{ "best_metric": 3.8638370037078857, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/4/checkpoints/checkpoint-992160", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 1908000, "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": 10.9521, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8262, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1939, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9899, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8315, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.734, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6212, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5598, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4784, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4148, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3678, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3295, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2839, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2291, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1923, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1557, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1189, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0961, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0691, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0371, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0251, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9935, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9745, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9472, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9372, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.9066, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8872, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8746, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8532, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8294, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.824, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740117521192533e-05, "loss": 4.8135, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731731573682013e-05, "loss": 4.7994, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7811, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.777, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.754, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.7444, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7168, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7181, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.7048, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.7026, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6893, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6854, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6668, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963113296116324e-05, "loss": 4.6605, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6566, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6392, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6453, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.6222, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.95892359812181e-05, "loss": 4.6061, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958085003370758e-05, "loss": 4.6182, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957246408619706e-05, "loss": 4.5989, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956407813868654e-05, "loss": 4.5903, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5709, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5828, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5577, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5893, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5521, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5646, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5548, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.53, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948863736869932e-05, "loss": 4.5234, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.528, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.5125, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.506, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945510995746097e-05, "loss": 4.5236, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.507, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4937, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4786, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4766, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.487, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.489, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4771, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4754, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4726, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4661, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.454, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4516, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4477, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4351, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4384, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4397, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4394, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 4.4221, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.4017, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 4.4219, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 4.4163, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 4.4146, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.4065, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.4078, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3966, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3884, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.3916, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3893, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3966, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 4.3941, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.3859, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3678, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3704, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3724, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3715, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.9153314119904636e-05, "loss": 4.3604, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3594, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3481, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3645, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3332, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3462, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3458, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3349, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3354, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.3367, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3286, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3344, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.3296, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3226, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3259, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.33, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.3205, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.3099, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.3134, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.314, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.3069, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.2962, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.3048, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.3082, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2993, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2944, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2866, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2897, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2842, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2976, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2894, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2701, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2808, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.2843, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.2759, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2816, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515674187595e-05, "loss": 4.2675, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2764, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2789, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2674, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.8818040007521146e-05, "loss": 4.2642, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809654060010626e-05, "loss": 4.2654, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801268112500106e-05, "loss": 4.2532, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2532, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.266, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877611026996855e-05, "loss": 4.2455, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.2504, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.2546, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875096880624072e-05, "loss": 4.2507, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.215391635894775, "eval_runtime": 310.9131, "eval_samples_per_second": 1227.324, "eval_steps_per_second": 38.355, "step": 76320 }, { "epoch": 0.0, "learning_rate": 4.87425828587302e-05, "loss": 4.2277, "step": 76800 }, { "epoch": 0.0, "learning_rate": 4.873419691121968e-05, "loss": 4.2349, "step": 77312 }, { "epoch": 0.0, "learning_rate": 4.872581096370916e-05, "loss": 4.253, "step": 77824 }, { "epoch": 0.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2354, "step": 78336 }, { "epoch": 0.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.2476, "step": 78848 }, { "epoch": 0.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.2215, "step": 79360 }, { "epoch": 0.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.2376, "step": 79872 }, { "epoch": 0.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.2233, "step": 80384 }, { "epoch": 0.0, "learning_rate": 4.867549527864604e-05, "loss": 4.2222, "step": 80896 }, { "epoch": 0.0, "learning_rate": 4.866710933113552e-05, "loss": 4.2242, "step": 81408 }, { "epoch": 0.0, "learning_rate": 4.8658723383625e-05, "loss": 4.2245, "step": 81920 }, { "epoch": 0.0, "learning_rate": 4.865033743611448e-05, "loss": 4.2279, "step": 82432 }, { "epoch": 0.0, "learning_rate": 4.864198424621142e-05, "loss": 4.2123, "step": 82944 }, { "epoch": 0.0, "learning_rate": 4.86335982987009e-05, "loss": 4.2083, "step": 83456 }, { "epoch": 0.0, "learning_rate": 4.862521235119038e-05, "loss": 4.2065, "step": 83968 }, { "epoch": 0.0, "learning_rate": 4.861682640367986e-05, "loss": 4.2035, "step": 84480 }, { "epoch": 0.0, "learning_rate": 4.860844045616934e-05, "loss": 4.202, "step": 84992 }, { "epoch": 0.0, "learning_rate": 4.860005450865882e-05, "loss": 4.2046, "step": 85504 }, { "epoch": 0.0, "learning_rate": 4.85916685611483e-05, "loss": 4.2018, "step": 86016 }, { "epoch": 0.0, "learning_rate": 4.858328261363778e-05, "loss": 4.2275, "step": 86528 }, { "epoch": 0.0, "learning_rate": 4.857489666612726e-05, "loss": 4.2, "step": 87040 }, { "epoch": 0.0, "learning_rate": 4.856651071861674e-05, "loss": 4.2051, "step": 87552 }, { "epoch": 0.0, "learning_rate": 4.8558124771106226e-05, "loss": 4.1988, "step": 88064 }, { "epoch": 0.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.2047, "step": 88576 }, { "epoch": 0.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.1937, "step": 89088 }, { "epoch": 0.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.1918, "step": 89600 }, { "epoch": 0.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.1903, "step": 90112 }, { "epoch": 0.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.1845, "step": 90624 }, { "epoch": 0.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.1698, "step": 91136 }, { "epoch": 0.01, "learning_rate": 4.849947227494377e-05, "loss": 4.1863, "step": 91648 }, { "epoch": 0.01, "learning_rate": 4.849108632743325e-05, "loss": 4.1834, "step": 92160 }, { "epoch": 0.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1882, "step": 92672 }, { "epoch": 0.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1787, "step": 93184 }, { "epoch": 0.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1829, "step": 93696 }, { "epoch": 0.01, "learning_rate": 4.845755891619491e-05, "loss": 4.1718, "step": 94208 }, { "epoch": 0.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1724, "step": 94720 }, { "epoch": 0.01, "learning_rate": 4.844078702117387e-05, "loss": 4.1591, "step": 95232 }, { "epoch": 0.01, "learning_rate": 4.843240107366335e-05, "loss": 4.1669, "step": 95744 }, { "epoch": 0.01, "learning_rate": 4.842401512615282e-05, "loss": 4.1633, "step": 96256 }, { "epoch": 0.01, "learning_rate": 4.84156291786423e-05, "loss": 4.1638, "step": 96768 }, { "epoch": 0.01, "learning_rate": 4.840725960993552e-05, "loss": 4.1644, "step": 97280 }, { "epoch": 0.01, "learning_rate": 4.8398873662425e-05, "loss": 4.1699, "step": 97792 }, { "epoch": 0.01, "learning_rate": 4.839048771491447e-05, "loss": 4.1592, "step": 98304 }, { "epoch": 0.01, "learning_rate": 4.838210176740395e-05, "loss": 4.1607, "step": 98816 }, { "epoch": 0.01, "learning_rate": 4.837371581989343e-05, "loss": 4.1635, "step": 99328 }, { "epoch": 0.01, "learning_rate": 4.836532987238292e-05, "loss": 4.1495, "step": 99840 }, { "epoch": 0.01, "learning_rate": 4.8356960303676126e-05, "loss": 4.1611, "step": 100352 }, { "epoch": 0.01, "learning_rate": 4.8348574356165606e-05, "loss": 4.1478, "step": 100864 }, { "epoch": 0.01, "learning_rate": 4.8340188408655086e-05, "loss": 4.1404, "step": 101376 }, { "epoch": 0.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.1568, "step": 101888 }, { "epoch": 0.01, "learning_rate": 4.8323416513634046e-05, "loss": 4.1439, "step": 102400 }, { "epoch": 0.01, "learning_rate": 4.8315046944927255e-05, "loss": 4.1408, "step": 102912 }, { "epoch": 0.01, "learning_rate": 4.8306660997416735e-05, "loss": 4.1337, "step": 103424 }, { "epoch": 0.01, "learning_rate": 4.8298275049906215e-05, "loss": 4.1415, "step": 103936 }, { "epoch": 0.01, "learning_rate": 4.8289889102395695e-05, "loss": 4.1263, "step": 104448 }, { "epoch": 0.01, "learning_rate": 4.8281519533688904e-05, "loss": 4.1564, "step": 104960 }, { "epoch": 0.01, "learning_rate": 4.8273133586178384e-05, "loss": 4.1318, "step": 105472 }, { "epoch": 0.01, "learning_rate": 4.826474763866787e-05, "loss": 4.1453, "step": 105984 }, { "epoch": 0.01, "learning_rate": 4.825636169115735e-05, "loss": 4.1426, "step": 106496 }, { "epoch": 0.01, "learning_rate": 4.824797574364683e-05, "loss": 4.1245, "step": 107008 }, { "epoch": 0.01, "learning_rate": 4.823960617494004e-05, "loss": 4.1192, "step": 107520 }, { "epoch": 0.01, "learning_rate": 4.823122022742952e-05, "loss": 4.1306, "step": 108032 }, { "epoch": 0.01, "learning_rate": 4.8222834279919e-05, "loss": 4.1206, "step": 108544 }, { "epoch": 0.01, "learning_rate": 4.821446471121221e-05, "loss": 4.1166, "step": 109056 }, { "epoch": 0.01, "learning_rate": 4.820607876370169e-05, "loss": 4.1337, "step": 109568 }, { "epoch": 0.01, "learning_rate": 4.819769281619117e-05, "loss": 4.1317, "step": 110080 }, { "epoch": 0.01, "learning_rate": 4.818930686868065e-05, "loss": 4.1154, "step": 110592 }, { "epoch": 0.01, "learning_rate": 4.818093729997386e-05, "loss": 4.1098, "step": 111104 }, { "epoch": 0.01, "learning_rate": 4.817255135246334e-05, "loss": 4.1121, "step": 111616 }, { "epoch": 0.01, "learning_rate": 4.816416540495282e-05, "loss": 4.1219, "step": 112128 }, { "epoch": 0.01, "learning_rate": 4.8155779457442305e-05, "loss": 4.1236, "step": 112640 }, { "epoch": 0.01, "learning_rate": 4.8147393509931785e-05, "loss": 4.1217, "step": 113152 }, { "epoch": 0.01, "learning_rate": 4.8139023941224994e-05, "loss": 4.1226, "step": 113664 }, { "epoch": 0.01, "learning_rate": 4.8130637993714474e-05, "loss": 4.1226, "step": 114176 }, { "epoch": 0.01, "learning_rate": 4.8122252046203954e-05, "loss": 4.1236, "step": 114688 }, { "epoch": 0.01, "learning_rate": 4.8113866098693434e-05, "loss": 4.1056, "step": 115200 }, { "epoch": 0.01, "learning_rate": 4.810549652998664e-05, "loss": 4.1138, "step": 115712 }, { "epoch": 0.01, "learning_rate": 4.809711058247612e-05, "loss": 4.1126, "step": 116224 }, { "epoch": 0.01, "learning_rate": 4.80887246349656e-05, "loss": 4.0995, "step": 116736 }, { "epoch": 0.01, "learning_rate": 4.808033868745508e-05, "loss": 4.1112, "step": 117248 }, { "epoch": 0.01, "learning_rate": 4.807196911874829e-05, "loss": 4.1137, "step": 117760 }, { "epoch": 0.01, "learning_rate": 4.806358317123777e-05, "loss": 4.1145, "step": 118272 }, { "epoch": 0.01, "learning_rate": 4.805519722372726e-05, "loss": 4.0972, "step": 118784 }, { "epoch": 0.01, "learning_rate": 4.804681127621674e-05, "loss": 4.0862, "step": 119296 }, { "epoch": 0.01, "learning_rate": 4.803844170750995e-05, "loss": 4.103, "step": 119808 }, { "epoch": 0.01, "learning_rate": 4.803005575999943e-05, "loss": 4.1014, "step": 120320 }, { "epoch": 0.01, "learning_rate": 4.802166981248891e-05, "loss": 4.1048, "step": 120832 }, { "epoch": 0.01, "learning_rate": 4.801328386497839e-05, "loss": 4.0976, "step": 121344 }, { "epoch": 0.01, "learning_rate": 4.8004914296271596e-05, "loss": 4.0983, "step": 121856 }, { "epoch": 0.02, "learning_rate": 4.7996528348761076e-05, "loss": 4.0983, "step": 122368 }, { "epoch": 0.02, "learning_rate": 4.7988142401250556e-05, "loss": 4.0844, "step": 122880 }, { "epoch": 0.02, "learning_rate": 4.7979756453740036e-05, "loss": 4.0928, "step": 123392 }, { "epoch": 0.02, "learning_rate": 4.7971370506229516e-05, "loss": 4.0927, "step": 123904 }, { "epoch": 0.02, "learning_rate": 4.7962984558718996e-05, "loss": 4.1017, "step": 124416 }, { "epoch": 0.02, "learning_rate": 4.7954598611208476e-05, "loss": 4.1035, "step": 124928 }, { "epoch": 0.02, "learning_rate": 4.7946212663697956e-05, "loss": 4.0972, "step": 125440 }, { "epoch": 0.02, "learning_rate": 4.793784309499117e-05, "loss": 4.0823, "step": 125952 }, { "epoch": 0.02, "learning_rate": 4.792945714748065e-05, "loss": 4.0875, "step": 126464 }, { "epoch": 0.02, "learning_rate": 4.792107119997013e-05, "loss": 4.0865, "step": 126976 }, { "epoch": 0.02, "learning_rate": 4.7912685252459605e-05, "loss": 4.0953, "step": 127488 }, { "epoch": 0.02, "learning_rate": 4.790431568375282e-05, "loss": 4.0823, "step": 128000 }, { "epoch": 0.02, "learning_rate": 4.78959297362423e-05, "loss": 4.0804, "step": 128512 }, { "epoch": 0.02, "learning_rate": 4.7887543788731774e-05, "loss": 4.0732, "step": 129024 }, { "epoch": 0.02, "learning_rate": 4.7879157841221254e-05, "loss": 4.0938, "step": 129536 }, { "epoch": 0.02, "learning_rate": 4.787078827251447e-05, "loss": 4.0612, "step": 130048 }, { "epoch": 0.02, "learning_rate": 4.786240232500395e-05, "loss": 4.0773, "step": 130560 }, { "epoch": 0.02, "learning_rate": 4.7854032756297166e-05, "loss": 4.0838, "step": 131072 }, { "epoch": 0.02, "learning_rate": 4.7845646808786646e-05, "loss": 4.0714, "step": 131584 }, { "epoch": 0.02, "learning_rate": 4.7837260861276126e-05, "loss": 