9479864881420737e-05, + "loss": 3.5086, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9471478933910217e-05, + "loss": 3.5172, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.946312574400716e-05, + "loss": 3.5377, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.945473979649664e-05, + "loss": 3.5267, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944635384898612e-05, + "loss": 3.5203, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.94379679014756e-05, + "loss": 3.5125, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.942958195396508e-05, + "loss": 3.5179, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.9421196006454558e-05, + "loss": 3.5163, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.941281005894404e-05, + "loss": 3.5316, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940442411143352e-05, + "loss": 3.5147, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939605454272673e-05, + "loss": 3.5298, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.938766859521621e-05, + "loss": 3.5265, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.937928264770569e-05, + "loss": 3.5344, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.937089670019517e-05, + "loss": 3.5205, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.936251075268465e-05, + "loss": 3.5247, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354141183977863e-05, + "loss": 3.5291, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.9345755236467343e-05, + "loss": 3.531, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.9337369288956823e-05, + "loss": 3.5228, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9328983341446303e-05, + "loss": 3.5242, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9320613772739512e-05, + "loss": 3.53, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312227825228995e-05, + "loss": 3.5234, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9303841877718475e-05, + "loss": 3.5139, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9295455930207955e-05, + "loss": 3.5156, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287086361501164e-05, + "loss": 3.5274, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.9278700413990644e-05, + "loss": 3.5284, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.9270314466480124e-05, + "loss": 3.5199, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.9261928518969604e-05, + "loss": 3.5232, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.9253558950262817e-05, + "loss": 3.5167, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.9245173002752297e-05, + "loss": 3.5132, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9236787055241777e-05, + "loss": 3.5166, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9228401107731257e-05, + "loss": 3.5273, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.9220031539024466e-05, + "loss": 3.5254, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921164559151395e-05, + "loss": 3.5316, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920325964400343e-05, + "loss": 3.5286, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.919487369649291e-05, + "loss": 3.5144, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.9186504127786118e-05, + "loss": 3.52, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178118180275598e-05, + "loss": 3.528, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9169732232765078e-05, + "loss": 3.5282, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161346285254558e-05, + "loss": 3.5306, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.915297671654777e-05, + "loss": 3.5188, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.914459076903725e-05, + "loss": 3.5159, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.913620482152673e-05, + "loss": 3.5334, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.912781887401621e-05, + "loss": 3.5138, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.911943292650569e-05, + "loss": 3.5216, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111063357798903e-05, + "loss": 3.5184, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9102677410288383e-05, + "loss": 3.5249, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094291462777863e-05, + "loss": 3.5103, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9085905515267342e-05, + "loss": 3.5208, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.907753594656055e-05, + "loss": 3.5165, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.906914999905003e-05, + "loss": 3.5253, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.906076405153951e-05, + "loss": 3.5234, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9052378104028995e-05, + "loss": 3.5172, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044008535322204e-05, + "loss": 3.5295, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9035622587811684e-05, + "loss": 3.5383, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027236640301164e-05, + "loss": 3.527, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901885069279064e-05, + "loss": 3.5193, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.9010481124083856e-05, + "loss": 3.5195, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.9002095176573336e-05, + "loss": 3.517, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.8993709229062816e-05, + "loss": 3.5231, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.898532328155229e-05, + "loss": 3.5187, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8976953712845505e-05, + "loss": 3.5147, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.8968567765334985e-05, + "loss": 3.5232, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.8960181817824465e-05, + "loss": 3.521, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.8951795870313942e-05, + "loss": 3.5231, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.8943426301607158e-05, + "loss": 3.521, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.8935040354096638e-05, + "loss": 3.5173, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892665440658611e-05, + "loss": 3.517, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918268459075594e-05, + "loss": 3.5303, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.890989889036881e-05, + "loss": 3.5351, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.890151294285829e-05, + "loss": 3.53, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893126995347763e-05, + "loss": 3.5124, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8884741047837243e-05, + "loss": 3.5225, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.887637147913046e-05, + "loss": 3.5222, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.886798553161994e-05, + "loss": 3.5264, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8859599584109415e-05, + "loss": 3.5195, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851213636598895e-05, + "loss": 3.5338, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.884284406789211e-05, + "loss": 3.5211, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8834458120381584e-05, + "loss": 3.5376, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826072172871064e-05, + "loss": 3.5167, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8817686225360548e-05, + "loss": 3.5317, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809316656653764e-05, + "loss": 3.5188, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8800930709143237e-05, + "loss": 3.5174, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8792544761632717e-05, + "loss": 3.5256, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784158814122197e-05, + "loss": 3.5129, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.877578924541541e-05, + "loss": 3.5192, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876740329790489e-05, + "loss": 3.5164, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875901735039437e-05, + "loss": 3.5188, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.854368209838867, + "eval_runtime": 302.443, + "eval_samples_per_second": 1261.696, + "eval_steps_per_second": 39.429, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.875063140288385e-05, + "loss": 3.52, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742261834177058e-05, + "loss": 3.517, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8733875886666538e-05, + "loss": 3.5295, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8725489939156018e-05, + "loss": 3.5248, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.87171039916455e-05, + "loss": 3.5361, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870873442293871e-05, + "loss": 3.5174, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870034847542819e-05, + "loss": 3.517, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869196252791767e-05, + "loss": 3.5096, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868357658040715e-05, + "loss": 3.5244, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.8675207011700363e-05, + "loss": 3.5203, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8666821064189843e-05, + "loss": 3.5181, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8658435116679323e-05, + "loss": 3.5235, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.8650065547972532e-05, + "loss": 3.5055, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.8641679600462012e-05, + "loss": 3.5185, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.8633293652951492e-05, + "loss": 3.5078, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8624907705440972e-05, + "loss": 3.5107, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8616521757930455e-05, + "loss": 3.5135, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608135810419935e-05, + "loss": 3.5154, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8599749862909415e-05, + "loss": 3.5146, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591363915398895e-05, + "loss": 3.5354, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8582994346692104e-05, + "loss": 3.5166, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8574608399181584e-05, + "loss": 3.5191, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.8566222451671064e-05, + "loss": 3.5189, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.8557836504160544e-05, + "loss": 3.5218, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8549466935453756e-05, + "loss": 3.5172, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541080987943236e-05, + "loss": 3.5233, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8532695040432716e-05, + "loss": 3.5125, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524309092922196e-05, + "loss": 3.5185, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8515939524215405e-05, + "loss": 3.5068, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850755357670489e-05, + "loss": 3.5171, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849916762919437e-05, + "loss": 3.5207, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849078168168385e-05, + "loss": 3.5204, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8482412112977058e-05, + "loss": 3.5258, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474026165466538e-05, + "loss": 3.5162, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8465640217956018e-05, + "loss": 3.5189, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457254270445498e-05, + "loss": 3.5229, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844888470173871e-05, + "loss": 3.5121, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.844049875422819e-05, + "loss": 3.5123, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.843211280671767e-05, + "loss": 3.5032, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.842372685920715e-05, + "loss": 3.5091, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.841535729050036e-05, + "loss": 3.5105, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8406971342989842e-05, + "loss": 3.5241, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8398585395479322e-05, + "loss": 3.5148, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390199447968802e-05, + "loss": 3.5109, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8381813500458282e-05, + "loss": 3.5175, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.837344393175149e-05, + "loss": 3.5126, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.836505798424097e-05, + "loss": 3.5154, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.835667203673045e-05, + "loss": 3.5026, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348286089219935e-05, + "loss": 3.5042, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8339916520513144e-05, + "loss": 3.5278, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.8331530573002624e-05, + "loss": 3.5231, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.8323144625492104e-05, + "loss": 3.5095, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.8314758677981584e-05, + "loss": 3.5126, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.8306389109274796e-05, + "loss": 3.5168, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.8298003161764276e-05, + "loss": 3.5022, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8289617214253756e-05, + "loss": 3.5209, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281231266743236e-05, + "loss": 3.4995, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8272861698036445e-05, + "loss": 3.525, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.8264475750525925e-05, + "loss": 3.5212, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.8256089803015405e-05, + "loss": 3.5047, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.8247703855504888e-05, + "loss": 3.5066, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.8239334286798097e-05, + "loss": 3.5213, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.8230948339287577e-05, + "loss": 3.4917, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.8222562391777057e-05, + "loss": 3.5058, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.8214192823070266e-05, + "loss": 3.5214, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.820580687555975e-05, + "loss": 3.5142, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.819742092804923e-05, + "loss": 3.5049, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.818903498053871e-05, + "loss": 3.4986, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.818064903302819e-05, + "loss": 3.5052, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172263085517663e-05, + "loss": 3.5036, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8163877138007143e-05, + "loss": 3.5128, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8155491190496626e-05, + "loss": 3.5028, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147121621789842e-05, + "loss": 3.5187, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8138735674279315e-05, + "loss": 3.5156, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130349726768795e-05, + "loss": 3.519, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8121963779258275e-05, + "loss": 3.5048, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8113594210551488e-05, + "loss": 3.5116, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105208263040967e-05, + "loss": 3.5135, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8096822315530447e-05, + "loss": 3.5138, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8088436368019927e-05, + "loss": 3.5127, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080066799313136e-05, + "loss": 3.5097, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8071680851802616e-05, + "loss": 3.518, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063294904292096e-05, + "loss": 3.5102, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.805490895678158e-05, + "loss": 3.4972, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.804653938807479e-05, + "loss": 3.5032, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.803815344056427e-05, + "loss": 3.5101, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.802976749305375e-05, + "loss": 3.5147, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802138154554323e-05, + "loss": 3.5088, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.801301197683644e-05, + "loss": 3.5062, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.800462602932592e-05, + "loss": 3.5019, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.79962400818154e-05, + "loss": 3.497, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.798785413430488e-05, + "loss": 3.5024, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.797948456559809e-05, + "loss": 3.5138, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797109861808757e-05, + "loss": 3.5117, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.796271267057705e-05, + "loss": 3.5188, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954326723066533e-05, + "loss": 3.5152, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7945940775556013e-05, + "loss": 3.5013, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7937571206849222e-05, + "loss": 3.5075, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929185259338702e-05, + "loss": 3.5098, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7920799311828182e-05, + "loss": 3.5151, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7912413364317662e-05, + "loss": 3.516, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.7904043795610875e-05, + "loss": 3.508, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.7895657848100355e-05, + "loss": 3.502, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.7887271900589835e-05, + "loss": 3.5192, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.7878885953079315e-05, + "loss": 3.5006, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7870516384372524e-05, + "loss": 3.5106, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862130436862004e-05, + "loss": 3.5077, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.7853744489351487e-05, + "loss": 3.5088, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.7845358541840967e-05, + "loss": 3.4975, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.7836988973134176e-05, + "loss": 3.5096, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.7828603025623656e-05, + "loss": 3.5011, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.7820217078113136e-05, + "loss": 3.5109, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.7811831130602616e-05, + "loss": 3.5113, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.780346156189583e-05, + "loss": 3.5012, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.779507561438531e-05, + "loss": 3.5206, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.778668966687479e-05, + "loss": 3.5244, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.777830371936427e-05, + "loss": 3.5143, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.7769934150657477e-05, + "loss": 3.5067, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.7761548203146957e-05, + "loss": 3.5034, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753162255636437e-05, + "loss": 3.5063, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.774477630812592e-05, + "loss": 3.5047, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.773640673941913e-05, + "loss": 3.5118, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.772802079190861e-05, + "loss": 3.5006, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.771963484439809e-05, + "loss": 3.5067, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.771124889688757e-05, + "loss": 3.5116, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7702879328180782e-05, + "loss": 3.5141, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7694493380670262e-05, + "loss": 3.5038, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686107433159742e-05, + "loss": 3.5044, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7677721485649222e-05, + "loss": 3.5101, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.766935191694243e-05, + "loss": 3.5116, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.766096596943191e-05, + "loss": 3.5216, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.765258002192139e-05, + "loss": 3.5173, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644194074410874e-05, + "loss": 3.4993, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7635808126900354e-05, + "loss": 3.51, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7627438558193563e-05, + "loss": 3.5111, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619052610683043e-05, + "loss": 3.5089, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7610666663172523e-05, + "loss": 3.508, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.7602280715662003e-05, + "loss": 3.5178, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.7593911146955216e-05, + "loss": 3.5115, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.7585525199444696e-05, + "loss": 3.525, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.7577139251934176e-05, + "loss": 3.505, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.7568753304423656e-05, + "loss": 3.5158, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.7560383735716865e-05, + "loss": 3.5062, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.7551997788206345e-05, + "loss": 3.504, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.7543611840695828e-05, + "loss": 3.5105, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.7535225893185308e-05, + "loss": 3.5062, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.7526856324478517e-05, + "loss": 3.5061, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.7518470376967997e-05, + "loss": 3.4998, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.7510084429457477e-05, + "loss": 3.5058, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8539671897888184, + "eval_runtime": 303.0675, + "eval_samples_per_second": 1259.096, + "eval_steps_per_second": 39.348, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7501698481946957e-05, + "loss": 3.5044, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493312534436437e-05, + "loss": 3.5031, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.748492658692592e-05, + "loss": 3.5181, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7476540639415393e-05, + "loss": 3.5087, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.746817107070861e-05, + "loss": 3.5257, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.745978512319809e-05, + "loss": 3.503, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7451399175687566e-05, + "loss": 3.506, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443013228177046e-05, + "loss": 3.492, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.743464365947026e-05, + "loss": 3.5116, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.742625771195974e-05, + "loss": 3.5058, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7417871764449215e-05, + "loss": 3.5014, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7409485816938695e-05, + "loss": 3.5149, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401132627035643e-05, + "loss": 3.4944, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7392746679525123e-05, + "loss": 3.5082, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384360732014603e-05, + "loss": 3.4941, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7375974784504083e-05, + "loss": 3.4982, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7367588836993563e-05, + "loss": 3.4957, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359202889483036e-05, + "loss": 3.5058, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.735081694197252e-05, + "loss": 3.5006, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.7342430994462e-05, + "loss": 3.5206, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334061425755215e-05, + "loss": 3.5046, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.732567547824469e-05, + "loss": 3.5067, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.731728953073417e-05, + "loss": 3.5074, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.730890358322365e-05, + "loss": 3.5111, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7300534014516864e-05, + "loss": 3.5025, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729214806700634e-05, + "loss": 3.5105, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728376211949582e-05, + "loss": 3.5024, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.72753761719853e-05, + "loss": 3.503, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726700660327851e-05, + "loss": 3.4921, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725862065576799e-05, + "loss": 3.5047, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.7250234708257473e-05, + "loss": 3.5091, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7241848760746953e-05, + "loss": 3.5059, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7233479192040162e-05, + "loss": 3.5141, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225093244529642e-05, + "loss": 3.5054, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7216707297019122e-05, + "loss": 3.5014, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.7208321349508602e-05, + "loss": 3.5101, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7199951780801815e-05, + "loss": 3.4994, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7191565833291295e-05, + "loss": 3.4977, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183179885780774e-05, + "loss": 3.4886, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7174793938270254e-05, + "loss": 3.4969, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7166424369563464e-05, + "loss": 3.4981, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158038422052943e-05, + "loss": 3.5094, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.7149652474542427e-05, + "loss": 3.5029, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.7141266527031907e-05, + "loss": 3.4926, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.7132896958325116e-05, + "loss": 3.5088, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.7124511010814596e-05, + "loss": 3.5014, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.7116125063304076e-05, + "loss": 3.497, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7107739115793556e-05, + "loss": 3.4925, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099369547086768e-05, + "loss": 3.487, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.7090983599576248e-05, + "loss": 3.5132, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.7082597652065728e-05, + "loss": 3.5094, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.7074211704555208e-05, + "loss": 3.497, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.7065842135848417e-05, + "loss": 3.4977, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.7057472567141633e-05, + "loss": 3.5061, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.704908661963111e-05, + "loss": 3.4861, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.704070067212059e-05, + "loss": 3.5064, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.703231472461007e-05, + "loss": 3.4869, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.702392877709955e-05, + "loss": 3.5087, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.701554282958903e-05, + "loss": 3.5119, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.700715688207851e-05, + "loss": 3.4949, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6998787313371722e-05, + "loss": 3.4904, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990401365861202e-05, + "loss": 3.5105, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982015418350682e-05, + "loss": 3.4807, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6973629470840162e-05, + "loss": 3.4938, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.696525990213337e-05, + "loss": 3.5055, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.695687395462285e-05, + "loss": 3.5031, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6948488007112334e-05, + "loss": 3.4937, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940102059601814e-05, + "loss": 3.4857, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6931732490895023e-05, + "loss": 3.488, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923346543384503e-05, + "loss": 3.489, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6914960595873983e-05, + "loss": 3.501, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6906574648363463e-05, + "loss": 3.4883, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.6898205079656676e-05, + "loss": 3.5075, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.6889819132146156e-05, + "loss": 3.503, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.6881433184635635e-05, + "loss": 3.5053, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.6873047237125115e-05, + "loss": 3.491, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.6864677668418325e-05, + "loss": 3.4972, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.6856291720907804e-05, + "loss": 3.5035, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.6847905773397284e-05, + "loss": 3.4988, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.6839519825886768e-05, + "loss": 3.5016, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.6831150257179977e-05, + "loss": 3.4974, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.6822764309669457e-05, + "loss": 3.5011, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.6814378362158937e-05, + "loss": 3.4997, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.6805992414648417e-05, + "loss": 3.4837, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679762284594163e-05, + "loss": 3.4942, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678923689843111e-05, + "loss": 3.4941, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.678085095092059e-05, + "loss": 3.503, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.677246500341007e-05, + "loss": 3.4953, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764095434703278e-05, + "loss": 3.4937, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6755709487192758e-05, + "loss": 3.4891, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747323539682238e-05, + "loss": 3.4866, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.673893759217172e-05, + "loss": 3.4867, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.673056802346493e-05, + "loss": 3.4977, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.672218207595441e-05, + "loss": 3.508, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.671379612844389e-05, + "loss": 3.5029, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.670541018093337e-05, + "loss": 3.5, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697040612226583e-05, + "loss": 3.4909, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.6688654664716063e-05, + "loss": 3.4973, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.6680268717205543e-05, + "loss": 3.4949, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.6671882769695023e-05, + "loss": 3.5041, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.6663513200988232e-05, + "loss": 3.5029, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.6655127253477712e-05, + "loss": 3.4958, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.6646741305967192e-05, + "loss": 3.4883, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.6638355358456675e-05, + "loss": 3.5079, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6629985789749884e-05, + "loss": 3.4877, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6621599842239364e-05, + "loss": 3.5026, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613213894728844e-05, + "loss": 3.4878, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6604827947218324e-05, + "loss": 3.4986, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596458378511537e-05, + "loss": 3.4864, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588072431001017e-05, + "loss": 3.4985, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6579686483490496e-05, + "loss": 3.4909, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571300535979976e-05, + "loss": 3.4925, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6562930967273186e-05, + "loss": 3.5013, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6554545019762665e-05, + "loss": 3.4877, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546159072252145e-05, + "loss": 3.507, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.653777312474163e-05, + "loss": 3.5091, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529403556034838e-05, + "loss": 3.501, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521017608524318e-05, + "loss": 3.4944, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6512631661013798e-05, + "loss": 3.492, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504245713503278e-05, + "loss": 3.4901, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6495859765992758e-05, + "loss": 3.4922, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.648749019728597e-05, + "loss": 3.4983, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.647910424977545e-05, + "loss": 3.4868, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.647071830226493e-05, + "loss": 3.4969, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646233235475441e-05, + "loss": 3.5002, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645396278604762e-05, + "loss": 3.4991, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.64455768385371e-05, + "loss": 3.4909, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437190891026582e-05, + "loss": 3.4906, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.6428804943516062e-05, + "loss": 3.4991, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642043537480927e-05, + "loss": 3.4979, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641204942729875e-05, + "loss": 3.5033, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.640366347978823e-05, + "loss": 3.5053, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639527753227771e-05, + "loss": 3.4871, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.6386907963570924e-05, + "loss": 3.4983, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.6378522016060404e-05, + "loss": 3.4979, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370136068549884e-05, + "loss": 3.4955, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6361750121039364e-05, + "loss": 3.4944, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353380552332573e-05, + "loss": 3.5071, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6344994604822053e-05, + "loss": 3.4959, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.6336608657311536e-05, + "loss": 3.5118, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.632822270980101e-05, + "loss": 3.4927, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6319853141094225e-05, + "loss": 3.4979, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6311467193583705e-05, + "loss": 3.4968, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303081246073185e-05, + "loss": 3.4917, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.629469529856266e-05, + "loss": 3.4954, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286325729855878e-05, + "loss": 3.4939, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6277939782345357e-05, + "loss": 3.491, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6269553834834837e-05, + "loss": 3.4884, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.626116788732431e-05, + "loss": 3.4925, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8564682006835938, + "eval_runtime": 303.7917, + "eval_samples_per_second": 1256.094, + "eval_steps_per_second": 39.254, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6252798318617526e-05, + "loss": 3.495, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244412371107006e-05, + "loss": 3.4899, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236026423596483e-05, + "loss": 3.5006, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6227640476085963e-05, + "loss": 3.4952, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.621927090737918e-05, + "loss": 3.5176, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.621088495986866e-05, + "loss": 3.4917, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6202499012358135e-05, + "loss": 3.4945, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194113064847615e-05, + "loss": 3.4798, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.618574349614083e-05, + "loss": 3.4984, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177357548630304e-05, + "loss": 3.4956, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6168971601119784e-05, + "loss": 3.4876, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6160585653609264e-05, + "loss": 3.4986, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615221608490248e-05, + "loss": 3.4853, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.6143830137391957e-05, + "loss": 3.4939, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135444189881437e-05, + "loss": 3.4834, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127058242370917e-05, + "loss": 3.4843, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6118672294860397e-05, + "loss": 3.4842, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110286347349877e-05, + "loss": 3.4908, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6101900399839356e-05, + "loss": 3.4873, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6093514452328836e-05, + "loss": 3.5084, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.608514488362205e-05, + "loss": 3.4923, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.607675893611153e-05, + "loss": 3.4983, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606837298860101e-05, + "loss": 3.4922, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.605998704109049e-05, + "loss": 3.4951, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6051617472383698e-05, + "loss": 3.488, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043231524873178e-05, + "loss": 3.4987, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.603484557736266e-05, + "loss": 3.4924, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.602645962985214e-05, + "loss": 3.4855, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.601809006114535e-05, + "loss": 3.4821, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.600970411363483e-05, + "loss": 3.4903, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600131816612431e-05, + "loss": 3.5016, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599293221861379e-05, + "loss": 3.4922, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.5984562649907003e-05, + "loss": 3.5042, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.5976176702396483e-05, + "loss": 3.4928, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5967790754885963e-05, + "loss": 3.4875, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.5959404807375442e-05, + "loss": 3.4956, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595103523866865e-05, + "loss": 3.493, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.594264929115813e-05, + "loss": 3.4812, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.5934263343647615e-05, + "loss": 3.479, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5925877396137095e-05, + "loss": 