4.0724, "step": 132096 }, { "epoch": 0.02, "learning_rate": 4.7828874913765606e-05, "loss": 4.0809, "step": 132608 }, { "epoch": 0.02, "learning_rate": 4.782048896625508e-05, "loss": 4.071, "step": 133120 }, { "epoch": 0.02, "learning_rate": 4.781210301874456e-05, "loss": 4.0731, "step": 133632 }, { "epoch": 0.02, "learning_rate": 4.780371707123404e-05, "loss": 4.0769, "step": 134144 }, { "epoch": 0.02, "learning_rate": 4.779534750252725e-05, "loss": 4.0702, "step": 134656 }, { "epoch": 0.02, "learning_rate": 4.778696155501673e-05, "loss": 4.0772, "step": 135168 }, { "epoch": 0.02, "learning_rate": 4.777857560750621e-05, "loss": 4.0821, "step": 135680 }, { "epoch": 0.02, "learning_rate": 4.7770206038799423e-05, "loss": 4.0731, "step": 136192 }, { "epoch": 0.02, "learning_rate": 4.7761820091288903e-05, "loss": 4.0653, "step": 136704 }, { "epoch": 0.02, "learning_rate": 4.7753434143778383e-05, "loss": 4.0699, "step": 137216 }, { "epoch": 0.02, "learning_rate": 4.774504819626786e-05, "loss": 4.0673, "step": 137728 }, { "epoch": 0.02, "learning_rate": 4.773666224875734e-05, "loss": 4.0636, "step": 138240 }, { "epoch": 0.02, "learning_rate": 4.772827630124682e-05, "loss": 4.0588, "step": 138752 }, { "epoch": 0.02, "learning_rate": 4.77198903537363e-05, "loss": 4.0619, "step": 139264 }, { "epoch": 0.02, "learning_rate": 4.771150440622578e-05, "loss": 4.0748, "step": 139776 }, { "epoch": 0.02, "learning_rate": 4.770313483751899e-05, "loss": 4.0638, "step": 140288 }, { "epoch": 0.02, "learning_rate": 4.769474889000847e-05, "loss": 4.0637, "step": 140800 }, { "epoch": 0.02, "learning_rate": 4.768636294249795e-05, "loss": 4.0532, "step": 141312 }, { "epoch": 0.02, "learning_rate": 4.767799337379116e-05, "loss": 4.0561, "step": 141824 }, { "epoch": 0.02, "learning_rate": 4.766960742628064e-05, "loss": 4.0539, "step": 142336 }, { "epoch": 0.02, "learning_rate": 4.766122147877012e-05, "loss": 4.0708, "step": 142848 }, { "epoch": 0.02, "learning_rate": 4.76528355312596e-05, "loss": 4.0662, "step": 143360 }, { "epoch": 0.02, "learning_rate": 4.764444958374909e-05, "loss": 4.044, "step": 143872 }, { "epoch": 0.02, "learning_rate": 4.76360800150423e-05, "loss": 4.0523, "step": 144384 }, { "epoch": 0.02, "learning_rate": 4.762769406753178e-05, "loss": 4.0622, "step": 144896 }, { "epoch": 0.02, "learning_rate": 4.761930812002126e-05, "loss": 4.0547, "step": 145408 }, { "epoch": 0.02, "learning_rate": 4.761092217251074e-05, "loss": 4.0627, "step": 145920 }, { "epoch": 0.02, "learning_rate": 4.7602552603803946e-05, "loss": 4.0484, "step": 146432 }, { "epoch": 0.02, "learning_rate": 4.7594166656293426e-05, "loss": 4.0548, "step": 146944 }, { "epoch": 0.02, "learning_rate": 4.7585780708782906e-05, "loss": 4.0605, "step": 147456 }, { "epoch": 0.02, "learning_rate": 4.7577394761272386e-05, "loss": 4.05, "step": 147968 }, { "epoch": 0.02, "learning_rate": 4.7569025192565595e-05, "loss": 4.0513, "step": 148480 }, { "epoch": 0.02, "learning_rate": 4.7560639245055075e-05, "loss": 4.0532, "step": 148992 }, { "epoch": 0.02, "learning_rate": 4.7552253297544555e-05, "loss": 4.0434, "step": 149504 }, { "epoch": 0.02, "learning_rate": 4.7543867350034035e-05, "loss": 4.042, "step": 150016 }, { "epoch": 0.02, "learning_rate": 4.753549778132725e-05, "loss": 4.0553, "step": 150528 }, { "epoch": 0.02, "learning_rate": 4.752711183381673e-05, "loss": 4.0371, "step": 151040 }, { "epoch": 0.02, "learning_rate": 4.751872588630621e-05, "loss": 4.0451, "step": 151552 }, { "epoch": 0.02, "learning_rate": 4.751035631759942e-05, "loss": 4.0469, "step": 152064 }, { "epoch": 0.02, "learning_rate": 4.75019703700889e-05, "loss": 4.0435, "step": 152576 }, { "epoch": 0.03, "eval_loss": 4.046647071838379, "eval_runtime": 311.1083, "eval_samples_per_second": 1226.554, "eval_steps_per_second": 38.331, "step": 152640 }, { "epoch": 1.0, "learning_rate": 4.749358442257838e-05, "loss": 4.0327, "step": 153088 }, { "epoch": 1.0, "learning_rate": 4.748519847506786e-05, "loss": 4.0312, "step": 153600 }, { "epoch": 1.0, "learning_rate": 4.747682890636107e-05, "loss": 4.0519, "step": 154112 }, { "epoch": 1.0, "learning_rate": 4.746844295885055e-05, "loss": 4.033, "step": 154624 }, { "epoch": 1.0, "learning_rate": 4.746005701134003e-05, "loss": 4.0513, "step": 155136 }, { "epoch": 1.0, "learning_rate": 4.745167106382951e-05, "loss": 4.0273, "step": 155648 }, { "epoch": 1.0, "learning_rate": 4.7443301495122724e-05, "loss": 4.0415, "step": 156160 }, { "epoch": 1.0, "learning_rate": 4.7434915547612204e-05, "loss": 4.0236, "step": 156672 }, { "epoch": 1.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.0375, "step": 157184 }, { "epoch": 1.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0319, "step": 157696 }, { "epoch": 1.0, "learning_rate": 4.740977408388437e-05, "loss": 4.0307, "step": 158208 }, { "epoch": 1.0, "learning_rate": 4.740138813637385e-05, "loss": 4.0398, "step": 158720 }, { "epoch": 1.0, "learning_rate": 4.739303494647079e-05, "loss": 4.0228, "step": 159232 }, { "epoch": 1.0, "learning_rate": 4.738464899896027e-05, "loss": 4.0213, "step": 159744 }, { "epoch": 1.0, "learning_rate": 4.737626305144975e-05, "loss": 4.0197, "step": 160256 }, { "epoch": 1.0, "learning_rate": 4.736787710393923e-05, "loss": 4.0152, "step": 160768 }, { "epoch": 1.0, "learning_rate": 4.735949115642871e-05, "loss": 4.02, "step": 161280 }, { "epoch": 1.0, "learning_rate": 4.73511052089182e-05, "loss": 4.0234, "step": 161792 }, { "epoch": 1.0, "learning_rate": 4.734271926140768e-05, "loss": 4.0184, "step": 162304 }, { "epoch": 1.0, "learning_rate": 4.733433331389716e-05, "loss": 4.0446, "step": 162816 }, { "epoch": 1.0, "learning_rate": 4.732594736638664e-05, "loss": 4.0219, "step": 163328 }, { "epoch": 1.0, "learning_rate": 4.731756141887612e-05, "loss": 4.027, "step": 163840 }, { "epoch": 1.0, "learning_rate": 4.73091754713656e-05, "loss": 4.0213, "step": 164352 }, { "epoch": 1.0, "learning_rate": 4.730080590265881e-05, "loss": 4.0271, "step": 164864 }, { "epoch": 1.0, "learning_rate": 4.7292436333952016e-05, "loss": 4.0184, "step": 165376 }, { "epoch": 1.0, "learning_rate": 4.7284050386441496e-05, "loss": 4.0156, "step": 165888 }, { "epoch": 1.0, "learning_rate": 4.7275664438930976e-05, "loss": 4.0186, "step": 166400 }, { "epoch": 1.0, "learning_rate": 4.7267278491420456e-05, "loss": 4.0088, "step": 166912 }, { "epoch": 1.0, "learning_rate": 4.7258892543909936e-05, "loss": 3.9972, "step": 167424 }, { "epoch": 1.01, "learning_rate": 4.7250506596399416e-05, "loss": 4.0124, "step": 167936 }, { "epoch": 1.01, "learning_rate": 4.7242120648888896e-05, "loss": 4.0198, "step": 168448 }, { "epoch": 1.01, "learning_rate": 4.723375108018211e-05, "loss": 4.0134, "step": 168960 }, { "epoch": 1.01, "learning_rate": 4.722536513267159e-05, "loss": 4.0135, "step": 169472 }, { "epoch": 1.01, "learning_rate": 4.721697918516107e-05, "loss": 4.0162, "step": 169984 }, { "epoch": 1.01, "learning_rate": 4.720859323765055e-05, "loss": 4.0041, "step": 170496 }, { "epoch": 1.01, "learning_rate": 4.720020729014003e-05, "loss": 4.0056, "step": 171008 }, { "epoch": 1.01, "learning_rate": 4.7191821342629505e-05, "loss": 3.9981, "step": 171520 }, { "epoch": 1.01, "learning_rate": 4.7183435395118985e-05, "loss": 4.0008, "step": 172032 }, { "epoch": 1.01, "learning_rate": 4.71750658264122e-05, "loss": 3.9971, "step": 172544 }, { "epoch": 1.01, "learning_rate": 4.716667987890168e-05, "loss": 4.0007, "step": 173056 }, { "epoch": 1.01, "learning_rate": 4.7158293931391154e-05, "loss": 4.0031, "step": 173568 }, { "epoch": 1.01, "learning_rate": 4.7149907983880634e-05, "loss": 4.0095, "step": 174080 }, { "epoch": 1.01, "learning_rate": 4.714153841517385e-05, "loss": 3.9988, "step": 174592 }, { "epoch": 1.01, "learning_rate": 4.713315246766333e-05, "loss": 4.0011, "step": 175104 }, { "epoch": 1.01, "learning_rate": 4.712476652015281e-05, "loss": 4.0069, "step": 175616 }, { "epoch": 1.01, "learning_rate": 4.711638057264229e-05, "loss": 3.9893, "step": 176128 }, { "epoch": 1.01, "learning_rate": 4.7108011003935505e-05, "loss": 4.0018, "step": 176640 }, { "epoch": 1.01, "learning_rate": 4.7099641435228714e-05, "loss": 3.9958, "step": 177152 }, { "epoch": 1.01, "learning_rate": 4.7091255487718194e-05, "loss": 3.9801, "step": 177664 }, { "epoch": 1.01, "learning_rate": 4.7082869540207674e-05, "loss": 3.9993, "step": 178176 }, { "epoch": 1.01, "learning_rate": 4.7074483592697154e-05, "loss": 3.9926, "step": 178688 }, { "epoch": 1.01, "learning_rate": 4.706609764518663e-05, "loss": 3.9863, "step": 179200 }, { "epoch": 1.01, "learning_rate": 4.705771169767611e-05, "loss": 3.9854, "step": 179712 }, { "epoch": 1.01, "learning_rate": 4.704932575016559e-05, "loss": 3.9889, "step": 180224 }, { "epoch": 1.01, "learning_rate": 4.70409561814588e-05, "loss": 3.9718, "step": 180736 }, { "epoch": 1.01, "learning_rate": 4.703257023394828e-05, "loss": 3.9995, "step": 181248 }, { "epoch": 1.01, "learning_rate": 4.702418428643776e-05, "loss": 3.984, "step": 181760 }, { "epoch": 1.01, "learning_rate": 4.701579833892724e-05, "loss": 3.9949, "step": 182272 }, { "epoch": 1.01, "learning_rate": 4.700742877022045e-05, "loss": 3.9958, "step": 182784 }, { "epoch": 1.01, "learning_rate": 4.699904282270993e-05, "loss": 3.9784, "step": 183296 }, { "epoch": 1.01, "learning_rate": 4.699065687519941e-05, "loss": 3.9725, "step": 183808 }, { "epoch": 1.01, "learning_rate": 4.698227092768889e-05, "loss": 3.9873, "step": 184320 }, { "epoch": 1.01, "learning_rate": 4.69739013589821e-05, "loss": 3.9731, "step": 184832 }, { "epoch": 1.01, "learning_rate": 4.696551541147158e-05, "loss": 3.9704, "step": 185344 }, { "epoch": 1.01, "learning_rate": 4.695712946396106e-05, "loss": 3.9896, "step": 185856 }, { "epoch": 1.01, "learning_rate": 4.694874351645054e-05, "loss": 3.989, "step": 186368 }, { "epoch": 1.01, "learning_rate": 4.694037394774376e-05, "loss": 3.9721, "step": 186880 }, { "epoch": 1.01, "learning_rate": 4.693200437903697e-05, "loss": 3.9668, "step": 187392 }, { "epoch": 1.01, "learning_rate": 4.692361843152645e-05, "loss": 3.9691, "step": 187904 }, { "epoch": 1.01, "learning_rate": 4.6915232484015926e-05, "loss": 3.9776, "step": 188416 }, { "epoch": 1.01, "learning_rate": 4.6906846536505406e-05, "loss": 3.9826, "step": 188928 }, { "epoch": 1.01, "learning_rate": 4.6898460588994886e-05, "loss": 3.9799, "step": 189440 }, { "epoch": 1.01, "learning_rate": 4.6890074641484366e-05, "loss": 3.9864, "step": 189952 }, { "epoch": 1.01, "learning_rate": 4.6881688693973846e-05, "loss": 3.9788, "step": 190464 }, { "epoch": 1.01, "learning_rate": 4.6873302746463326e-05, "loss": 3.9868, "step": 190976 }, { "epoch": 1.01, "learning_rate": 4.6864933177756535e-05, "loss": 3.9687, "step": 191488 }, { "epoch": 1.01, "learning_rate": 4.6856547230246015e-05, "loss": 3.976, "step": 192000 }, { "epoch": 1.01, "learning_rate": 4.6848161282735495e-05, "loss": 3.9782, "step": 192512 }, { "epoch": 1.01, "learning_rate": 4.683977533522498e-05, "loss": 3.9617, "step": 193024 }, { "epoch": 1.01, "learning_rate": 4.683140576651819e-05, "loss": 3.9745, "step": 193536 }, { "epoch": 1.01, "learning_rate": 4.682301981900767e-05, "loss": 3.9822, "step": 194048 }, { "epoch": 1.01, "learning_rate": 4.681463387149715e-05, "loss": 3.9793, "step": 194560 }, { "epoch": 1.01, "learning_rate": 4.680624792398663e-05, "loss": 3.9633, "step": 195072 }, { "epoch": 1.01, "learning_rate": 4.679787835527984e-05, "loss": 3.9512, "step": 195584 }, { "epoch": 1.01, "learning_rate": 4.678950878657305e-05, "loss": 3.9693, "step": 196096 }, { "epoch": 1.01, "learning_rate": 4.678112283906253e-05, "loss": 3.9614, "step": 196608 }, { "epoch": 1.01, "learning_rate": 4.677273689155201e-05, "loss": 3.9752, "step": 197120 }, { "epoch": 1.01, "learning_rate": 4.676435094404149e-05, "loss": 3.9674, "step": 197632 }, { "epoch": 1.01, "learning_rate": 4.675596499653097e-05, "loss": 3.9663, "step": 198144 }, { "epoch": 1.02, "learning_rate": 4.674757904902045e-05, "loss": 3.9661, "step": 198656 }, { "epoch": 1.02, "learning_rate": 4.6739209480313664e-05, "loss": 3.9531, "step": 199168 }, { "epoch": 1.02, "learning_rate": 4.6730823532803144e-05, "loss": 3.9639, "step": 199680 }, { "epoch": 1.02, "learning_rate": 4.6722437585292624e-05, "loss": 3.9619, "step": 200192 }, { "epoch": 1.02, "learning_rate": 4.6714051637782104e-05, "loss": 3.9754, "step": 200704 }, { "epoch": 1.02, "learning_rate": 4.6705665690271584e-05, "loss": 3.9767, "step": 201216 }, { "epoch": 1.02, "learning_rate": 4.669729612156479e-05, "loss": 3.9678, "step": 201728 }, { "epoch": 1.02, "learning_rate": 4.668891017405427e-05, "loss": 3.9526, "step": 202240 }, { "epoch": 1.02, "learning_rate": 4.668052422654375e-05, "loss": 3.9628, "step": 202752 }, { "epoch": 1.02, "learning_rate": 4.667213827903323e-05, "loss": 3.9596, "step": 203264 }, { "epoch": 1.02, "learning_rate": 4.666376871032644e-05, "loss": 3.9689, "step": 203776 }, { "epoch": 1.02, "learning_rate": 4.665538276281592e-05, "loss": 3.9552, "step": 204288 }, { "epoch": 1.02, "learning_rate": 4.66469968153054e-05, "loss": 3.9609, "step": 204800 }, { "epoch": 1.02, "learning_rate": 4.663861086779488e-05, "loss": 3.9477, "step": 205312 }, { "epoch": 1.02, "learning_rate": 4.663022492028437e-05, "loss": 3.9694, "step": 205824 }, { "epoch": 1.02, "learning_rate": 4.662183897277385e-05, "loss": 3.9395, "step": 206336 }, { "epoch": 1.02, "learning_rate": 4.661345302526333e-05, "loss": 3.9569, "step": 206848 }, { "epoch": 1.02, "learning_rate": 4.660508345655654e-05, "loss": 3.9525, "step": 207360 }, { "epoch": 1.02, "learning_rate": 4.659669750904602e-05, "loss": 3.9535, "step": 207872 }, { "epoch": 1.02, "learning_rate": 4.65883115615355e-05, "loss": 3.9485, "step": 208384 }, { "epoch": 1.02, "learning_rate": 4.657992561402498e-05, "loss": 3.9583, "step": 208896 }, { "epoch": 1.02, "learning_rate": 4.6571556045318187e-05, "loss": 3.957, "step": 209408 }, { "epoch": 1.02, "learning_rate": 4.6563170097807667e-05, "loss": 3.9495, "step": 209920 }, { "epoch": 1.02, "learning_rate": 4.6554784150297146e-05, "loss": 3.9584, "step": 210432 }, { "epoch": 1.02, "learning_rate": 4.6546398202786626e-05, "loss": 3.945, "step": 210944 }, { "epoch": 1.02, "learning_rate": 4.6538028634079836e-05, "loss": 3.9632, "step": 211456 }, { "epoch": 1.02, "learning_rate": 4.652964268656932e-05, "loss": 3.9656, "step": 211968 }, { "epoch": 1.02, "learning_rate": 4.652127311786253e-05, "loss": 3.9494, "step": 212480 }, { "epoch": 1.02, "learning_rate": 4.651288717035201e-05, "loss": 3.9473, "step": 212992 }, { "epoch": 1.02, "learning_rate": 4.650450122284149e-05, "loss": 3.9496, "step": 213504 }, { "epoch": 1.02, "learning_rate": 4.649611527533097e-05, "loss": 3.9493, "step": 214016 }, { "epoch": 1.02, "learning_rate": 4.648772932782045e-05, "loss": 3.9442, "step": 214528 }, { "epoch": 1.02, "learning_rate": 4.647934338030993e-05, "loss": 3.9441, "step": 215040 }, { "epoch": 1.02, "learning_rate": 4.6470957432799404e-05, "loss": 3.9407, "step": 215552 }, { "epoch": 1.02, "learning_rate": 4.6462571485288884e-05, "loss": 3.9588, "step": 216064 }, { "epoch": 1.02, "learning_rate": 4.6454185537778364e-05, "loss": 3.9502, "step": 216576 }, { "epoch": 1.02, "learning_rate": 4.6445799590267844e-05, "loss": 3.9466, "step": 217088 }, { "epoch": 1.02, "learning_rate": 4.643743002156106e-05, "loss": 3.9386, "step": 217600 }, { "epoch": 1.02, "learning_rate": 4.642904407405054e-05, "loss": 3.9433, "step": 218112 }, { "epoch": 1.02, "learning_rate": 4.642065812654002e-05, "loss": 3.9371, "step": 218624 }, { "epoch": 1.02, "learning_rate": 4.64122721790295e-05, "loss": 3.9583, "step": 219136 }, { "epoch": 1.02, "learning_rate": 4.640390261032271e-05, "loss": 3.9533, "step": 219648 }, { "epoch": 1.02, "learning_rate": 4.639551666281219e-05, "loss": 3.935, "step": 220160 }, { "epoch": 1.02, "learning_rate": 4.638713071530167e-05, "loss": 3.9359, "step": 220672 }, { "epoch": 1.02, "learning_rate": 4.637874476779115e-05, "loss": 3.95, "step": 221184 }, { "epoch": 1.02, "learning_rate": 4.637035882028063e-05, "loss": 3.9411, "step": 221696 }, { "epoch": 1.02, "learning_rate": 4.636198925157384e-05, "loss": 3.9529, "step": 222208 }, { "epoch": 1.02, "learning_rate": 4.635360330406332e-05, "loss": 3.9349, "step": 222720 }, { "epoch": 1.02, "learning_rate": 4.63452173565528e-05, "loss": 3.9482, "step": 223232 }, { "epoch": 1.02, "learning_rate": 4.633683140904228e-05, "loss": 3.9436, "step": 223744 }, { "epoch": 1.02, "learning_rate": 4.632844546153176e-05, "loss": 3.9447, "step": 224256 }, { "epoch": 1.02, "learning_rate": 4.6320075892824974e-05, "loss": 3.9419, "step": 224768 }, { "epoch": 1.02, "learning_rate": 4.6311689945314454e-05, "loss": 3.9416, "step": 225280 }, { "epoch": 1.02, "learning_rate": 4.6303303997803934e-05, "loss": 3.9338, "step": 225792 }, { "epoch": 1.02, "learning_rate": 4.6294918050293413e-05, "loss": 3.9367, "step": 226304 }, { "epoch": 1.02, "learning_rate": 4.6286532102782893e-05, "loss": 3.9452, "step": 226816 }, { "epoch": 1.02, "learning_rate": 4.62781625340761e-05, "loss": 3.9343, "step": 227328 }, { "epoch": 1.02, "learning_rate": 4.626977658656558e-05, "loss": 3.9327, "step": 227840 }, { "epoch": 1.02, "learning_rate": 4.626139063905506e-05, "loss": 3.9366, "step": 228352 }, { "epoch": 1.02, "learning_rate": 4.625300469154454e-05, "loss": 3.936, "step": 228864 }, { "epoch": 1.03, "eval_loss": 3.972496509552002, "eval_runtime": 310.4496, "eval_samples_per_second": 1229.156, "eval_steps_per_second": 38.412, "step": 228960 }, { "epoch": 0.0, "learning_rate": 4.624461874403402e-05, "loss": 3.9217, "step": 229376 }, { "epoch": 0.0, "learning_rate": 4.62362327965235e-05, "loss": 3.9254, "step": 229888 }, { "epoch": 0.0, "learning_rate": 4.622784684901298e-05, "loss": 3.9456, "step": 230400 }, { "epoch": 0.0, "learning_rate": 4.621946090150246e-05, "loss": 3.9274, "step": 230912 }, { "epoch": 0.0, "learning_rate": 4.621107495399194e-05, "loss": 3.9492, "step": 231424 }, { "epoch": 0.0, "learning_rate": 4.620268900648142e-05, "loss": 3.9189, "step": 231936 }, { "epoch": 0.0, "learning_rate": 4.61943030589709e-05, "loss": 3.9386, "step": 232448 }, { "epoch": 0.0, "learning_rate": 4.618591711146038e-05, "loss": 3.923, "step": 232960 }, { "epoch": 0.0, "learning_rate": 4.617754754275359e-05, "loss": 3.9291, "step": 233472 }, { "epoch": 0.0, "learning_rate": 4.616916159524307e-05, "loss": 3.9294, "step": 233984 }, { "epoch": 0.0, "learning_rate": 4.616077564773255e-05, "loss": 3.9265, "step": 234496 }, { "epoch": 0.0, "learning_rate": 4.615238970022203e-05, "loss": 3.9348, "step": 235008 }, { "epoch": 0.0, "learning_rate": 4.6144036510318976e-05, "loss": 3.9207, "step": 235520 }, { "epoch": 0.0, "learning_rate": 4.6135650562808456e-05, "loss": 3.919, "step": 236032 }, { "epoch": 0.0, "learning_rate": 4.6127264615297936e-05, "loss": 3.923, "step": 236544 }, { "epoch": 0.0, "learning_rate": 4.6118878667787416e-05, "loss": 3.9097, "step": 237056 }, { "epoch": 0.0, "learning_rate": 4.6110492720276896e-05, "loss": 3.9217, "step": 237568 }, { "epoch": 0.0, "learning_rate": 4.6102106772766376e-05, "loss": 3.9227, "step": 238080 }, { "epoch": 0.0, "learning_rate": 4.6093720825255856e-05, "loss": 3.9173, "step": 238592 }, { "epoch": 0.0, "learning_rate": 4.6085334877745336e-05, "loss": 3.9409, "step": 239104 }, { "epoch": 0.0, "learning_rate": 4.6076965309038545e-05, "loss": 3.925, "step": 239616 }, { "epoch": 