3.481, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5917507827430304e-05, + "loss": 3.4918, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909121879919784e-05, + "loss": 3.4923, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5900735932409264e-05, + "loss": 3.4924, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892349984898744e-05, + "loss": 3.4805, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5883980416191956e-05, + "loss": 3.4933, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5875594468681436e-05, + "loss": 3.488, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867208521170916e-05, + "loss": 3.4855, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5858822573660396e-05, + "loss": 3.4785, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5850453004953605e-05, + "loss": 3.469, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842067057443085e-05, + "loss": 3.5071, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.583368110993257e-05, + "loss": 3.496, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.582529516242205e-05, + "loss": 3.488, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5816925593715258e-05, + "loss": 3.4889, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5808556025008467e-05, + "loss": 3.4876, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800170077497947e-05, + "loss": 3.4755, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.579178412998743e-05, + "loss": 3.4919, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.578339818247691e-05, + "loss": 3.479, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.577501223496639e-05, + "loss": 3.4893, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576662628745587e-05, + "loss": 3.5038, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575824033994535e-05, + "loss": 3.4831, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.574985439243483e-05, + "loss": 3.4746, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.574148482372804e-05, + "loss": 3.5033, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.5733098876217522e-05, + "loss": 3.4693, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.5724712928707002e-05, + "loss": 3.4796, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571634336000021e-05, + "loss": 3.4974, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.570795741248969e-05, + "loss": 3.4897, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.569957146497917e-05, + "loss": 3.4811, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569118551746865e-05, + "loss": 3.4771, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.5682815948761864e-05, + "loss": 3.4715, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.5674430001251344e-05, + "loss": 3.4747, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.5666044053740824e-05, + "loss": 3.4917, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5657658106230303e-05, + "loss": 3.4746, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649288537523513e-05, + "loss": 3.4959, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5640902590012993e-05, + "loss": 3.488, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5632516642502476e-05, + "loss": 3.497, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624130694991956e-05, + "loss": 3.4818, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5615761126285165e-05, + "loss": 3.482, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607375178774645e-05, + "loss": 3.493, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5598989231264125e-05, + "loss": 3.4822, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5590603283753605e-05, + "loss": 3.4964, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582233715046817e-05, + "loss": 3.4847, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5573847767536297e-05, + "loss": 3.4856, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.5565461820025777e-05, + "loss": 3.4855, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.5557075872515257e-05, + "loss": 3.4735, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.5548689925004737e-05, + "loss": 3.4802, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.5540320356297946e-05, + "loss": 3.4846, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553193440878743e-05, + "loss": 3.4895, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552354846127691e-05, + "loss": 3.4823, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.551517889257012e-05, + "loss": 3.4844, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.55067929450596e-05, + "loss": 3.4769, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.549840699754908e-05, + "loss": 3.473, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.549002105003856e-05, + "loss": 3.4772, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.548165148133177e-05, + "loss": 3.4839, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.547326553382125e-05, + "loss": 3.4955, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.546487958631073e-05, + "loss": 3.4954, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.545649363880021e-05, + "loss": 3.4865, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.544812407009342e-05, + "loss": 3.4744, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.54397381225829e-05, + "loss": 3.4848, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431352175072383e-05, + "loss": 3.4832, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5422966227561856e-05, + "loss": 3.4893, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5414580280051336e-05, + "loss": 3.4893, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406210711344552e-05, + "loss": 3.4847, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5397824763834032e-05, + "loss": 3.4745, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.538943881632351e-05, + "loss": 3.497, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.538105286881299e-05, + "loss": 3.4715, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5372683300106205e-05, + "loss": 3.4907, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364297352595685e-05, + "loss": 3.4732, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5355911405085158e-05, + "loss": 3.4872, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.5347525457574638e-05, + "loss": 3.4756, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339155888867854e-05, + "loss": 3.4845, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.533076994135733e-05, + "loss": 3.4796, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.532238399384681e-05, + "loss": 3.4809, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.531399804633629e-05, + "loss": 3.4864, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.5305628477629506e-05, + "loss": 3.4785, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.5297242530118982e-05, + "loss": 3.493, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.5288856582608462e-05, + "loss": 3.4951, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.5280470635097942e-05, + "loss": 3.4903, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.5272101066391158e-05, + "loss": 3.4812, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526371511888063e-05, + "loss": 3.4826, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525532917137011e-05, + "loss": 3.4767, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.524694322385959e-05, + "loss": 3.4807, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5238573655152804e-05, + "loss": 3.4878, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.5230187707642284e-05, + "loss": 3.4702, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.5221801760131764e-05, + "loss": 3.4855, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.5213415812621244e-05, + "loss": 3.4834, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205046243914453e-05, + "loss": 3.4892, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5196660296403936e-05, + "loss": 3.4794, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188274348893416e-05, + "loss": 3.4809, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5179888401382896e-05, + "loss": 3.48, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5171518832676105e-05, + "loss": 3.4913, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163132885165585e-05, + "loss": 3.4884, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5154746937655065e-05, + "loss": 3.4966, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146360990144545e-05, + "loss": 3.4718, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5137991421437757e-05, + "loss": 3.4891, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5129605473927237e-05, + "loss": 3.4863, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121219526416717e-05, + "loss": 3.4796, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5112833578906197e-05, + "loss": 3.4822, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104464010199406e-05, + "loss": 3.4966, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096078062688886e-05, + "loss": 3.489, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.508769211517837e-05, + "loss": 3.5005, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.507930616766785e-05, + "loss": 3.4795, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.507093659896106e-05, + "loss": 3.4884, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506255065145054e-05, + "loss": 3.4789, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505416470394002e-05, + "loss": 3.4817, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.50457787564295e-05, + "loss": 3.4829, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503740918772271e-05, + "loss": 3.4802, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502902324021219e-05, + "loss": 3.4809, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502063729270167e-05, + "loss": 3.4736, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501225134519115e-05, + "loss": 3.4832, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8571736812591553, + "eval_runtime": 303.6047, + "eval_samples_per_second": 1256.868, + "eval_steps_per_second": 39.278, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500386539768063e-05, + "loss": 3.482, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499547945017011e-05, + "loss": 3.4795, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498709350265959e-05, + "loss": 3.4882, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497870755514907e-05, + "loss": 3.4859, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.4970337986442283e-05, + "loss": 3.4986, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.4961952038931763e-05, + "loss": 3.4844, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.4953566091421243e-05, + "loss": 3.4818, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.4945180143910723e-05, + "loss": 3.4681, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.4936810575203932e-05, + "loss": 3.4825, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.4928424627693416e-05, + "loss": 3.4832, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.4920038680182896e-05, + "loss": 3.4814, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.4911652732672372e-05, + "loss": 3.4816, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.4903283163965585e-05, + "loss": 3.4707, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4894897216455065e-05, + "loss": 3.4822, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4886511268944545e-05, + "loss": 3.4725, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.4878125321434024e-05, + "loss": 3.4714, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.4869755752727237e-05, + "loss": 3.4702, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.4861369805216717e-05, + "loss": 3.4816, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.4852983857706197e-05, + "loss": 3.4734, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.4844597910195673e-05, + "loss": 3.4942, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.4836228341488886e-05, + "loss": 3.4804, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482784239397837e-05, + "loss": 3.4861, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.4819456446467846e-05, + "loss": 3.4808, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811070498957326e-05, + "loss": 3.4793, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.4802700930250538e-05, + "loss": 3.4772, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794314982740018e-05, + "loss": 3.4859, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4785929035229495e-05, + "loss": 3.479, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.477755946652271e-05, + "loss": 3.4786, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.476917351901219e-05, + "loss": 3.4698, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.476078757150167e-05, + "loss": 3.4744, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752401623991147e-05, + "loss": 3.4883, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.474403205528436e-05, + "loss": 3.4814, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.473564610777384e-05, + "loss": 3.4876, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.472726016026332e-05, + "loss": 3.4773, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.47188742127528e-05, + "loss": 3.4802, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.471048826524228e-05, + "loss": 3.486, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702118696535492e-05, + "loss": 3.4824, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469373274902497e-05, + "loss": 3.4666, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.468534680151445e-05, + "loss": 3.4711, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4676960854003932e-05, + "loss": 3.4668, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4668591285297144e-05, + "loss": 3.4759, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.466020533778662e-05, + "loss": 3.4862, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.46518193902761e-05, + "loss": 3.4773, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.464343344276558e-05, + "loss": 3.472, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.4635063874058793e-05, + "loss": 3.4792, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.4626677926548273e-05, + "loss": 3.4736, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.4618291979037753e-05, + "loss": 3.4777, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.4609906031527233e-05, + "loss": 3.4705, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.4601536462820442e-05, + "loss": 3.4537, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.4593150515309922e-05, + "loss": 3.4956, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.4584764567799402e-05, + "loss": 3.4815, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.4576378620288885e-05, + "loss": 3.4814, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.4568009051582095e-05, + "loss": 3.4743, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.4559639482875307e-05, + "loss": 3.4747, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.4551253535364787e-05, + "loss": 3.464, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4542867587854264e-05, + "loss": 3.4779, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534481640343747e-05, + "loss": 3.4712, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526095692833227e-05, + "loss": 3.4757, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4517709745322707e-05, + "loss": 3.4909, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.4509323797812187e-05, + "loss": 3.4712, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.4500937850301667e-05, + "loss": 3.4662, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.4492568281594876e-05, + "loss": 3.4893, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.4484182334084356e-05, + "loss": 3.4587, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447579638657384e-05, + "loss": 3.4679, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446741043906332e-05, + "loss": 3.4812, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459040870356528e-05, + "loss": 3.4774, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.4450654922846008e-05, + "loss": 3.4709, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442268975335488e-05, + "loss": 3.4657, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.44338994066287e-05, + "loss": 3.4573, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.442551345911818e-05, + "loss": 3.4658, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.441712751160766e-05, + "loss": 3.4773, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.440874156409714e-05, + "loss": 3.4643, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.440037199539035e-05, + "loss": 3.4801, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.439198604787983e-05, + "loss": 3.4781, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.438360010036931e-05, + "loss": 3.4852, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375214152858793e-05, + "loss": 3.4698, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4366844584152002e-05, + "loss": 3.4686, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358458636641482e-05, + "loss": 3.48, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350072689130962e-05, + "loss": 3.4674, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4341686741620442e-05, + "loss": 3.4841, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333317172913654e-05, + "loss": 3.4732, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4324931225403134e-05, + "loss": 3.4733, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4316545277892614e-05, + "loss": 3.4786, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308159330382094e-05, + "loss": 3.4605, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4299789761675303e-05, + "loss": 3.4666, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291403814164783e-05, + "loss": 3.4706, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283017866654263e-05, + "loss": 3.4794, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4274631919143743e-05, + "loss": 3.4663, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266262350436956e-05, + "loss": 3.4718, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4257876402926436e-05, + "loss": 3.4641, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.4249490455415915e-05, + "loss": 3.4669, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241104507905392e-05, + "loss": 3.4598, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4232734939198608e-05, + "loss": 3.4744, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.4224348991688088e-05, + "loss": 3.483, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.4215963044177568e-05, + "loss": 3.478, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4207577096667044e-05, + "loss": 3.4801, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199207527960257e-05, + "loss": 3.4637, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4190821580449737e-05, + "loss": 3.4714, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182435632939217e-05, + "loss": 3.472, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.4174049685428697e-05, + "loss": 3.4792, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416568011672191e-05, + "loss": 3.4772, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415729416921139e-05, + "loss": 3.4723, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.4148908221700866e-05, + "loss": 3.4667, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.4140522274190346e-05, + "loss": 3.4834, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413215270548356e-05, + "loss": 3.4625, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.412376675797304e-05, + "loss": 3.4755, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115380810462518e-05, + "loss": 3.4624, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4106994862951998e-05, + "loss": 3.4748, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.409862529424521e-05, + "loss": 3.4629, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.4090239346734687e-05, + "loss": 3.4736, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408185339922417e-05, + "loss": 3.4664, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.407346745171365e-05, + "loss": 3.4719, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065097883006863e-05, + "loss": 3.4733, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.405671193549634e-05, + "loss": 3.4669, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.404832598798582e-05, + "loss": 3.4811, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.40399400404753e-05, + "loss": 3.4845, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.4031570471768515e-05, + "loss": 3.4756, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023184524257992e-05, + "loss": 3.4738, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4014798576747472e-05, + "loss": 3.465, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006412629236952e-05, + "loss": 3.4687, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.399804306053016e-05, + "loss": 3.4674, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.398965711301964e-05, + "loss": 3.48, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981271165509124e-05, + "loss": 3.4564, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3972885217998604e-05, + "loss": 3.4726, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964515649291813e-05, + "loss": 3.4706, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956129701781293e-05, + "loss": 3.4763, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3947743754270773e-05, + "loss": 3.4689, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939357806760253e-05, + "loss": 3.469, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3930988238053466e-05, + "loss": 3.4665, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3922602290542946e-05, + "loss": 3.4785, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.3914216343032425e-05, + "loss": 3.4785, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3905830395521905e-05, + "loss": 3.4808, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897460826815115e-05, + "loss": 3.463, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889074879304594e-05, + "loss": 3.4776, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3880688931794078e-05, + "loss": 3.4746, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872302984283558e-05, + "loss": 3.4684, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.3863933415576767e-05, + "loss": 3.4701, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855547468066247e-05, + "loss": 3.4816, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847161520555727e-05, + "loss": 3.4707, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3838775573045207e-05, + "loss": 3.4936, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.383040600433842e-05, + "loss": 3.4679, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.38220200568279e-05, + "loss": 3.4744, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381363410931738e-05, + "loss": 3.4679, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380524816180686e-05, + "loss": 3.4708, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.3796878593100068e-05, + "loss": 3.4733, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.3788492645589548e-05, + "loss": 3.4693, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378010669807903e-05, + "loss": 3.4729, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377172075056851e-05, + "loss": 3.4555, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376335118186172e-05, + "loss": 3.4735, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.859895706176758, + "eval_runtime": 304.9652, + "eval_samples_per_second": 1251.261, + "eval_steps_per_second": 39.103, + "step": 1602720 + }, + { + "epoch": 1.0, + "learning_rate": 2.37549652343512e-05, + "loss": 3.4732, + "step": 1603072 + }, + { + "epoch": 1.0, + "learning_rate": 2.374657928684068e-05, + "loss": 3.4684, + "step": 1603584 + }, + { + "epoch": 1.0, + "learning_rate": 2.373819333933016e-05, + "loss": 3.4751, + "step": 1604096 + }, + { + "epoch": 1.0, + "learning_rate": 2.3729823770623373e-05, + "loss": 3.4748, + "step": 1604608 + }, + { + "epoch": 1.0, + "learning_rate": 2.3721437823112853e-05, + "loss": 3.4848, + "step": 1605120 + }, + { + "epoch": 1.0, + "learning_rate": 2.3713051875602333e-05, + "loss": 3.4722, + "step": 1605632 + }, + { + "epoch": 1.0, + "learning_rate": 2.3704665928091813e-05, + "loss": 3.4723, + "step": 1606144 + }, + { + "epoch": 1.0, + "learning_rate": 2.3696296359385022e-05, + "loss": 3.4566, + "step": 1606656 + }, + { + "epoch": 1.0, + "learning_rate": 2.3687910411874502e-05, + "loss": 3.4708, + "step": 1607168 + }, + { + "epoch": 1.0, + "learning_rate": 2.3679524464363985e-05, + "loss": 3.4713, + "step": 1607680 + }, + { + "epoch": 1.0, + "learning_rate": 2.3671138516853465e-05, + "loss": 3.4723, + "step": 1608192 + }, + { + "epoch": 1.0, + "learning_rate": 2.3662768948146674e-05, + "loss": 3.4646, + "step": 1608704 + }, + { + "epoch": 1.0, + "learning_rate": 2.3654399379439883e-05, + "loss": 3.4653, + "step": 1609216 + }, + { + "epoch": 1.0, + "learning_rate": 2.3646013431929363e-05, + "loss": 3.4637, + "step": 1609728 + }, + { + "epoch": 1.0, + "learning_rate": 2.3637627484418847e-05, + "loss": 3.462, + "step": 1610240 + }, + { + "epoch": 1.0, + "learning_rate": 2.3629241536908327e-05, + "loss": 3.4565, + "step": 1610752 + }, + { + "epoch": 1.0, + "learning_rate": 2.3620855589397807e-05, + "loss": 3.462, + "step": 1611264 + }, + { + "epoch": 1.0, + "learning_rate": 2.3612469641887286e-05, + "loss": 3.4699, + "step": 1611776 + }, + { + "epoch": 1.0, + "learning_rate": 2.3604083694376763e-05, + "loss": 3.4616, + "step": 1612288 + }, + { + "epoch": 1.0, + "learning_rate": 2.3595697746866243e-05, + "loss": 3.4839, + "step": 1612800 + }, + { + "epoch": 1.0, + "learning_rate": 2.3587328178159455e-05, + "loss": 3.4705, + "step": 1613312 + }, + { + "epoch": 1.0, + "learning_rate": 2.357894223064894e-05, + "loss": 3.4801, + "step": 1613824 + }, + { + "epoch": 1.0, + "learning_rate": 2.3570556283138415e-05, + "loss": 3.4654, + "step": 1614336 + }, + { + "epoch": 1.0, + "learning_rate": 2.3562170335627895e-05, + "loss": 3.4674, + "step": 1614848 + }, + { + "epoch": 1.0, + "learning_rate": 2.3553800766921108e-05, + "loss": 3.4631, + "step": 1615360 + }, + { + "epoch": 1.0, + "learning_rate": 2.3545414819410584e-05, + "loss": 3.4795, + "step": 1615872 + }, + { + "epoch": 1.0, + "learning_rate": 2.3537028871900064e-05, + "loss": 3.4675, + "step": 1616384 + }, + { + "epoch": 1.0, + "learning_rate": 2.3528642924389548e-05, + "loss": 3.4643, + "step": 1616896 + }, + { + "epoch": 1.0, + "learning_rate": 2.352027335568276e-05, + "loss": 3.4601, + "step": 1617408 + }, + { + "epoch": 1.0, + "learning_rate": 2.3511887408172237e-05, + "loss": 3.4654, + "step": 1617920 + }, + { + "epoch": 1.01, + "learning_rate": 2.3503501460661717e-05, + "loss": 3.4707, + "step": 1618432 + }, + { + "epoch": 1.01, + "learning_rate": 2.3495115513151197e-05, + "loss": 3.4734, + "step": 1618944 + }, + { + "epoch": 1.01, + "learning_rate": 2.348674594444441e-05, + "loss": 3.4729, + "step": 1619456 + }, + { + "epoch": 1.01, + "learning_rate": 2.347835999693389e-05, + "loss": 3.471, + "step": 1619968 + }, + { + "epoch": 1.01, + "learning_rate": 2.346997404942337e-05, + "loss": 3.4657, + "step": 1620480 + }, + { + "epoch": 1.01, + "learning_rate": 2.346158810191285e-05, + "loss": 3.4737, + "step": 1620992 + }, + { + "epoch": 1.01, + "learning_rate": 2.3453218533206058e-05, + "loss": 3.4699, + "step": 1621504 + }, + { + "epoch": 1.01, + "learning_rate": 2.3444832585695538e-05, + "loss": 3.4579, + "step": 1622016 + }, + { + "epoch": 1.01, + "learning_rate": 2.3436446638185018e-05, + "loss": 3.4597, + "step": 1622528 + }, + { + "epoch": 1.01, + "learning_rate": 2.34280606906745e-05, + "loss": 3.4532, + "step": 1623040 + }, + { + "epoch": 1.01, + "learning_rate": 2.341969112196771e-05, + "loss": 3.4596, + "step": 1623552 + }, + { + "epoch": 1.01, + "learning_rate": 2.341130517445719e-05, + "loss": 3.4741, + "step": 1624064 + }, + { + "epoch": 1.01, + "learning_rate": 2.340291922694667e-05, + "loss": 3.4692, + "step": 1624576 + }, + { + "epoch": 1.01, + "learning_rate": 2.3394549658239883e-05, + "loss": 3.46, + "step": 1625088 + }, + { + "epoch": 1.01, + "learning_rate": 2.3386163710729363e-05, + "loss": 3.4682, + "step": 1625600 + }, + { + "epoch": 1.01, + "learning_rate": 2.3377777763218843e-05, + "loss": 3.4621, + "step": 1626112 + }, + { + "epoch": 1.01, + "learning_rate": 2.3369391815708323e-05, + "loss": 3.4651, + "step": 1626624 + }, + { + "epoch": 1.01, + "learning_rate": 2.3361022247001532e-05, + "loss": 3.4575, + "step": 1627136 + }, + { + "epoch": 1.01, + "learning_rate": 2.3352636299491012e-05, + "loss": 3.4409, + "step": 1627648 + }, + { + "epoch": 1.01, + "learning_rate": 2.3344250351980492e-05, + "loss": 3.4858, + "step": 1628160 + }, + { + "epoch": 1.01, + "learning_rate": 2.333586440446997e-05, + "loss": 3.4651, + "step": 1628672 + }, + { + "epoch": 1.01, + "learning_rate": 2.3327494835763184e-05, + "loss": 3.4716, + "step": 1629184 + }, + { + "epoch": 1.01, + "learning_rate": 2.3319108888252664e-05, + "loss": 3.4602, + "step": 1629696 + }, + { + "epoch": 1.01, + "learning_rate": 2.3310739319545877e-05, + "loss": 3.4677, + "step": 1630208 + }, + { + "epoch": 1.01, + "learning_rate": 2.3302353372035357e-05, + "loss": 3.4527, + "step": 1630720 + }, + { + "epoch": 1.01, + "learning_rate": 2.3293967424524833e-05, + "loss": 3.4632, + "step": 1631232 + }, + { + "epoch": 1.01, + "learning_rate": 2.3285581477014316e-05, + "loss": 3.4624, + "step": 1631744 + }, + { + "epoch": 1.01, + "learning_rate": 2.3277195529503796e-05, + "loss": 3.4636, + "step": 1632256 + }, + { + "epoch": 1.01, + "learning_rate": 2.3268809581993276e-05, + "loss": 3.4798, + "step": 1632768 + }, + { + "epoch": 1.01, + "learning_rate": 2.3260423634482756e-05, + "loss": 3.4573, + "step": 1633280 + }, + { + "epoch": 1.01, + "learning_rate": 2.3252037686972236e-05, + "loss": 3.4513, + "step": 1633792 + }, + { + "epoch": 1.01, + "learning_rate": 2.3243668118265445e-05, + "loss": 3.4795, + "step": 1634304 + }, + { + "epoch": 1.01, + "learning_rate": 2.3235282170754925e-05, + "loss": 3.4454, + "step": 1634816 + }, + { + "epoch": 1.01, + "learning_rate": 2.322689622324441e-05, + "loss": 3.4543, + "step": 1635328 + }, + { + "epoch": 1.01, + "learning_rate": 2.321851027573389e-05, + "loss": 3.4698, + "step": 1635840 + }, + { + "epoch": 1.01, + "learning_rate": 2.321015708583083e-05, + "loss": 3.4689, + "step": 1636352 + }, + { + "epoch": 1.01, + "learning_rate": 2.3201771138320307e-05, + "loss": 3.4543, + "step": 1636864 + }, + { + "epoch": 1.01, + "learning_rate": 2.3193385190809787e-05, + "loss": 3.4591, + "step": 1637376 + }, + { + "epoch": 1.01, + "learning_rate": 2.318499924329927e-05, + "loss": 3.4435, + "step": 1637888 + }, + { + "epoch": 1.01, + "learning_rate": 2.317661329578875e-05, + "loss": 3.4562, + "step": 1638400 + }, + { + "epoch": 1.01, + "learning_rate": 2.316822734827823e-05, + "loss": 3.4642, + "step": 1638912 + }, + { + "epoch": 1.01, + "learning_rate": 2.315984140076771e-05, + "loss": 3.4519, + "step": 1639424 + }, + { + "epoch": 1.01, + "learning_rate": 2.315147183206092e-05, + "loss": 3.4672, + "step": 1639936 + }, + { + "epoch": 1.01, + "learning_rate": 2.31430858845504e-05, + "loss": 3.4624, + "step": 1640448 + }, + { + "epoch": 1.01, + "learning_rate": 2.313469993703988e-05, + "loss": 3.4783, + "step": 1640960 + }, + { + "epoch": 1.01, + "learning_rate": 2.3126313989529362e-05, + "loss": 3.4567, + "step": 1641472 + }, + { + "epoch": 1.01, + "learning_rate": 2.311794442082257e-05, + "loss": 3.4615, + "step": 1641984 + }, + { + "epoch": 1.01, + "learning_rate": 2.310955847331205e-05, + "loss": 3.4664, + "step": 1642496 + }, + { + "epoch": 1.01, + "learning_rate": 2.310117252580153e-05, + "loss": 3.4576, + "step": 1643008 + }, + { + "epoch": 1.01, + "learning_rate": 2.309278657829101e-05, + "loss": 3.4693, + "step": 1643520 + }, + { + "epoch": 1.01, + "learning_rate": 2.3084417009584224e-05, + "loss": 3.4644, + "step": 1644032 + }, + { + "epoch": 1.01, + "learning_rate": 2.3076031062073704e-05, + "loss": 3.4621, + "step": 1644544 + }, + { + "epoch": 1.01, + "learning_rate": 2.3067645114563184e-05, + "loss": 3.4673, + "step": 1645056 + }, + { + "epoch": 1.01, + "learning_rate": 2.305925916705266e-05, + "loss": 3.4513, + "step": 1645568 + }, + { + "epoch": 1.01, + "learning_rate": 2.3050889598345873e-05, + "loss": 3.4501, + "step": 1646080 + }, + { + "epoch": 1.01, + "learning_rate": 2.3042503650835353e-05, + "loss": 3.4611, + "step": 1646592 + }, + { + "epoch": 1.01, + "learning_rate": 2.3034117703324833e-05, + "loss": 3.4665, + "step": 1647104 + }, + { + "epoch": 1.01, + "learning_rate": 2.3025731755814313e-05, + "loss": 3.4564, + "step": 1647616 + }, + { + "epoch": 1.01, + "learning_rate": 2.3017362187107525e-05, + "loss": 3.4612, + "step": 1648128 + }, + { + "epoch": 1.02, + "learning_rate": 2.3008976239597005e-05, + "loss": 3.4492, + "step": 1648640 + }, + { + "epoch": 1.02, + "learning_rate": 2.3000590292086485e-05, + "loss": 3.4578, + "step": 1649152 + }, + { + "epoch": 1.02, + "learning_rate": 2.299220434457596e-05, + "loss": 3.4504, + "step": 1649664 + }, + { + "epoch": 1.02, + "learning_rate": 2.2983834775869174e-05, + "loss": 3.4608, + "step": 1650176 + }, + { + "epoch": 1.02, + "learning_rate": 2.2975448828358657e-05, + "loss": 3.4751, + "step": 1650688 + }, + { + "epoch": 1.02, + "learning_rate": 2.2967062880848134e-05, + "loss": 3.464, + "step": 1651200 + }, + { + "epoch": 1.02, + "learning_rate": 2.2958676933337614e-05, + "loss": 3.4673, + "step": 1651712 + }, + { + "epoch": 1.02, + "learning_rate": 2.2950307364630826e-05, + "loss": 3.4516, + "step": 1652224 + }, + { + "epoch": 1.02, + "learning_rate": 2.2941921417120306e-05, + "loss": 3.4584, + "step": 1652736 + }, + { + "epoch": 1.02, + "learning_rate": 2.2933535469609786e-05, + "loss": 3.4585, + "step": 1653248 + }, + { + "epoch": 1.02, + "learning_rate": 2.2925149522099266e-05, + "loss": 3.4684, + "step": 1653760 + }, + { + "epoch": 1.02, + "learning_rate": 2.291677995339248e-05, + "loss": 3.4616, + "step": 1654272 + }, + { + "epoch": 1.02, + "learning_rate": 2.2908394005881955e-05, + "loss": 3.4663, + "step": 1654784 + }, + { + "epoch": 1.02, + "learning_rate": 2.2900008058371435e-05, + "loss": 3.4537, + "step": 1655296 + }, + { + "epoch": 1.02, + "learning_rate": 2.2891622110860915e-05, + "loss": 3.4681, + "step": 1655808 + }, + { + "epoch": 1.02, + "learning_rate": 2.2883252542154128e-05, + "loss": 3.4534, + "step": 1656320 + }, + { + "epoch": 1.02, + "learning_rate": 2.2874866594643608e-05, + "loss": 3.465, + "step": 1656832 + }, + { + "epoch": 1.02, + "learning_rate": 2.2866480647133088e-05, + "loss": 3.4494, + "step": 1657344 + }, + { + "epoch": 1.02, + "learning_rate": 2.2858094699622568e-05, + "loss": 3.4641, + "step": 1657856 + }, + { + "epoch": 1.02, + "learning_rate": 2.284972513091578e-05, + "loss": 3.453, + "step": 1658368 + }, + { + "epoch": 1.02, + "learning_rate": 2.2841339183405257e-05, + "loss": 3.4612, + "step": 1658880 + }, + { + "epoch": 1.02, + "learning_rate": 2.283295323589474e-05, + "loss": 3.4556, + "step": 1659392 + }, + { + "epoch": 1.02, + "learning_rate": 2.282456728838422e-05, + "loss": 3.4617, + "step": 1659904 + }, + { + "epoch": 1.02, + "learning_rate": 2.281619771967743e-05, + "loss": 3.4598, + "step": 1660416 + }, + { + "epoch": 1.02, + "learning_rate": 2.280781177216691e-05, + "loss": 3.4563, + "step": 1660928 + }, + { + "epoch": 1.02, + "learning_rate": 2.279942582465639e-05, + "loss": 3.4666, + "step": 1661440 + }, + { + "epoch": 1.02, + "learning_rate": 2.279103987714587e-05, + "loss": 3.4704, + "step": 1661952 + }, + { + "epoch": 1.02, + "learning_rate": 2.278267030843908e-05, + "loss": 3.4663, + "step": 1662464 + }, + { + "epoch": 1.02, + "learning_rate": 2.277428436092856e-05, + "loss": 3.4641, + "step": 1662976 + }, + { + "epoch": 1.02, + "learning_rate": 2.276589841341804e-05, + "loss": 3.4507, + "step": 1663488 + }, + { + "epoch": 1.02, + "learning_rate": 2.275751246590752e-05, + "loss": 3.4561, + "step": 1664000 + }, + { + "epoch": 1.02, + "learning_rate": 2.274914289720073e-05, + "loss": 3.4578, + "step": 1664512 + }, + { + "epoch": 1.02, + "learning_rate": 2.274075694969021e-05, + "loss": 3.4663, + "step": 1665024 + }, + { + "epoch": 1.02, + "learning_rate": 2.2732371002179694e-05, + "loss": 3.4449, + "step": 1665536 + }, + { + "epoch": 1.02, + "learning_rate": 2.2723985054669174e-05, + "loss": 3.4598, + "step": 1666048 + }, + { + "epoch": 1.02, + "learning_rate": 2.2715615485962383e-05, + "loss": 3.4605, + "step": 1666560 + }, + { + "epoch": 1.02, + "learning_rate": 2.2707229538451863e-05, + "loss": 3.4623, + "step": 1667072 + }, + { + "epoch": 1.02, + "learning_rate": 2.2698843590941343e-05, + "loss": 3.4582, + "step": 1667584 + }, + { + "epoch": 1.02, + "learning_rate": 2.2690457643430823e-05, + "loss": 3.46, + "step": 1668096 + }, + { + "epoch": 1.02, + "learning_rate": 2.2682088074724035e-05, + "loss": 3.4563, + "step": 1668608 + }, + { + "epoch": 1.02, + "learning_rate": 2.2673702127213515e-05, + "loss": 3.4679, + "step": 1669120 + }, + { + "epoch": 1.02, + "learning_rate": 2.2665316179702995e-05, + "loss": 3.4664, + "step": 1669632 + }, + { + "epoch": 1.02, + "learning_rate": 2.2656930232192475e-05, + "loss": 3.4704, + "step": 1670144 + }, + { + "epoch": 1.02, + "learning_rate": 2.2648560663485684e-05, + "loss": 3.449, + "step": 1670656 + }, + { + "epoch": 1.02, + "learning_rate": 2.2640174715975164e-05, + "loss": 3.467, + "step": 1671168 + }, + { + "epoch": 1.02, + "learning_rate": 2.2631788768464647e-05, + "loss": 3.4624, + "step": 1671680 + }, + { + "epoch": 1.02, + "learning_rate": 2.2623402820954127e-05, + "loss": 3.4562, + "step": 1672192 + }, + { + "epoch": 1.02, + "learning_rate": 2.2615033252247336e-05, + "loss": 3.4594, + "step": 1672704 + }, + { + "epoch": 1.02, + "learning_rate": 2.2606647304736816e-05, + "loss": 3.4686, + "step": 1673216 + }, + { + "epoch": 1.02, + "learning_rate": 2.2598261357226296e-05, + "loss": 3.4634, + "step": 1673728 + }, + { + "epoch": 1.02, + "learning_rate": 2.2589875409715776e-05, + "loss": 3.4792, + "step": 1674240 + }, + { + "epoch": 1.02, + "learning_rate": 2.258150584100899e-05, + "loss": 3.4576, + "step": 1674752 + }, + { + "epoch": 1.02, + "learning_rate": 2.257311989349847e-05, + "loss": 3.4613, + "step": 1675264 + }, + { + "epoch": 1.02, + "learning_rate": 2.256473394598795e-05, + "loss": 3.4586, + "step": 1675776 + }, + { + "epoch": 1.02, + "learning_rate": 2.255634799847743e-05, + "loss": 3.461, + "step": 1676288 + }, + { + "epoch": 1.02, + "learning_rate": 2.2547978429770638e-05, + "loss": 3.4587, + "step": 1676800 + }, + { + "epoch": 1.02, + "learning_rate": 2.2539592482260118e-05, + "loss": 3.4542, + "step": 1677312 + }, + { + "epoch": 1.02, + "learning_rate": 2.2531206534749598e-05, + "loss": 3.4637, + "step": 1677824 + }, + { + "epoch": 1.02, + "learning_rate": 2.252282058723908e-05, + "loss": 3.4421, + "step": 1678336 + }, + { + "epoch": 1.02, + "learning_rate": 