0.0, "learning_rate": 4.6068579361528025e-05, "loss": 3.9313, "step": 240128 }, { "epoch": 0.0, "learning_rate": 4.6060193414017505e-05, "loss": 3.9201, "step": 240640 }, { "epoch": 0.0, "learning_rate": 4.6051807466506985e-05, "loss": 3.9252, "step": 241152 }, { "epoch": 0.0, "learning_rate": 4.6043437897800194e-05, "loss": 3.9186, "step": 241664 }, { "epoch": 0.0, "learning_rate": 4.6035051950289674e-05, "loss": 3.9183, "step": 242176 }, { "epoch": 0.0, "learning_rate": 4.6026666002779154e-05, "loss": 3.9209, "step": 242688 }, { "epoch": 0.0, "learning_rate": 4.6018280055268634e-05, "loss": 3.9092, "step": 243200 }, { "epoch": 0.0, "learning_rate": 4.6009894107758114e-05, "loss": 3.9056, "step": 243712 }, { "epoch": 0.01, "learning_rate": 4.600152453905133e-05, "loss": 3.9104, "step": 244224 }, { "epoch": 0.01, "learning_rate": 4.599313859154081e-05, "loss": 3.9226, "step": 244736 }, { "epoch": 0.01, "learning_rate": 4.598475264403029e-05, "loss": 3.9192, "step": 245248 }, { "epoch": 0.01, "learning_rate": 4.597636669651977e-05, "loss": 3.9207, "step": 245760 }, { "epoch": 0.01, "learning_rate": 4.596799712781298e-05, "loss": 3.9225, "step": 246272 }, { "epoch": 0.01, "learning_rate": 4.595961118030246e-05, "loss": 3.9037, "step": 246784 }, { "epoch": 0.01, "learning_rate": 4.595122523279194e-05, "loss": 3.9113, "step": 247296 }, { "epoch": 0.01, "learning_rate": 4.594283928528142e-05, "loss": 3.9082, "step": 247808 }, { "epoch": 0.01, "learning_rate": 4.593446971657463e-05, "loss": 3.9012, "step": 248320 }, { "epoch": 0.01, "learning_rate": 4.592608376906411e-05, "loss": 3.9038, "step": 248832 }, { "epoch": 0.01, "learning_rate": 4.591769782155359e-05, "loss": 3.9035, "step": 249344 }, { "epoch": 0.01, "learning_rate": 4.590931187404307e-05, "loss": 3.9113, "step": 249856 }, { "epoch": 0.01, "learning_rate": 4.590094230533628e-05, "loss": 3.9138, "step": 250368 }, { "epoch": 0.01, "learning_rate": 4.589255635782576e-05, "loss": 3.9101, "step": 250880 }, { "epoch": 0.01, "learning_rate": 4.588417041031524e-05, "loss": 3.9032, "step": 251392 }, { "epoch": 0.01, "learning_rate": 4.587578446280472e-05, "loss": 3.9155, "step": 251904 }, { "epoch": 0.01, "learning_rate": 4.58673985152942e-05, "loss": 3.8973, "step": 252416 }, { "epoch": 0.01, "learning_rate": 4.585902894658741e-05, "loss": 3.9085, "step": 252928 }, { "epoch": 0.01, "learning_rate": 4.585064299907689e-05, "loss": 3.9034, "step": 253440 }, { "epoch": 0.01, "learning_rate": 4.584225705156637e-05, "loss": 3.8887, "step": 253952 }, { "epoch": 0.01, "learning_rate": 4.583388748285958e-05, "loss": 3.9101, "step": 254464 }, { "epoch": 0.01, "learning_rate": 4.582550153534906e-05, "loss": 3.9018, "step": 254976 }, { "epoch": 0.01, "learning_rate": 4.581711558783854e-05, "loss": 3.9, "step": 255488 }, { "epoch": 0.01, "learning_rate": 4.580872964032802e-05, "loss": 3.8919, "step": 256000 }, { "epoch": 0.01, "learning_rate": 4.580034369281751e-05, "loss": 3.8971, "step": 256512 }, { "epoch": 0.01, "learning_rate": 4.579197412411072e-05, "loss": 3.8835, "step": 257024 }, { "epoch": 0.01, "learning_rate": 4.57835881766002e-05, "loss": 3.9064, "step": 257536 }, { "epoch": 0.01, "learning_rate": 4.577520222908968e-05, "loss": 3.8969, "step": 258048 }, { "epoch": 0.01, "learning_rate": 4.576681628157916e-05, "loss": 3.9018, "step": 258560 }, { "epoch": 0.01, "learning_rate": 4.5758430334068637e-05, "loss": 3.9077, "step": 259072 }, { "epoch": 0.01, "learning_rate": 4.5750060765361846e-05, "loss": 3.8916, "step": 259584 }, { "epoch": 0.01, "learning_rate": 4.5741674817851326e-05, "loss": 3.8833, "step": 260096 }, { "epoch": 0.01, "learning_rate": 4.5733288870340806e-05, "loss": 3.9025, "step": 260608 }, { "epoch": 0.01, "learning_rate": 4.5724902922830286e-05, "loss": 3.8844, "step": 261120 }, { "epoch": 0.01, "learning_rate": 4.5716533354123495e-05, "loss": 3.8822, "step": 261632 }, { "epoch": 0.01, "learning_rate": 4.5708147406612975e-05, "loss": 3.9011, "step": 262144 }, { "epoch": 0.01, "learning_rate": 4.569976145910246e-05, "loss": 3.8981, "step": 262656 }, { "epoch": 0.01, "learning_rate": 4.569137551159194e-05, "loss": 3.8866, "step": 263168 }, { "epoch": 0.01, "learning_rate": 4.568300594288515e-05, "loss": 3.8839, "step": 263680 }, { "epoch": 0.01, "learning_rate": 4.567461999537463e-05, "loss": 3.8768, "step": 264192 }, { "epoch": 0.01, "learning_rate": 4.566623404786411e-05, "loss": 3.8869, "step": 264704 }, { "epoch": 0.01, "learning_rate": 4.565784810035359e-05, "loss": 3.8984, "step": 265216 }, { "epoch": 0.01, "learning_rate": 4.56494785316468e-05, "loss": 3.8971, "step": 265728 }, { "epoch": 0.01, "learning_rate": 4.564109258413628e-05, "loss": 3.8999, "step": 266240 }, { "epoch": 0.01, "learning_rate": 4.563270663662576e-05, "loss": 3.8909, "step": 266752 }, { "epoch": 0.01, "learning_rate": 4.562432068911524e-05, "loss": 3.907, "step": 267264 }, { "epoch": 0.01, "learning_rate": 4.561595112040845e-05, "loss": 3.8818, "step": 267776 }, { "epoch": 0.01, "learning_rate": 4.560756517289793e-05, "loss": 3.8937, "step": 268288 }, { "epoch": 0.01, "learning_rate": 4.5599179225387415e-05, "loss": 3.8888, "step": 268800 }, { "epoch": 0.01, "learning_rate": 4.5590793277876895e-05, "loss": 3.8754, "step": 269312 }, { "epoch": 0.01, "learning_rate": 4.5582407330366375e-05, "loss": 3.8969, "step": 269824 }, { "epoch": 0.01, "learning_rate": 4.5574037761659584e-05, "loss": 3.8972, "step": 270336 }, { "epoch": 0.01, "learning_rate": 4.5565651814149064e-05, "loss": 3.8899, "step": 270848 }, { "epoch": 0.01, "learning_rate": 4.5557265866638544e-05, "loss": 3.8799, "step": 271360 }, { "epoch": 0.01, "learning_rate": 4.5548879919128024e-05, "loss": 3.872, "step": 271872 }, { "epoch": 0.01, "learning_rate": 4.554051035042123e-05, "loss": 3.8837, "step": 272384 }, { "epoch": 0.01, "learning_rate": 4.553212440291071e-05, "loss": 3.8843, "step": 272896 }, { "epoch": 0.01, "learning_rate": 4.552373845540019e-05, "loss": 3.8908, "step": 273408 }, { "epoch": 0.01, "learning_rate": 4.5515352507889666e-05, "loss": 3.8801, "step": 273920 }, { "epoch": 0.01, "learning_rate": 4.550698293918288e-05, "loss": 3.8875, "step": 274432 }, { "epoch": 0.02, "learning_rate": 4.549859699167237e-05, "loss": 3.8804, "step": 274944 }, { "epoch": 0.02, "learning_rate": 4.549021104416185e-05, "loss": 3.8762, "step": 275456 }, { "epoch": 0.02, "learning_rate": 4.548182509665132e-05, "loss": 3.879, "step": 275968 }, { "epoch": 0.02, "learning_rate": 4.547345552794454e-05, "loss": 3.8761, "step": 276480 }, { "epoch": 0.02, "learning_rate": 4.546506958043402e-05, "loss": 3.8947, "step": 276992 }, { "epoch": 0.02, "learning_rate": 4.54566836329235e-05, "loss": 3.8919, "step": 277504 }, { "epoch": 0.02, "learning_rate": 4.544829768541297e-05, "loss": 3.8919, "step": 278016 }, { "epoch": 0.02, "learning_rate": 4.543992811670619e-05, "loss": 3.8697, "step": 278528 }, { "epoch": 0.02, "learning_rate": 4.5431542169195667e-05, "loss": 3.8834, "step": 279040 }, { "epoch": 0.02, "learning_rate": 4.542315622168514e-05, "loss": 3.8794, "step": 279552 }, { "epoch": 0.02, "learning_rate": 4.541477027417462e-05, "loss": 3.885, "step": 280064 }, { "epoch": 0.02, "learning_rate": 4.5406400705467836e-05, "loss": 3.878, "step": 280576 }, { "epoch": 0.02, "learning_rate": 4.539801475795732e-05, "loss": 3.8783, "step": 281088 }, { "epoch": 0.02, "learning_rate": 4.5389628810446796e-05, "loss": 3.8685, "step": 281600 }, { "epoch": 0.02, "learning_rate": 4.5381242862936275e-05, "loss": 3.8893, "step": 282112 }, { "epoch": 0.02, "learning_rate": 4.537287329422949e-05, "loss": 3.8616, "step": 282624 }, { "epoch": 0.02, "learning_rate": 4.536448734671897e-05, "loss": 3.8763, "step": 283136 }, { "epoch": 0.02, "learning_rate": 4.5356101399208444e-05, "loss": 3.8748, "step": 283648 }, { "epoch": 0.02, "learning_rate": 4.5347715451697924e-05, "loss": 3.8738, "step": 284160 }, { "epoch": 0.02, "learning_rate": 4.533934588299114e-05, "loss": 3.8693, "step": 284672 }, { "epoch": 0.02, "learning_rate": 4.5330959935480613e-05, "loss": 3.8843, "step": 285184 }, { "epoch": 0.02, "learning_rate": 4.5322573987970093e-05, "loss": 3.8775, "step": 285696 }, { "epoch": 0.02, "learning_rate": 4.5314188040459573e-05, "loss": 3.87, "step": 286208 }, { "epoch": 0.02, "learning_rate": 4.530580209294906e-05, "loss": 3.8833, "step": 286720 }, { "epoch": 0.02, "learning_rate": 4.529743252424227e-05, "loss": 3.8692, "step": 287232 }, { "epoch": 0.02, "learning_rate": 4.528904657673175e-05, "loss": 3.8814, "step": 287744 }, { "epoch": 0.02, "learning_rate": 4.528066062922123e-05, "loss": 3.8877, "step": 288256 }, { "epoch": 0.02, "learning_rate": 4.5272291060514445e-05, "loss": 3.8764, "step": 288768 }, { "epoch": 0.02, "learning_rate": 4.526390511300392e-05, "loss": 3.8712, "step": 289280 }, { "epoch": 0.02, "learning_rate": 4.52555191654934e-05, "loss": 3.8692, "step": 289792 }, { "epoch": 0.02, "learning_rate": 4.524713321798288e-05, "loss": 3.8695, "step": 290304 }, { "epoch": 0.02, "learning_rate": 4.523874727047236e-05, "loss": 3.8679, "step": 290816 }, { "epoch": 0.02, "learning_rate": 4.523036132296184e-05, "loss": 3.8735, "step": 291328 }, { "epoch": 0.02, "learning_rate": 4.522197537545132e-05, "loss": 3.8586, "step": 291840 }, { "epoch": 0.02, "learning_rate": 4.52135894279408e-05, "loss": 3.8814, "step": 292352 }, { "epoch": 0.02, "learning_rate": 4.520521985923401e-05, "loss": 3.877, "step": 292864 }, { "epoch": 0.02, "learning_rate": 4.5196833911723494e-05, "loss": 3.8732, "step": 293376 }, { "epoch": 0.02, "learning_rate": 4.5188447964212974e-05, "loss": 3.8604, "step": 293888 }, { "epoch": 0.02, "learning_rate": 4.5180062016702454e-05, "loss": 3.8665, "step": 294400 }, { "epoch": 0.02, "learning_rate": 4.517169244799566e-05, "loss": 3.8641, "step": 294912 }, { "epoch": 0.02, "learning_rate": 4.516330650048514e-05, "loss": 3.878, "step": 295424 }, { "epoch": 0.02, "learning_rate": 4.515492055297462e-05, "loss": 3.8808, "step": 295936 }, { "epoch": 0.02, "learning_rate": 4.51465346054641e-05, "loss": 3.8664, "step": 296448 }, { "epoch": 0.02, "learning_rate": 4.513816503675731e-05, "loss": 3.8539, "step": 296960 }, { "epoch": 0.02, "learning_rate": 4.512977908924679e-05, "loss": 3.8741, "step": 297472 }, { "epoch": 0.02, "learning_rate": 4.512139314173627e-05, "loss": 3.8653, "step": 297984 }, { "epoch": 0.02, "learning_rate": 4.511300719422575e-05, "loss": 3.8803, "step": 298496 }, { "epoch": 0.02, "learning_rate": 4.510463762551896e-05, "loss": 3.8593, "step": 299008 }, { "epoch": 0.02, "learning_rate": 4.509625167800845e-05, "loss": 3.8721, "step": 299520 }, { "epoch": 0.02, "learning_rate": 4.508786573049793e-05, "loss": 3.8709, "step": 300032 }, { "epoch": 0.02, "learning_rate": 4.507947978298741e-05, "loss": 3.8751, "step": 300544 }, { "epoch": 0.02, "learning_rate": 4.5071110214280616e-05, "loss": 3.8701, "step": 301056 }, { "epoch": 0.02, "learning_rate": 4.5062724266770096e-05, "loss": 3.867, "step": 301568 }, { "epoch": 0.02, "learning_rate": 4.5054338319259576e-05, "loss": 3.8605, "step": 302080 }, { "epoch": 0.02, "learning_rate": 4.5045952371749056e-05, "loss": 3.8637, "step": 302592 }, { "epoch": 0.02, "learning_rate": 4.5037582803042265e-05, "loss": 3.8686, "step": 303104 }, { "epoch": 0.02, "learning_rate": 4.5029196855531745e-05, "loss": 3.8658, "step": 303616 }, { "epoch": 0.02, "learning_rate": 4.5020810908021225e-05, "loss": 3.8593, "step": 304128 }, { "epoch": 0.02, "learning_rate": 4.5012424960510705e-05, "loss": 3.8691, "step": 304640 }, { "epoch": 0.02, "learning_rate": 4.5004055391803914e-05, "loss": 3.8613, "step": 305152 }, { "epoch": 0.03, "eval_loss": 3.9313888549804688, "eval_runtime": 306.8209, "eval_samples_per_second": 1243.693, "eval_steps_per_second": 38.866, "step": 305280 }, { "epoch": 1.0, "learning_rate": 4.49956694442934e-05, "loss": 3.8555, "step": 305664 }, { "epoch": 1.0, "learning_rate": 4.498728349678288e-05, "loss": 3.8555, "step": 306176 }, { "epoch": 1.0, "learning_rate": 4.497889754927236e-05, "loss": 3.8705, "step": 306688 }, { "epoch": 1.0, "learning_rate": 4.497052798056557e-05, "loss": 3.8593, "step": 307200 }, { "epoch": 1.0, "learning_rate": 4.496214203305505e-05, "loss": 3.873, "step": 307712 }, { "epoch": 1.0, "learning_rate": 4.495375608554453e-05, "loss": 3.8557, "step": 308224 }, { "epoch": 1.0, "learning_rate": 4.494537013803401e-05, "loss": 3.8616, "step": 308736 }, { "epoch": 1.0, "learning_rate": 4.493700056932722e-05, "loss": 3.8545, "step": 309248 }, { "epoch": 1.0, "learning_rate": 4.49286146218167e-05, "loss": 3.8587, "step": 309760 }, { "epoch": 1.0, "learning_rate": 4.492022867430618e-05, "loss": 3.8582, "step": 310272 }, { "epoch": 1.0, "learning_rate": 4.491184272679566e-05, "loss": 3.8573, "step": 310784 }, { "epoch": 1.0, "learning_rate": 4.490347315808887e-05, "loss": 3.8651, "step": 311296 }, { "epoch": 1.0, "learning_rate": 4.4895103589382084e-05, "loss": 3.8536, "step": 311808 }, { "epoch": 1.0, "learning_rate": 4.4886717641871564e-05, "loss": 3.849, "step": 312320 }, { "epoch": 1.0, "learning_rate": 4.4878331694361044e-05, "loss": 3.8506, "step": 312832 }, { "epoch": 1.0, "learning_rate": 4.4869945746850524e-05, "loss": 3.8408, "step": 313344 }, { "epoch": 1.0, "learning_rate": 4.4861559799340004e-05, "loss": 3.8506, "step": 313856 }, { "epoch": 1.0, "learning_rate": 4.4853173851829484e-05, "loss": 3.8518, "step": 314368 }, { "epoch": 1.0, "learning_rate": 4.4844787904318964e-05, "loss": 3.8495, "step": 314880 }, { "epoch": 1.0, "learning_rate": 4.4836401956808444e-05, "loss": 3.8714, "step": 315392 }, { "epoch": 1.0, "learning_rate": 4.482803238810165e-05, "loss": 3.8558, "step": 315904 }, { "epoch": 1.0, "learning_rate": 4.481964644059113e-05, "loss": 3.8614, "step": 316416 }, { "epoch": 1.0, "learning_rate": 4.481126049308061e-05, "loss": 3.8525, "step": 316928 }, { "epoch": 1.0, "learning_rate": 4.480287454557009e-05, "loss": 3.8561, "step": 317440 }, { "epoch": 1.0, "learning_rate": 4.479450497686331e-05, "loss": 3.8466, "step": 317952 }, { "epoch": 1.0, "learning_rate": 4.478611902935279e-05, "loss": 3.8556, "step": 318464 }, { "epoch": 1.0, "learning_rate": 4.477773308184227e-05, "loss": 3.8514, "step": 318976 }, { "epoch": 1.0, "learning_rate": 4.476934713433175e-05, "loss": 3.8448, "step": 319488 }, { "epoch": 1.0, "learning_rate": 4.476097756562496e-05, "loss": 3.8405, "step": 320000 }, { "epoch": 1.0, "learning_rate": 4.475259161811444e-05, "loss": 3.8438, "step": 320512 }, { "epoch": 1.01, "learning_rate": 4.474420567060392e-05, "loss": 3.8511, "step": 321024 }, { "epoch": 1.01, "learning_rate": 4.4735836101897126e-05, "loss": 3.8545, "step": 321536 }, { "epoch": 1.01, "learning_rate": 4.4727450154386606e-05, "loss": 3.8505, "step": 322048 }, { "epoch": 1.01, "learning_rate": 4.4719064206876086e-05, "loss": 3.8533, "step": 322560 }, { "epoch": 1.01, "learning_rate": 4.4710678259365566e-05, "loss": 3.8387, "step": 323072 }, { "epoch": 1.01, "learning_rate": 4.4702292311855046e-05, "loss": 3.8461, "step": 323584 }, { "epoch": 1.01, "learning_rate": 4.4693906364344526e-05, "loss": 3.8431, "step": 324096 }, { "epoch": 1.01, "learning_rate": 4.4685520416834006e-05, "loss": 3.8338, "step": 324608 }, { "epoch": 1.01, "learning_rate": 4.4677134469323486e-05, "loss": 3.8408, "step": 325120 }, { "epoch": 1.01, "learning_rate": 4.4668764900616695e-05, "loss": 3.8351, "step": 325632 }, { "epoch": 1.01, "learning_rate": 4.4660378953106175e-05, "loss": 3.847, "step": 326144 }, { "epoch": 1.01, "learning_rate": 4.4651993005595655e-05, "loss": 3.8489, "step": 326656 }, { "epoch": 1.01, "learning_rate": 4.464362343688887e-05, "loss": 3.8442, "step": 327168 }, { "epoch": 1.01, "learning_rate": 4.4635237489378344e-05, "loss": 3.8358, "step": 327680 }, { "epoch": 1.01, "learning_rate": 4.4626851541867824e-05, "loss": 3.8504, "step": 328192 }, { "epoch": 1.01, "learning_rate": 4.4618465594357304e-05, "loss": 3.8324, "step": 328704 }, { "epoch": 1.01, "learning_rate": 4.4610079646846784e-05, "loss": 3.8458, "step": 329216 }, { "epoch": 1.01, "learning_rate": 4.460171007814e-05, "loss": 3.838, "step": 329728 }, { "epoch": 1.01, "learning_rate": 4.459332413062948e-05, "loss": 3.8229, "step": 330240 }, { "epoch": 1.01, "learning_rate": 4.458493818311896e-05, "loss": 3.8477, "step": 330752 }, { "epoch": 1.01, "learning_rate": 4.457656861441217e-05, "loss": 3.8371, "step": 331264 }, { "epoch": 1.01, "learning_rate": 4.456818266690165e-05, "loss": 3.8354, "step": 331776 }, { "epoch": 1.01, "learning_rate": 4.455979671939113e-05, "loss": 3.831, "step": 332288 }, { "epoch": 1.01, "learning_rate": 4.455141077188061e-05, "loss": 3.8288, "step": 332800 }, { "epoch": 1.01, "learning_rate": 4.454304120317382e-05, "loss": 3.8257, "step": 333312 }, { "epoch": 1.01, "learning_rate": 4.45346552556633e-05, "loss": 3.8375, "step": 333824 }, { "epoch": 1.01, "learning_rate": 4.452626930815278e-05, "loss": 3.8373, "step": 334336 }, { "epoch": 1.01, "learning_rate": 4.451788336064226e-05, "loss": 3.8365, "step": 334848 }, { "epoch": 1.01, "learning_rate": 4.450951379193547e-05, "loss": 3.8422, "step": 335360 }, { "epoch": 1.01, "learning_rate": 4.4501127844424954e-05, "loss": 3.8306, "step": 335872 }, { "epoch": 1.01, "learning_rate": 4.4492741896914433e-05, "loss": 3.8184, "step": 336384 }, { "epoch": 1.01, "learning_rate": 4.4484355949403913e-05, "loss": 3.8401, "step": 336896 }, { "epoch": 1.01, "learning_rate": 4.447598638069712e-05, "loss": 3.8232, "step": 337408 }, { "epoch": 1.01, "learning_rate": 4.44676004331866e-05, "loss": 3.8165, "step": 337920 }, { "epoch": 1.01, "learning_rate": 4.445921448567608e-05, "loss": 3.8426, "step": 338432 }, { "epoch": 1.01, "learning_rate": 4.445082853816556e-05, "loss": 3.8343, "step": 338944 }, { "epoch": 1.01, "learning_rate": 4.444245896945877e-05, "loss": 3.8263, "step": 339456 }, { "epoch": 1.01, "learning_rate": 4.443407302194825e-05, "loss": 3.8228, "step": 339968 }, { "epoch": 1.01, "learning_rate": 4.442568707443773e-05, "loss": 3.8134, "step": 340480 }, { "epoch": 1.01, "learning_rate": 4.441730112692721e-05, "loss": 3.825, "step": 340992 }, { "epoch": 1.01, "learning_rate": 4.440893155822042e-05, "loss": 3.8403, "step": 341504 }, { "epoch": 1.01, "learning_rate": 4.44005456107099e-05, "loss": 3.8326, "step": 342016 }, { "epoch": 1.01, "learning_rate": 4.439215966319939e-05, "loss": 3.8358, "step": 342528 }, { "epoch": 1.01, "learning_rate": 4.438377371568887e-05, "loss": 3.8293, "step": 343040 }, { "epoch": 1.01, "learning_rate": 4.4375404146982076e-05, "loss": 3.8459, "step": 343552 }, { "epoch": 1.01, "learning_rate": 4.4367018199471556e-05, "loss": 3.8215, "step": 344064 }, { "epoch": 1.01, "learning_rate": 4.4358632251961036e-05, "loss": 3.8344, "step": 344576 }, { "epoch": 1.01, "learning_rate": 4.4350246304450516e-05, "loss": 3.8293, "step": 345088 }, { "epoch": 1.01, "learning_rate": 4.4341876735743725e-05, "loss": 3.8098, "step": 345600 }, { "epoch": 1.01, "learning_rate": 4.4333490788233205e-05, "loss": 3.8406, "step": 346112 }, { "epoch": 1.01, "learning_rate": 4.4325104840722685e-05, "loss": 3.8351, "step": 346624 }, { "epoch": 1.01, "learning_rate": 4.4316718893212165e-05, "loss": 3.8314, "step": 347136 }, { "epoch": 1.01, "learning_rate": 4.4308349324505374e-05, "loss": 3.8213, "step": 347648 }, { "epoch": 1.01, "learning_rate": 4.4299963376994854e-05, "loss": 3.8099, "step": 348160 }, { "epoch": 