2.251445101853229e-05, + "loss": 3.4643, + "step": 1678848 + }, + { + "epoch": 1.03, + "eval_loss": 3.861781597137451, + "eval_runtime": 304.6158, + "eval_samples_per_second": 1252.696, + "eval_steps_per_second": 39.148, + "step": 1679040 + }, + { + "epoch": 0.0, + "learning_rate": 2.250606507102177e-05, + "loss": 3.4635, + "step": 1679360 + }, + { + "epoch": 0.0, + "learning_rate": 2.249767912351125e-05, + "loss": 3.4563, + "step": 1679872 + }, + { + "epoch": 0.0, + "learning_rate": 2.248929317600073e-05, + "loss": 3.4623, + "step": 1680384 + }, + { + "epoch": 0.0, + "learning_rate": 2.248090722849021e-05, + "loss": 3.4635, + "step": 1680896 + }, + { + "epoch": 0.0, + "learning_rate": 2.2472537659783422e-05, + "loss": 3.475, + "step": 1681408 + }, + { + "epoch": 0.0, + "learning_rate": 2.2464151712272902e-05, + "loss": 3.4593, + "step": 1681920 + }, + { + "epoch": 0.0, + "learning_rate": 2.2455765764762382e-05, + "loss": 3.4605, + "step": 1682432 + }, + { + "epoch": 0.0, + "learning_rate": 2.244737981725186e-05, + "loss": 3.4468, + "step": 1682944 + }, + { + "epoch": 0.0, + "learning_rate": 2.243901024854507e-05, + "loss": 3.4594, + "step": 1683456 + }, + { + "epoch": 0.0, + "learning_rate": 2.243062430103455e-05, + "loss": 3.459, + "step": 1683968 + }, + { + "epoch": 0.0, + "learning_rate": 2.242223835352403e-05, + "loss": 3.4607, + "step": 1684480 + }, + { + "epoch": 0.0, + "learning_rate": 2.241385240601351e-05, + "loss": 3.4543, + "step": 1684992 + }, + { + "epoch": 0.0, + "learning_rate": 2.2405499216110453e-05, + "loss": 3.453, + "step": 1685504 + }, + { + "epoch": 0.0, + "learning_rate": 2.2397113268599933e-05, + "loss": 3.4531, + "step": 1686016 + }, + { + "epoch": 0.0, + "learning_rate": 2.2388727321089413e-05, + "loss": 3.4542, + "step": 1686528 + }, + { + "epoch": 0.0, + "learning_rate": 2.2380341373578896e-05, + "loss": 3.4459, + "step": 1687040 + }, + { + "epoch": 0.0, + "learning_rate": 2.2371955426068376e-05, + "loss": 3.4495, + "step": 1687552 + }, + { + "epoch": 0.0, + "learning_rate": 2.2363569478557856e-05, + "loss": 3.4563, + "step": 1688064 + }, + { + "epoch": 0.0, + "learning_rate": 2.2355183531047333e-05, + "loss": 3.4509, + "step": 1688576 + }, + { + "epoch": 0.0, + "learning_rate": 2.2346797583536813e-05, + "loss": 3.4684, + "step": 1689088 + }, + { + "epoch": 0.0, + "learning_rate": 2.2338428014830025e-05, + "loss": 3.4593, + "step": 1689600 + }, + { + "epoch": 0.0, + "learning_rate": 2.2330042067319505e-05, + "loss": 3.4681, + "step": 1690112 + }, + { + "epoch": 0.0, + "learning_rate": 2.2321656119808985e-05, + "loss": 3.4496, + "step": 1690624 + }, + { + "epoch": 0.0, + "learning_rate": 2.2313270172298465e-05, + "loss": 3.4571, + "step": 1691136 + }, + { + "epoch": 0.0, + "learning_rate": 2.2304900603591677e-05, + "loss": 3.4531, + "step": 1691648 + }, + { + "epoch": 0.0, + "learning_rate": 2.2296514656081154e-05, + "loss": 3.4668, + "step": 1692160 + }, + { + "epoch": 0.0, + "learning_rate": 2.2288128708570634e-05, + "loss": 3.4552, + "step": 1692672 + }, + { + "epoch": 0.0, + "learning_rate": 2.2279742761060117e-05, + "loss": 3.4579, + "step": 1693184 + }, + { + "epoch": 0.0, + "learning_rate": 2.2271373192353326e-05, + "loss": 3.4489, + "step": 1693696 + }, + { + "epoch": 0.0, + "learning_rate": 2.2262987244842806e-05, + "loss": 3.4511, + "step": 1694208 + }, + { + "epoch": 0.01, + "learning_rate": 2.2254601297332286e-05, + "loss": 3.4561, + "step": 1694720 + }, + { + "epoch": 0.01, + "learning_rate": 2.2246215349821766e-05, + "loss": 3.4649, + "step": 1695232 + }, + { + "epoch": 0.01, + "learning_rate": 2.223784578111498e-05, + "loss": 3.463, + "step": 1695744 + }, + { + "epoch": 0.01, + "learning_rate": 2.222945983360446e-05, + "loss": 3.4577, + "step": 1696256 + }, + { + "epoch": 0.01, + "learning_rate": 2.222107388609394e-05, + "loss": 3.4543, + "step": 1696768 + }, + { + "epoch": 0.01, + "learning_rate": 2.221268793858342e-05, + "loss": 3.4556, + "step": 1697280 + }, + { + "epoch": 0.01, + "learning_rate": 2.2204318369876628e-05, + "loss": 3.4594, + "step": 1697792 + }, + { + "epoch": 0.01, + "learning_rate": 2.2195932422366108e-05, + "loss": 3.4487, + "step": 1698304 + }, + { + "epoch": 0.01, + "learning_rate": 2.2187546474855588e-05, + "loss": 3.4455, + "step": 1698816 + }, + { + "epoch": 0.01, + "learning_rate": 2.217916052734507e-05, + "loss": 3.4424, + "step": 1699328 + }, + { + "epoch": 0.01, + "learning_rate": 2.217079095863828e-05, + "loss": 3.4505, + "step": 1699840 + }, + { + "epoch": 0.01, + "learning_rate": 2.216240501112776e-05, + "loss": 3.4572, + "step": 1700352 + }, + { + "epoch": 0.01, + "learning_rate": 2.215401906361724e-05, + "loss": 3.4573, + "step": 1700864 + }, + { + "epoch": 0.01, + "learning_rate": 2.214563311610672e-05, + "loss": 3.449, + "step": 1701376 + }, + { + "epoch": 0.01, + "learning_rate": 2.2137263547399932e-05, + "loss": 3.4533, + "step": 1701888 + }, + { + "epoch": 0.01, + "learning_rate": 2.2128877599889412e-05, + "loss": 3.4532, + "step": 1702400 + }, + { + "epoch": 0.01, + "learning_rate": 2.2120491652378892e-05, + "loss": 3.4553, + "step": 1702912 + }, + { + "epoch": 0.01, + "learning_rate": 2.21121220836721e-05, + "loss": 3.4441, + "step": 1703424 + }, + { + "epoch": 0.01, + "learning_rate": 2.210373613616158e-05, + "loss": 3.4274, + "step": 1703936 + }, + { + "epoch": 0.01, + "learning_rate": 2.209535018865106e-05, + "loss": 3.4708, + "step": 1704448 + }, + { + "epoch": 0.01, + "learning_rate": 2.208696424114054e-05, + "loss": 3.4542, + "step": 1704960 + }, + { + "epoch": 0.01, + "learning_rate": 2.2078594672433754e-05, + "loss": 3.4632, + "step": 1705472 + }, + { + "epoch": 0.01, + "learning_rate": 2.2070208724923234e-05, + "loss": 3.4525, + "step": 1705984 + }, + { + "epoch": 0.01, + "learning_rate": 2.2061822777412714e-05, + "loss": 3.4511, + "step": 1706496 + }, + { + "epoch": 0.01, + "learning_rate": 2.2053436829902194e-05, + "loss": 3.4412, + "step": 1707008 + }, + { + "epoch": 0.01, + "learning_rate": 2.2045067261195403e-05, + "loss": 3.4504, + "step": 1707520 + }, + { + "epoch": 0.01, + "learning_rate": 2.2036681313684886e-05, + "loss": 3.4535, + "step": 1708032 + }, + { + "epoch": 0.01, + "learning_rate": 2.2028295366174366e-05, + "loss": 3.4496, + "step": 1708544 + }, + { + "epoch": 0.01, + "learning_rate": 2.2019909418663846e-05, + "loss": 3.4695, + "step": 1709056 + }, + { + "epoch": 0.01, + "learning_rate": 2.2011539849957055e-05, + "loss": 3.4488, + "step": 1709568 + }, + { + "epoch": 0.01, + "learning_rate": 2.2003153902446535e-05, + "loss": 3.4397, + "step": 1710080 + }, + { + "epoch": 0.01, + "learning_rate": 2.1994767954936015e-05, + "loss": 3.466, + "step": 1710592 + }, + { + "epoch": 0.01, + "learning_rate": 2.1986382007425495e-05, + "loss": 3.4381, + "step": 1711104 + }, + { + "epoch": 0.01, + "learning_rate": 2.1978012438718707e-05, + "loss": 3.436, + "step": 1711616 + }, + { + "epoch": 0.01, + "learning_rate": 2.1969626491208187e-05, + "loss": 3.4635, + "step": 1712128 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961240543697667e-05, + "loss": 3.4564, + "step": 1712640 + }, + { + "epoch": 0.01, + "learning_rate": 2.1952854596187147e-05, + "loss": 3.4417, + "step": 1713152 + }, + { + "epoch": 0.01, + "learning_rate": 2.1944485027480356e-05, + "loss": 3.448, + "step": 1713664 + }, + { + "epoch": 0.01, + "learning_rate": 2.1936099079969836e-05, + "loss": 3.4355, + "step": 1714176 + }, + { + "epoch": 0.01, + "learning_rate": 2.192771313245932e-05, + "loss": 3.446, + "step": 1714688 + }, + { + "epoch": 0.01, + "learning_rate": 2.19193271849488e-05, + "loss": 3.4491, + "step": 1715200 + }, + { + "epoch": 0.01, + "learning_rate": 2.191095761624201e-05, + "loss": 3.4426, + "step": 1715712 + }, + { + "epoch": 0.01, + "learning_rate": 2.190257166873149e-05, + "loss": 3.4539, + "step": 1716224 + }, + { + "epoch": 0.01, + "learning_rate": 2.189418572122097e-05, + "loss": 3.4551, + "step": 1716736 + }, + { + "epoch": 0.01, + "learning_rate": 2.188579977371045e-05, + "loss": 3.4627, + "step": 1717248 + }, + { + "epoch": 0.01, + "learning_rate": 2.187743020500366e-05, + "loss": 3.4471, + "step": 1717760 + }, + { + "epoch": 0.01, + "learning_rate": 2.186904425749314e-05, + "loss": 3.4492, + "step": 1718272 + }, + { + "epoch": 0.01, + "learning_rate": 2.186065830998262e-05, + "loss": 3.4536, + "step": 1718784 + }, + { + "epoch": 0.01, + "learning_rate": 2.18522723624721e-05, + "loss": 3.4463, + "step": 1719296 + }, + { + "epoch": 0.01, + "learning_rate": 2.184390279376531e-05, + "loss": 3.4582, + "step": 1719808 + }, + { + "epoch": 0.01, + "learning_rate": 2.183551684625479e-05, + "loss": 3.4537, + "step": 1720320 + }, + { + "epoch": 0.01, + "learning_rate": 2.1827130898744273e-05, + "loss": 3.45, + "step": 1720832 + }, + { + "epoch": 0.01, + "learning_rate": 2.1818744951233753e-05, + "loss": 3.461, + "step": 1721344 + }, + { + "epoch": 0.01, + "learning_rate": 2.1810375382526962e-05, + "loss": 3.4351, + "step": 1721856 + }, + { + "epoch": 0.01, + "learning_rate": 2.1801989435016442e-05, + "loss": 3.4409, + "step": 1722368 + }, + { + "epoch": 0.01, + "learning_rate": 2.1793603487505922e-05, + "loss": 3.4513, + "step": 1722880 + }, + { + "epoch": 0.01, + "learning_rate": 2.1785217539995402e-05, + "loss": 3.4549, + "step": 1723392 + }, + { + "epoch": 0.01, + "learning_rate": 2.1776847971288615e-05, + "loss": 3.4474, + "step": 1723904 + }, + { + "epoch": 0.01, + "learning_rate": 2.1768462023778095e-05, + "loss": 3.451, + "step": 1724416 + }, + { + "epoch": 0.02, + "learning_rate": 2.1760076076267575e-05, + "loss": 3.4355, + "step": 1724928 + }, + { + "epoch": 0.02, + "learning_rate": 2.175169012875705e-05, + "loss": 3.4462, + "step": 1725440 + }, + { + "epoch": 0.02, + "learning_rate": 2.1743320560050264e-05, + "loss": 3.4401, + "step": 1725952 + }, + { + "epoch": 0.02, + "learning_rate": 2.1734934612539744e-05, + "loss": 3.4494, + "step": 1726464 + }, + { + "epoch": 0.02, + "learning_rate": 2.1726548665029227e-05, + "loss": 3.4626, + "step": 1726976 + }, + { + "epoch": 0.02, + "learning_rate": 2.1718162717518704e-05, + "loss": 3.4517, + "step": 1727488 + }, + { + "epoch": 0.02, + "learning_rate": 2.1709793148811916e-05, + "loss": 3.4567, + "step": 1728000 + }, + { + "epoch": 0.02, + "learning_rate": 2.1701407201301396e-05, + "loss": 3.4402, + "step": 1728512 + }, + { + "epoch": 0.02, + "learning_rate": 2.1693021253790873e-05, + "loss": 3.4448, + "step": 1729024 + }, + { + "epoch": 0.02, + "learning_rate": 2.1684635306280356e-05, + "loss": 3.4444, + "step": 1729536 + }, + { + "epoch": 0.02, + "learning_rate": 2.167626573757357e-05, + "loss": 3.4606, + "step": 1730048 + }, + { + "epoch": 0.02, + "learning_rate": 2.166787979006305e-05, + "loss": 3.4523, + "step": 1730560 + }, + { + "epoch": 0.02, + "learning_rate": 2.1659493842552525e-05, + "loss": 3.4557, + "step": 1731072 + }, + { + "epoch": 0.02, + "learning_rate": 2.1651107895042005e-05, + "loss": 3.4412, + "step": 1731584 + }, + { + "epoch": 0.02, + "learning_rate": 2.1642738326335217e-05, + "loss": 3.4526, + "step": 1732096 + }, + { + "epoch": 0.02, + "learning_rate": 2.1634352378824697e-05, + "loss": 3.4453, + "step": 1732608 + }, + { + "epoch": 0.02, + "learning_rate": 2.1625966431314177e-05, + "loss": 3.4518, + "step": 1733120 + }, + { + "epoch": 0.02, + "learning_rate": 2.1617580483803657e-05, + "loss": 3.4369, + "step": 1733632 + }, + { + "epoch": 0.02, + "learning_rate": 2.160921091509687e-05, + "loss": 3.452, + "step": 1734144 + }, + { + "epoch": 0.02, + "learning_rate": 2.1600824967586346e-05, + "loss": 3.4391, + "step": 1734656 + }, + { + "epoch": 0.02, + "learning_rate": 2.1592439020075826e-05, + "loss": 3.4511, + "step": 1735168 + }, + { + "epoch": 0.02, + "learning_rate": 2.1584053072565306e-05, + "loss": 3.4422, + "step": 1735680 + }, + { + "epoch": 0.02, + "learning_rate": 2.1575683503858522e-05, + "loss": 3.4545, + "step": 1736192 + }, + { + "epoch": 0.02, + "learning_rate": 2.1567297556348e-05, + "loss": 3.4445, + "step": 1736704 + }, + { + "epoch": 0.02, + "learning_rate": 2.155891160883748e-05, + "loss": 3.4465, + "step": 1737216 + }, + { + "epoch": 0.02, + "learning_rate": 2.155052566132696e-05, + "loss": 3.4577, + "step": 1737728 + }, + { + "epoch": 0.02, + "learning_rate": 2.154213971381644e-05, + "loss": 3.46, + "step": 1738240 + }, + { + "epoch": 0.02, + "learning_rate": 2.153375376630592e-05, + "loss": 3.4571, + "step": 1738752 + }, + { + "epoch": 0.02, + "learning_rate": 2.15253678187954e-05, + "loss": 3.4499, + "step": 1739264 + }, + { + "epoch": 0.02, + "learning_rate": 2.151698187128488e-05, + "loss": 3.4437, + "step": 1739776 + }, + { + "epoch": 0.02, + "learning_rate": 2.150861230257809e-05, + "loss": 3.4433, + "step": 1740288 + }, + { + "epoch": 0.02, + "learning_rate": 2.150022635506757e-05, + "loss": 3.4497, + "step": 1740800 + }, + { + "epoch": 0.02, + "learning_rate": 2.149184040755705e-05, + "loss": 3.4515, + "step": 1741312 + }, + { + "epoch": 0.02, + "learning_rate": 2.1483454460046527e-05, + "loss": 3.4358, + "step": 1741824 + }, + { + "epoch": 0.02, + "learning_rate": 2.1475084891339743e-05, + "loss": 3.45, + "step": 1742336 + }, + { + "epoch": 0.02, + "learning_rate": 2.1466698943829223e-05, + "loss": 3.45, + "step": 1742848 + }, + { + "epoch": 0.02, + "learning_rate": 2.1458312996318703e-05, + "loss": 3.4502, + "step": 1743360 + }, + { + "epoch": 0.02, + "learning_rate": 2.144992704880818e-05, + "loss": 3.4478, + "step": 1743872 + }, + { + "epoch": 0.02, + "learning_rate": 2.1441557480101392e-05, + "loss": 3.4475, + "step": 1744384 + }, + { + "epoch": 0.02, + "learning_rate": 2.1433171532590872e-05, + "loss": 3.4431, + "step": 1744896 + }, + { + "epoch": 0.02, + "learning_rate": 2.1424785585080352e-05, + "loss": 3.4583, + "step": 1745408 + }, + { + "epoch": 0.02, + "learning_rate": 2.1416416016373565e-05, + "loss": 3.4563, + "step": 1745920 + }, + { + "epoch": 0.02, + "learning_rate": 2.1408030068863044e-05, + "loss": 3.4571, + "step": 1746432 + }, + { + "epoch": 0.02, + "learning_rate": 2.1399644121352524e-05, + "loss": 3.4401, + "step": 1746944 + }, + { + "epoch": 0.02, + "learning_rate": 2.1391258173842e-05, + "loss": 3.455, + "step": 1747456 + }, + { + "epoch": 0.02, + "learning_rate": 2.138287222633148e-05, + "loss": 3.4496, + "step": 1747968 + }, + { + "epoch": 0.02, + "learning_rate": 2.1374502657624697e-05, + "loss": 3.4448, + "step": 1748480 + }, + { + "epoch": 0.02, + "learning_rate": 2.1366116710114177e-05, + "loss": 3.4541, + "step": 1748992 + }, + { + "epoch": 0.02, + "learning_rate": 2.1357730762603653e-05, + "loss": 3.4517, + "step": 1749504 + }, + { + "epoch": 0.02, + "learning_rate": 2.1349361193896866e-05, + "loss": 3.4519, + "step": 1750016 + }, + { + "epoch": 0.02, + "learning_rate": 2.1340975246386346e-05, + "loss": 3.4669, + "step": 1750528 + }, + { + "epoch": 0.02, + "learning_rate": 2.1332589298875826e-05, + "loss": 3.4466, + "step": 1751040 + }, + { + "epoch": 0.02, + "learning_rate": 2.1324203351365306e-05, + "loss": 3.4509, + "step": 1751552 + }, + { + "epoch": 0.02, + "learning_rate": 2.1315817403854786e-05, + "loss": 3.4531, + "step": 1752064 + }, + { + "epoch": 0.02, + "learning_rate": 2.1307431456344266e-05, + "loss": 3.4506, + "step": 1752576 + }, + { + "epoch": 0.02, + "learning_rate": 2.1299045508833746e-05, + "loss": 3.444, + "step": 1753088 + }, + { + "epoch": 0.02, + "learning_rate": 2.1290659561323226e-05, + "loss": 3.4434, + "step": 1753600 + }, + { + "epoch": 0.02, + "learning_rate": 2.1282289992616435e-05, + "loss": 3.4515, + "step": 1754112 + }, + { + "epoch": 0.02, + "learning_rate": 2.1273904045105918e-05, + "loss": 3.4359, + "step": 1754624 + }, + { + "epoch": 0.02, + "learning_rate": 2.1265518097595398e-05, + "loss": 3.4536, + "step": 1755136 + }, + { + "epoch": 0.03, + "eval_loss": 3.8627891540527344, + "eval_runtime": 305.6401, + "eval_samples_per_second": 1248.498, + "eval_steps_per_second": 39.016, + "step": 1755360 + }, + { + "epoch": 1.0, + "learning_rate": 2.1257132150084878e-05, + "loss": 3.4488, + "step": 1755648 + }, + { + "epoch": 1.0, + "learning_rate": 2.1248762581378087e-05, + "loss": 3.4442, + "step": 1756160 + }, + { + "epoch": 1.0, + "learning_rate": 2.1240376633867567e-05, + "loss": 3.4473, + "step": 1756672 + }, + { + "epoch": 1.0, + "learning_rate": 2.1231990686357047e-05, + "loss": 3.4532, + "step": 1757184 + }, + { + "epoch": 1.0, + "learning_rate": 2.1223604738846527e-05, + "loss": 3.4615, + "step": 1757696 + }, + { + "epoch": 1.0, + "learning_rate": 2.121523517013974e-05, + "loss": 3.4479, + "step": 1758208 + }, + { + "epoch": 1.0, + "learning_rate": 2.120684922262922e-05, + "loss": 3.4518, + "step": 1758720 + }, + { + "epoch": 1.0, + "learning_rate": 2.11984632751187e-05, + "loss": 3.4384, + "step": 1759232 + }, + { + "epoch": 1.0, + "learning_rate": 2.119007732760818e-05, + "loss": 3.4402, + "step": 1759744 + }, + { + "epoch": 1.0, + "learning_rate": 2.1181707758901388e-05, + "loss": 3.4534, + "step": 1760256 + }, + { + "epoch": 1.0, + "learning_rate": 2.1173321811390868e-05, + "loss": 3.4467, + "step": 1760768 + }, + { + "epoch": 1.0, + "learning_rate": 2.116493586388035e-05, + "loss": 3.4417, + "step": 1761280 + }, + { + "epoch": 1.0, + "learning_rate": 2.115656629517356e-05, + "loss": 3.4505, + "step": 1761792 + }, + { + "epoch": 1.0, + "learning_rate": 2.114818034766304e-05, + "loss": 3.4366, + "step": 1762304 + }, + { + "epoch": 1.0, + "learning_rate": 2.113979440015252e-05, + "loss": 3.4392, + "step": 1762816 + }, + { + "epoch": 1.0, + "learning_rate": 2.1131408452642e-05, + "loss": 3.437, + "step": 1763328 + }, + { + "epoch": 1.0, + "learning_rate": 2.112302250513148e-05, + "loss": 3.4382, + "step": 1763840 + }, + { + "epoch": 1.0, + "learning_rate": 2.111463655762096e-05, + "loss": 3.4483, + "step": 1764352 + }, + { + "epoch": 1.0, + "learning_rate": 2.110625061011044e-05, + "loss": 3.4361, + "step": 1764864 + }, + { + "epoch": 1.0, + "learning_rate": 2.109786466259992e-05, + "loss": 3.463, + "step": 1765376 + }, + { + "epoch": 1.0, + "learning_rate": 2.108949509389313e-05, + "loss": 3.4488, + "step": 1765888 + }, + { + "epoch": 1.0, + "learning_rate": 2.108110914638261e-05, + "loss": 3.4564, + "step": 1766400 + }, + { + "epoch": 1.0, + "learning_rate": 2.107272319887209e-05, + "loss": 3.4395, + "step": 1766912 + }, + { + "epoch": 1.0, + "learning_rate": 2.1064337251361573e-05, + "loss": 3.443, + "step": 1767424 + }, + { + "epoch": 1.0, + "learning_rate": 2.1055967682654782e-05, + "loss": 3.4483, + "step": 1767936 + }, + { + "epoch": 1.0, + "learning_rate": 2.1047581735144262e-05, + "loss": 3.4511, + "step": 1768448 + }, + { + "epoch": 1.0, + "learning_rate": 2.1039195787633742e-05, + "loss": 3.4446, + "step": 1768960 + }, + { + "epoch": 1.0, + "learning_rate": 2.1030809840123222e-05, + "loss": 3.4483, + "step": 1769472 + }, + { + "epoch": 1.0, + "learning_rate": 2.1022440271416434e-05, + "loss": 3.4378, + "step": 1769984 + }, + { + "epoch": 1.0, + "learning_rate": 2.1014054323905914e-05, + "loss": 3.4386, + "step": 1770496 + }, + { + "epoch": 1.01, + "learning_rate": 2.1005668376395394e-05, + "loss": 3.4454, + "step": 1771008 + }, + { + "epoch": 1.01, + "learning_rate": 2.0997282428884874e-05, + "loss": 3.4534, + "step": 1771520 + }, + { + "epoch": 1.01, + "learning_rate": 2.0988912860178083e-05, + "loss": 3.4503, + "step": 1772032 + }, + { + "epoch": 1.01, + "learning_rate": 2.0980526912667563e-05, + "loss": 3.4512, + "step": 1772544 + }, + { + "epoch": 1.01, + "learning_rate": 2.0972140965157043e-05, + "loss": 3.4436, + "step": 1773056 + }, + { + "epoch": 1.01, + "learning_rate": 2.0963755017646526e-05, + "loss": 3.4434, + "step": 1773568 + }, + { + "epoch": 1.01, + "learning_rate": 2.0955385448939735e-05, + "loss": 3.4505, + "step": 1774080 + }, + { + "epoch": 1.01, + "learning_rate": 2.0946999501429215e-05, + "loss": 3.4377, + "step": 1774592 + }, + { + "epoch": 1.01, + "learning_rate": 2.0938613553918695e-05, + "loss": 3.4357, + "step": 1775104 + }, + { + "epoch": 1.01, + "learning_rate": 2.0930227606408175e-05, + "loss": 3.4298, + "step": 1775616 + }, + { + "epoch": 1.01, + "learning_rate": 2.0921858037701388e-05, + "loss": 3.4396, + "step": 1776128 + }, + { + "epoch": 1.01, + "learning_rate": 2.0913472090190868e-05, + "loss": 3.44, + "step": 1776640 + }, + { + "epoch": 1.01, + "learning_rate": 2.0905086142680348e-05, + "loss": 3.4485, + "step": 1777152 + }, + { + "epoch": 1.01, + "learning_rate": 2.0896700195169828e-05, + "loss": 3.4427, + "step": 1777664 + }, + { + "epoch": 1.01, + "learning_rate": 2.0888330626463037e-05, + "loss": 3.4397, + "step": 1778176 + }, + { + "epoch": 1.01, + "learning_rate": 2.0879944678952517e-05, + "loss": 3.4447, + "step": 1778688 + }, + { + "epoch": 1.01, + "learning_rate": 2.0871558731441997e-05, + "loss": 3.4452, + "step": 1779200 + }, + { + "epoch": 1.01, + "learning_rate": 2.086318916273521e-05, + "loss": 3.4332, + "step": 1779712 + }, + { + "epoch": 1.01, + "learning_rate": 2.085480321522469e-05, + "loss": 3.418, + "step": 1780224 + }, + { + "epoch": 1.01, + "learning_rate": 2.084641726771417e-05, + "loss": 3.455, + "step": 1780736 + }, + { + "epoch": 1.01, + "learning_rate": 2.083803132020365e-05, + "loss": 3.4473, + "step": 1781248 + }, + { + "epoch": 1.01, + "learning_rate": 2.0829661751496858e-05, + "loss": 3.4534, + "step": 1781760 + }, + { + "epoch": 1.01, + "learning_rate": 2.0821275803986338e-05, + "loss": 3.4404, + "step": 1782272 + }, + { + "epoch": 1.01, + "learning_rate": 2.081288985647582e-05, + "loss": 3.4408, + "step": 1782784 + }, + { + "epoch": 1.01, + "learning_rate": 2.08045039089653e-05, + "loss": 3.4324, + "step": 1783296 + }, + { + "epoch": 1.01, + "learning_rate": 2.079613434025851e-05, + "loss": 3.4376, + "step": 1783808 + }, + { + "epoch": 1.01, + "learning_rate": 2.078774839274799e-05, + "loss": 3.4477, + "step": 1784320 + }, + { + "epoch": 1.01, + "learning_rate": 2.077936244523747e-05, + "loss": 3.4308, + "step": 1784832 + }, + { + "epoch": 1.01, + "learning_rate": 2.077097649772695e-05, + "loss": 3.46, + "step": 1785344 + }, + { + "epoch": 1.01, + "learning_rate": 2.0762606929020163e-05, + "loss": 3.4428, + "step": 1785856 + }, + { + "epoch": 1.01, + "learning_rate": 2.0754220981509643e-05, + "loss": 3.4212, + "step": 1786368 + }, + { + "epoch": 1.01, + "learning_rate": 2.0745835033999123e-05, + "loss": 3.4544, + "step": 1786880 + }, + { + "epoch": 1.01, + "learning_rate": 2.0737449086488603e-05, + "loss": 3.4297, + "step": 1787392 + }, + { + "epoch": 1.01, + "learning_rate": 2.0729079517781812e-05, + "loss": 3.4242, + "step": 1787904 + }, + { + "epoch": 1.01, + "learning_rate": 2.0720693570271292e-05, + "loss": 3.4523, + "step": 1788416 + }, + { + "epoch": 1.01, + "learning_rate": 2.0712307622760775e-05, + "loss": 3.4432, + "step": 1788928 + }, + { + "epoch": 1.01, + "learning_rate": 2.0703921675250255e-05, + "loss": 3.4308, + "step": 1789440 + }, + { + "epoch": 1.01, + "learning_rate": 2.0695552106543464e-05, + "loss": 3.4373, + "step": 1789952 + }, + { + "epoch": 1.01, + "learning_rate": 2.0687166159032944e-05, + "loss": 3.4269, + "step": 1790464 + }, + { + "epoch": 1.01, + "learning_rate": 2.0678780211522424e-05, + "loss": 3.4336, + "step": 1790976 + }, + { + "epoch": 1.01, + "learning_rate": 2.0670394264011904e-05, + "loss": 3.4423, + "step": 1791488 + }, + { + "epoch": 1.01, + "learning_rate": 2.0662024695305117e-05, + "loss": 3.4325, + "step": 1792000 + }, + { + "epoch": 1.01, + "learning_rate": 2.0653638747794596e-05, + "loss": 3.4441, + "step": 1792512 + }, + { + "epoch": 1.01, + "learning_rate": 2.0645252800284076e-05, + "loss": 3.4392, + "step": 1793024 + }, + { + "epoch": 1.01, + "learning_rate": 2.0636866852773553e-05, + "loss": 3.4496, + "step": 1793536 + }, + { + "epoch": 1.01, + "learning_rate": 2.0628497284066766e-05, + "loss": 3.4361, + "step": 1794048 + }, + { + "epoch": 1.01, + "learning_rate": 2.0620111336556245e-05, + "loss": 3.4419, + "step": 1794560 + }, + { + "epoch": 1.01, + "learning_rate": 2.061172538904573e-05, + "loss": 3.4407, + "step": 1795072 + }, + { + "epoch": 1.01, + "learning_rate": 2.0603339441535205e-05, + "loss": 3.4335, + "step": 1795584 + }, + { + "epoch": 1.01, + "learning_rate": 2.0594969872828418e-05, + "loss": 3.4479, + "step": 1796096 + }, + { + "epoch": 1.01, + "learning_rate": 2.0586583925317898e-05, + "loss": 3.4434, + "step": 1796608 + }, + { + "epoch": 1.01, + "learning_rate": 2.0578197977807374e-05, + "loss": 3.4357, + "step": 1797120 + }, + { + "epoch": 1.01, + "learning_rate": 2.0569812030296858e-05, + "loss": 3.4522, + "step": 1797632 + }, + { + "epoch": 1.01, + "learning_rate": 2.056144246159007e-05, + "loss": 3.4235, + "step": 1798144 + }, + { + "epoch": 1.01, + "learning_rate": 2.055305651407955e-05, + "loss": 3.4269, + "step": 1798656 + }, + { + "epoch": 1.01, + "learning_rate": 2.0544670566569027e-05, + "loss": 3.4426, + "step": 1799168 + }, + { + "epoch": 1.01, + "learning_rate": 2.0536284619058507e-05, + "loss": 3.4427, + "step": 1799680 + }, + { + "epoch": 1.01, + "learning_rate": 2.052791505035172e-05, + "loss": 3.4355, + "step": 1800192 + }, + { + "epoch": 1.01, + "learning_rate": 2.05195291028412e-05, + "loss": 3.4435, + "step": 1800704 + }, + { + "epoch": 1.02, + "learning_rate": 2.051114315533068e-05, + "loss": 3.4253, + "step": 1801216 + }, + { + "epoch": 1.02, + "learning_rate": 2.050275720782016e-05, + "loss": 3.4322, + "step": 1801728 + }, + { + "epoch": 1.02, + "learning_rate": 2.049438763911337e-05, + "loss": 3.4325, + "step": 1802240 + }, + { + "epoch": 1.02, + "learning_rate": 2.0486001691602848e-05, + "loss": 3.434, + "step": 1802752 + }, + { + "epoch": 1.02, + "learning_rate": 2.0477615744092328e-05, + "loss": 3.4517, + "step": 1803264 + }, + { + "epoch": 1.02, + "learning_rate": 2.046922979658181e-05, + "loss": 3.439, + "step": 1803776 + }, + { + "epoch": 1.02, + "learning_rate": 2.0460860227875024e-05, + "loss": 3.4468, + "step": 1804288 + }, + { + "epoch": 1.02, + "learning_rate": 2.04524742803645e-05, + "loss": 3.4306, + "step": 1804800 + }, + { + "epoch": 1.02, + "learning_rate": 2.044408833285398e-05, + "loss": 3.4355, + "step": 1805312 + }, + { + "epoch": 1.02, + "learning_rate": 2.043570238534346e-05, + "loss": 3.4355, + "step": 1805824 + }, + { + "epoch": 1.02, + "learning_rate": 2.0427332816636673e-05, + "loss": 3.4452, + "step": 1806336 + }, + { + "epoch": 1.02, + "learning_rate": 2.0418946869126153e-05, + "loss": 3.4406, + "step": 1806848 + }, + { + "epoch": 1.02, + "learning_rate": 2.0410560921615633e-05, + "loss": 3.4448, + "step": 1807360 + }, + { + "epoch": 1.02, + "learning_rate": 2.0402174974105113e-05, + "loss": 3.4332, + "step": 1807872 + }, + { + "epoch": 1.02, + "learning_rate": 2.0393805405398322e-05, + "loss": 3.4393, + "step": 1808384 + }, + { + "epoch": 1.02, + "learning_rate": 2.0385419457887802e-05, + "loss": 3.4393, + "step": 1808896 + }, + { + "epoch": 1.02, + "learning_rate": 2.0377049889181014e-05, + "loss": 3.439, + "step": 1809408 + }, + { + "epoch": 1.02, + "learning_rate": 2.0368663941670498e-05, + "loss": 3.4249, + "step": 1809920 + }, + { + "epoch": 1.02, + "learning_rate": 2.0360277994159974e-05, + "loss": 3.4445, + "step": 1810432 + }, + { + "epoch": 1.02, + "learning_rate": 2.0351892046649454e-05, + "loss": 3.4286, + "step": 1810944 + }, + { + "epoch": 1.02, + "learning_rate": 2.0343506099138934e-05, + "loss": 3.4368, + "step": 1811456 + }, + { + "epoch": 1.02, + "learning_rate": 2.0335120151628414e-05, + "loss": 3.4304, + "step": 1811968 + }, + { + "epoch": 1.02, + "learning_rate": 2.0326750582921627e-05, + "loss": 3.441, + "step": 1812480 + }, + { + "epoch": 1.02, + "learning_rate": 2.0318364635411106e-05, + "loss": 3.4368, + "step": 1812992 + }, + { + "epoch": 1.02, + "learning_rate": 2.0309978687900586e-05, + "loss": 3.4347, + "step": 1813504 + }, + { + "epoch": 1.02, + "learning_rate": 2.0301592740390066e-05, + "loss": 3.4427, + "step": 1814016 + }, + { + "epoch": 1.02, + "learning_rate": 2.0293206792879546e-05, + "loss": 3.4513, + "step": 1814528 + }, + { + "epoch": 1.02, + "learning_rate": 2.0284820845369026e-05, + "loss": 3.4483, + "step": 1815040 + }, + { + "epoch": 1.02, + "learning_rate": 2.0276434897858503e-05, + "loss": 3.4372, + "step": 1815552 + }, + { + "epoch": 1.02, + "learning_rate": 2.0268048950347983e-05, + "loss": 3.435, + "step": 1816064 + }, + { + "epoch": 1.02, + "learning_rate": 2.0259695760444928e-05, + "loss": 3.4331, + "step": 1816576 + }, + { + "epoch": 1.02, + "learning_rate": 2.0251309812934408e-05, + "loss": 3.438, + "step": 1817088 + }, + { + "epoch": 1.02, + "learning_rate": 2.0242923865423888e-05, + "loss": 3.4375, + "step": 1817600 + }, + { + "epoch": 1.02, + "learning_rate": 2.0234537917913368e-05, + "loss": 3.4266, + "step": 1818112 + }, + { + "epoch": 1.02, + "learning_rate": 2.0226151970402848e-05, + "loss": 3.4403, + "step": 1818624 + }, + { + "epoch": 1.02, + "learning_rate": 2.0217766022892328e-05, + "loss": 3.4433, + "step": 1819136 + }, + { + "epoch": 1.02, + "learning_rate": 2.0209380075381808e-05, + "loss": 3.4356, + "step": 1819648 + }, + { + "epoch": 1.02, + "learning_rate": 2.0200994127871288e-05, + "loss": 3.4378, + "step": 1820160 + }, + { + "epoch": 1.02, + "learning_rate": 2.01926245591645e-05, + "loss": 3.4388, + "step": 1820672 + }, + { + "epoch": 1.02, + "learning_rate": 2.0184238611653977e-05, + "loss": 3.432, + "step": 1821184 + }, + { + "epoch": 1.02, + "learning_rate": 2.0175852664143457e-05, + "loss": 3.4463, + "step": 1821696 + }, + { + "epoch": 1.02, + "learning_rate": 2.016748309543667e-05, + "loss": 3.4426, + "step": 1822208 + }, + { + "epoch": 1.02, + "learning_rate": 2.0159097147926152e-05, + "loss": 3.45, + "step": 1822720 + }, + { + "epoch": 1.02, + "learning_rate": 2.015071120041563e-05, + "loss": 3.4304, + "step": 1823232 + }, + { + "epoch": 1.02, + "learning_rate": 2.014232525290511e-05, + "loss": 3.4429, + "step": 1823744 + }, + { + "epoch": 1.02, + "learning_rate": 2.013395568419832e-05, + "loss": 3.4399, + "step": 1824256 + }, + { + "epoch": 1.02, + "learning_rate": 2.0125569736687798e-05, + "loss": 3.4375, + "step": 1824768 + }, + { + "epoch": 1.02, + "learning_rate": 2.011718378917728e-05, + "loss": 3.4383, + "step": 1825280 + }, + { + "epoch": 1.02, + "learning_rate": 2.010879784166676e-05, + "loss": 3.4394, + "step": 1825792 + }, + { + "epoch": 1.02, + "learning_rate": 2.0100444651763703e-05, + "loss": 3.4432, + "step": 1826304 + }, + { + "epoch": 1.02, + "learning_rate": 2.0092058704253183e-05, + "loss": 3.4596, + "step": 1826816 + }, + { + "epoch": 1.02, + "learning_rate": 2.0083672756742663e-05, + "loss": 3.4319, + "step": 1827328 + }, + { + "epoch": 1.02, + "learning_rate": 2.0075286809232143e-05, + "loss": 3.4415, + "step": 1827840 + }, + { + "epoch": 1.02, + "learning_rate": 2.0066900861721623e-05, + "loss": 3.4388, + "step": 1828352 + }, + { + "epoch": 1.02, + "learning_rate": 2.0058514914211103e-05, + "loss": 3.4402, + "step": 1828864 + }, + { + "epoch": 1.02, + "learning_rate": 2.0050128966700583e-05, + "loss": 3.4339, + "step": 1829376 + }, + { + "epoch": 1.02, + "learning_rate": 2.0041743019190063e-05, + "loss": 3.4299, + "step": 1829888 + }, + { + "epoch": 1.02, + "learning_rate": 2.003337345048327e-05, + "loss": 3.4422, + "step": 1830400 + }, + { + "epoch": 1.02, + "learning_rate": 2.002498750297275e-05, + "loss": 3.4243, + "step": 1830912 + }, + { + "epoch": 1.02, + "learning_rate": 2.0016601555462235e-05, + "loss": 3.4408, + "step": 1831424 + }, + { + "epoch": 1.03, + "eval_loss": 3.8637804985046387, + "eval_runtime": 305.3676, + "eval_samples_per_second": 1249.612, + "eval_steps_per_second": 39.051, + "step": 1831680 + }, + { + "epoch": 0.0, + "learning_rate": 2.0008215607951715e-05, + "loss": 3.4388, + "step": 1831936 + }, + { + "epoch": 0.0, + "learning_rate": 1.9999829660441195e-05, + "loss": 3.4342, + "step": 1832448 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991443712930675e-05, + "loss": 3.4374, + "step": 1832960 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983057765420155e-05, + "loss": 3.4418, + "step": 1833472 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974688196713364e-05, + "loss": 3.4498, + "step": 1833984 + }, + { + "epoch": 0.0, + "learning_rate": 1.9966302249202844e-05, + "loss": 3.4383, + "step": 1834496 + }, + { + "epoch": 0.0, + "learning_rate": 1.9957916301692324e-05, + "loss": 3.4431, + "step": 1835008 + }, + { + "epoch": 0.0, + "learning_rate": 1.9949530354181807e-05, + "loss": 3.4282, + "step": 1835520 + }, + { + "epoch": 0.0, + "learning_rate": 1.9941160785475016e-05, + "loss": 3.4291, + "step": 1836032 + }, + { + "epoch": 0.0, + "learning_rate": 1.9932774837964496e-05, + "loss": 3.4451, + "step": 1836544 + }, + { + "epoch": 0.0, + "learning_rate": 1.9924388890453976e-05, + "loss": 3.4361, + "step": 1837056 + }, + { + "epoch": 0.0, + "learning_rate": 1.9916002942943453e-05, + "loss": 3.4316, + "step": 1837568 + }, + { + "epoch": 0.0, + "learning_rate": 1.9907649753040398e-05, + "loss": 3.4416, + "step": 1838080 + }, + { + "epoch": 0.0, + "learning_rate": 1.9899263805529878e-05, + "loss": 3.4234, + "step": 1838592 + }, + { + "epoch": 0.0, + "learning_rate": 1.9890877858019358e-05, + "loss": 3.4304, + "step": 1839104 + }, + { + "epoch": 0.0, + "learning_rate": 1.9882491910508838e-05, + "loss": 3.4182, + "step": 1839616 + }, + { + "epoch": 0.0, + "learning_rate": 1.9874105962998318e-05, + "loss": 3.4304, + "step": 1840128 + }, + { + "epoch": 0.0, + "learning_rate": 1.9865720015487797e-05, + "loss": 3.4401, + "step": 1840640 + }, + { + "epoch": 0.0, + "learning_rate": 1.9857334067977277e-05, + "loss": 3.4254, + "step": 1841152 + }, + { + "epoch": 0.0, + "learning_rate": 1.9848948120466757e-05, + "loss": 3.4479, + "step": 1841664 + }, + { + "epoch": 0.0, + "learning_rate": 1.984057855175997e-05, + "loss": 3.4405, + "step": 1842176 + }, + { + "epoch": 0.0, + "learning_rate": 1.983219260424945e-05, + "loss": 3.4422, + "step": 1842688 + }, + { + "epoch": 0.0, + "learning_rate": 1.9823806656738926e-05, + "loss": 3.434, + "step": 1843200 + }, + { + "epoch": 0.0, + "learning_rate": 1.9815420709228406e-05, + "loss": 3.4335, + "step": 1843712 + }, + { + "epoch": 0.0, + "learning_rate": 1.9807051140521622e-05, + "loss": 3.4364, + "step": 1844224 + }, + { + "epoch": 0.0, + "learning_rate": 1.9798665193011102e-05, + "loss": 3.4394, + "step": 1844736 + }, + { + "epoch": 0.0, + "learning_rate": 1.979027924550058e-05, + "loss": 3.43, + "step": 1845248 + }, + { + "epoch": 0.0, + "learning_rate": 1.978189329799006e-05, + "loss": 3.438, + "step": 1845760 + }, + { + "epoch": 0.0, + "learning_rate": 1.977352372928327e-05, + "loss": 3.4268, + "step": 1846272 + }, + { + "epoch": 0.0, + "learning_rate": 1.976513778177275e-05, + "loss": 3.4303, + "step": 1846784 + }, + { + "epoch": 0.01, + "learning_rate": 1.975675183426223e-05, + "loss": 3.4372, + "step": 1847296 + }, + { + "epoch": 0.01, + "learning_rate": 1.974836588675171e-05, + "loss": 3.4397, + "step": 1847808 + }, + { + "epoch": 0.01, + "learning_rate": 1.9739996318044924e-05, + "loss": 3.4405, + "step": 1848320 + }, + { + "epoch": 0.01, + "learning_rate": 1.97316103705344e-05, + "loss": 3.4432, + "step": 1848832 + }, + { + "epoch": 0.01, + "learning_rate": 1.972322442302388e-05, + "loss": 3.4286, + "step": 1849344 + }, + { + "epoch": 0.01, + "learning_rate": 1.971483847551336e-05, + "loss": 3.4363, + "step": 1849856 + }, + { + "epoch": 0.01, + "learning_rate": 1.9706468906806576e-05, + "loss": 3.4396, + "step": 1850368 + }, + { + "epoch": 0.01, + "learning_rate": 1.9698082959296052e-05, + "loss": 3.4245, + "step": 1850880 + }, + { + "epoch": 0.01, + "learning_rate": 1.9689697011785532e-05, + "loss": 3.4279, + "step": 1851392 + }, + { + "epoch": 0.01, + "learning_rate": 1.9681311064275012e-05, + "loss": 3.4209, + "step": 1851904 + }, + { + "epoch": 0.01, + "learning_rate": 1.967294149556822e-05, + "loss": 3.4249, + "step": 1852416 + }, + { + "epoch": 0.01, + "learning_rate": 1.9664555548057705e-05, + "loss": 3.4326, + "step": 1852928 + }, + { + "epoch": 0.01, + "learning_rate": 1.9656169600547185e-05, + "loss": 3.439, + "step": 1853440 + }, + { + "epoch": 0.01, + "learning_rate": 1.9647800031840397e-05, + "loss": 3.4303, + "step": 1853952 + }, + { + "epoch": 0.01, + "learning_rate": 1.9639414084329874e-05, + "loss": 3.4292, + "step": 1854464 + }, + { + "epoch": 0.01, + "learning_rate": 1.9631028136819354e-05, + "loss": 3.4285, + "step": 1854976 + }, + { + "epoch": 0.01, + "learning_rate": 1.9622642189308834e-05, + "loss": 3.4382, + "step": 1855488 + }, + { + "epoch": 0.01, + "learning_rate": 1.9614272620602046e-05, + "loss": 3.4215, + "step": 1856000 + }, + { + "epoch": 0.01, + "learning_rate": 1.9605886673091526e-05, + "loss": 3.4108, + "step": 1856512 + }, + { + "epoch": 0.01, + "learning_rate": 1.9597500725581006e-05, + "loss": 3.4414, + "step": 1857024 + }, + { + "epoch": 0.01, + "learning_rate": 1.9589114778070486e-05, + "loss": 3.4342, + "step": 1857536 + }, + { + "epoch": 0.01, + "learning_rate": 1.9580745209363695e-05, + "loss": 3.442, + "step": 1858048 + }, + { + "epoch": 0.01, + "learning_rate": 1.9572359261853175e-05, + "loss": 3.4275, + "step": 1858560 + }, + { + "epoch": 0.01, + "learning_rate": 1.956398969314639e-05, + "loss": 3.426, + "step": 1859072 + }, + { + "epoch": 0.01, + "learning_rate": 1.955560374563587e-05, + "loss": 3.4249, + "step": 1859584 + }, + { + "epoch": 0.01, + "learning_rate": 1.9547217798125348e-05, + "loss": 3.4278, + "step": 1860096 + }, + { + "epoch": 0.01, + "learning_rate": 1.9538831850614827e-05, + "loss": 3.4379, + "step": 1860608 + }, + { + "epoch": 0.01, + "learning_rate": 1.9530445903104307e-05, + "loss": 3.4179, + "step": 1861120 + }, + { + "epoch": 0.01, + "learning_rate": 1.9522059955593787e-05, + "loss": 3.4528, + "step": 1861632 + }, + { + "epoch": 0.01, + "learning_rate": 1.9513674008083267e-05, + "loss": 3.4279, + "step": 1862144 + }, + { + "epoch": 0.01, + "learning_rate": 1.9505288060572747e-05, + "loss": 3.4129, + "step": 1862656 + }, + { + "epoch": 0.01, + "learning_rate": 1.949691849186596e-05, + "loss": 3.4442, + "step": 1863168 + }, + { + "epoch": 0.01, + "learning_rate": 1.948853254435544e-05, + "loss": 3.4251, + "step": 1863680 + }, + { + "epoch": 0.01, + "learning_rate": 1.948014659684492e-05, + "loss": 3.4139, + "step": 1864192 + }, + { + "epoch": 0.01, + "learning_rate": 1.94717606493344e-05, + "loss": 3.4393, + "step": 1864704 + }, + { + "epoch": 0.01, + "learning_rate": 1.946339108062761e-05, + "loss": 3.4338, + "step": 1865216 + }, + { + "epoch": 0.01, + "learning_rate": 1.9455005133117092e-05, + "loss": 3.4212, + "step": 1865728 + }, + { + "epoch": 0.01, + "learning_rate": 1.9446619185606572e-05, + "loss": 3.4233, + "step": 1866240 + }, + { + "epoch": 0.01, + "learning_rate": 1.9438233238096052e-05, + "loss": 3.412, + "step": 1866752 + }, + { + "epoch": 0.01, + "learning_rate": 1.942986366938926e-05, + "loss": 3.4213, + "step": 1867264 + }, + { + "epoch": 0.01, + "learning_rate": 1.942147772187874e-05, + "loss": 3.4317, + "step": 1867776 + }, + { + "epoch": 0.01, + "learning_rate": 1.941309177436822e-05, + "loss": 3.4218, + "step": 1868288 + }, + { + "epoch": 0.01, + "learning_rate": 1.94047058268577e-05, + "loss": 3.431, + "step": 1868800 + }, + { + "epoch": 0.01, + "learning_rate": 1.9396336258150913e-05, + "loss": 3.4286, + "step": 1869312 + }, + { + "epoch": 0.01, + "learning_rate": 1.9387950310640393e-05, + "loss": 3.4412, + "step": 