1.01, "learning_rate": 4.429157742948434e-05, "loss": 3.8259, "step": 348672 }, { "epoch": 1.01, "learning_rate": 4.428320786077755e-05, "loss": 3.8224, "step": 349184 }, { "epoch": 1.01, "learning_rate": 4.427482191326703e-05, "loss": 3.8309, "step": 349696 }, { "epoch": 1.01, "learning_rate": 4.426643596575651e-05, "loss": 3.8223, "step": 350208 }, { "epoch": 1.01, "learning_rate": 4.425805001824599e-05, "loss": 3.8257, "step": 350720 }, { "epoch": 1.02, "learning_rate": 4.424966407073547e-05, "loss": 3.8216, "step": 351232 }, { "epoch": 1.02, "learning_rate": 4.424127812322495e-05, "loss": 3.8206, "step": 351744 }, { "epoch": 1.02, "learning_rate": 4.423289217571443e-05, "loss": 3.8193, "step": 352256 }, { "epoch": 1.02, "learning_rate": 4.422452260700764e-05, "loss": 3.8172, "step": 352768 }, { "epoch": 1.02, "learning_rate": 4.421613665949712e-05, "loss": 3.8323, "step": 353280 }, { "epoch": 1.02, "learning_rate": 4.42077507119866e-05, "loss": 3.8329, "step": 353792 }, { "epoch": 1.02, "learning_rate": 4.419936476447608e-05, "loss": 3.8374, "step": 354304 }, { "epoch": 1.02, "learning_rate": 4.4190995195769294e-05, "loss": 3.8094, "step": 354816 }, { "epoch": 1.02, "learning_rate": 4.4182609248258774e-05, "loss": 3.825, "step": 355328 }, { "epoch": 1.02, "learning_rate": 4.4174223300748254e-05, "loss": 3.8219, "step": 355840 }, { "epoch": 1.02, "learning_rate": 4.4165837353237734e-05, "loss": 3.8247, "step": 356352 }, { "epoch": 1.02, "learning_rate": 4.4157467784530943e-05, "loss": 3.8219, "step": 356864 }, { "epoch": 1.02, "learning_rate": 4.4149081837020423e-05, "loss": 3.8166, "step": 357376 }, { "epoch": 1.02, "learning_rate": 4.41406958895099e-05, "loss": 3.8154, "step": 357888 }, { "epoch": 1.02, "learning_rate": 4.413230994199938e-05, "loss": 3.8294, "step": 358400 }, { "epoch": 1.02, "learning_rate": 4.412394037329259e-05, "loss": 3.8035, "step": 358912 }, { "epoch": 1.02, "learning_rate": 4.411555442578207e-05, "loss": 3.8174, "step": 359424 }, { "epoch": 1.02, "learning_rate": 4.410716847827155e-05, "loss": 3.8115, "step": 359936 }, { "epoch": 1.02, "learning_rate": 4.409878253076103e-05, "loss": 3.8206, "step": 360448 }, { "epoch": 1.02, "learning_rate": 4.409041296205425e-05, "loss": 3.8125, "step": 360960 }, { "epoch": 1.02, "learning_rate": 4.408202701454373e-05, "loss": 3.824, "step": 361472 }, { "epoch": 1.02, "learning_rate": 4.407364106703321e-05, "loss": 3.8217, "step": 361984 }, { "epoch": 1.02, "learning_rate": 4.406525511952269e-05, "loss": 3.8131, "step": 362496 }, { "epoch": 1.02, "learning_rate": 4.40568855508159e-05, "loss": 3.8252, "step": 363008 }, { "epoch": 1.02, "learning_rate": 4.404849960330538e-05, "loss": 3.8131, "step": 363520 }, { "epoch": 1.02, "learning_rate": 4.404011365579486e-05, "loss": 3.8264, "step": 364032 }, { "epoch": 1.02, "learning_rate": 4.403172770828434e-05, "loss": 3.8281, "step": 364544 }, { "epoch": 1.02, "learning_rate": 4.4023358139577546e-05, "loss": 3.817, "step": 365056 }, { "epoch": 1.02, "learning_rate": 4.4014972192067026e-05, "loss": 3.8145, "step": 365568 }, { "epoch": 1.02, "learning_rate": 4.4006586244556506e-05, "loss": 3.8168, "step": 366080 }, { "epoch": 1.02, "learning_rate": 4.3998200297045986e-05, "loss": 3.8113, "step": 366592 }, { "epoch": 1.02, "learning_rate": 4.39898307283392e-05, "loss": 3.8137, "step": 367104 }, { "epoch": 1.02, "learning_rate": 4.398144478082868e-05, "loss": 3.817, "step": 367616 }, { "epoch": 1.02, "learning_rate": 4.397305883331816e-05, "loss": 3.804, "step": 368128 }, { "epoch": 1.02, "learning_rate": 4.396467288580764e-05, "loss": 3.8237, "step": 368640 }, { "epoch": 1.02, "learning_rate": 4.395630331710085e-05, "loss": 3.8193, "step": 369152 }, { "epoch": 1.02, "learning_rate": 4.394791736959033e-05, "loss": 3.8199, "step": 369664 }, { "epoch": 1.02, "learning_rate": 4.393953142207981e-05, "loss": 3.8051, "step": 370176 }, { "epoch": 1.02, "learning_rate": 4.393114547456929e-05, "loss": 3.8111, "step": 370688 }, { "epoch": 1.02, "learning_rate": 4.39227759058625e-05, "loss": 3.8103, "step": 371200 }, { "epoch": 1.02, "learning_rate": 4.391438995835198e-05, "loss": 3.8197, "step": 371712 }, { "epoch": 1.02, "learning_rate": 4.390600401084146e-05, "loss": 3.8226, "step": 372224 }, { "epoch": 1.02, "learning_rate": 4.389761806333094e-05, "loss": 3.8139, "step": 372736 }, { "epoch": 1.02, "learning_rate": 4.3889248494624155e-05, "loss": 3.7994, "step": 373248 }, { "epoch": 1.02, "learning_rate": 4.3880862547113635e-05, "loss": 3.8197, "step": 373760 }, { "epoch": 1.02, "learning_rate": 4.3872476599603115e-05, "loss": 3.8103, "step": 374272 }, { "epoch": 1.02, "learning_rate": 4.3864090652092595e-05, "loss": 3.8227, "step": 374784 }, { "epoch": 1.02, "learning_rate": 4.3855721083385804e-05, "loss": 3.805, "step": 375296 }, { "epoch": 1.02, "learning_rate": 4.3847335135875284e-05, "loss": 3.8204, "step": 375808 }, { "epoch": 1.02, "learning_rate": 4.3838949188364764e-05, "loss": 3.8159, "step": 376320 }, { "epoch": 1.02, "learning_rate": 4.3830563240854244e-05, "loss": 3.8217, "step": 376832 }, { "epoch": 1.02, "learning_rate": 4.3822193672147453e-05, "loss": 3.8135, "step": 377344 }, { "epoch": 1.02, "learning_rate": 4.381380772463693e-05, "loss": 3.8125, "step": 377856 }, { "epoch": 1.02, "learning_rate": 4.380543815593014e-05, "loss": 3.8064, "step": 378368 }, { "epoch": 1.02, "learning_rate": 4.379705220841962e-05, "loss": 3.811, "step": 378880 }, { "epoch": 1.02, "learning_rate": 4.378866626090911e-05, "loss": 3.815, "step": 379392 }, { "epoch": 1.02, "learning_rate": 4.378028031339859e-05, "loss": 3.8113, "step": 379904 }, { "epoch": 1.02, "learning_rate": 4.377189436588807e-05, "loss": 3.8064, "step": 380416 }, { "epoch": 1.02, "learning_rate": 4.376350841837754e-05, "loss": 3.81, "step": 380928 }, { "epoch": 1.02, "learning_rate": 4.375512247086702e-05, "loss": 3.8119, "step": 381440 }, { "epoch": 1.03, "eval_loss": 3.906362533569336, "eval_runtime": 307.2937, "eval_samples_per_second": 1241.78, "eval_steps_per_second": 38.807, "step": 381600 }, { "epoch": 0.0, "learning_rate": 4.37467365233565e-05, "loss": 3.7979, "step": 381952 }, { "epoch": 0.0, "learning_rate": 4.373835057584598e-05, "loss": 3.7982, "step": 382464 }, { "epoch": 0.0, "learning_rate": 4.372996462833546e-05, "loss": 3.8167, "step": 382976 }, { "epoch": 0.0, "learning_rate": 4.372157868082494e-05, "loss": 3.8041, "step": 383488 }, { "epoch": 0.0, "learning_rate": 4.371319273331442e-05, "loss": 3.8176, "step": 384000 }, { "epoch": 0.0, "learning_rate": 4.37048067858039e-05, "loss": 3.8029, "step": 384512 }, { "epoch": 0.0, "learning_rate": 4.369642083829338e-05, "loss": 3.8066, "step": 385024 }, { "epoch": 0.0, "learning_rate": 4.368803489078286e-05, "loss": 3.8054, "step": 385536 }, { "epoch": 0.0, "learning_rate": 4.367968170087981e-05, "loss": 3.8036, "step": 386048 }, { "epoch": 0.0, "learning_rate": 4.367129575336929e-05, "loss": 3.8043, "step": 386560 }, { "epoch": 0.0, "learning_rate": 4.366290980585877e-05, "loss": 3.8082, "step": 387072 }, { "epoch": 0.0, "learning_rate": 4.365452385834825e-05, "loss": 3.8081, "step": 387584 }, { "epoch": 0.0, "learning_rate": 4.3646154289641456e-05, "loss": 3.8025, "step": 388096 }, { "epoch": 0.0, "learning_rate": 4.3637768342130936e-05, "loss": 3.795, "step": 388608 }, { "epoch": 0.0, "learning_rate": 4.3629382394620416e-05, "loss": 3.8022, "step": 389120 }, { "epoch": 0.0, "learning_rate": 4.3620996447109896e-05, "loss": 3.7877, "step": 389632 }, { "epoch": 0.0, "learning_rate": 4.3612610499599376e-05, "loss": 3.7975, "step": 390144 }, { "epoch": 0.0, "learning_rate": 4.3604224552088856e-05, "loss": 3.7994, "step": 390656 }, { "epoch": 0.0, "learning_rate": 4.3595838604578336e-05, "loss": 3.7985, "step": 391168 }, { "epoch": 0.0, "learning_rate": 4.3587452657067816e-05, "loss": 3.82, "step": 391680 }, { "epoch": 0.0, "learning_rate": 4.3579066709557295e-05, "loss": 3.8066, "step": 392192 }, { "epoch": 0.0, "learning_rate": 4.3570680762046775e-05, "loss": 3.8101, "step": 392704 }, { "epoch": 0.0, "learning_rate": 4.3562294814536255e-05, "loss": 3.8009, "step": 393216 }, { "epoch": 0.0, "learning_rate": 4.355392524582947e-05, "loss": 3.8044, "step": 393728 }, { "epoch": 0.0, "learning_rate": 4.354553929831895e-05, "loss": 3.7964, "step": 394240 }, { "epoch": 0.0, "learning_rate": 4.353715335080843e-05, "loss": 3.8039, "step": 394752 }, { "epoch": 0.0, "learning_rate": 4.3528767403297904e-05, "loss": 3.7966, "step": 395264 }, { "epoch": 0.0, "learning_rate": 4.3520381455787384e-05, "loss": 3.7955, "step": 395776 }, { "epoch": 0.0, "learning_rate": 4.3511995508276864e-05, "loss": 3.7909, "step": 396288 }, { "epoch": 0.0, "learning_rate": 4.3503609560766344e-05, "loss": 3.7919, "step": 396800 }, { "epoch": 0.01, "learning_rate": 4.3495223613255824e-05, "loss": 3.7975, "step": 397312 }, { "epoch": 0.01, "learning_rate": 4.348685404454903e-05, "loss": 3.8055, "step": 397824 }, { "epoch": 0.01, "learning_rate": 4.347846809703851e-05, "loss": 3.799, "step": 398336 }, { "epoch": 0.01, "learning_rate": 4.347008214952799e-05, "loss": 3.8064, "step": 398848 }, { "epoch": 0.01, "learning_rate": 4.346169620201748e-05, "loss": 3.7874, "step": 399360 }, { "epoch": 0.01, "learning_rate": 4.345332663331069e-05, "loss": 3.7977, "step": 399872 }, { "epoch": 0.01, "learning_rate": 4.344494068580017e-05, "loss": 3.7916, "step": 400384 }, { "epoch": 0.01, "learning_rate": 4.343655473828965e-05, "loss": 3.7854, "step": 400896 }, { "epoch": 0.01, "learning_rate": 4.342816879077913e-05, "loss": 3.7931, "step": 401408 }, { "epoch": 0.01, "learning_rate": 4.341979922207234e-05, "loss": 3.7797, "step": 401920 }, { "epoch": 0.01, "learning_rate": 4.341141327456182e-05, "loss": 3.7955, "step": 402432 }, { "epoch": 0.01, "learning_rate": 4.34030273270513e-05, "loss": 3.7982, "step": 402944 }, { "epoch": 0.01, "learning_rate": 4.339464137954078e-05, "loss": 3.7986, "step": 403456 }, { "epoch": 0.01, "learning_rate": 4.338628818963772e-05, "loss": 3.7892, "step": 403968 }, { "epoch": 0.01, "learning_rate": 4.33779022421272e-05, "loss": 3.8023, "step": 404480 }, { "epoch": 0.01, "learning_rate": 4.336951629461668e-05, "loss": 3.781, "step": 404992 }, { "epoch": 0.01, "learning_rate": 4.336113034710616e-05, "loss": 3.7983, "step": 405504 }, { "epoch": 0.01, "learning_rate": 4.335274439959564e-05, "loss": 3.7871, "step": 406016 }, { "epoch": 0.01, "learning_rate": 4.334435845208512e-05, "loss": 3.7668, "step": 406528 }, { "epoch": 0.01, "learning_rate": 4.33359725045746e-05, "loss": 3.8028, "step": 407040 }, { "epoch": 0.01, "learning_rate": 4.332760293586781e-05, "loss": 3.7853, "step": 407552 }, { "epoch": 0.01, "learning_rate": 4.331921698835729e-05, "loss": 3.793, "step": 408064 }, { "epoch": 0.01, "learning_rate": 4.331083104084677e-05, "loss": 3.7798, "step": 408576 }, { "epoch": 0.01, "learning_rate": 4.330244509333625e-05, "loss": 3.7801, "step": 409088 }, { "epoch": 0.01, "learning_rate": 4.329405914582573e-05, "loss": 3.7797, "step": 409600 }, { "epoch": 0.01, "learning_rate": 4.328567319831521e-05, "loss": 3.7836, "step": 410112 }, { "epoch": 0.01, "learning_rate": 4.327728725080469e-05, "loss": 3.7907, "step": 410624 }, { "epoch": 0.01, "learning_rate": 4.32689176820979e-05, "loss": 3.7854, "step": 411136 }, { "epoch": 0.01, "learning_rate": 4.326053173458739e-05, "loss": 3.7979, "step": 411648 }, { "epoch": 0.01, "learning_rate": 4.325214578707687e-05, "loss": 3.7806, "step": 412160 }, { "epoch": 0.01, "learning_rate": 4.324375983956635e-05, "loss": 3.7706, "step": 412672 }, { "epoch": 0.01, "learning_rate": 4.3235390270859556e-05, "loss": 3.7899, "step": 413184 }, { "epoch": 0.01, "learning_rate": 4.3227004323349036e-05, "loss": 3.7708, "step": 413696 }, { "epoch": 0.01, "learning_rate": 4.3218618375838516e-05, "loss": 3.7707, "step": 414208 }, { "epoch": 0.01, "learning_rate": 4.3210232428327996e-05, "loss": 3.7913, "step": 414720 }, { "epoch": 0.01, "learning_rate": 4.3201862859621205e-05, "loss": 3.7877, "step": 415232 }, { "epoch": 0.01, "learning_rate": 4.3193493290914414e-05, "loss": 3.776, "step": 415744 }, { "epoch": 0.01, "learning_rate": 4.3185107343403894e-05, "loss": 3.7757, "step": 416256 }, { "epoch": 0.01, "learning_rate": 4.3176721395893374e-05, "loss": 3.7667, "step": 416768 }, { "epoch": 0.01, "learning_rate": 4.3168335448382854e-05, "loss": 3.7769, "step": 417280 }, { "epoch": 0.01, "learning_rate": 4.315994950087234e-05, "loss": 3.7922, "step": 417792 }, { "epoch": 0.01, "learning_rate": 4.315156355336182e-05, "loss": 3.7868, "step": 418304 }, { "epoch": 0.01, "learning_rate": 4.31431776058513e-05, "loss": 3.7883, "step": 418816 }, { "epoch": 0.01, "learning_rate": 4.313480803714451e-05, "loss": 3.7824, "step": 419328 }, { "epoch": 0.01, "learning_rate": 4.312642208963399e-05, "loss": 3.7976, "step": 419840 }, { "epoch": 0.01, "learning_rate": 4.311803614212347e-05, "loss": 3.7737, "step": 420352 }, { "epoch": 0.01, "learning_rate": 4.310965019461295e-05, "loss": 3.7882, "step": 420864 }, { "epoch": 0.01, "learning_rate": 4.310126424710243e-05, "loss": 3.7797, "step": 421376 }, { "epoch": 0.01, "learning_rate": 4.309287829959191e-05, "loss": 3.7639, "step": 421888 }, { "epoch": 0.01, "learning_rate": 4.308449235208139e-05, "loss": 3.7922, "step": 422400 }, { "epoch": 0.01, "learning_rate": 4.30761227833746e-05, "loss": 3.7865, "step": 422912 }, { "epoch": 0.01, "learning_rate": 4.306773683586408e-05, "loss": 3.7835, "step": 423424 }, { "epoch": 0.01, "learning_rate": 4.305935088835356e-05, "loss": 3.7776, "step": 423936 }, { "epoch": 0.01, "learning_rate": 4.305096494084304e-05, "loss": 3.7668, "step": 424448 }, { "epoch": 0.01, "learning_rate": 4.3042595372136254e-05, "loss": 3.7724, "step": 424960 }, { "epoch": 0.01, "learning_rate": 4.3034225803429464e-05, "loss": 3.7775, "step": 425472 }, { "epoch": 0.01, "learning_rate": 4.3025839855918944e-05, "loss": 3.785, "step": 425984 }, { "epoch": 0.01, "learning_rate": 4.3017453908408424e-05, "loss": 3.7728, "step": 426496 }, { "epoch": 0.01, "learning_rate": 4.3009067960897903e-05, "loss": 3.7809, "step": 427008 }, { "epoch": 0.02, "learning_rate": 4.3000682013387383e-05, "loss": 3.7722, "step": 427520 }, { "epoch": 0.02, "learning_rate": 4.299231244468059e-05, "loss": 3.7767, "step": 428032 }, { "epoch": 0.02, "learning_rate": 4.298392649717007e-05, "loss": 3.7707, "step": 428544 }, { "epoch": 0.02, "learning_rate": 4.297554054965955e-05, "loss": 3.7738, "step": 429056 }, { "epoch": 0.02, "learning_rate": 4.296715460214903e-05, "loss": 3.7857, "step": 429568 }, { "epoch": 0.02, "learning_rate": 4.295876865463851e-05, "loss": 3.7898, "step": 430080 }, { "epoch": 0.02, "learning_rate": 4.295038270712799e-05, "loss": 3.7897, "step": 430592 }, { "epoch": 0.02, "learning_rate": 4.294199675961747e-05, "loss": 3.7611, "step": 431104 }, { "epoch": 0.02, "learning_rate": 4.293361081210695e-05, "loss": 3.7802, "step": 431616 }, { "epoch": 0.02, "learning_rate": 4.292524124340016e-05, "loss": 3.7705, "step": 432128 }, { "epoch": 0.02, "learning_rate": 4.291687167469338e-05, "loss": 3.7834, "step": 432640 }, { "epoch": 0.02, "learning_rate": 4.290848572718286e-05, "loss": 3.7722, "step": 433152 }, { "epoch": 0.02, "learning_rate": 4.290009977967234e-05, "loss": 3.7757, "step": 433664 }, { "epoch": 0.02, "learning_rate": 4.289171383216181e-05, "loss": 3.7661, "step": 434176 }, { "epoch": 0.02, "learning_rate": 4.288332788465129e-05, "loss": 3.7814, "step": 434688 }, { "epoch": 0.02, "learning_rate": 4.287494193714077e-05, "loss": 3.7592, "step": 435200 }, { "epoch": 0.02, "learning_rate": 4.286655598963025e-05, "loss": 3.7776, "step": 435712 }, { "epoch": 0.02, "learning_rate": 4.285817004211973e-05, "loss": 3.7624, "step": 436224 }, { "epoch": 0.02, "learning_rate": 4.2849800473412946e-05, "loss": 3.7805, "step": 436736 }, { "epoch": 0.02, "learning_rate": 4.2841414525902426e-05, "loss": 3.77, "step": 437248 }, { "epoch": 0.02, "learning_rate": 4.2833028578391906e-05, "loss": 3.7732, "step": 437760 }, { "epoch": 0.02, "learning_rate": 4.2824642630881386e-05, "loss": 3.7745, "step": 438272 }, { "epoch": 0.02, "learning_rate": 4.2816273062174595e-05, "loss": 3.7735, "step": 438784 }, { "epoch": 0.02, "learning_rate": 4.2807887114664075e-05, "loss": 3.7777, "step": 439296 }, { "epoch": 0.02, "learning_rate": 4.2799501167153555e-05, "loss": 3.7702, "step": 439808 }, { "epoch": 0.02, "learning_rate": 4.2791115219643035e-05, "loss": 3.7757, "step": 440320 }, { "epoch": 0.02, "learning_rate": 4.2782729272132515e-05, "loss": 3.7892, "step": 440832 }, { "epoch": 0.02, "learning_rate": 4.2774343324621995e-05, "loss": 3.7709, "step": 441344 }, { "epoch": 0.02, "learning_rate": 4.2765957377111475e-05, "loss": 3.7692, "step": 441856 }, { "epoch": 0.02, "learning_rate": 4.2757587808404684e-05, "loss": 3.7742, "step": 442368 }, { "epoch": 0.02, "learning_rate": 4.2749201860894164e-05, "loss": 3.7695, "step": 442880 }, { "epoch": 0.02, "learning_rate": 4.274081591338365e-05, "loss": 3.7629, "step": 443392 }, { "epoch": 0.02, "learning_rate": 4.273242996587313e-05, "loss": 3.774, "step": 443904 }, { "epoch": 0.02, "learning_rate": 4.272404401836261e-05, "loss": 3.7591, "step": 444416 }, { "epoch": 0.02, "learning_rate": 4.271565807085209e-05, "loss": 3.7801, "step": 444928 }, { "epoch": 0.02, "learning_rate": 4.27072885021453e-05, "loss": 3.7779, "step": 445440 }, { "epoch": 0.02, "learning_rate": 4.269890255463478e-05, "loss": 3.7733, "step": 445952 }, { "epoch": 0.02, "learning_rate": 4.269051660712426e-05, "loss": 3.7647, "step": 446464 }, { "epoch": 0.02, "learning_rate": 4.268213065961374e-05, "loss": 3.7636, "step": 446976 }, { "epoch": 0.02, "learning_rate": 4.267374471210322e-05, "loss": 3.7679, "step": 447488 }, { "epoch": 0.02, "learning_rate": 4.26653587645927e-05, "loss": 3.7768, "step": 448000 }, { "epoch": 0.02, "learning_rate": 4.265697281708217e-05, "loss": 3.7715, "step": 448512 }, { "epoch": 0.02, "learning_rate": 4.264858686957165e-05, "loss": 3.7762, "step": 449024 }, { "epoch": 0.02, "learning_rate": 4.264021730086487e-05, "loss": 3.7525, "step": 449536 }, { "epoch": 0.02, "learning_rate": 4.263183135335435e-05, "loss": 3.776, "step": 450048 }, { "epoch": 0.02, "learning_rate": 4.262344540584383e-05, "loss": 3.7684, "step": 450560 }, { "epoch": 0.02, "learning_rate": 4.2615075837137044e-05, "loss": 3.7763, "step": 451072 }, { "epoch": 0.02, "learning_rate": 4.2606689889626524e-05, "loss": 3.7598, "step": 451584 }, { "epoch": 0.02, "learning_rate": 4.2598303942116e-05, "loss": 3.7785, "step": 452096 }, { "epoch": 0.02, "learning_rate": 4.258991799460548e-05, "loss": 3.7706, "step": 452608 }, { "epoch": 0.02, "learning_rate": 4.258154842589869e-05, "loss": 3.7804, "step": 453120 }, { "epoch": 0.02, "learning_rate": 4.257316247838817e-05, "loss": 3.7641, "step": 453632 }, { "epoch": 0.02, "learning_rate": 4.2564776530877646e-05, "loss": 3.7756, "step": 454144 }, { "epoch": 0.02, "learning_rate": 4.2556390583367126e-05, "loss": 3.7558, "step": 454656 }, { "epoch": 0.02, "learning_rate": 4.2548004635856606e-05, "loss": 3.7694, "step": 455168 }, { "epoch": 0.02, "learning_rate": 4.2539618688346086e-05, "loss": 3.7729, "step": 455680 }, { "epoch": 0.02, "learning_rate": 4.25312491196393e-05, "loss": 3.7642, "step": 456192 }, { "epoch": 0.02, "learning_rate": 4.252286317212878e-05, "loss": 3.7684, "step": 456704 }, { "epoch": 