1869824 + }, + { + "epoch": 0.01, + "learning_rate": 1.9379564363129873e-05, + "loss": 3.4254, + "step": 1870336 + }, + { + "epoch": 0.01, + "learning_rate": 1.937117841561935e-05, + "loss": 3.4322, + "step": 1870848 + }, + { + "epoch": 0.01, + "learning_rate": 1.9362808846912562e-05, + "loss": 3.4269, + "step": 1871360 + }, + { + "epoch": 0.01, + "learning_rate": 1.9354422899402046e-05, + "loss": 3.4253, + "step": 1871872 + }, + { + "epoch": 0.01, + "learning_rate": 1.9346036951891526e-05, + "loss": 3.4398, + "step": 1872384 + }, + { + "epoch": 0.01, + "learning_rate": 1.9337667383184735e-05, + "loss": 3.4316, + "step": 1872896 + }, + { + "epoch": 0.01, + "learning_rate": 1.9329281435674215e-05, + "loss": 3.4269, + "step": 1873408 + }, + { + "epoch": 0.01, + "learning_rate": 1.9320895488163695e-05, + "loss": 3.437, + "step": 1873920 + }, + { + "epoch": 0.01, + "learning_rate": 1.9312509540653175e-05, + "loss": 3.4134, + "step": 1874432 + }, + { + "epoch": 0.01, + "learning_rate": 1.9304139971946387e-05, + "loss": 3.4185, + "step": 1874944 + }, + { + "epoch": 0.01, + "learning_rate": 1.9295754024435867e-05, + "loss": 3.4298, + "step": 1875456 + }, + { + "epoch": 0.01, + "learning_rate": 1.9287368076925347e-05, + "loss": 3.4323, + "step": 1875968 + }, + { + "epoch": 0.01, + "learning_rate": 1.9278982129414824e-05, + "loss": 3.4204, + "step": 1876480 + }, + { + "epoch": 0.01, + "learning_rate": 1.9270612560708036e-05, + "loss": 3.4339, + "step": 1876992 + }, + { + "epoch": 0.02, + "learning_rate": 1.9262226613197516e-05, + "loss": 3.4193, + "step": 1877504 + }, + { + "epoch": 0.02, + "learning_rate": 1.9253840665687e-05, + "loss": 3.4201, + "step": 1878016 + }, + { + "epoch": 0.02, + "learning_rate": 1.9245454718176476e-05, + "loss": 3.4179, + "step": 1878528 + }, + { + "epoch": 0.02, + "learning_rate": 1.923708514946969e-05, + "loss": 3.4264, + "step": 1879040 + }, + { + "epoch": 0.02, + "learning_rate": 1.922869920195917e-05, + "loss": 3.4409, + "step": 1879552 + }, + { + "epoch": 0.02, + "learning_rate": 1.922031325444865e-05, + "loss": 3.4291, + "step": 1880064 + }, + { + "epoch": 0.02, + "learning_rate": 1.921192730693813e-05, + "loss": 3.434, + "step": 1880576 + }, + { + "epoch": 0.02, + "learning_rate": 1.920355773823134e-05, + "loss": 3.4213, + "step": 1881088 + }, + { + "epoch": 0.02, + "learning_rate": 1.919517179072082e-05, + "loss": 3.4224, + "step": 1881600 + }, + { + "epoch": 0.02, + "learning_rate": 1.9186785843210297e-05, + "loss": 3.4243, + "step": 1882112 + }, + { + "epoch": 0.02, + "learning_rate": 1.9178399895699777e-05, + "loss": 3.4357, + "step": 1882624 + }, + { + "epoch": 0.02, + "learning_rate": 1.917003032699299e-05, + "loss": 3.4289, + "step": 1883136 + }, + { + "epoch": 0.02, + "learning_rate": 1.916164437948247e-05, + "loss": 3.4322, + "step": 1883648 + }, + { + "epoch": 0.02, + "learning_rate": 1.915325843197195e-05, + "loss": 3.4291, + "step": 1884160 + }, + { + "epoch": 0.02, + "learning_rate": 1.914487248446143e-05, + "loss": 3.4272, + "step": 1884672 + }, + { + "epoch": 0.02, + "learning_rate": 1.9136502915754642e-05, + "loss": 3.4264, + "step": 1885184 + }, + { + "epoch": 0.02, + "learning_rate": 1.912813334704785e-05, + "loss": 3.4277, + "step": 1885696 + }, + { + "epoch": 0.02, + "learning_rate": 1.911974739953733e-05, + "loss": 3.4144, + "step": 1886208 + }, + { + "epoch": 0.02, + "learning_rate": 1.9111361452026815e-05, + "loss": 3.432, + "step": 1886720 + }, + { + "epoch": 0.02, + "learning_rate": 1.9102975504516295e-05, + "loss": 3.4207, + "step": 1887232 + }, + { + "epoch": 0.02, + "learning_rate": 1.909458955700577e-05, + "loss": 3.4261, + "step": 1887744 + }, + { + "epoch": 0.02, + "learning_rate": 1.908620360949525e-05, + "loss": 3.4231, + "step": 1888256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9077834040788464e-05, + "loss": 3.4248, + "step": 1888768 + }, + { + "epoch": 0.02, + "learning_rate": 1.9069448093277943e-05, + "loss": 3.4279, + "step": 1889280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9061062145767423e-05, + "loss": 3.423, + "step": 1889792 + }, + { + "epoch": 0.02, + "learning_rate": 1.9052676198256903e-05, + "loss": 3.4358, + "step": 1890304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9044290250746383e-05, + "loss": 3.4386, + "step": 1890816 + }, + { + "epoch": 0.02, + "learning_rate": 1.9035904303235863e-05, + "loss": 3.4366, + "step": 1891328 + }, + { + "epoch": 0.02, + "learning_rate": 1.9027518355725343e-05, + "loss": 3.4251, + "step": 1891840 + }, + { + "epoch": 0.02, + "learning_rate": 1.9019132408214823e-05, + "loss": 3.4258, + "step": 1892352 + }, + { + "epoch": 0.02, + "learning_rate": 1.9010779218311768e-05, + "loss": 3.4202, + "step": 1892864 + }, + { + "epoch": 0.02, + "learning_rate": 1.9002393270801245e-05, + "loss": 3.4302, + "step": 1893376 + }, + { + "epoch": 0.02, + "learning_rate": 1.8994007323290725e-05, + "loss": 3.4296, + "step": 1893888 + }, + { + "epoch": 0.02, + "learning_rate": 1.8985621375780205e-05, + "loss": 3.4167, + "step": 1894400 + }, + { + "epoch": 0.02, + "learning_rate": 1.8977235428269685e-05, + "loss": 3.4266, + "step": 1894912 + }, + { + "epoch": 0.02, + "learning_rate": 1.8968849480759165e-05, + "loss": 3.4297, + "step": 1895424 + }, + { + "epoch": 0.02, + "learning_rate": 1.8960463533248645e-05, + "loss": 3.4294, + "step": 1895936 + }, + { + "epoch": 0.02, + "learning_rate": 1.8952077585738125e-05, + "loss": 3.4251, + "step": 1896448 + }, + { + "epoch": 0.02, + "learning_rate": 1.8943708017031337e-05, + "loss": 3.4266, + "step": 1896960 + }, + { + "epoch": 0.02, + "learning_rate": 1.8935322069520817e-05, + "loss": 3.4217, + "step": 1897472 + }, + { + "epoch": 0.02, + "learning_rate": 1.8926936122010297e-05, + "loss": 3.4371, + "step": 1897984 + }, + { + "epoch": 0.02, + "learning_rate": 1.8918550174499773e-05, + "loss": 3.4308, + "step": 1898496 + }, + { + "epoch": 0.02, + "learning_rate": 1.8910180605792986e-05, + "loss": 3.4423, + "step": 1899008 + }, + { + "epoch": 0.02, + "learning_rate": 1.890179465828247e-05, + "loss": 3.4187, + "step": 1899520 + }, + { + "epoch": 0.02, + "learning_rate": 1.889340871077195e-05, + "loss": 3.4326, + "step": 1900032 + }, + { + "epoch": 0.02, + "learning_rate": 1.888503914206516e-05, + "loss": 3.4324, + "step": 1900544 + }, + { + "epoch": 0.02, + "learning_rate": 1.887665319455464e-05, + "loss": 3.4263, + "step": 1901056 + }, + { + "epoch": 0.02, + "learning_rate": 1.8868267247044118e-05, + "loss": 3.428, + "step": 1901568 + }, + { + "epoch": 0.02, + "learning_rate": 1.8859881299533598e-05, + "loss": 3.4294, + "step": 1902080 + }, + { + "epoch": 0.02, + "learning_rate": 1.885152810963054e-05, + "loss": 3.4303, + "step": 1902592 + }, + { + "epoch": 0.02, + "learning_rate": 1.884314216212002e-05, + "loss": 3.4473, + "step": 1903104 + }, + { + "epoch": 0.02, + "learning_rate": 1.88347562146095e-05, + "loss": 3.4252, + "step": 1903616 + }, + { + "epoch": 0.02, + "learning_rate": 1.882637026709898e-05, + "loss": 3.4304, + "step": 1904128 + }, + { + "epoch": 0.02, + "learning_rate": 1.881798431958846e-05, + "loss": 3.4298, + "step": 1904640 + }, + { + "epoch": 0.02, + "learning_rate": 1.880959837207794e-05, + "loss": 3.426, + "step": 1905152 + }, + { + "epoch": 0.02, + "learning_rate": 1.8801212424567423e-05, + "loss": 3.4225, + "step": 1905664 + }, + { + "epoch": 0.02, + "learning_rate": 1.87928264770569e-05, + "loss": 3.4211, + "step": 1906176 + }, + { + "epoch": 0.02, + "learning_rate": 1.8784456908350112e-05, + "loss": 3.4293, + "step": 1906688 + }, + { + "epoch": 0.02, + "learning_rate": 1.8776070960839592e-05, + "loss": 3.4202, + "step": 1907200 + }, + { + "epoch": 0.02, + "learning_rate": 1.8767685013329072e-05, + "loss": 3.4261, + "step": 1907712 + }, + { + "epoch": 0.03, + "eval_loss": 3.865877151489258, + "eval_runtime": 304.4743, + "eval_samples_per_second": 1253.278, + "eval_steps_per_second": 39.166, + "step": 1908000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8759299065818552e-05, + "loss": 3.4266, + "step": 1908224 + }, + { + "epoch": 1.0, + "learning_rate": 1.8750929497111764e-05, + "loss": 3.423, + "step": 1908736 + }, + { + "epoch": 1.0, + "learning_rate": 1.8742543549601244e-05, + "loss": 3.4254, + "step": 1909248 + }, + { + "epoch": 1.0, + "learning_rate": 1.873415760209072e-05, + "loss": 3.4335, + "step": 1909760 + }, + { + "epoch": 1.0, + "learning_rate": 1.87257716545802e-05, + "loss": 3.4418, + "step": 1910272 + }, + { + "epoch": 1.0, + "learning_rate": 1.8717402085873413e-05, + "loss": 3.4271, + "step": 1910784 + }, + { + "epoch": 1.0, + "learning_rate": 1.8709016138362893e-05, + "loss": 3.4285, + "step": 1911296 + }, + { + "epoch": 1.0, + "learning_rate": 1.8700630190852373e-05, + "loss": 3.4204, + "step": 1911808 + }, + { + "epoch": 1.0, + "learning_rate": 1.8692244243341853e-05, + "loss": 3.4196, + "step": 1912320 + }, + { + "epoch": 1.0, + "learning_rate": 1.8683874674635066e-05, + "loss": 3.4295, + "step": 1912832 + }, + { + "epoch": 1.0, + "learning_rate": 1.8675488727124546e-05, + "loss": 3.4271, + "step": 1913344 + }, + { + "epoch": 1.0, + "learning_rate": 1.8667102779614022e-05, + "loss": 3.4222, + "step": 1913856 + }, + { + "epoch": 1.0, + "learning_rate": 1.8658733210907238e-05, + "loss": 3.4305, + "step": 1914368 + }, + { + "epoch": 1.0, + "learning_rate": 1.8650347263396718e-05, + "loss": 3.414, + "step": 1914880 + }, + { + "epoch": 1.0, + "learning_rate": 1.8641961315886195e-05, + "loss": 3.4186, + "step": 1915392 + }, + { + "epoch": 1.0, + "learning_rate": 1.8633575368375675e-05, + "loss": 3.4072, + "step": 1915904 + }, + { + "epoch": 1.0, + "learning_rate": 1.8625189420865155e-05, + "loss": 3.4228, + "step": 1916416 + }, + { + "epoch": 1.0, + "learning_rate": 1.8616803473354634e-05, + "loss": 3.4285, + "step": 1916928 + }, + { + "epoch": 1.0, + "learning_rate": 1.8608417525844114e-05, + "loss": 3.4148, + "step": 1917440 + }, + { + "epoch": 1.0, + "learning_rate": 1.8600031578333594e-05, + "loss": 3.4351, + "step": 1917952 + }, + { + "epoch": 1.0, + "learning_rate": 1.8591662009626807e-05, + "loss": 3.4287, + "step": 1918464 + }, + { + "epoch": 1.0, + "learning_rate": 1.8583276062116287e-05, + "loss": 3.4343, + "step": 1918976 + }, + { + "epoch": 1.0, + "learning_rate": 1.8574890114605767e-05, + "loss": 3.4222, + "step": 1919488 + }, + { + "epoch": 1.0, + "learning_rate": 1.8566504167095247e-05, + "loss": 3.4247, + "step": 1920000 + }, + { + "epoch": 1.0, + "learning_rate": 1.8558150977192192e-05, + "loss": 3.4233, + "step": 1920512 + }, + { + "epoch": 1.0, + "learning_rate": 1.854976502968167e-05, + "loss": 3.4323, + "step": 1921024 + }, + { + "epoch": 1.0, + "learning_rate": 1.8541379082171148e-05, + "loss": 3.4162, + "step": 1921536 + }, + { + "epoch": 1.0, + "learning_rate": 1.8532993134660628e-05, + "loss": 3.4293, + "step": 1922048 + }, + { + "epoch": 1.0, + "learning_rate": 1.8524607187150108e-05, + "loss": 3.4163, + "step": 1922560 + }, + { + "epoch": 1.0, + "learning_rate": 1.8516221239639588e-05, + "loss": 3.4178, + "step": 1923072 + }, + { + "epoch": 1.01, + "learning_rate": 1.85078516709328e-05, + "loss": 3.4275, + "step": 1923584 + }, + { + "epoch": 1.01, + "learning_rate": 1.849946572342228e-05, + "loss": 3.4321, + "step": 1924096 + }, + { + "epoch": 1.01, + "learning_rate": 1.849107977591176e-05, + "loss": 3.4223, + "step": 1924608 + }, + { + "epoch": 1.01, + "learning_rate": 1.848269382840124e-05, + "loss": 3.4359, + "step": 1925120 + }, + { + "epoch": 1.01, + "learning_rate": 1.847430788089072e-05, + "loss": 3.421, + "step": 1925632 + }, + { + "epoch": 1.01, + "learning_rate": 1.84659219333802e-05, + "loss": 3.4236, + "step": 1926144 + }, + { + "epoch": 1.01, + "learning_rate": 1.8457535985869677e-05, + "loss": 3.4272, + "step": 1926656 + }, + { + "epoch": 1.01, + "learning_rate": 1.844915003835916e-05, + "loss": 3.4121, + "step": 1927168 + }, + { + "epoch": 1.01, + "learning_rate": 1.8440780469652373e-05, + "loss": 3.4181, + "step": 1927680 + }, + { + "epoch": 1.01, + "learning_rate": 1.843239452214185e-05, + "loss": 3.4137, + "step": 1928192 + }, + { + "epoch": 1.01, + "learning_rate": 1.842400857463133e-05, + "loss": 3.4142, + "step": 1928704 + }, + { + "epoch": 1.01, + "learning_rate": 1.841562262712081e-05, + "loss": 3.4193, + "step": 1929216 + }, + { + "epoch": 1.01, + "learning_rate": 1.8407253058414022e-05, + "loss": 3.432, + "step": 1929728 + }, + { + "epoch": 1.01, + "learning_rate": 1.8398867110903502e-05, + "loss": 3.4184, + "step": 1930240 + }, + { + "epoch": 1.01, + "learning_rate": 1.839048116339298e-05, + "loss": 3.4177, + "step": 1930752 + }, + { + "epoch": 1.01, + "learning_rate": 1.838209521588246e-05, + "loss": 3.4175, + "step": 1931264 + }, + { + "epoch": 1.01, + "learning_rate": 1.837372564717567e-05, + "loss": 3.4247, + "step": 1931776 + }, + { + "epoch": 1.01, + "learning_rate": 1.836533969966515e-05, + "loss": 3.4121, + "step": 1932288 + }, + { + "epoch": 1.01, + "learning_rate": 1.835695375215463e-05, + "loss": 3.4021, + "step": 1932800 + }, + { + "epoch": 1.01, + "learning_rate": 1.834856780464411e-05, + "loss": 3.4306, + "step": 1933312 + }, + { + "epoch": 1.01, + "learning_rate": 1.8340198235937323e-05, + "loss": 3.4243, + "step": 1933824 + }, + { + "epoch": 1.01, + "learning_rate": 1.8331812288426803e-05, + "loss": 3.4337, + "step": 1934336 + }, + { + "epoch": 1.01, + "learning_rate": 1.8323426340916283e-05, + "loss": 3.4147, + "step": 1934848 + }, + { + "epoch": 1.01, + "learning_rate": 1.8315056772209495e-05, + "loss": 3.4182, + "step": 1935360 + }, + { + "epoch": 1.01, + "learning_rate": 1.8306670824698975e-05, + "loss": 3.4146, + "step": 1935872 + }, + { + "epoch": 1.01, + "learning_rate": 1.8298284877188455e-05, + "loss": 3.4153, + "step": 1936384 + }, + { + "epoch": 1.01, + "learning_rate": 1.8289898929677935e-05, + "loss": 3.4334, + "step": 1936896 + }, + { + "epoch": 1.01, + "learning_rate": 1.8281512982167415e-05, + "loss": 3.4054, + "step": 1937408 + }, + { + "epoch": 1.01, + "learning_rate": 1.8273127034656895e-05, + "loss": 3.4438, + "step": 1937920 + }, + { + "epoch": 1.01, + "learning_rate": 1.8264741087146375e-05, + "loss": 3.4228, + "step": 1938432 + }, + { + "epoch": 1.01, + "learning_rate": 1.8256355139635852e-05, + "loss": 3.3992, + "step": 1938944 + }, + { + "epoch": 1.01, + "learning_rate": 1.8247985570929064e-05, + "loss": 3.4299, + "step": 1939456 + }, + { + "epoch": 1.01, + "learning_rate": 1.8239599623418548e-05, + "loss": 3.416, + "step": 1939968 + }, + { + "epoch": 1.01, + "learning_rate": 1.8231213675908028e-05, + "loss": 3.4048, + "step": 1940480 + }, + { + "epoch": 1.01, + "learning_rate": 1.8222827728397504e-05, + "loss": 3.4236, + "step": 1940992 + }, + { + "epoch": 1.01, + "learning_rate": 1.8214458159690717e-05, + "loss": 3.4292, + "step": 1941504 + }, + { + "epoch": 1.01, + "learning_rate": 1.8206072212180197e-05, + "loss": 3.4094, + "step": 1942016 + }, + { + "epoch": 1.01, + "learning_rate": 1.8197686264669677e-05, + "loss": 3.4155, + "step": 1942528 + }, + { + "epoch": 1.01, + "learning_rate": 1.8189300317159156e-05, + "loss": 3.4022, + "step": 1943040 + }, + { + "epoch": 1.01, + "learning_rate": 1.818093074845237e-05, + "loss": 3.4127, + "step": 1943552 + }, + { + "epoch": 1.01, + "learning_rate": 1.817254480094185e-05, + "loss": 3.4187, + "step": 1944064 + }, + { + "epoch": 1.01, + "learning_rate": 1.8164158853431325e-05, + "loss": 3.4101, + "step": 1944576 + }, + { + "epoch": 1.01, + "learning_rate": 1.8155772905920805e-05, + "loss": 3.4231, + "step": 1945088 + }, + { + "epoch": 1.01, + "learning_rate": 1.814741971601775e-05, + "loss": 3.4125, + "step": 1945600 + }, + { + "epoch": 1.01, + "learning_rate": 1.813903376850723e-05, + "loss": 3.4336, + "step": 1946112 + }, + { + "epoch": 1.01, + "learning_rate": 1.813064782099671e-05, + "loss": 3.4162, + "step": 1946624 + }, + { + "epoch": 1.01, + "learning_rate": 1.812226187348619e-05, + "loss": 3.4237, + "step": 1947136 + }, + { + "epoch": 1.01, + "learning_rate": 1.811387592597567e-05, + "loss": 3.4165, + "step": 1947648 + }, + { + "epoch": 1.01, + "learning_rate": 1.810548997846515e-05, + "loss": 3.4137, + "step": 1948160 + }, + { + "epoch": 1.01, + "learning_rate": 1.809710403095463e-05, + "loss": 3.425, + "step": 1948672 + }, + { + "epoch": 1.01, + "learning_rate": 1.808871808344411e-05, + "loss": 3.4183, + "step": 1949184 + }, + { + "epoch": 1.01, + "learning_rate": 1.8080348514737323e-05, + "loss": 3.423, + "step": 1949696 + }, + { + "epoch": 1.01, + "learning_rate": 1.80719625672268e-05, + "loss": 3.4241, + "step": 1950208 + }, + { + "epoch": 1.01, + "learning_rate": 1.806357661971628e-05, + "loss": 3.4108, + "step": 1950720 + }, + { + "epoch": 1.01, + "learning_rate": 1.805520705100949e-05, + "loss": 3.4039, + "step": 1951232 + }, + { + "epoch": 1.01, + "learning_rate": 1.804682110349897e-05, + "loss": 3.4187, + "step": 1951744 + }, + { + "epoch": 1.01, + "learning_rate": 1.803843515598845e-05, + "loss": 3.4248, + "step": 1952256 + }, + { + "epoch": 1.01, + "learning_rate": 1.803004920847793e-05, + "loss": 3.4118, + "step": 1952768 + }, + { + "epoch": 1.01, + "learning_rate": 1.8021679639771144e-05, + "loss": 3.4189, + "step": 1953280 + }, + { + "epoch": 1.02, + "learning_rate": 1.8013293692260624e-05, + "loss": 3.41, + "step": 1953792 + }, + { + "epoch": 1.02, + "learning_rate": 1.80049077447501e-05, + "loss": 3.4101, + "step": 1954304 + }, + { + "epoch": 1.02, + "learning_rate": 1.7996521797239584e-05, + "loss": 3.4093, + "step": 1954816 + }, + { + "epoch": 1.02, + "learning_rate": 1.7988152228532796e-05, + "loss": 3.4154, + "step": 1955328 + }, + { + "epoch": 1.02, + "learning_rate": 1.7979766281022273e-05, + "loss": 3.4287, + "step": 1955840 + }, + { + "epoch": 1.02, + "learning_rate": 1.7971380333511753e-05, + "loss": 3.4211, + "step": 1956352 + }, + { + "epoch": 1.02, + "learning_rate": 1.7962994386001233e-05, + "loss": 3.4244, + "step": 1956864 + }, + { + "epoch": 1.02, + "learning_rate": 1.7954624817294445e-05, + "loss": 3.4127, + "step": 1957376 + }, + { + "epoch": 1.02, + "learning_rate": 1.7946238869783925e-05, + "loss": 3.4117, + "step": 1957888 + }, + { + "epoch": 1.02, + "learning_rate": 1.7937869301077138e-05, + "loss": 3.4161, + "step": 1958400 + }, + { + "epoch": 1.02, + "learning_rate": 1.7929483353566618e-05, + "loss": 3.4225, + "step": 1958912 + }, + { + "epoch": 1.02, + "learning_rate": 1.7921097406056098e-05, + "loss": 3.4184, + "step": 1959424 + }, + { + "epoch": 1.02, + "learning_rate": 1.7912711458545574e-05, + "loss": 3.425, + "step": 1959936 + }, + { + "epoch": 1.02, + "learning_rate": 1.7904325511035054e-05, + "loss": 3.4158, + "step": 1960448 + }, + { + "epoch": 1.02, + "learning_rate": 1.7895939563524534e-05, + "loss": 3.4115, + "step": 1960960 + }, + { + "epoch": 1.02, + "learning_rate": 1.7887553616014017e-05, + "loss": 3.4211, + "step": 1961472 + }, + { + "epoch": 1.02, + "learning_rate": 1.7879184047307227e-05, + "loss": 3.4135, + "step": 1961984 + }, + { + "epoch": 1.02, + "learning_rate": 1.7870798099796707e-05, + "loss": 3.4077, + "step": 1962496 + }, + { + "epoch": 1.02, + "learning_rate": 1.7862412152286186e-05, + "loss": 3.4183, + "step": 1963008 + }, + { + "epoch": 1.02, + "learning_rate": 1.7854026204775666e-05, + "loss": 3.4109, + "step": 1963520 + }, + { + "epoch": 1.02, + "learning_rate": 1.7845640257265146e-05, + "loss": 3.4125, + "step": 1964032 + }, + { + "epoch": 1.02, + "learning_rate": 1.7837254309754626e-05, + "loss": 3.4118, + "step": 1964544 + }, + { + "epoch": 1.02, + "learning_rate": 1.782888474104784e-05, + "loss": 3.4126, + "step": 1965056 + }, + { + "epoch": 1.02, + "learning_rate": 1.782049879353732e-05, + "loss": 3.4206, + "step": 1965568 + }, + { + "epoch": 