0.02, "learning_rate": 4.251447722461826e-05, "loss": 3.7614, "step": 457216 }, { "epoch": 0.02, "learning_rate": 4.250609127710774e-05, "loss": 3.7702, "step": 457728 }, { "epoch": 0.03, "eval_loss": 3.891617774963379, "eval_runtime": 303.681, "eval_samples_per_second": 1256.552, "eval_steps_per_second": 39.268, "step": 457920 }, { "epoch": 1.0, "learning_rate": 4.249770532959722e-05, "loss": 3.7651, "step": 458240 }, { "epoch": 1.0, "learning_rate": 4.248933576089043e-05, "loss": 3.7546, "step": 458752 }, { "epoch": 1.0, "learning_rate": 4.248094981337991e-05, "loss": 3.7721, "step": 459264 }, { "epoch": 1.0, "learning_rate": 4.247256386586939e-05, "loss": 3.7623, "step": 459776 }, { "epoch": 1.0, "learning_rate": 4.246417791835887e-05, "loss": 3.7743, "step": 460288 }, { "epoch": 1.0, "learning_rate": 4.245580834965208e-05, "loss": 3.7604, "step": 460800 }, { "epoch": 1.0, "learning_rate": 4.244742240214156e-05, "loss": 3.7646, "step": 461312 }, { "epoch": 1.0, "learning_rate": 4.243903645463104e-05, "loss": 3.7651, "step": 461824 }, { "epoch": 1.0, "learning_rate": 4.243065050712052e-05, "loss": 3.7618, "step": 462336 }, { "epoch": 1.0, "learning_rate": 4.2422264559610006e-05, "loss": 3.7615, "step": 462848 }, { "epoch": 1.0, "learning_rate": 4.2413878612099486e-05, "loss": 3.7642, "step": 463360 }, { "epoch": 1.0, "learning_rate": 4.2405492664588966e-05, "loss": 3.7663, "step": 463872 }, { "epoch": 1.0, "learning_rate": 4.2397123095882175e-05, "loss": 3.7623, "step": 464384 }, { "epoch": 1.0, "learning_rate": 4.2388737148371655e-05, "loss": 3.7543, "step": 464896 }, { "epoch": 1.0, "learning_rate": 4.2380351200861135e-05, "loss": 3.7602, "step": 465408 }, { "epoch": 1.0, "learning_rate": 4.2371965253350615e-05, "loss": 3.7443, "step": 465920 }, { "epoch": 1.0, "learning_rate": 4.2363579305840095e-05, "loss": 3.7554, "step": 466432 }, { "epoch": 1.0, "learning_rate": 4.2355193358329575e-05, "loss": 3.7572, "step": 466944 }, { "epoch": 1.0, "learning_rate": 4.2346807410819055e-05, "loss": 3.7541, "step": 467456 }, { "epoch": 1.0, "learning_rate": 4.233842146330853e-05, "loss": 3.7789, "step": 467968 }, { "epoch": 1.0, "learning_rate": 4.2330051894601744e-05, "loss": 3.767, "step": 468480 }, { "epoch": 1.0, "learning_rate": 4.232168232589496e-05, "loss": 3.7693, "step": 468992 }, { "epoch": 1.0, "learning_rate": 4.231329637838444e-05, "loss": 3.7559, "step": 469504 }, { "epoch": 1.0, "learning_rate": 4.230491043087392e-05, "loss": 3.76, "step": 470016 }, { "epoch": 1.0, "learning_rate": 4.22965244833634e-05, "loss": 3.7562, "step": 470528 }, { "epoch": 1.0, "learning_rate": 4.228813853585288e-05, "loss": 3.7624, "step": 471040 }, { "epoch": 1.0, "learning_rate": 4.227975258834236e-05, "loss": 3.7572, "step": 471552 }, { "epoch": 1.0, "learning_rate": 4.227136664083183e-05, "loss": 3.759, "step": 472064 }, { "epoch": 1.0, "learning_rate": 4.226298069332131e-05, "loss": 3.7465, "step": 472576 }, { "epoch": 1.0, "learning_rate": 4.225461112461453e-05, "loss": 3.7516, "step": 473088 }, { "epoch": 1.01, "learning_rate": 4.2246225177104e-05, "loss": 3.7535, "step": 473600 }, { "epoch": 1.01, "learning_rate": 4.223785560839722e-05, "loss": 3.7651, "step": 474112 }, { "epoch": 1.01, "learning_rate": 4.22294696608867e-05, "loss": 3.7606, "step": 474624 }, { "epoch": 1.01, "learning_rate": 4.222108371337618e-05, "loss": 3.7651, "step": 475136 }, { "epoch": 1.01, "learning_rate": 4.221269776586566e-05, "loss": 3.7469, "step": 475648 }, { "epoch": 1.01, "learning_rate": 4.220431181835514e-05, "loss": 3.7528, "step": 476160 }, { "epoch": 1.01, "learning_rate": 4.219592587084462e-05, "loss": 3.7552, "step": 476672 }, { "epoch": 1.01, "learning_rate": 4.2187556302137833e-05, "loss": 3.7461, "step": 477184 }, { "epoch": 1.01, "learning_rate": 4.217917035462731e-05, "loss": 3.7499, "step": 477696 }, { "epoch": 1.01, "learning_rate": 4.2170784407116787e-05, "loss": 3.7442, "step": 478208 }, { "epoch": 1.01, "learning_rate": 4.2162398459606267e-05, "loss": 3.7535, "step": 478720 }, { "epoch": 1.01, "learning_rate": 4.2154012512095746e-05, "loss": 3.7597, "step": 479232 }, { "epoch": 1.01, "learning_rate": 4.2145626564585226e-05, "loss": 3.7557, "step": 479744 }, { "epoch": 1.01, "learning_rate": 4.2137256995878436e-05, "loss": 3.7509, "step": 480256 }, { "epoch": 1.01, "learning_rate": 4.2128871048367915e-05, "loss": 3.7568, "step": 480768 }, { "epoch": 1.01, "learning_rate": 4.2120485100857395e-05, "loss": 3.7472, "step": 481280 }, { "epoch": 1.01, "learning_rate": 4.211209915334688e-05, "loss": 3.7548, "step": 481792 }, { "epoch": 1.01, "learning_rate": 4.210371320583636e-05, "loss": 3.7471, "step": 482304 }, { "epoch": 1.01, "learning_rate": 4.209532725832584e-05, "loss": 3.7267, "step": 482816 }, { "epoch": 1.01, "learning_rate": 4.208694131081532e-05, "loss": 3.7685, "step": 483328 }, { "epoch": 1.01, "learning_rate": 4.207857174210853e-05, "loss": 3.7438, "step": 483840 }, { "epoch": 1.01, "learning_rate": 4.207018579459801e-05, "loss": 3.7544, "step": 484352 }, { "epoch": 1.01, "learning_rate": 4.206179984708749e-05, "loss": 3.7364, "step": 484864 }, { "epoch": 1.01, "learning_rate": 4.205341389957697e-05, "loss": 3.744, "step": 485376 }, { "epoch": 1.01, "learning_rate": 4.204504433087018e-05, "loss": 3.7326, "step": 485888 }, { "epoch": 1.01, "learning_rate": 4.203665838335966e-05, "loss": 3.7465, "step": 486400 }, { "epoch": 1.01, "learning_rate": 4.202827243584914e-05, "loss": 3.7494, "step": 486912 }, { "epoch": 1.01, "learning_rate": 4.201988648833862e-05, "loss": 3.7491, "step": 487424 }, { "epoch": 1.01, "learning_rate": 4.20115005408281e-05, "loss": 3.7581, "step": 487936 }, { "epoch": 1.01, "learning_rate": 4.200311459331758e-05, "loss": 3.7428, "step": 488448 }, { "epoch": 1.01, "learning_rate": 4.1994745024610796e-05, "loss": 3.7313, "step": 488960 }, { "epoch": 1.01, "learning_rate": 4.1986359077100276e-05, "loss": 3.7561, "step": 489472 }, { "epoch": 1.01, "learning_rate": 4.1977973129589756e-05, "loss": 3.7306, "step": 489984 }, { "epoch": 1.01, "learning_rate": 4.1969587182079236e-05, "loss": 3.7289, "step": 490496 }, { "epoch": 1.01, "learning_rate": 4.1961201234568716e-05, "loss": 3.7516, "step": 491008 }, { "epoch": 1.01, "learning_rate": 4.1952831665861925e-05, "loss": 3.75, "step": 491520 }, { "epoch": 1.01, "learning_rate": 4.1944445718351405e-05, "loss": 3.7353, "step": 492032 }, { "epoch": 1.01, "learning_rate": 4.1936059770840885e-05, "loss": 3.7399, "step": 492544 }, { "epoch": 1.01, "learning_rate": 4.1927673823330365e-05, "loss": 3.7285, "step": 493056 }, { "epoch": 1.01, "learning_rate": 4.1919304254623574e-05, "loss": 3.7366, "step": 493568 }, { "epoch": 1.01, "learning_rate": 4.1910918307113054e-05, "loss": 3.7483, "step": 494080 }, { "epoch": 1.01, "learning_rate": 4.1902532359602534e-05, "loss": 3.747, "step": 494592 }, { "epoch": 1.01, "learning_rate": 4.1894146412092014e-05, "loss": 3.7519, "step": 495104 }, { "epoch": 1.01, "learning_rate": 4.1885760464581493e-05, "loss": 3.7473, "step": 495616 }, { "epoch": 1.01, "learning_rate": 4.187739089587471e-05, "loss": 3.7552, "step": 496128 }, { "epoch": 1.01, "learning_rate": 4.186900494836419e-05, "loss": 3.7343, "step": 496640 }, { "epoch": 1.01, "learning_rate": 4.186061900085366e-05, "loss": 3.7516, "step": 497152 }, { "epoch": 1.01, "learning_rate": 4.185223305334314e-05, "loss": 3.737, "step": 497664 }, { "epoch": 1.01, "learning_rate": 4.184384710583262e-05, "loss": 3.7306, "step": 498176 }, { "epoch": 1.01, "learning_rate": 4.18354611583221e-05, "loss": 3.7501, "step": 498688 }, { "epoch": 1.01, "learning_rate": 4.182707521081158e-05, "loss": 3.7514, "step": 499200 }, { "epoch": 1.01, "learning_rate": 4.181868926330106e-05, "loss": 3.7462, "step": 499712 }, { "epoch": 1.01, "learning_rate": 4.181031969459427e-05, "loss": 3.7412, "step": 500224 }, { "epoch": 1.01, "learning_rate": 4.180193374708375e-05, "loss": 3.7282, "step": 500736 }, { "epoch": 1.01, "learning_rate": 4.179356417837697e-05, "loss": 3.7313, "step": 501248 }, { "epoch": 1.01, "learning_rate": 4.178517823086645e-05, "loss": 3.7427, "step": 501760 }, { "epoch": 1.01, "learning_rate": 4.177679228335593e-05, "loss": 3.7479, "step": 502272 }, { "epoch": 1.01, "learning_rate": 4.176840633584541e-05, "loss": 3.7354, "step": 502784 }, { "epoch": 1.01, "learning_rate": 4.1760036767138616e-05, "loss": 3.7438, "step": 503296 }, { "epoch": 1.02, "learning_rate": 4.1751650819628096e-05, "loss": 3.7289, "step": 503808 }, { "epoch": 1.02, "learning_rate": 4.1743264872117576e-05, "loss": 3.7422, "step": 504320 }, { "epoch": 1.02, "learning_rate": 4.1734878924607056e-05, "loss": 3.7337, "step": 504832 }, { "epoch": 1.02, "learning_rate": 4.1726492977096536e-05, "loss": 3.7366, "step": 505344 }, { "epoch": 1.02, "learning_rate": 4.1718107029586016e-05, "loss": 3.7468, "step": 505856 }, { "epoch": 1.02, "learning_rate": 4.1709737460879225e-05, "loss": 3.7524, "step": 506368 }, { "epoch": 1.02, "learning_rate": 4.1701351513368705e-05, "loss": 3.7508, "step": 506880 }, { "epoch": 1.02, "learning_rate": 4.169296556585819e-05, "loss": 3.7265, "step": 507392 }, { "epoch": 1.02, "learning_rate": 4.168457961834767e-05, "loss": 3.7425, "step": 507904 }, { "epoch": 1.02, "learning_rate": 4.167619367083715e-05, "loss": 3.7314, "step": 508416 }, { "epoch": 1.02, "learning_rate": 4.166782410213036e-05, "loss": 3.7448, "step": 508928 }, { "epoch": 1.02, "learning_rate": 4.165943815461984e-05, "loss": 3.7349, "step": 509440 }, { "epoch": 1.02, "learning_rate": 4.165105220710932e-05, "loss": 3.7405, "step": 509952 }, { "epoch": 1.02, "learning_rate": 4.16426662595988e-05, "loss": 3.7307, "step": 510464 }, { "epoch": 1.02, "learning_rate": 4.163428031208828e-05, "loss": 3.741, "step": 510976 }, { "epoch": 1.02, "learning_rate": 4.162591074338149e-05, "loss": 3.7255, "step": 511488 }, { "epoch": 1.02, "learning_rate": 4.161752479587097e-05, "loss": 3.7387, "step": 512000 }, { "epoch": 1.02, "learning_rate": 4.160913884836045e-05, "loss": 3.724, "step": 512512 }, { "epoch": 1.02, "learning_rate": 4.160075290084993e-05, "loss": 3.7435, "step": 513024 }, { "epoch": 1.02, "learning_rate": 4.1592383332143145e-05, "loss": 3.733, "step": 513536 }, { "epoch": 1.02, "learning_rate": 4.1583997384632625e-05, "loss": 3.7346, "step": 514048 }, { "epoch": 1.02, "learning_rate": 4.1575611437122105e-05, "loss": 3.7352, "step": 514560 }, { "epoch": 1.02, "learning_rate": 4.1567225489611585e-05, "loss": 3.7378, "step": 515072 }, { "epoch": 1.02, "learning_rate": 4.1558855920904794e-05, "loss": 3.7384, "step": 515584 }, { "epoch": 1.02, "learning_rate": 4.1550469973394274e-05, "loss": 3.7333, "step": 516096 }, { "epoch": 1.02, "learning_rate": 4.1542084025883754e-05, "loss": 3.7422, "step": 516608 }, { "epoch": 1.02, "learning_rate": 4.1533698078373234e-05, "loss": 3.7476, "step": 517120 }, { "epoch": 1.02, "learning_rate": 4.1525312130862714e-05, "loss": 3.7402, "step": 517632 }, { "epoch": 1.02, "learning_rate": 4.1516926183352194e-05, "loss": 3.7334, "step": 518144 }, { "epoch": 1.02, "learning_rate": 4.15085566146454e-05, "loss": 3.7325, "step": 518656 }, { "epoch": 1.02, "learning_rate": 4.150017066713488e-05, "loss": 3.7369, "step": 519168 }, { "epoch": 1.02, "learning_rate": 4.149178471962436e-05, "loss": 3.7268, "step": 519680 }, { "epoch": 1.02, "learning_rate": 4.148339877211384e-05, "loss": 3.7378, "step": 520192 }, { "epoch": 1.02, "learning_rate": 4.147502920340706e-05, "loss": 3.7198, "step": 520704 }, { "epoch": 1.02, "learning_rate": 4.146664325589654e-05, "loss": 3.7428, "step": 521216 }, { "epoch": 1.02, "learning_rate": 4.145825730838602e-05, "loss": 3.7397, "step": 521728 }, { "epoch": 1.02, "learning_rate": 4.14498713608755e-05, "loss": 3.7377, "step": 522240 }, { "epoch": 1.02, "learning_rate": 4.144148541336497e-05, "loss": 3.7298, "step": 522752 }, { "epoch": 1.02, "learning_rate": 4.143311584465819e-05, "loss": 3.7272, "step": 523264 }, { "epoch": 1.02, "learning_rate": 4.142472989714767e-05, "loss": 3.7312, "step": 523776 }, { "epoch": 1.02, "learning_rate": 4.141634394963715e-05, "loss": 3.7435, "step": 524288 }, { "epoch": 1.02, "learning_rate": 4.140795800212662e-05, "loss": 3.7344, "step": 524800 }, { "epoch": 1.02, "learning_rate": 4.13995720546161e-05, "loss": 3.7368, "step": 525312 }, { "epoch": 1.02, "learning_rate": 4.139120248590932e-05, "loss": 3.7194, "step": 525824 }, { "epoch": 1.02, "learning_rate": 4.13828165383988e-05, "loss": 3.7408, "step": 526336 }, { "epoch": 1.02, "learning_rate": 4.137443059088828e-05, "loss": 3.732, "step": 526848 }, { "epoch": 1.02, "learning_rate": 4.136604464337776e-05, "loss": 3.743, "step": 527360 }, { "epoch": 1.02, "learning_rate": 4.135767507467097e-05, "loss": 3.7229, "step": 527872 }, { "epoch": 1.02, "learning_rate": 4.1349289127160446e-05, "loss": 3.7413, "step": 528384 }, { "epoch": 1.02, "learning_rate": 4.1340903179649926e-05, "loss": 3.7313, "step": 528896 }, { "epoch": 1.02, "learning_rate": 4.1332517232139406e-05, "loss": 3.7506, "step": 529408 }, { "epoch": 1.02, "learning_rate": 4.1324131284628886e-05, "loss": 3.7289, "step": 529920 }, { "epoch": 1.02, "learning_rate": 4.1315761715922095e-05, "loss": 3.7369, "step": 530432 }, { "epoch": 1.02, "learning_rate": 4.1307375768411575e-05, "loss": 3.7232, "step": 530944 }, { "epoch": 1.02, "learning_rate": 4.1298989820901055e-05, "loss": 3.7333, "step": 531456 }, { "epoch": 1.02, "learning_rate": 4.1290603873390535e-05, "loss": 3.7354, "step": 531968 }, { "epoch": 1.02, "learning_rate": 4.128221792588002e-05, "loss": 3.7263, "step": 532480 }, { "epoch": 1.02, "learning_rate": 4.127384835717323e-05, "loss": 3.7391, "step": 532992 }, { "epoch": 1.02, "learning_rate": 4.126546240966271e-05, "loss": 3.7218, "step": 533504 }, { "epoch": 1.02, "learning_rate": 4.125707646215219e-05, "loss": 3.7381, "step": 534016 }, { "epoch": 1.03, "eval_loss": 3.879366636276245, "eval_runtime": 311.5372, "eval_samples_per_second": 1224.865, "eval_steps_per_second": 38.278, "step": 534240 }, { "epoch": 0.0, "learning_rate": 4.124869051464167e-05, "loss": 3.7263, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.124030456713115e-05, "loss": 3.7176, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.123191861962063e-05, "loss": 3.7335, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.122353267211011e-05, "loss": 3.7263, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.121514672459959e-05, "loss": 3.7403, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.120676077708907e-05, "loss": 3.7272, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.119839120838228e-05, "loss": 3.7265, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.119000526087176e-05, "loss": 3.7298, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.118161931336124e-05, "loss": 3.7256, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.117323336585072e-05, "loss": 3.7278, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.11648474183402e-05, "loss": 3.729, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.1156461470829686e-05, "loss": 3.7315, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.1148091902122895e-05, "loss": 3.7308, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.1139705954612375e-05, "loss": 3.717, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.1131320007101855e-05, "loss": 3.7212, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.1122934059591335e-05, "loss": 3.7128, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.111454811208081e-05, "loss": 3.7195, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.110616216457029e-05, "loss": 3.7254, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109777621705977e-05, "loss": 3.7155, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.1089406648352984e-05, "loss": 3.7437, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108102070084246e-05, "loss": 3.7345, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.107263475333194e-05, "loss": 3.7353, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.1064248805821423e-05, "loss": 3.7222, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.105587923711463e-05, "loss": 3.7238, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.104749328960411e-05, "loss": 3.7294, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.103910734209359e-05, "loss": 3.724, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.103072139458307e-05, "loss": 3.7237, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.102235182587628e-05, "loss": 3.7295, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.101396587836576e-05, "loss": 3.7088, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.100557993085524e-05, "loss": 3.7164, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.099719398334472e-05, "loss": 3.7197, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.09888080358342e-05, "loss": 3.7274, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.098043846712741e-05, "loss": 3.7286, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.097205251961689e-05, "loss": 3.7304, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.096366657210638e-05, "loss": 3.7143, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.095528062459586e-05, "loss": 3.7166, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.094689467708534e-05, "loss": 3.7232, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.0938525108378546e-05, "loss": 3.7115, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.0930139160868026e-05, "loss": 3.7175, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.0921753213357506e-05, "loss": 3.706, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.0913367265846986e-05, "loss": 3.7216, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.0904981318336466e-05, "loss": 3.7183, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.0896611749629675e-05, "loss": 3.7222, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.0888225802119155e-05, "loss": 3.7215, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.0879839854608635e-05, "loss": 3.7201, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.0871453907098115e-05, "loss": 3.7151, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.0863067959587595e-05, "loss": 3.7194, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.085469839088081e-05, "loss": 3.7124, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.084631244337029e-05, "loss": 3.6952, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.083792649585977e-05, "loss": 3.7333, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.082954054834925e-05, "loss": 3.7086, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.082117097964246e-05, "loss": 3.7235, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.081278503213194e-05, "loss": 3.7081, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.080439908462142e-05, "loss": 3.7054, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.07960131371109e-05, "loss": 3.6983, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.078762718960038e-05, "loss": 3.7118, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.077925762089359e-05, "loss": 3.7201, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.077087167338307e-05, "loss": 3.7117, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.076248572587255e-05, "loss": 3.7252, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.075409977836203e-05, "loss": 3.7157, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.0745730209655244e-05, "loss": 3.6944, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.0737344262144724e-05, "loss": 3.718, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.0728958314634204e-05, "loss": 3.7011, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.0720572367123684e-05, "loss": 3.6951, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.0712186419613164e-05, "loss": 3.7236, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.070381685090637e-05, "loss": 3.7162, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.069543090339585e-05, "loss": 3.7018, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.068704495588533e-05, "loss": 3.7078, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.067865900837481e-05, "loss": 3.6962, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.067028943966802e-05, "loss": 3.7046, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.06619034921575e-05, "loss": 3.713, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.065351754464698e-05, "loss": 3.714, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.064513159713646e-05, "loss": 3.7186, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.063674564962594e-05, "loss": 3.7103, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.062835970211542e-05, "loss": 3.7217, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.061999013340864e-05, "loss": 3.7009, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.061160418589812e-05, "loss": 3.7207, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.060321823838759e-05, "loss": 3.7041, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.059483229087707e-05, "loss": 3.7017, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.058646272217029e-05, "loss": 3.7168, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.057807677465976e-05, "loss": 3.7196, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.056969082714924e-05, "loss": 3.7128, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.056130487963872e-05, "loss": 3.7116, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.0552935310931936e-05, "loss": 3.6916, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.0544549363421416e-05, "loss": 3.6971, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.0536163415910896e-05, "loss": 3.7092, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.0527777468400376e-05, "loss": 3.7158, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.0519391520889856e-05, "loss": 3.7048, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.0511021952183065e-05, "loss": 3.7121, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.0502636004672545e-05, "loss": 3.6973, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.0494250057162025e-05, "loss": 3.712, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.0485864109651505e-05, "loss": 3.7022, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.0477478162140985e-05, "loss": 3.7043, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.0469092214630465e-05, "loss": 3.7133, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.0460722645923674e-05, "loss": 3.7172, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.0452336698413154e-05, "loss": 3.7194, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.044395075090264e-05, "loss": 3.6971, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.043556480339212e-05, "loss": 3.7079, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.04271788558816e-05, "loss": 3.6994, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.041880928717481e-05, "loss": 3.7111, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.041042333966429e-05, "loss": 3.7037, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.040203739215377e-05, "loss": 3.7105, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.039365144464325e-05, "loss": 3.699, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.038526549713273e-05, "loss": 3.7047, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.037689592842594e-05, "loss": 3.6993, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.036850998091542e-05, "loss": 3.7039, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.03601240334049e-05, "loss": 3.6914, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.035173808589438e-05, "loss": 3.7119, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.0343368517187594e-05, "loss": 3.702, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.0334982569677074e-05, "loss": 3.7038, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.0326596622166554e-05, "loss": 3.7027, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.0318210674656034e-05, "loss": 3.7055, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.030984110594924e-05, "loss": 3.7097, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.030145515843872e-05, "loss": 3.7026, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.02930692109282e-05, "loss": 3.7088, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.028468326341768e-05, "loss": 3.715, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.027631369471089e-05, "loss": 3.702, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.026792774720037e-05, "loss": 3.7101, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.025954179968985e-05, "loss": 3.7015, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.025115585217933e-05, "loss": 3.7001, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.024278628347255e-05, "loss": 3.7022, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.023440033596203e-05, "loss": 3.705, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.022601438845151e-05, "loss": 3.6867, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.021762844094099e-05, "loss": 3.7106, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.0209258872234197e-05, "loss": 3.7079, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.0200872924723677e-05, "loss": 3.71, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.0192486977213157e-05, "loss": 3.6986, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.0184101029702636e-05, "loss": 3.6954, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.0175715082192116e-05, "loss": 3.6985, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.0167345513485326e-05, "loss": 3.7093, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.0158959565974805e-05, "loss": 3.7031, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.0150573618464285e-05, "loss": 3.7095, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.0142187670953765e-05, "loss": 3.6865, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.013381810224698e-05, "loss": 3.7087, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012543215473646e-05, "loss": 3.6997, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011704620722594e-05, "loss": 3.7126, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.010866025971542e-05, "loss": 3.6952, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.0100274312204894e-05, "loss": 3.7061, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.009190474349811e-05, "loss": 3.6997, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008351879598759e-05, "loss": 3.7206, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.007513284847707e-05, "loss": 3.7001, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.006674690096654e-05, "loss": 3.7044, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.005837733225976e-05, "loss": 3.6963, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.004999138474924e-05, "loss": 3.704, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.004160543723872e-05, "loss": 3.6998, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.00332194897282e-05, "loss": 3.696, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.0024849921021415e-05, "loss": 3.7091, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.0016463973510895e-05, "loss": 3.6878, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.000807802600037e-05, "loss": 3.7121, "step": 610304 }, { "epoch": 0.03, "eval_loss": 3.87300968170166, "eval_runtime": 304.8147, "eval_samples_per_second": 1251.878, "eval_steps_per_second": 39.122, "step": 610560 }, { "epoch": 1.0, "learning_rate": 3.999969207848985e-05, "loss": 3.6966, "step": 610816 }, { "epoch": 1.0, "learning_rate": 3.999130613097933e-05, "loss": 3.6902, "step": 611328 }, { "epoch": 1.0, "learning_rate": 3.9982936562272544e-05, "loss": 3.7024, "step": 611840 }, { "epoch": 1.0, "learning_rate": 3.997455061476202e-05, "loss": 3.6982, "step": 612352 }, { "epoch": 1.0, "learning_rate": 3.99661646672515e-05, "loss": 3.7101, "step": 612864 }, { "epoch": 1.0, "learning_rate": 3.995777871974098e-05, "loss": 3.697, "step": 613376 }, { "epoch": 1.0, "learning_rate": 3.994940915103419e-05, "loss": 3.7004, "step": 613888 }, { "epoch": 1.0, "learning_rate": 3.994102320352367e-05, "loss": 3.6986, "step": 614400 }, { "epoch": 1.0, "learning_rate": 3.993263725601315e-05, "loss": 3.6946, "step": 614912 }, { "epoch": 1.0, "learning_rate": 3.992425130850263e-05, "loss": 3.6995, "step": 615424 }, { "epoch": 1.0, "learning_rate": 3.991588173979584e-05, "loss": 3.699, "step": 615936 }, { "epoch": 1.0, "learning_rate": 3.990749579228532e-05, "loss": 3.7005, "step": 616448 }, { "epoch": 1.0, "learning_rate": 3.989912622357854e-05, "loss": 3.7064, "step": 616960 }, { "epoch": 1.0, "learning_rate": 3.989074027606802e-05, "loss": 3.6816, "step": 617472 }, { "epoch": 1.0, "learning_rate": 3.988235432855749e-05, "loss": 3.694, "step": 617984 }, { "epoch": 1.0, "learning_rate": 3.987396838104697e-05, "loss": 3.6799, "step": 618496 }, { "epoch": 1.0, "learning_rate": 3.986558243353645e-05, "loss": 3.6918, "step": 619008 }, { "epoch": 1.0, "learning_rate": 3.985719648602593e-05, "loss": 3.6944, "step": 619520 }, { "epoch": 1.0, "learning_rate": 3.984881053851541e-05, "loss": 3.6865, "step": 620032 }, { "epoch": 1.0, "learning_rate": 3.984042459100489e-05, "loss": 3.711, "step": 620544 }, { "epoch": 1.0, "learning_rate": 3.983203864349437e-05, "loss": 3.705, "step": 621056 }, { "epoch": 1.0, "learning_rate": 3.9823669074787586e-05, "loss": 3.7038, "step": 621568 }, { "epoch": 1.0, "learning_rate": 3.9815283127277066e-05, "loss": 3.6943, "step": 622080 }, { "epoch": 1.0, "learning_rate": 3.9806897179766546e-05, "loss": 3.6947, "step": 622592 }, { "epoch": 1.0, "learning_rate": 3.9798511232256026e-05, "loss": 3.6997, "step": 623104 }, { "epoch": 1.0, "learning_rate": 3.9790125284745506e-05, "loss": 3.6926, "step": 623616 }, { "epoch": 1.0, "learning_rate": 3.9781755716038715e-05, "loss": 3.6923, "step": 624128 }, { "epoch": 1.0, "learning_rate": 3.9773369768528195e-05, "loss": 3.6992, "step": 624640 }, { "epoch": 1.0, "learning_rate": 3.9764983821017675e-05, "loss": 3.6825, "step": 625152 }, { "epoch": 1.0, "learning_rate": 3.9756597873507155e-05, "loss": 3.6838, "step": 625664 }, { "epoch": 1.01, "learning_rate": 3.9748211925996635e-05, "loss": 3.6945, "step": 626176 }, { "epoch": 1.01, "learning_rate": 3.9739842357289844e-05, "loss": 3.6985, "step": 626688 }, { "epoch": 1.01, "learning_rate": 3.9731456409779324e-05, "loss": 3.6927, "step": 627200 }, { "epoch": 1.01, "learning_rate": 3.972307046226881e-05, "loss": 3.7062, "step": 627712 }, { "epoch": 1.01, "learning_rate": 3.971468451475829e-05, "loss": 3.6858, "step": 628224 }, { "epoch": 1.01, "learning_rate": 3.97063149460515e-05, "loss": 3.6875, "step": 628736 }, { "epoch": 1.01, "learning_rate": 3.969792899854098e-05, "loss": 3.6935, "step": 629248 }, { "epoch": 1.01, "learning_rate": 3.968954305103046e-05, "loss": 3.6815, "step": 629760 }, { "epoch": 1.01, "learning_rate": 3.968115710351994e-05, "loss": 3.6899, "step": 630272 }, { "epoch": 1.01, "learning_rate": 3.967278753481315e-05, "loss": 3.6813, "step": 630784 }, { "epoch": 1.01, "learning_rate": 3.966440158730263e-05, "loss": 3.6878, "step": 631296 }, { "epoch": 1.01, "learning_rate": 3.965601563979211e-05, "loss": 3.6915, "step": 631808 }, { "epoch": 1.01, "learning_rate": 3.964762969228159e-05, "loss": 3.6934, "step": 632320 }, { "epoch": 1.01, "learning_rate": 3.96392601235748e-05, "loss": 3.6924, "step": 632832 }, { "epoch": 1.01, "learning_rate": 3.963087417606428e-05, "loss": 3.689, "step": 633344 }, { "epoch": 1.01, "learning_rate": 3.9622488228553764e-05, "loss": 3.6866, "step": 633856 }, { "epoch": 1.01, "learning_rate": 3.9614102281043244e-05, "loss": 3.6881, "step": 634368 }, { "epoch": 1.01, "learning_rate": 3.9605732712336454e-05, "loss": 3.689, "step": 634880 }, { "epoch": 1.01, "learning_rate": 3.9597346764825933e-05, "loss": 3.6655, "step": 635392 }, { "epoch": 1.01, "learning_rate": 3.9588960817315413e-05, "loss": 3.6996, "step": 635904 }, { "epoch": 1.01, "learning_rate": 3.9580574869804893e-05, "loss": 3.6802, "step": 636416 }, { "epoch": 1.01, "learning_rate": 3.957218892229437e-05, "loss": 3.6951, "step": 636928 }, { "epoch": 1.01, "learning_rate": 3.956381935358758e-05, "loss": 3.6798, "step": 637440 }, { "epoch": 1.01, "learning_rate": 3.955543340607706e-05, "loss": 3.6765, "step": 637952 }, { "epoch": 1.01, "learning_rate": 3.954704745856654e-05, "loss": 3.6752, "step": 638464 }, { "epoch": 1.01, "learning_rate": 3.953866151105602e-05, "loss": 3.6781, "step": 638976 }, { "epoch": 1.01, "learning_rate": 3.95302755635455e-05, "loss": 3.6959, "step": 639488 }, { "epoch": 1.01, "learning_rate": 3.952190599483872e-05, "loss": 3.6788, "step": 640000 }, { "epoch": 1.01, "learning_rate": 3.95135200473282e-05, "loss": 3.6981, "step": 640512 }, { "epoch": 1.01, "learning_rate": 3.950513409981768e-05, "loss": 3.6871, "step": 641024 }, { "epoch": 1.01, "learning_rate": 3.949674815230715e-05, "loss": 3.6661, "step": 641536 }, { "epoch": 1.01, "learning_rate": 3.948836220479663e-05, "loss": 3.6873, "step": 642048 }, { "epoch": 1.01, "learning_rate": 3.947999263608985e-05, "loss": 3.6793, "step": 642560 }, { "epoch": 1.01, "learning_rate": 3.947160668857933e-05, "loss": 3.6662, "step": 643072 }, { "epoch": 1.01, "learning_rate": 3.94632207410688e-05, "loss": 3.6927, "step": 643584 }, { "epoch": 1.01, "learning_rate": 3.945483479355828e-05, "loss": 3.6862, "step": 644096 }, { "epoch": 1.01, "learning_rate": 3.9446465224851496e-05, "loss": 3.6759, "step": 644608 }, { "epoch": 1.01, "learning_rate": 3.943807927734097e-05, "loss": 3.6806, "step": 645120 }, { "epoch": 1.01, "learning_rate": 3.9429693329830456e-05, "loss": 3.6637, "step": 645632 }, { "epoch": 1.01, "learning_rate": 3.9421307382319936e-05, "loss": 3.6788, "step": 646144 }, { "epoch": 1.01, "learning_rate": 3.941293781361315e-05, "loss": 3.6833, "step": 646656 }, { "epoch": 1.01, "learning_rate": 3.9404551866102625e-05, "loss": 3.6823, "step": 647168 }, { "epoch": 1.01, "learning_rate": 3.9396165918592105e-05, "loss": 3.6947, "step": 647680 }, { "epoch": 1.01, "learning_rate": 3.9387779971081585e-05, "loss": 3.6798, "step": 648192 }, { "epoch": 1.01, "learning_rate": 3.93794104023748e-05, "loss": 3.6926, "step": 648704 }, { "epoch": 1.01, "learning_rate": 3.9371024454864274e-05, "loss": 3.679, "step": 649216 }, { "epoch": 1.01, "learning_rate": 3.9362638507353754e-05, "loss": 3.69, "step": 649728 }, { "epoch": 1.01, "learning_rate": 3.9354252559843234e-05, "loss": 3.6726, "step": 650240 }, { "epoch": 1.01, "learning_rate": 3.9345866612332714e-05, "loss": 3.673, "step": 650752 }, { "epoch": 1.01, "learning_rate": 3.933749704362592e-05, "loss": 3.6889, "step": 651264 }, { "epoch": 1.01, "learning_rate": 3.932911109611541e-05, "loss": 3.6928, "step": 651776 }, { "epoch": 1.01, "learning_rate": 3.932072514860489e-05, "loss": 3.6833, "step": 652288 }, { "epoch": 1.01, "learning_rate": 3.931233920109437e-05, "loss": 3.6856, "step": 652800 }, { "epoch": 1.01, "learning_rate": 3.930396963238758e-05, "loss": 3.6606, "step": 653312 }, { "epoch": 1.01, "learning_rate": 3.929558368487706e-05, "loss": 3.6698, "step": 653824 }, { "epoch": 1.01, "learning_rate": 3.928719773736654e-05, "loss": 3.6835, "step": 654336 }, { "epoch": 1.01, "learning_rate": 3.927881178985602e-05, "loss": 3.6854, "step": 654848 }, { "epoch": 1.01, "learning_rate": 3.927044222114923e-05, "loss": 3.6764, "step": 655360 }, { "epoch": 1.01, "learning_rate": 3.926205627363871e-05, "loss": 3.6831, "step": 655872 }, { "epoch": 1.02, "learning_rate": 3.925367032612819e-05, "loss": 3.672, "step": 656384 }, { "epoch": 1.02, "learning_rate": 3.924528437861767e-05, "loss": 3.6806, "step": 656896 }, { "epoch": 1.02, "learning_rate": 3.9236914809910877e-05, "loss": 3.6736, "step": 657408 }, { "epoch": 1.02, "learning_rate": 3.922852886240036e-05, "loss": 3.6782, "step": 657920 }, { "epoch": 1.02, "learning_rate": 3.922014291488984e-05, "loss": 3.6863, "step": 658432 }, { "epoch": 1.02, "learning_rate": 3.921175696737932e-05, "loss": 3.6898, "step": 658944 }, { "epoch": 1.02, "learning_rate": 3.92033710198688e-05, "loss": 3.693, "step": 659456 }, { "epoch": 1.02, "learning_rate": 3.919498507235828e-05, "loss": 3.6703, "step": 659968 }, { "epoch": 1.02, "learning_rate": 3.918661550365149e-05, "loss": 3.681, "step": 660480 }, { "epoch": 1.02, "learning_rate": 3.917822955614097e-05, "loss": 3.6756, "step": 660992 }, { "epoch": 1.02, "learning_rate": 3.916984360863045e-05, "loss": 3.6823, "step": 661504 }, { "epoch": 1.02, "learning_rate": 3.916145766111993e-05, "loss": 3.6766, "step": 662016 }, { "epoch": 1.02, "learning_rate": 3.915308809241314e-05, "loss": 3.6799, "step": 662528 }, { "epoch": 1.02, "learning_rate": 3.914470214490262e-05, "loss": 3.6745, "step": 663040 }, { "epoch": 1.02, "learning_rate": 3.91363161973921e-05, "loss": 3.6742, "step": 663552 }, { "epoch": 1.02, "learning_rate": 3.912793024988158e-05, "loss": 3.6733, "step": 664064 }, { "epoch": 1.02, "learning_rate": 3.911954430237106e-05, "loss": 3.6755, "step": 664576 }, { "epoch": 1.02, "learning_rate": 3.911117473366428e-05, "loss": 3.6636, "step": 665088 }, { "epoch": 1.02, "learning_rate": 3.910278878615376e-05, "loss": 3.6835, "step": 665600 }, { "epoch": 1.02, "learning_rate": 3.909440283864324e-05, "loss": 3.6772, "step": 666112 }, { "epoch": 1.02, "learning_rate": 3.908601689113272e-05, "loss": 3.6722, "step": 666624 }, { "epoch": 1.02, "learning_rate": 3.9077647322425926e-05, "loss": 3.6797, "step": 667136 }, { "epoch": 1.02, "learning_rate": 3.9069261374915406e-05, "loss": 3.6734, "step": 667648 }, { "epoch": 1.02, "learning_rate": 3.9060875427404886e-05, "loss": 3.6842, "step": 668160 }, { "epoch": 1.02, "learning_rate": 3.9052489479894366e-05, "loss": 3.6738, "step": 668672 }, { "epoch": 1.02, "learning_rate": 3.9044119911187575e-05, "loss": 3.6852, "step": 669184 }, { "epoch": 1.02, "learning_rate": 3.9035733963677055e-05, "loss": 3.6887, "step": 669696 }, { "epoch": 1.02, "learning_rate": 3.9027348016166535e-05, "loss": 3.6787, "step": 670208 }, { "epoch": 1.02, "learning_rate": 3.9018962068656015e-05, "loss": 3.6789, "step": 670720 }, { "epoch": 1.02, "learning_rate": 3.901059249994923e-05, "loss": 3.6757, "step": 671232 }, { "epoch": 1.02, "learning_rate": 3.900220655243871e-05, "loss": 3.6711, "step": 671744 }, { "epoch": 1.02, "learning_rate": 3.899382060492819e-05, "loss": 3.6763, "step": 672256 }, { "epoch": 1.02, "learning_rate": 3.898543465741767e-05, "loss": 3.6771, "step": 672768 }, { "epoch": 1.02, "learning_rate": 3.897706508871088e-05, "loss": 3.6575, "step": 673280 }, { "epoch": 1.02, "learning_rate": 3.896867914120036e-05, "loss": 3.6862, "step": 