1.02, + "learning_rate": 1.78121128460268e-05, + "loss": 3.4136, + "step": 1966080 + }, + { + "epoch": 1.02, + "learning_rate": 1.7803726898516275e-05, + "loss": 3.4217, + "step": 1966592 + }, + { + "epoch": 1.02, + "learning_rate": 1.7795340951005755e-05, + "loss": 3.4258, + "step": 1967104 + }, + { + "epoch": 1.02, + "learning_rate": 1.778695500349524e-05, + "loss": 3.4285, + "step": 1967616 + }, + { + "epoch": 1.02, + "learning_rate": 1.777856905598472e-05, + "loss": 3.4164, + "step": 1968128 + }, + { + "epoch": 1.02, + "learning_rate": 1.77701831084742e-05, + "loss": 3.4178, + "step": 1968640 + }, + { + "epoch": 1.02, + "learning_rate": 1.776182991857114e-05, + "loss": 3.4084, + "step": 1969152 + }, + { + "epoch": 1.02, + "learning_rate": 1.775344397106062e-05, + "loss": 3.4208, + "step": 1969664 + }, + { + "epoch": 1.02, + "learning_rate": 1.77450580235501e-05, + "loss": 3.4174, + "step": 1970176 + }, + { + "epoch": 1.02, + "learning_rate": 1.773667207603958e-05, + "loss": 3.406, + "step": 1970688 + }, + { + "epoch": 1.02, + "learning_rate": 1.772828612852906e-05, + "loss": 3.416, + "step": 1971200 + }, + { + "epoch": 1.02, + "learning_rate": 1.771990018101854e-05, + "loss": 3.4174, + "step": 1971712 + }, + { + "epoch": 1.02, + "learning_rate": 1.771151423350802e-05, + "loss": 3.4198, + "step": 1972224 + }, + { + "epoch": 1.02, + "learning_rate": 1.77031282859975e-05, + "loss": 3.4136, + "step": 1972736 + }, + { + "epoch": 1.02, + "learning_rate": 1.769475871729071e-05, + "loss": 3.415, + "step": 1973248 + }, + { + "epoch": 1.02, + "learning_rate": 1.7686372769780192e-05, + "loss": 3.4102, + "step": 1973760 + }, + { + "epoch": 1.02, + "learning_rate": 1.7677986822269672e-05, + "loss": 3.427, + "step": 1974272 + }, + { + "epoch": 1.02, + "learning_rate": 1.7669600874759152e-05, + "loss": 3.4183, + "step": 1974784 + }, + { + "epoch": 1.02, + "learning_rate": 1.766123130605236e-05, + "loss": 3.4319, + "step": 1975296 + }, + { + "epoch": 1.02, + "learning_rate": 1.765284535854184e-05, + "loss": 3.4084, + "step": 1975808 + }, + { + "epoch": 1.02, + "learning_rate": 1.764445941103132e-05, + "loss": 3.4198, + "step": 1976320 + }, + { + "epoch": 1.02, + "learning_rate": 1.76360734635208e-05, + "loss": 3.4231, + "step": 1976832 + }, + { + "epoch": 1.02, + "learning_rate": 1.7627703894814014e-05, + "loss": 3.4131, + "step": 1977344 + }, + { + "epoch": 1.02, + "learning_rate": 1.7619317947303494e-05, + "loss": 3.4178, + "step": 1977856 + }, + { + "epoch": 1.02, + "learning_rate": 1.7610931999792974e-05, + "loss": 3.4175, + "step": 1978368 + }, + { + "epoch": 1.02, + "learning_rate": 1.7602562431086183e-05, + "loss": 3.4237, + "step": 1978880 + }, + { + "epoch": 1.02, + "learning_rate": 1.7594192862379395e-05, + "loss": 3.4313, + "step": 1979392 + }, + { + "epoch": 1.02, + "learning_rate": 1.7585806914868875e-05, + "loss": 3.4191, + "step": 1979904 + }, + { + "epoch": 1.02, + "learning_rate": 1.7577420967358355e-05, + "loss": 3.4174, + "step": 1980416 + }, + { + "epoch": 1.02, + "learning_rate": 1.7569035019847835e-05, + "loss": 3.4194, + "step": 1980928 + }, + { + "epoch": 1.02, + "learning_rate": 1.7560649072337315e-05, + "loss": 3.415, + "step": 1981440 + }, + { + "epoch": 1.02, + "learning_rate": 1.7552263124826795e-05, + "loss": 3.4147, + "step": 1981952 + }, + { + "epoch": 1.02, + "learning_rate": 1.7543877177316275e-05, + "loss": 3.4089, + "step": 1982464 + }, + { + "epoch": 1.02, + "learning_rate": 1.7535507608609487e-05, + "loss": 3.4167, + "step": 1982976 + }, + { + "epoch": 1.02, + "learning_rate": 1.7527121661098967e-05, + "loss": 3.4103, + "step": 1983488 + }, + { + "epoch": 1.02, + "learning_rate": 1.7518735713588447e-05, + "loss": 3.4152, + "step": 1984000 + }, + { + "epoch": 1.03, + "eval_loss": 3.86711049079895, + "eval_runtime": 302.8611, + "eval_samples_per_second": 1259.954, + "eval_steps_per_second": 39.374, + "step": 1984320 + }, + { + "epoch": 0.0, + "learning_rate": 1.7510349766077927e-05, + "loss": 3.42, + "step": 1984512 + }, + { + "epoch": 0.0, + "learning_rate": 1.7501963818567404e-05, + "loss": 3.411, + "step": 1985024 + }, + { + "epoch": 0.0, + "learning_rate": 1.7493577871056884e-05, + "loss": 3.4143, + "step": 1985536 + }, + { + "epoch": 0.0, + "learning_rate": 1.7485191923546364e-05, + "loss": 3.423, + "step": 1986048 + }, + { + "epoch": 0.0, + "learning_rate": 1.747682235483958e-05, + "loss": 3.4335, + "step": 1986560 + }, + { + "epoch": 0.0, + "learning_rate": 1.7468436407329056e-05, + "loss": 3.4159, + "step": 1987072 + }, + { + "epoch": 0.0, + "learning_rate": 1.7460050459818536e-05, + "loss": 3.4224, + "step": 1987584 + }, + { + "epoch": 0.0, + "learning_rate": 1.7451664512308016e-05, + "loss": 3.4104, + "step": 1988096 + }, + { + "epoch": 0.0, + "learning_rate": 1.744329494360123e-05, + "loss": 3.4087, + "step": 1988608 + }, + { + "epoch": 0.0, + "learning_rate": 1.743490899609071e-05, + "loss": 3.4171, + "step": 1989120 + }, + { + "epoch": 0.0, + "learning_rate": 1.742652304858019e-05, + "loss": 3.4202, + "step": 1989632 + }, + { + "epoch": 0.0, + "learning_rate": 1.741813710106967e-05, + "loss": 3.4123, + "step": 1990144 + }, + { + "epoch": 0.0, + "learning_rate": 1.740978391116661e-05, + "loss": 3.4167, + "step": 1990656 + }, + { + "epoch": 0.0, + "learning_rate": 1.740139796365609e-05, + "loss": 3.4025, + "step": 1991168 + }, + { + "epoch": 0.0, + "learning_rate": 1.739301201614557e-05, + "loss": 3.4076, + "step": 1991680 + }, + { + "epoch": 0.0, + "learning_rate": 1.738462606863505e-05, + "loss": 3.3946, + "step": 1992192 + }, + { + "epoch": 0.0, + "learning_rate": 1.737624012112453e-05, + "loss": 3.4154, + "step": 1992704 + }, + { + "epoch": 0.0, + "learning_rate": 1.736785417361401e-05, + "loss": 3.4148, + "step": 1993216 + }, + { + "epoch": 0.0, + "learning_rate": 1.735946822610349e-05, + "loss": 3.4031, + "step": 1993728 + }, + { + "epoch": 0.0, + "learning_rate": 1.735108227859297e-05, + "loss": 3.4212, + "step": 1994240 + }, + { + "epoch": 0.0, + "learning_rate": 1.734271270988618e-05, + "loss": 3.4212, + "step": 1994752 + }, + { + "epoch": 0.0, + "learning_rate": 1.7334326762375662e-05, + "loss": 3.4239, + "step": 1995264 + }, + { + "epoch": 0.0, + "learning_rate": 1.7325940814865142e-05, + "loss": 3.4121, + "step": 1995776 + }, + { + "epoch": 0.0, + "learning_rate": 1.7317554867354622e-05, + "loss": 3.412, + "step": 1996288 + }, + { + "epoch": 0.0, + "learning_rate": 1.7309201677451564e-05, + "loss": 3.4175, + "step": 1996800 + }, + { + "epoch": 0.0, + "learning_rate": 1.7300815729941044e-05, + "loss": 3.4194, + "step": 1997312 + }, + { + "epoch": 0.0, + "learning_rate": 1.7292429782430524e-05, + "loss": 3.4072, + "step": 1997824 + }, + { + "epoch": 0.0, + "learning_rate": 1.7284043834920004e-05, + "loss": 3.4189, + "step": 1998336 + }, + { + "epoch": 0.0, + "learning_rate": 1.7275657887409484e-05, + "loss": 3.4086, + "step": 1998848 + }, + { + "epoch": 0.0, + "learning_rate": 1.7267271939898963e-05, + "loss": 3.4036, + "step": 1999360 + }, + { + "epoch": 0.01, + "learning_rate": 1.7258885992388443e-05, + "loss": 3.4155, + "step": 1999872 + }, + { + "epoch": 0.01, + "learning_rate": 1.7250500044877923e-05, + "loss": 3.4182, + "step": 2000384 + }, + { + "epoch": 0.01, + "learning_rate": 1.7242130476171132e-05, + "loss": 3.4157, + "step": 2000896 + }, + { + "epoch": 0.01, + "learning_rate": 1.7233744528660616e-05, + "loss": 3.4234, + "step": 2001408 + }, + { + "epoch": 0.01, + "learning_rate": 1.7225358581150096e-05, + "loss": 3.4102, + "step": 2001920 + }, + { + "epoch": 0.01, + "learning_rate": 1.7216972633639576e-05, + "loss": 3.4154, + "step": 2002432 + }, + { + "epoch": 0.01, + "learning_rate": 1.7208603064932785e-05, + "loss": 3.4197, + "step": 2002944 + }, + { + "epoch": 0.01, + "learning_rate": 1.7200217117422265e-05, + "loss": 3.401, + "step": 2003456 + }, + { + "epoch": 0.01, + "learning_rate": 1.7191831169911745e-05, + "loss": 3.4051, + "step": 2003968 + }, + { + "epoch": 0.01, + "learning_rate": 1.7183445222401225e-05, + "loss": 3.4042, + "step": 2004480 + }, + { + "epoch": 0.01, + "learning_rate": 1.7175075653694437e-05, + "loss": 3.3998, + "step": 2004992 + }, + { + "epoch": 0.01, + "learning_rate": 1.7166689706183917e-05, + "loss": 3.411, + "step": 2005504 + }, + { + "epoch": 0.01, + "learning_rate": 1.7158303758673397e-05, + "loss": 3.423, + "step": 2006016 + }, + { + "epoch": 0.01, + "learning_rate": 1.7149917811162877e-05, + "loss": 3.4073, + "step": 2006528 + }, + { + "epoch": 0.01, + "learning_rate": 1.7141548242456086e-05, + "loss": 3.4087, + "step": 2007040 + }, + { + "epoch": 0.01, + "learning_rate": 1.7133162294945566e-05, + "loss": 3.4113, + "step": 2007552 + }, + { + "epoch": 0.01, + "learning_rate": 1.712477634743505e-05, + "loss": 3.4139, + "step": 2008064 + }, + { + "epoch": 0.01, + "learning_rate": 1.711639039992453e-05, + "loss": 3.3995, + "step": 2008576 + }, + { + "epoch": 0.01, + "learning_rate": 1.710802083121774e-05, + "loss": 3.3928, + "step": 2009088 + }, + { + "epoch": 0.01, + "learning_rate": 1.709963488370722e-05, + "loss": 3.4172, + "step": 2009600 + }, + { + "epoch": 0.01, + "learning_rate": 1.70912489361967e-05, + "loss": 3.4172, + "step": 2010112 + }, + { + "epoch": 0.01, + "learning_rate": 1.708286298868618e-05, + "loss": 3.4237, + "step": 2010624 + }, + { + "epoch": 0.01, + "learning_rate": 1.707449341997939e-05, + "loss": 3.4062, + "step": 2011136 + }, + { + "epoch": 0.01, + "learning_rate": 1.70661238512726e-05, + "loss": 3.4057, + "step": 2011648 + }, + { + "epoch": 0.01, + "learning_rate": 1.705773790376208e-05, + "loss": 3.4044, + "step": 2012160 + }, + { + "epoch": 0.01, + "learning_rate": 1.704935195625156e-05, + "loss": 3.4044, + "step": 2012672 + }, + { + "epoch": 0.01, + "learning_rate": 1.704096600874104e-05, + "loss": 3.4212, + "step": 2013184 + }, + { + "epoch": 0.01, + "learning_rate": 1.703258006123052e-05, + "loss": 3.3915, + "step": 2013696 + }, + { + "epoch": 0.01, + "learning_rate": 1.7024194113720003e-05, + "loss": 3.4344, + "step": 2014208 + }, + { + "epoch": 0.01, + "learning_rate": 1.701580816620948e-05, + "loss": 3.4135, + "step": 2014720 + }, + { + "epoch": 0.01, + "learning_rate": 1.700742221869896e-05, + "loss": 3.3924, + "step": 2015232 + }, + { + "epoch": 0.01, + "learning_rate": 1.6999052649992172e-05, + "loss": 3.4179, + "step": 2015744 + }, + { + "epoch": 0.01, + "learning_rate": 1.6990666702481652e-05, + "loss": 3.4049, + "step": 2016256 + }, + { + "epoch": 0.01, + "learning_rate": 1.6982280754971132e-05, + "loss": 3.3933, + "step": 2016768 + }, + { + "epoch": 0.01, + "learning_rate": 1.6973894807460612e-05, + "loss": 3.4148, + "step": 2017280 + }, + { + "epoch": 0.01, + "learning_rate": 1.6965525238753824e-05, + "loss": 3.4172, + "step": 2017792 + }, + { + "epoch": 0.01, + "learning_rate": 1.69571392912433e-05, + "loss": 3.3971, + "step": 2018304 + }, + { + "epoch": 0.01, + "learning_rate": 1.694875334373278e-05, + "loss": 3.4114, + "step": 2018816 + }, + { + "epoch": 0.01, + "learning_rate": 1.694036739622226e-05, + "loss": 3.3896, + "step": 2019328 + }, + { + "epoch": 0.01, + "learning_rate": 1.6931997827515473e-05, + "loss": 3.4032, + "step": 2019840 + }, + { + "epoch": 0.01, + "learning_rate": 1.6923611880004953e-05, + "loss": 3.4048, + "step": 2020352 + }, + { + "epoch": 0.01, + "learning_rate": 1.6915225932494433e-05, + "loss": 3.4043, + "step": 2020864 + }, + { + "epoch": 0.01, + "learning_rate": 1.6906839984983913e-05, + "loss": 3.4089, + "step": 2021376 + }, + { + "epoch": 0.01, + "learning_rate": 1.6898486795080855e-05, + "loss": 3.4046, + "step": 2021888 + }, + { + "epoch": 0.01, + "learning_rate": 1.6890100847570335e-05, + "loss": 3.4234, + "step": 2022400 + }, + { + "epoch": 0.01, + "learning_rate": 1.6881714900059818e-05, + "loss": 3.4056, + "step": 2022912 + }, + { + "epoch": 0.01, + "learning_rate": 1.6873328952549298e-05, + "loss": 3.4146, + "step": 2023424 + }, + { + "epoch": 0.01, + "learning_rate": 1.6864943005038775e-05, + "loss": 3.405, + "step": 2023936 + }, + { + "epoch": 0.01, + "learning_rate": 1.6856557057528255e-05, + "loss": 3.4026, + "step": 2024448 + }, + { + "epoch": 0.01, + "learning_rate": 1.6848171110017735e-05, + "loss": 3.4189, + "step": 2024960 + }, + { + "epoch": 0.01, + "learning_rate": 1.6839785162507215e-05, + "loss": 3.407, + "step": 2025472 + }, + { + "epoch": 0.01, + "learning_rate": 1.6831415593800427e-05, + "loss": 3.4123, + "step": 2025984 + }, + { + "epoch": 0.01, + "learning_rate": 1.6823029646289907e-05, + "loss": 3.4166, + "step": 2026496 + }, + { + "epoch": 0.01, + "learning_rate": 1.6814643698779387e-05, + "loss": 3.4014, + "step": 2027008 + }, + { + "epoch": 0.01, + "learning_rate": 1.6806257751268867e-05, + "loss": 3.391, + "step": 2027520 + }, + { + "epoch": 0.01, + "learning_rate": 1.6797888182562076e-05, + "loss": 3.4053, + "step": 2028032 + }, + { + "epoch": 0.01, + "learning_rate": 1.6789502235051556e-05, + "loss": 3.4141, + "step": 2028544 + }, + { + "epoch": 0.01, + "learning_rate": 1.678111628754104e-05, + "loss": 3.3985, + "step": 2029056 + }, + { + "epoch": 0.01, + "learning_rate": 1.677273034003052e-05, + "loss": 3.412, + "step": 2029568 + }, + { + "epoch": 0.01, + "learning_rate": 1.676436077132373e-05, + "loss": 3.4026, + "step": 2030080 + }, + { + "epoch": 0.02, + "learning_rate": 1.675599120261694e-05, + "loss": 3.3963, + "step": 2030592 + }, + { + "epoch": 0.02, + "learning_rate": 1.674760525510642e-05, + "loss": 3.3981, + "step": 2031104 + }, + { + "epoch": 0.02, + "learning_rate": 1.67392193075959e-05, + "loss": 3.4025, + "step": 2031616 + }, + { + "epoch": 0.02, + "learning_rate": 1.673083336008538e-05, + "loss": 3.4216, + "step": 2032128 + }, + { + "epoch": 0.02, + "learning_rate": 1.672244741257486e-05, + "loss": 3.4085, + "step": 2032640 + }, + { + "epoch": 0.02, + "learning_rate": 1.671406146506434e-05, + "loss": 3.4141, + "step": 2033152 + }, + { + "epoch": 0.02, + "learning_rate": 1.670567551755382e-05, + "loss": 3.4016, + "step": 2033664 + }, + { + "epoch": 0.02, + "learning_rate": 1.66972895700433e-05, + "loss": 3.3993, + "step": 2034176 + }, + { + "epoch": 0.02, + "learning_rate": 1.668892000133651e-05, + "loss": 3.4037, + "step": 2034688 + }, + { + "epoch": 0.02, + "learning_rate": 1.668053405382599e-05, + "loss": 3.4141, + "step": 2035200 + }, + { + "epoch": 0.02, + "learning_rate": 1.6672148106315473e-05, + "loss": 3.41, + "step": 2035712 + }, + { + "epoch": 0.02, + "learning_rate": 1.6663762158804953e-05, + "loss": 3.4122, + "step": 2036224 + }, + { + "epoch": 0.02, + "learning_rate": 1.6655392590098162e-05, + "loss": 3.4062, + "step": 2036736 + }, + { + "epoch": 0.02, + "learning_rate": 1.6647006642587642e-05, + "loss": 3.3995, + "step": 2037248 + }, + { + "epoch": 0.02, + "learning_rate": 1.6638620695077122e-05, + "loss": 3.4114, + "step": 2037760 + }, + { + "epoch": 0.02, + "learning_rate": 1.6630251126370334e-05, + "loss": 3.406, + "step": 2038272 + }, + { + "epoch": 0.02, + "learning_rate": 1.6621865178859814e-05, + "loss": 3.3995, + "step": 2038784 + }, + { + "epoch": 0.02, + "learning_rate": 1.6613479231349294e-05, + "loss": 3.4043, + "step": 2039296 + }, + { + "epoch": 0.02, + "learning_rate": 1.6605093283838774e-05, + "loss": 3.4049, + "step": 2039808 + }, + { + "epoch": 0.02, + "learning_rate": 1.6596707336328254e-05, + "loss": 3.4031, + "step": 2040320 + }, + { + "epoch": 0.02, + "learning_rate": 1.658832138881773e-05, + "loss": 3.4004, + "step": 2040832 + }, + { + "epoch": 0.02, + "learning_rate": 1.6579951820110943e-05, + "loss": 3.4011, + "step": 2041344 + }, + { + "epoch": 0.02, + "learning_rate": 1.6571565872600427e-05, + "loss": 3.4098, + "step": 2041856 + }, + { + "epoch": 0.02, + "learning_rate": 1.6563179925089903e-05, + "loss": 3.4104, + "step": 2042368 + }, + { + "epoch": 0.02, + "learning_rate": 1.6554793977579383e-05, + "loss": 3.4073, + "step": 2042880 + }, + { + "epoch": 0.02, + "learning_rate": 1.6546408030068863e-05, + "loss": 3.4146, + "step": 2043392 + }, + { + "epoch": 0.02, + "learning_rate": 1.6538022082558343e-05, + "loss": 3.4183, + "step": 2043904 + }, + { + "epoch": 0.02, + "learning_rate": 1.6529636135047823e-05, + "loss": 3.4048, + "step": 2044416 + }, + { + "epoch": 0.02, + "learning_rate": 1.6521250187537303e-05, + "loss": 3.4064, + "step": 2044928 + }, + { + "epoch": 0.02, + "learning_rate": 1.6512896997634248e-05, + "loss": 3.3985, + "step": 2045440 + }, + { + "epoch": 0.02, + "learning_rate": 1.6504511050123725e-05, + "loss": 3.4083, + "step": 2045952 + }, + { + "epoch": 0.02, + "learning_rate": 1.6496125102613205e-05, + "loss": 3.4054, + "step": 2046464 + }, + { + "epoch": 0.02, + "learning_rate": 1.6487739155102685e-05, + "loss": 3.3989, + "step": 2046976 + }, + { + "epoch": 0.02, + "learning_rate": 1.6479353207592164e-05, + "loss": 3.4002, + "step": 2047488 + }, + { + "epoch": 0.02, + "learning_rate": 1.6470967260081648e-05, + "loss": 3.4104, + "step": 2048000 + }, + { + "epoch": 0.02, + "learning_rate": 1.6462581312571128e-05, + "loss": 3.4103, + "step": 2048512 + }, + { + "epoch": 0.02, + "learning_rate": 1.6454195365060608e-05, + "loss": 3.4002, + "step": 2049024 + }, + { + "epoch": 0.02, + "learning_rate": 1.6445825796353817e-05, + "loss": 3.4031, + "step": 2049536 + }, + { + "epoch": 0.02, + "learning_rate": 1.6437439848843297e-05, + "loss": 3.4048, + "step": 2050048 + }, + { + "epoch": 0.02, + "learning_rate": 1.6429053901332777e-05, + "loss": 3.4123, + "step": 2050560 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420667953822257e-05, + "loss": 3.4093, + "step": 2051072 + }, + { + "epoch": 0.02, + "learning_rate": 1.641229838511547e-05, + "loss": 3.4214, + "step": 2051584 + }, + { + "epoch": 0.02, + "learning_rate": 1.640391243760495e-05, + "loss": 3.3977, + "step": 2052096 + }, + { + "epoch": 0.02, + "learning_rate": 1.6395542868898158e-05, + "loss": 3.4109, + "step": 2052608 + }, + { + "epoch": 0.02, + "learning_rate": 1.6387156921387638e-05, + "loss": 3.4102, + "step": 2053120 + }, + { + "epoch": 0.02, + "learning_rate": 1.6378770973877118e-05, + "loss": 3.4015, + "step": 2053632 + }, + { + "epoch": 0.02, + "learning_rate": 1.6370385026366598e-05, + "loss": 3.4066, + "step": 2054144 + }, + { + "epoch": 0.02, + "learning_rate": 1.636199907885608e-05, + "loss": 3.4093, + "step": 2054656 + }, + { + "epoch": 0.02, + "learning_rate": 1.6353613131345558e-05, + "loss": 3.4165, + "step": 2055168 + }, + { + "epoch": 0.02, + "learning_rate": 1.634524356263877e-05, + "loss": 3.4189, + "step": 2055680 + }, + { + "epoch": 0.02, + "learning_rate": 1.633685761512825e-05, + "loss": 3.4087, + "step": 2056192 + }, + { + "epoch": 0.02, + "learning_rate": 1.632847166761773e-05, + "loss": 3.4081, + "step": 2056704 + }, + { + "epoch": 0.02, + "learning_rate": 1.632008572010721e-05, + "loss": 3.4107, + "step": 2057216 + }, + { + "epoch": 0.02, + "learning_rate": 1.631169977259669e-05, + "loss": 3.4045, + "step": 2057728 + }, + { + "epoch": 0.02, + "learning_rate": 1.630331382508617e-05, + "loss": 3.4043, + "step": 2058240 + }, + { + "epoch": 0.02, + "learning_rate": 1.629492787757565e-05, + "loss": 3.4042, + "step": 2058752 + }, + { + "epoch": 0.02, + "learning_rate": 1.628655830886886e-05, + "loss": 3.4026, + "step": 2059264 + }, + { + "epoch": 0.02, + "learning_rate": 1.627817236135834e-05, + "loss": 3.4052, + "step": 2059776 + }, + { + "epoch": 0.02, + "learning_rate": 1.626978641384782e-05, + "loss": 3.4012, + "step": 2060288 + }, + { + "epoch": 0.03, + "eval_loss": 3.868530035018921, + "eval_runtime": 316.0855, + "eval_samples_per_second": 1207.24, + "eval_steps_per_second": 37.727, + "step": 2060640 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.407163916775472e+18, + "trial_name": null, + "trial_params": null +}