673792 }, { "epoch": 1.02, "learning_rate": 3.896029319368984e-05, "loss": 3.6799, "step": 674304 }, { "epoch": 1.02, "learning_rate": 3.895190724617932e-05, "loss": 3.6813, "step": 674816 }, { "epoch": 1.02, "learning_rate": 3.894353767747253e-05, "loss": 3.6737, "step": 675328 }, { "epoch": 1.02, "learning_rate": 3.893515172996201e-05, "loss": 3.6697, "step": 675840 }, { "epoch": 1.02, "learning_rate": 3.892676578245149e-05, "loss": 3.6709, "step": 676352 }, { "epoch": 1.02, "learning_rate": 3.891837983494097e-05, "loss": 3.681, "step": 676864 }, { "epoch": 1.02, "learning_rate": 3.8910010266234184e-05, "loss": 3.6786, "step": 677376 }, { "epoch": 1.02, "learning_rate": 3.8901624318723664e-05, "loss": 3.6848, "step": 677888 }, { "epoch": 1.02, "learning_rate": 3.8893238371213144e-05, "loss": 3.656, "step": 678400 }, { "epoch": 1.02, "learning_rate": 3.8884852423702624e-05, "loss": 3.6832, "step": 678912 }, { "epoch": 1.02, "learning_rate": 3.8876466476192104e-05, "loss": 3.6741, "step": 679424 }, { "epoch": 1.02, "learning_rate": 3.886809690748531e-05, "loss": 3.6874, "step": 679936 }, { "epoch": 1.02, "learning_rate": 3.885971095997479e-05, "loss": 3.6686, "step": 680448 }, { "epoch": 1.02, "learning_rate": 3.885132501246427e-05, "loss": 3.6757, "step": 680960 }, { "epoch": 1.02, "learning_rate": 3.884293906495375e-05, "loss": 3.675, "step": 681472 }, { "epoch": 1.02, "learning_rate": 3.883456949624696e-05, "loss": 3.6917, "step": 681984 }, { "epoch": 1.02, "learning_rate": 3.882618354873644e-05, "loss": 3.6728, "step": 682496 }, { "epoch": 1.02, "learning_rate": 3.881779760122592e-05, "loss": 3.6799, "step": 683008 }, { "epoch": 1.02, "learning_rate": 3.88094116537154e-05, "loss": 3.6686, "step": 683520 }, { "epoch": 1.02, "learning_rate": 3.880104208500862e-05, "loss": 3.6829, "step": 684032 }, { "epoch": 1.02, "learning_rate": 3.87926561374981e-05, "loss": 3.6694, "step": 684544 }, { "epoch": 1.02, "learning_rate": 3.878427018998758e-05, "loss": 3.6692, "step": 685056 }, { "epoch": 1.02, "learning_rate": 3.877588424247705e-05, "loss": 3.6791, "step": 685568 }, { "epoch": 1.02, "learning_rate": 3.876749829496653e-05, "loss": 3.6643, "step": 686080 }, { "epoch": 1.02, "learning_rate": 3.875912872625975e-05, "loss": 3.6823, "step": 686592 }, { "epoch": 1.03, "eval_loss": 3.8686816692352295, "eval_runtime": 311.4895, "eval_samples_per_second": 1225.053, "eval_steps_per_second": 38.284, "step": 686880 }, { "epoch": 0.0, "learning_rate": 3.875074277874923e-05, "loss": 3.6659, "step": 687104 }, { "epoch": 0.0, "learning_rate": 3.87423568312387e-05, "loss": 3.6612, "step": 687616 }, { "epoch": 0.0, "learning_rate": 3.873397088372818e-05, "loss": 3.6759, "step": 688128 }, { "epoch": 0.0, "learning_rate": 3.872558493621766e-05, "loss": 3.6713, "step": 688640 }, { "epoch": 0.0, "learning_rate": 3.8717215367510876e-05, "loss": 3.6868, "step": 689152 }, { "epoch": 0.0, "learning_rate": 3.8708829420000356e-05, "loss": 3.6712, "step": 689664 }, { "epoch": 0.0, "learning_rate": 3.8700443472489836e-05, "loss": 3.6688, "step": 690176 }, { "epoch": 0.0, "learning_rate": 3.8692057524979316e-05, "loss": 3.6762, "step": 690688 }, { "epoch": 0.0, "learning_rate": 3.8683687956272525e-05, "loss": 3.6678, "step": 691200 }, { "epoch": 0.0, "learning_rate": 3.8675302008762005e-05, "loss": 3.6728, "step": 691712 }, { "epoch": 0.0, "learning_rate": 3.8666916061251485e-05, "loss": 3.6717, "step": 692224 }, { "epoch": 0.0, "learning_rate": 3.8658530113740964e-05, "loss": 3.6748, "step": 692736 }, { "epoch": 0.0, "learning_rate": 3.8650160545034174e-05, "loss": 3.678, "step": 693248 }, { "epoch": 0.0, "learning_rate": 3.8641774597523654e-05, "loss": 3.6566, "step": 693760 }, { "epoch": 0.0, "learning_rate": 3.8633388650013133e-05, "loss": 3.667, "step": 694272 }, { "epoch": 0.0, "learning_rate": 3.8625002702502613e-05, "loss": 3.6518, "step": 694784 }, { "epoch": 0.0, "learning_rate": 3.8616616754992093e-05, "loss": 3.6654, "step": 695296 }, { "epoch": 0.0, "learning_rate": 3.860824718628531e-05, "loss": 3.6697, "step": 695808 }, { "epoch": 0.0, "learning_rate": 3.859986123877479e-05, "loss": 3.6589, "step": 696320 }, { "epoch": 0.0, "learning_rate": 3.859147529126427e-05, "loss": 3.6848, "step": 696832 }, { "epoch": 0.0, "learning_rate": 3.858308934375375e-05, "loss": 3.6773, "step": 697344 }, { "epoch": 0.0, "learning_rate": 3.857471977504696e-05, "loss": 3.6761, "step": 697856 }, { "epoch": 0.0, "learning_rate": 3.856633382753644e-05, "loss": 3.6707, "step": 698368 }, { "epoch": 0.0, "learning_rate": 3.855794788002592e-05, "loss": 3.6682, "step": 698880 }, { "epoch": 0.0, "learning_rate": 3.85495619325154e-05, "loss": 3.6729, "step": 699392 }, { "epoch": 0.0, "learning_rate": 3.854119236380861e-05, "loss": 3.6704, "step": 699904 }, { "epoch": 0.0, "learning_rate": 3.853280641629809e-05, "loss": 3.6601, "step": 700416 }, { "epoch": 0.0, "learning_rate": 3.852442046878757e-05, "loss": 3.6758, "step": 700928 }, { "epoch": 0.0, "learning_rate": 3.851603452127705e-05, "loss": 3.6543, "step": 701440 }, { "epoch": 0.0, "learning_rate": 3.850766495257026e-05, "loss": 3.6606, "step": 701952 }, { "epoch": 0.01, "learning_rate": 3.849927900505974e-05, "loss": 3.6694, "step": 702464 }, { "epoch": 0.01, "learning_rate": 3.849089305754922e-05, "loss": 3.6723, "step": 702976 }, { "epoch": 0.01, "learning_rate": 3.84825071100387e-05, "loss": 3.6664, "step": 703488 }, { "epoch": 0.01, "learning_rate": 3.847412116252818e-05, "loss": 3.6764, "step": 704000 }, { "epoch": 0.01, "learning_rate": 3.846575159382139e-05, "loss": 3.6629, "step": 704512 }, { "epoch": 0.01, "learning_rate": 3.845736564631087e-05, "loss": 3.6582, "step": 705024 }, { "epoch": 0.01, "learning_rate": 3.844897969880035e-05, "loss": 3.671, "step": 705536 }, { "epoch": 0.01, "learning_rate": 3.844059375128983e-05, "loss": 3.6528, "step": 706048 }, { "epoch": 0.01, "learning_rate": 3.843222418258304e-05, "loss": 3.6622, "step": 706560 }, { "epoch": 0.01, "learning_rate": 3.842383823507252e-05, "loss": 3.661, "step": 707072 }, { "epoch": 0.01, "learning_rate": 3.8415452287562e-05, "loss": 3.6606, "step": 707584 }, { "epoch": 0.01, "learning_rate": 3.840706634005148e-05, "loss": 3.665, "step": 708096 }, { "epoch": 0.01, "learning_rate": 3.8398696771344697e-05, "loss": 3.6688, "step": 708608 }, { "epoch": 0.01, "learning_rate": 3.8390310823834177e-05, "loss": 3.6681, "step": 709120 }, { "epoch": 0.01, "learning_rate": 3.8381924876323656e-05, "loss": 3.6626, "step": 709632 }, { "epoch": 0.01, "learning_rate": 3.8373538928813136e-05, "loss": 3.6593, "step": 710144 }, { "epoch": 0.01, "learning_rate": 3.8365152981302616e-05, "loss": 3.6611, "step": 710656 }, { "epoch": 0.01, "learning_rate": 3.8356783412595825e-05, "loss": 3.665, "step": 711168 }, { "epoch": 0.01, "learning_rate": 3.8348397465085305e-05, "loss": 3.6409, "step": 711680 }, { "epoch": 0.01, "learning_rate": 3.8340011517574785e-05, "loss": 3.6719, "step": 712192 }, { "epoch": 0.01, "learning_rate": 3.8331625570064265e-05, "loss": 3.6557, "step": 712704 }, { "epoch": 0.01, "learning_rate": 3.8323256001357474e-05, "loss": 3.6646, "step": 713216 }, { "epoch": 0.01, "learning_rate": 3.8314870053846954e-05, "loss": 3.6543, "step": 713728 }, { "epoch": 0.01, "learning_rate": 3.8306484106336434e-05, "loss": 3.6511, "step": 714240 }, { "epoch": 0.01, "learning_rate": 3.829809815882592e-05, "loss": 3.6498, "step": 714752 }, { "epoch": 0.01, "learning_rate": 3.828972859011913e-05, "loss": 3.6539, "step": 715264 }, { "epoch": 0.01, "learning_rate": 3.828134264260861e-05, "loss": 3.6703, "step": 715776 }, { "epoch": 0.01, "learning_rate": 3.827295669509809e-05, "loss": 3.6529, "step": 716288 }, { "epoch": 0.01, "learning_rate": 3.826457074758757e-05, "loss": 3.6744, "step": 716800 }, { "epoch": 0.01, "learning_rate": 3.825620117888078e-05, "loss": 3.6638, "step": 717312 }, { "epoch": 0.01, "learning_rate": 3.824781523137026e-05, "loss": 3.6406, "step": 717824 }, { "epoch": 0.01, "learning_rate": 3.823942928385974e-05, "loss": 3.6594, "step": 718336 }, { "epoch": 0.01, "learning_rate": 3.823104333634922e-05, "loss": 3.65, "step": 718848 }, { "epoch": 0.01, "learning_rate": 3.822267376764243e-05, "loss": 3.6482, "step": 719360 }, { "epoch": 0.01, "learning_rate": 3.821428782013191e-05, "loss": 3.6638, "step": 719872 }, { "epoch": 0.01, "learning_rate": 3.820590187262139e-05, "loss": 3.6616, "step": 720384 }, { "epoch": 0.01, "learning_rate": 3.8197515925110875e-05, "loss": 3.6513, "step": 720896 }, { "epoch": 0.01, "learning_rate": 3.8189129977600355e-05, "loss": 3.6566, "step": 721408 }, { "epoch": 0.01, "learning_rate": 3.8180760408893564e-05, "loss": 3.6433, "step": 721920 }, { "epoch": 0.01, "learning_rate": 3.8172374461383044e-05, "loss": 3.649, "step": 722432 }, { "epoch": 0.01, "learning_rate": 3.8163988513872524e-05, "loss": 3.6615, "step": 722944 }, { "epoch": 0.01, "learning_rate": 3.8155602566362004e-05, "loss": 3.6587, "step": 723456 }, { "epoch": 0.01, "learning_rate": 3.814723299765521e-05, "loss": 3.6689, "step": 723968 }, { "epoch": 0.01, "learning_rate": 3.813884705014469e-05, "loss": 3.6551, "step": 724480 }, { "epoch": 0.01, "learning_rate": 3.813046110263417e-05, "loss": 3.6712, "step": 724992 }, { "epoch": 0.01, "learning_rate": 3.812207515512365e-05, "loss": 3.6524, "step": 725504 }, { "epoch": 0.01, "learning_rate": 3.8113689207613126e-05, "loss": 3.6707, "step": 726016 }, { "epoch": 0.01, "learning_rate": 3.810531963890634e-05, "loss": 3.6454, "step": 726528 }, { "epoch": 0.01, "learning_rate": 3.809693369139583e-05, "loss": 3.6492, "step": 727040 }, { "epoch": 0.01, "learning_rate": 3.808854774388531e-05, "loss": 3.66, "step": 727552 }, { "epoch": 0.01, "learning_rate": 3.808016179637478e-05, "loss": 3.6678, "step": 728064 }, { "epoch": 0.01, "learning_rate": 3.8071792227668e-05, "loss": 3.6588, "step": 728576 }, { "epoch": 0.01, "learning_rate": 3.806340628015748e-05, "loss": 3.6635, "step": 729088 }, { "epoch": 0.01, "learning_rate": 3.805502033264696e-05, "loss": 3.6375, "step": 729600 }, { "epoch": 0.01, "learning_rate": 3.804663438513643e-05, "loss": 3.6422, "step": 730112 }, { "epoch": 0.01, "learning_rate": 3.8038264816429646e-05, "loss": 3.6595, "step": 730624 }, { "epoch": 0.01, "learning_rate": 3.8029878868919126e-05, "loss": 3.6577, "step": 731136 }, { "epoch": 0.01, "learning_rate": 3.80214929214086e-05, "loss": 3.6498, "step": 731648 }, { "epoch": 0.01, "learning_rate": 3.801310697389808e-05, "loss": 3.6587, "step": 732160 }, { "epoch": 0.02, "learning_rate": 3.8004737405191295e-05, "loss": 3.654, "step": 732672 }, { "epoch": 0.02, "learning_rate": 3.799635145768078e-05, "loss": 3.6531, "step": 733184 }, { "epoch": 0.02, "learning_rate": 3.7987965510170255e-05, "loss": 3.6481, "step": 733696 }, { "epoch": 0.02, "learning_rate": 3.7979579562659735e-05, "loss": 3.6515, "step": 734208 }, { "epoch": 0.02, "learning_rate": 3.797120999395295e-05, "loss": 3.6624, "step": 734720 }, { "epoch": 0.02, "learning_rate": 3.796282404644243e-05, "loss": 3.6676, "step": 735232 }, { "epoch": 0.02, "learning_rate": 3.7954438098931904e-05, "loss": 3.6666, "step": 735744 }, { "epoch": 0.02, "learning_rate": 3.7946052151421384e-05, "loss": 3.6457, "step": 736256 }, { "epoch": 0.02, "learning_rate": 3.79376825827146e-05, "loss": 3.6566, "step": 736768 }, { "epoch": 0.02, "learning_rate": 3.792929663520407e-05, "loss": 3.651, "step": 737280 }, { "epoch": 0.02, "learning_rate": 3.792091068769355e-05, "loss": 3.6585, "step": 737792 }, { "epoch": 0.02, "learning_rate": 3.791252474018303e-05, "loss": 3.6534, "step": 738304 }, { "epoch": 0.02, "learning_rate": 3.790415517147625e-05, "loss": 3.6526, "step": 738816 }, { "epoch": 0.02, "learning_rate": 3.789576922396573e-05, "loss": 3.6499, "step": 739328 }, { "epoch": 0.02, "learning_rate": 3.788738327645521e-05, "loss": 3.6469, "step": 739840 }, { "epoch": 0.02, "learning_rate": 3.787899732894469e-05, "loss": 3.652, "step": 740352 }, { "epoch": 0.02, "learning_rate": 3.787061138143417e-05, "loss": 3.6502, "step": 740864 }, { "epoch": 0.02, "learning_rate": 3.786224181272738e-05, "loss": 3.6425, "step": 741376 }, { "epoch": 0.02, "learning_rate": 3.785385586521686e-05, "loss": 3.6575, "step": 741888 }, { "epoch": 0.02, "learning_rate": 3.784546991770634e-05, "loss": 3.653, "step": 742400 }, { "epoch": 0.02, "learning_rate": 3.783708397019582e-05, "loss": 3.649, "step": 742912 }, { "epoch": 0.02, "learning_rate": 3.782871440148903e-05, "loss": 3.6521, "step": 743424 }, { "epoch": 0.02, "learning_rate": 3.782032845397851e-05, "loss": 3.6511, "step": 743936 }, { "epoch": 0.02, "learning_rate": 3.781194250646799e-05, "loss": 3.658, "step": 744448 }, { "epoch": 0.02, "learning_rate": 3.7803556558957474e-05, "loss": 3.6497, "step": 744960 }, { "epoch": 0.02, "learning_rate": 3.779518699025068e-05, "loss": 3.6607, "step": 745472 }, { "epoch": 0.02, "learning_rate": 3.778680104274016e-05, "loss": 3.6619, "step": 745984 }, { "epoch": 0.02, "learning_rate": 3.777841509522964e-05, "loss": 3.6566, "step": 746496 }, { "epoch": 0.02, "learning_rate": 3.777002914771912e-05, "loss": 3.6533, "step": 747008 }, { "epoch": 0.02, "learning_rate": 3.776165957901233e-05, "loss": 3.6541, "step": 747520 }, { "epoch": 0.02, "learning_rate": 3.775327363150181e-05, "loss": 3.645, "step": 748032 }, { "epoch": 0.02, "learning_rate": 3.774488768399129e-05, "loss": 3.6562, "step": 748544 }, { "epoch": 0.02, "learning_rate": 3.773650173648077e-05, "loss": 3.6496, "step": 749056 }, { "epoch": 0.02, "learning_rate": 3.772813216777398e-05, "loss": 3.637, "step": 749568 }, { "epoch": 0.02, "learning_rate": 3.771974622026346e-05, "loss": 3.6614, "step": 750080 }, { "epoch": 0.02, "learning_rate": 3.771136027275294e-05, "loss": 3.6565, "step": 750592 }, { "epoch": 0.02, "learning_rate": 3.770297432524243e-05, "loss": 3.6568, "step": 751104 }, { "epoch": 0.02, "learning_rate": 3.769458837773191e-05, "loss": 3.6507, "step": 751616 }, { "epoch": 0.02, "learning_rate": 3.7686218809025116e-05, "loss": 3.6436, "step": 752128 }, { "epoch": 0.02, "learning_rate": 3.7677832861514596e-05, "loss": 3.6478, "step": 752640 }, { "epoch": 0.02, "learning_rate": 3.7669446914004076e-05, "loss": 3.6573, "step": 753152 }, { "epoch": 0.02, "learning_rate": 3.7661077345297285e-05, "loss": 3.6534, "step": 753664 }, { "epoch": 0.02, "learning_rate": 3.7652691397786765e-05, "loss": 3.6615, "step": 754176 }, { "epoch": 0.02, "learning_rate": 3.7644305450276245e-05, "loss": 3.6335, "step": 754688 }, { "epoch": 0.02, "learning_rate": 3.7635919502765725e-05, "loss": 3.6621, "step": 755200 }, { "epoch": 0.02, "learning_rate": 3.7627533555255205e-05, "loss": 3.648, "step": 755712 }, { "epoch": 0.02, "learning_rate": 3.7619163986548414e-05, "loss": 3.6587, "step": 756224 }, { "epoch": 0.02, "learning_rate": 3.7610778039037894e-05, "loss": 3.6472, "step": 756736 }, { "epoch": 0.02, "learning_rate": 3.760239209152738e-05, "loss": 3.6457, "step": 757248 }, { "epoch": 0.02, "learning_rate": 3.759400614401686e-05, "loss": 3.6522, "step": 757760 }, { "epoch": 0.02, "learning_rate": 3.758563657531007e-05, "loss": 3.6702, "step": 758272 }, { "epoch": 0.02, "learning_rate": 3.757725062779955e-05, "loss": 3.6482, "step": 758784 }, { "epoch": 0.02, "learning_rate": 3.756886468028903e-05, "loss": 3.6574, "step": 759296 }, { "epoch": 0.02, "learning_rate": 3.756047873277851e-05, "loss": 3.6439, "step": 759808 }, { "epoch": 0.02, "learning_rate": 3.755210916407172e-05, "loss": 3.6551, "step": 760320 }, { "epoch": 0.02, "learning_rate": 3.75437232165612e-05, "loss": 3.6445, "step": 760832 }, { "epoch": 0.02, "learning_rate": 3.753533726905068e-05, "loss": 3.6457, "step": 761344 }, { "epoch": 0.02, "learning_rate": 3.752695132154016e-05, "loss": 3.6544, "step": 761856 }, { "epoch": 0.02, "learning_rate": 3.751858175283337e-05, "loss": 3.6451, "step": 762368 }, { "epoch": 0.02, "learning_rate": 3.751019580532285e-05, "loss": 3.6624, "step": 762880 }, { "epoch": 0.03, "eval_loss": 3.866302013397217, "eval_runtime": 319.9509, "eval_samples_per_second": 1192.655, "eval_steps_per_second": 37.271, "step": 763200 }, { "epoch": 1.0, "learning_rate": 3.750180985781233e-05, "loss": 3.6429, "step": 763392 }, { "epoch": 1.0, "learning_rate": 3.7493423910301815e-05, "loss": 3.6375, "step": 763904 }, { "epoch": 1.0, "learning_rate": 3.7485054341595024e-05, "loss": 3.652, "step": 764416 }, { "epoch": 1.0, "learning_rate": 3.7476668394084504e-05, "loss": 3.6497, "step": 764928 }, { "epoch": 1.0, "learning_rate": 3.7468282446573984e-05, "loss": 3.6639, "step": 765440 }, { "epoch": 1.0, "learning_rate": 3.7459896499063463e-05, "loss": 3.6468, "step": 765952 }, { "epoch": 1.0, "learning_rate": 3.745152693035667e-05, "loss": 3.6458, "step": 766464 }, { "epoch": 1.0, "learning_rate": 3.744314098284615e-05, "loss": 3.6533, "step": 766976 }, { "epoch": 1.0, "learning_rate": 3.743475503533563e-05, "loss": 3.6442, "step": 767488 }, { "epoch": 1.0, "learning_rate": 3.742636908782511e-05, "loss": 3.6433, "step": 768000 }, { "epoch": 1.0, "learning_rate": 3.741799951911832e-05, "loss": 3.6526, "step": 768512 }, { "epoch": 1.0, "learning_rate": 3.74096135716078e-05, "loss": 3.6516, "step": 769024 }, { "epoch": 1.0, "learning_rate": 3.740124400290102e-05, "loss": 3.6546, "step": 769536 }, { "epoch": 1.0, "learning_rate": 3.73928580553905e-05, "loss": 3.6353, "step": 770048 }, { "epoch": 1.0, "learning_rate": 3.738447210787998e-05, "loss": 3.6421, "step": 770560 }, { "epoch": 1.0, "learning_rate": 3.737608616036946e-05, "loss": 3.6279, "step": 771072 }, { "epoch": 1.0, "learning_rate": 3.736770021285894e-05, "loss": 3.6434, "step": 771584 }, { "epoch": 1.0, "learning_rate": 3.735931426534842e-05, "loss": 3.6485, "step": 772096 }, { "epoch": 1.0, "learning_rate": 3.73509283178379e-05, "loss": 3.6329, "step": 772608 }, { "epoch": 1.0, "learning_rate": 3.734254237032738e-05, "loss": 3.6604, "step": 773120 }, { "epoch": 1.0, "learning_rate": 3.7334172801620586e-05, "loss": 3.6577, "step": 773632 }, { "epoch": 1.0, "learning_rate": 3.7325786854110066e-05, "loss": 3.6533, "step": 774144 }, { "epoch": 1.0, "learning_rate": 3.7317400906599546e-05, "loss": 3.6464, "step": 774656 }, { "epoch": 1.0, "learning_rate": 3.7309014959089026e-05, "loss": 3.6449, "step": 775168 }, { "epoch": 1.0, "learning_rate": 3.7300645390382235e-05, "loss": 3.6497, "step": 775680 }, { "epoch": 1.0, "learning_rate": 3.729225944287172e-05, "loss": 3.6449, "step": 776192 }, { "epoch": 1.0, "learning_rate": 3.72838734953612e-05, "loss": 3.6408, "step": 776704 }, { "epoch": 1.0, "learning_rate": 3.727548754785068e-05, "loss": 3.6516, "step": 777216 }, { "epoch": 1.0, "learning_rate": 3.726711797914389e-05, "loss": 3.633, "step": 777728 }, { "epoch": 1.0, "learning_rate": 3.725873203163337e-05, "loss": 3.632, "step": 778240 }, { "epoch": 1.01, "learning_rate": 3.725034608412285e-05, "loss": 3.6478, "step": 778752 }, { "epoch": 1.01, "learning_rate": 3.724196013661233e-05, "loss": 3.6452, "step": 779264 }, { "epoch": 1.01, "learning_rate": 3.723359056790554e-05, "loss": 3.6484, "step": 779776 }, { "epoch": 1.01, "learning_rate": 3.722520462039502e-05, "loss": 3.6505, "step": 780288 }, { "epoch": 1.01, "learning_rate": 3.72168186728845e-05, "loss": 3.6397, "step": 780800 }, { "epoch": 1.01, "learning_rate": 3.720843272537398e-05, "loss": 3.6387, "step": 781312 }, { "epoch": 1.01, "learning_rate": 3.720006315666719e-05, "loss": 3.6443, "step": 781824 }, { "epoch": 1.01, "learning_rate": 3.7191677209156676e-05, "loss": 3.6322, "step": 782336 }, { "epoch": 1.01, "learning_rate": 3.7183291261646155e-05, "loss": 3.6402, "step": 782848 }, { "epoch": 1.01, "learning_rate": 3.717490531413563e-05, "loss": 3.6399, "step": 783360 }, { "epoch": 1.01, "learning_rate": 3.716651936662511e-05, "loss": 3.6335, "step": 783872 }, { "epoch": 1.01, "learning_rate": 3.715813341911459e-05, "loss": 3.6441, "step": 784384 }, { "epoch": 1.01, "learning_rate": 3.7149763850407804e-05, "loss": 3.6523, "step": 784896 }, { "epoch": 1.01, "learning_rate": 3.714137790289728e-05, "loss": 3.6415, "step": 785408 }, { "epoch": 1.01, "learning_rate": 3.713299195538676e-05, "loss": 3.6402, "step": 785920 }, { "epoch": 1.01, "learning_rate": 3.7124622386679973e-05, "loss": 3.6366, "step": 786432 }, { "epoch": 1.01, "learning_rate": 3.7116236439169453e-05, "loss": 3.6401, "step": 786944 }, { "epoch": 1.01, "learning_rate": 3.7107850491658927e-05, "loss": 3.6398, "step": 787456 }, { "epoch": 1.01, "learning_rate": 3.709946454414841e-05, "loss": 3.6228, "step": 787968 }, { "epoch": 1.01, "learning_rate": 3.709109497544163e-05, "loss": 3.6489, "step": 788480 }, { "epoch": 1.01, "learning_rate": 3.70827090279311e-05, "loss": 3.632, "step": 788992 }, { "epoch": 1.01, "learning_rate": 3.707432308042058e-05, "loss": 3.6443, "step": 789504 }, { "epoch": 1.01, "learning_rate": 3.706593713291006e-05, "loss": 3.6348, "step": 790016 }, { "epoch": 1.01, "learning_rate": 3.705756756420328e-05, "loss": 3.6257, "step": 790528 }, { "epoch": 1.01, "learning_rate": 3.704918161669275e-05, "loss": 3.6252, "step": 791040 }, { "epoch": 1.01, "learning_rate": 3.704079566918223e-05, "loss": 3.6293, "step": 791552 }, { "epoch": 1.01, "learning_rate": 3.703240972167171e-05, "loss": 3.651, "step": 792064 }, { "epoch": 1.01, "learning_rate": 3.702404015296493e-05, "loss": 3.629, "step": 792576 }, { "epoch": 1.01, "learning_rate": 3.70156542054544e-05, "loss": 3.651, "step": 793088 }, { "epoch": 1.01, "learning_rate": 3.700726825794388e-05, "loss": 3.641, "step": 793600 }, { "epoch": 1.01, "learning_rate": 3.699888231043337e-05, "loss": 3.6192, "step": 794112 }, { "epoch": 1.01, "learning_rate": 3.699049636292285e-05, "loss": 3.6378, "step": 794624 }, { "epoch": 1.01, "learning_rate": 3.6982126794216056e-05, "loss": 3.6272, "step": 795136 }, { "epoch": 1.01, "learning_rate": 3.6973740846705536e-05, "loss": 3.6244, "step": 795648 }, { "epoch": 1.01, "learning_rate": 3.6965354899195016e-05, "loss": 3.6391, "step": 796160 }, { "epoch": 1.01, "learning_rate": 3.6956968951684496e-05, "loss": 3.6404, "step": 796672 }, { "epoch": 1.01, "learning_rate": 3.6948599382977705e-05, "loss": 3.6262, "step": 797184 }, { "epoch": 1.01, "learning_rate": 3.6940213435467185e-05, "loss": 3.6376, "step": 797696 }, { "epoch": 1.01, "learning_rate": 3.6931827487956665e-05, "loss": 3.6183, "step": 798208 }, { "epoch": 1.01, "learning_rate": 3.6923441540446145e-05, "loss": 3.6297, "step": 798720 }, { "epoch": 1.01, "learning_rate": 3.6915071971739354e-05, "loss": 3.6367, "step": 799232 }, { "epoch": 1.01, "learning_rate": 3.6906686024228834e-05, "loss": 3.6382, "step": 799744 }, { "epoch": 1.01, "learning_rate": 3.689830007671832e-05, "loss": 3.6415, "step": 800256 }, { "epoch": 1.01, "learning_rate": 3.68899141292078e-05, "loss": 3.6357, "step": 800768 }, { "epoch": 1.01, "learning_rate": 3.688154456050101e-05, "loss": 3.6462, "step": 801280 }, { "epoch": 1.01, "learning_rate": 3.687315861299049e-05, "loss": 3.632, "step": 801792 }, { "epoch": 1.01, "learning_rate": 3.686477266547997e-05, "loss": 3.6454, "step": 802304 }, { "epoch": 1.01, "learning_rate": 3.685638671796945e-05, "loss": 3.6225, "step": 802816 }, { "epoch": 1.01, "learning_rate": 3.684801714926266e-05, "loss": 3.6276, "step": 803328 }, { "epoch": 1.01, "learning_rate": 3.683963120175214e-05, "loss": 3.6374, "step": 803840 }, { "epoch": 1.01, "learning_rate": 3.683124525424162e-05, "loss": 3.641, "step": 804352 }, { "epoch": 1.01, "learning_rate": 3.68228593067311e-05, "loss": 3.6393, "step": 804864 }, { "epoch": 1.01, "learning_rate": 3.681448973802431e-05, "loss": 3.6397, "step": 805376 }, { "epoch": 1.01, "learning_rate": 3.680610379051379e-05, "loss": 3.6212, "step": 805888 }, { "epoch": 1.01, "learning_rate": 3.6797717843003274e-05, "loss": 3.6162, "step": 806400 }, { "epoch": 1.01, "learning_rate": 3.6789331895492754e-05, "loss": 3.6389, "step": 806912 }, { "epoch": 1.01, "learning_rate": 3.678096232678596e-05, "loss": 3.6342, "step": 807424 }, { "epoch": 1.01, "learning_rate": 3.677257637927544e-05, "loss": 3.6298, "step": 807936 }, { "epoch": 1.01, "learning_rate": 3.676419043176492e-05, "loss": 3.6377, "step": 808448 }, { "epoch": 1.01, "learning_rate": 3.67558044842544e-05, "loss": 3.632, "step": 808960 }, { "epoch": 1.02, "learning_rate": 3.674741853674388e-05, "loss": 3.6293, "step": 809472 }, { "epoch": 1.02, "learning_rate": 3.673904896803709e-05, "loss": 3.6299, "step": 809984 }, { "epoch": 1.02, "learning_rate": 3.673066302052657e-05, "loss": 3.6279, "step": 810496 }, { "epoch": 1.02, "learning_rate": 3.672227707301605e-05, "loss": 3.6404, "step": 811008 }, { "epoch": 1.02, "learning_rate": 3.671389112550553e-05, "loss": 3.6446, "step": 811520 }, { "epoch": 1.02, "learning_rate": 3.670552155679874e-05, "loss": 3.6458, "step": 812032 }, { "epoch": 1.02, "learning_rate": 3.669713560928822e-05, "loss": 3.623, "step": 812544 }, { "epoch": 1.02, "learning_rate": 3.668874966177771e-05, "loss": 3.6317, "step": 813056 }, { "epoch": 1.02, "learning_rate": 3.668036371426719e-05, "loss": 3.6315, "step": 813568 }, { "epoch": 1.02, "learning_rate": 3.66719941455604e-05, "loss": 3.632, "step": 814080 }, { "epoch": 1.02, "learning_rate": 3.666360819804988e-05, "loss": 3.6351, "step": 814592 }, { "epoch": 1.02, "learning_rate": 3.665522225053936e-05, "loss": 3.6308, "step": 815104 }, { "epoch": 1.02, "learning_rate": 3.664683630302884e-05, "loss": 3.6311, "step": 815616 }, { "epoch": 1.02, "learning_rate": 3.6638466734322046e-05, "loss": 3.6234, "step": 816128 }, { "epoch": 1.02, "learning_rate": 3.6630080786811526e-05, "loss": 3.6304, "step": 816640 }, { "epoch": 1.02, "learning_rate": 3.6621694839301006e-05, "loss": 3.6273, "step": 817152 }, { "epoch": 1.02, "learning_rate": 3.6613308891790486e-05, "loss": 3.6243, "step": 817664 }, { "epoch": 1.02, "learning_rate": 3.6604939323083695e-05, "loss": 3.6346, "step": 818176 }, { "epoch": 1.02, "learning_rate": 3.6596553375573175e-05, "loss": 3.6293, "step": 818688 }, { "epoch": 1.02, "learning_rate": 3.658816742806266e-05, "loss": 3.6283, "step": 819200 }, { "epoch": 1.02, "learning_rate": 3.657978148055214e-05, "loss": 3.6351, "step": 819712 }, { "epoch": 1.02, "learning_rate": 3.657141191184535e-05, "loss": 3.6248, "step": 820224 }, { "epoch": 1.02, "learning_rate": 3.656302596433483e-05, "loss": 3.6358, "step": 820736 }, { "epoch": 1.02, "learning_rate": 3.655464001682431e-05, "loss": 3.6318, "step": 821248 }, { "epoch": 1.02, "learning_rate": 3.654625406931379e-05, "loss": 3.6339, "step": 821760 }, { "epoch": 1.02, "learning_rate": 3.6537884500607e-05, "loss": 3.6433, "step": 822272 }, { "epoch": 1.02, "learning_rate": 3.652949855309648e-05, "loss": 3.634, "step": 822784 }, { "epoch": 1.02, "learning_rate": 3.652111260558596e-05, "loss": 3.6295, "step": 823296 }, { "epoch": 1.02, "learning_rate": 3.651272665807544e-05, "loss": 3.6359, "step": 823808 }, { "epoch": 1.02, "learning_rate": 3.650435708936865e-05, "loss": 3.6241, "step": 824320 }, { "epoch": 1.02, "learning_rate": 3.649597114185813e-05, "loss": 3.6335, "step": 824832 }, { "epoch": 1.02, "learning_rate": 3.6487585194347615e-05, "loss": 3.6286, "step": 825344 }, { "epoch": 1.02, "learning_rate": 3.6479199246837095e-05, "loss": 3.6176, "step": 825856 }, { "epoch": 1.02, "learning_rate": 3.6470829678130304e-05, "loss": 3.6392, "step": 826368 }, { "epoch": 1.02, "learning_rate": 3.6462443730619784e-05, "loss": 3.6385, "step": 826880 }, { "epoch": 1.02, "learning_rate": 3.6454057783109264e-05, "loss": 3.6332, "step": 827392 }, { "epoch": 1.02, "learning_rate": 3.6445671835598744e-05, "loss": 3.6294, "step": 827904 }, { "epoch": 1.02, "learning_rate": 3.643730226689195e-05, "loss": 3.6246, "step": 828416 }, { "epoch": 1.02, "learning_rate": 3.642891631938143e-05, "loss": 3.6226, "step": 828928 }, { "epoch": 1.02, "learning_rate": 3.642053037187091e-05, "loss": 3.6377, "step": 829440 }, { "epoch": 1.02, "learning_rate": 3.641214442436039e-05, "loss": 3.6315, "step": 829952 }, { "epoch": 1.02, "learning_rate": 3.64037748556536e-05, "loss": 3.6393, "step": 830464 }, { "epoch": 1.02, "learning_rate": 3.639538890814308e-05, "loss": 3.6098, "step": 830976 }, { "epoch": 1.02, "learning_rate": 3.638700296063257e-05, "loss": 3.6422, "step": 831488 }, { "epoch": 1.02, "learning_rate": 3.637861701312205e-05, "loss": 3.6237, "step": 832000 }, { "epoch": 1.02, "learning_rate": 3.637024744441526e-05, "loss": 3.6448, "step": 832512 }, { "epoch": 1.02, "learning_rate": 3.636186149690474e-05, "loss": 3.6228, "step": 833024 }, { "epoch": 1.02, "learning_rate": 3.635347554939422e-05, "loss": 3.6248, "step": 833536 }, { "epoch": 1.02, "learning_rate": 3.63450896018837e-05, "loss": 3.6314, "step": 834048 }, { "epoch": 1.02, "learning_rate": 3.633672003317691e-05, "loss": 3.6511, "step": 834560 }, { "epoch": 1.02, "learning_rate": 3.632833408566639e-05, "loss": 3.6259, "step": 835072 }, { "epoch": 1.02, "learning_rate": 3.631994813815587e-05, "loss": 3.6385, "step": 835584 }, { "epoch": 1.02, "learning_rate": 3.631156219064535e-05, "loss": 3.619, "step": 836096 }, { "epoch": 1.02, "learning_rate": 3.630317624313483e-05, "loss": 3.6363, "step": 836608 }, { "epoch": 1.02, "learning_rate": 3.6294806674428036e-05, "loss": 3.6219, "step": 837120 }, { "epoch": 1.02, "learning_rate": 3.628642072691752e-05, "loss": 3.6281, "step": 837632 }, { "epoch": 1.02, "learning_rate": 3.6278034779407e-05, "loss": 3.6307, "step": 838144 }, { "epoch": 1.02, "learning_rate": 3.6269648831896476e-05, "loss": 3.6267, "step": 838656 }, { "epoch": 1.02, "learning_rate": 3.626127926318969e-05, "loss": 3.6374, "step": 839168 }, { "epoch": 1.03, "eval_loss": 3.864625930786133, "eval_runtime": 358.976, "eval_samples_per_second": 1062.999, "eval_steps_per_second": 33.219, "step": 839520 }, { "epoch": 0.0, "learning_rate": 3.625289331567917e-05, "loss": 3.6246, "step": 839680 }, { "epoch": 0.0, "learning_rate": 3.624450736816865e-05, "loss": 3.6148, "step": 840192 }, { "epoch": 0.0, "learning_rate": 3.6236121420658125e-05, "loss": 3.6321, "step": 840704 }, { "epoch": 0.0, "learning_rate": 3.6227735473147605e-05, "loss": 3.6259, "step": 841216 }, { "epoch": 0.0, "learning_rate": 3.621936590444082e-05, "loss": 3.6411, "step": 841728 }, { "epoch": 0.0, "learning_rate": 3.62109799569303e-05, "loss": 3.6269, "step": 842240 }, { "epoch": 0.0, "learning_rate": 3.6202594009419774e-05, "loss": 3.6255, "step": 842752 }, { "epoch": 0.0, "learning_rate": 3.619420806190926e-05, "loss": 3.6318, "step": 843264 }, { "epoch": 0.0, "learning_rate": 3.6185838493202476e-05, "loss": 3.6224, "step": 843776 }, { "epoch": 0.0, "learning_rate": 3.617745254569195e-05, "loss": 3.6203, "step": 844288 }, { "epoch": 0.0, "learning_rate": 3.616906659818143e-05, "loss": 3.6317, "step": 844800 }, { "epoch": 0.0, "learning_rate": 3.616068065067091e-05, "loss": 3.628, "step": 845312 }, { "epoch": 0.0, "learning_rate": 3.6152311081964125e-05, "loss": 3.6359, "step": 845824 }, { "epoch": 0.0, "learning_rate": 3.61439251344536e-05, "loss": 3.6116, "step": 846336 }, { "epoch": 0.0, "learning_rate": 3.613553918694308e-05, "loss": 3.616, "step": 846848 }, { "epoch": 0.0, "learning_rate": 3.612715323943256e-05, "loss": 3.6125, "step": 847360 }, { "epoch": 0.0, "learning_rate": 3.6118783670725774e-05, "loss": 3.6255, "step": 847872 }, { "epoch": 0.0, "learning_rate": 3.611039772321525e-05, "loss": 3.6211, "step": 848384 }, { "epoch": 0.0, "learning_rate": 3.610201177570473e-05, "loss": 3.6156, "step": 848896 }, { "epoch": 0.0, "learning_rate": 3.6093625828194214e-05, "loss": 3.6332, "step": 849408 }, { "epoch": 0.0, "learning_rate": 3.6085239880683694e-05, "loss": 3.6404, "step": 849920 }, { "epoch": 0.0, "learning_rate": 3.60768703119769e-05, "loss": 3.6321, "step": 850432 }, { "epoch": 0.0, "learning_rate": 3.606848436446638e-05, "loss": 3.6255, "step": 850944 }, { "epoch": 0.0, "learning_rate": 3.606009841695586e-05, "loss": 3.6248, "step": 851456 }, { "epoch": 0.0, "learning_rate": 3.605171246944534e-05, "loss": 3.6304, "step": 851968 }, { "epoch": 0.0, "learning_rate": 3.604334290073855e-05, "loss": 3.6215, "step": 852480 }, { "epoch": 0.0, "learning_rate": 3.603495695322803e-05, "loss": 3.6212, "step": 852992 }, { "epoch": 0.0, "learning_rate": 3.602657100571751e-05, "loss": 3.6316, "step": 853504 }, { "epoch": 0.0, "learning_rate": 3.601818505820699e-05, "loss": 3.6137, "step": 854016 }, { "epoch": 0.0, "learning_rate": 3.60098154895002e-05, "loss": 3.6123, "step": 854528 }, { "epoch": 0.01, "learning_rate": 3.600142954198968e-05, "loss": 3.6245, "step": 855040 }, { "epoch": 0.01, "learning_rate": 3.599304359447917e-05, "loss": 3.625, "step": 855552 }, { "epoch": 0.01, "learning_rate": 3.598465764696865e-05, "loss": 3.6307, "step": 856064 }, { "epoch": 0.01, "learning_rate": 3.597628807826186e-05, "loss": 3.6294, "step": 856576 }, { "epoch": 0.01, "learning_rate": 3.596790213075134e-05, "loss": 3.6182, "step": 857088 }, { "epoch": 0.01, "learning_rate": 3.595951618324082e-05, "loss": 3.6205, "step": 857600 }, { "epoch": 0.01, "learning_rate": 3.59511302357303e-05, "loss": 3.6209, "step": 858112 }, { "epoch": 0.01, "learning_rate": 3.5942760667023506e-05, "loss": 3.6136, "step": 858624 }, { "epoch": 0.01, "learning_rate": 3.5934374719512986e-05, "loss": 3.6247, "step": 859136 }, { "epoch": 0.01, "learning_rate": 3.5925988772002466e-05, "loss": 3.6158, "step": 859648 }, { "epoch": 0.01, "learning_rate": 3.5917602824491946e-05, "loss": 3.6151, "step": 860160 }, { "epoch": 0.01, "learning_rate": 3.5909216876981426e-05, "loss": 3.6207, "step": 860672 }, { "epoch": 0.01, "learning_rate": 3.5900847308274635e-05, "loss": 3.6342, "step": 861184 }, { "epoch": 0.01, "learning_rate": 3.589246136076412e-05, "loss": 3.6164, "step": 861696 }, { "epoch": 0.01, "learning_rate": 3.58840754132536e-05, "loss": 3.6217, "step": 862208 }, { "epoch": 0.01, "learning_rate": 3.587568946574308e-05, "loss": 3.6201, "step": 862720 }, { "epoch": 0.01, "learning_rate": 3.586731989703629e-05, "loss": 3.6161, "step": 863232 }, { "epoch": 0.01, "learning_rate": 3.585893394952577e-05, "loss": 3.6181, "step": 863744 }, { "epoch": 0.01, "learning_rate": 3.585054800201525e-05, "loss": 3.6046, "step": 864256 }, { "epoch": 0.01, "learning_rate": 3.584216205450473e-05, "loss": 3.6255, "step": 864768 }, { "epoch": 0.01, "learning_rate": 3.583379248579794e-05, "loss": 3.6142, "step": 865280 }, { "epoch": 0.01, "learning_rate": 3.582540653828742e-05, "loss": 3.6241, "step": 865792 }, { "epoch": 0.01, "learning_rate": 3.58170205907769e-05, "loss": 3.6156, "step": 866304 }, { "epoch": 0.01, "learning_rate": 3.580865102207011e-05, "loss": 3.6048, "step": 866816 }, { "epoch": 0.01, "learning_rate": 3.580026507455959e-05, "loss": 3.6046, "step": 867328 }, { "epoch": 0.01, "learning_rate": 3.579187912704907e-05, "loss": 3.6047, "step": 867840 }, { "epoch": 0.01, "learning_rate": 3.5783493179538555e-05, "loss": 3.6313, "step": 868352 }, { "epoch": 0.01, "learning_rate": 3.5775107232028035e-05, "loss": 3.6109, "step": 868864 }, { "epoch": 0.01, "learning_rate": 3.5766737663321244e-05, "loss": 3.631, "step": 869376 }, { "epoch": 0.01, "learning_rate": 3.5758351715810724e-05, "loss": 3.617, "step": 869888 }, { "epoch": 0.01, "learning_rate": 3.5749965768300204e-05, "loss": 3.6032, "step": 870400 }, { "epoch": 0.01, "learning_rate": 3.5741579820789684e-05, "loss": 3.6174, "step": 870912 }, { "epoch": 0.01, "learning_rate": 3.573321025208289e-05, "loss": 3.6065, "step": 871424 }, { "epoch": 0.01, "learning_rate": 3.572482430457237e-05, "loss": 3.6049, "step": 871936 }, { "epoch": 0.01, "learning_rate": 3.571643835706185e-05, "loss": 3.6185, "step": 872448 }, { "epoch": 0.01, "learning_rate": 3.570805240955133e-05, "loss": 3.6205, "step": 872960 }, { "epoch": 0.01, "learning_rate": 3.569968284084454e-05, "loss": 3.6083, "step": 873472 }, { "epoch": 0.01, "learning_rate": 3.569129689333402e-05, "loss": 3.6186, "step": 873984 }, { "epoch": 0.01, "learning_rate": 3.568291094582351e-05, "loss": 3.5969, "step": 874496 }, { "epoch": 0.01, "learning_rate": 3.567452499831299e-05, "loss": 3.6108, "step": 875008 }, { "epoch": 0.01, "learning_rate": 3.56661554296062e-05, "loss": 3.6157, "step": 875520 }, { "epoch": 0.01, "learning_rate": 3.565776948209568e-05, "loss": 3.6209, "step": 876032 }, { "epoch": 0.01, "learning_rate": 3.564938353458516e-05, "loss": 3.6205, "step": 876544 }, { "epoch": 0.01, "learning_rate": 3.564099758707464e-05, "loss": 3.6147, "step": 877056 }, { "epoch": 0.01, "learning_rate": 3.563261163956412e-05, "loss": 3.6273, "step": 877568 }, { "epoch": 0.01, "learning_rate": 3.562424207085733e-05, "loss": 3.6112, "step": 878080 }, { "epoch": 0.01, "learning_rate": 3.5615856123346807e-05, "loss": 3.6253, "step": 878592 }, { "epoch": 0.01, "learning_rate": 3.5607470175836287e-05, "loss": 3.6069, "step": 879104 }, { "epoch": 0.01, "learning_rate": 3.5599084228325767e-05, "loss": 3.6089, "step": 879616 }, { "epoch": 0.01, "learning_rate": 3.5590714659618976e-05, "loss": 3.615, "step": 880128 }, { "epoch": 0.01, "learning_rate": 3.558232871210846e-05, "loss": 3.6199, "step": 880640 }, { "epoch": 0.01, "learning_rate": 3.557394276459794e-05, "loss": 3.6154, "step": 881152 }, { "epoch": 0.01, "learning_rate": 3.556555681708742e-05, "loss": 3.6236, "step": 881664 }, { "epoch": 0.01, "learning_rate": 3.555718724838063e-05, "loss": 3.6011, "step": 882176 }, { "epoch": 0.01, "learning_rate": 3.554880130087011e-05, "loss": 3.5931, "step": 882688 }, { "epoch": 0.01, "learning_rate": 3.554041535335959e-05, "loss": 3.6147, "step": 883200 }, { "epoch": 0.01, "learning_rate": 3.553202940584907e-05, "loss": 3.619, "step": 883712 }, { "epoch": 0.01, "learning_rate": 3.552365983714228e-05, "loss": 3.6088, "step": 884224 }, { "epoch": 0.01, "learning_rate": 3.551527388963176e-05, "loss": 3.6154, "step": 884736 }, { "epoch": 0.01, "learning_rate": 3.550688794212124e-05, "loss": 3.6122, "step": 885248 }, { "epoch": 0.02, "learning_rate": 3.549850199461072e-05, "loss": 3.6089, "step": 885760 }, { "epoch": 0.02, "learning_rate": 3.549013242590393e-05, "loss": 3.61, "step": 886272 }, { "epoch": 0.02, "learning_rate": 3.5481746478393416e-05, "loss": 3.6083, "step": 886784 }, { "epoch": 0.02, "learning_rate": 3.5473360530882896e-05, "loss": 3.6189, "step": 887296 }, { "epoch": 0.02, "learning_rate": 3.5464974583372376e-05, "loss": 3.624, "step": 887808 }, { "epoch": 0.02, "learning_rate": 3.5456605014665585e-05, "loss": 3.6265, "step": 888320 }, { "epoch": 0.02, "learning_rate": 3.5448219067155065e-05, "loss": 3.6015, "step": 888832 }, { "epoch": 0.02, "learning_rate": 3.5439833119644545e-05, "loss": 3.615, "step": 889344 }, { "epoch": 0.02, "learning_rate": 3.5431447172134025e-05, "loss": 3.6091, "step": 889856 }, { "epoch": 0.02, "learning_rate": 3.5423077603427234e-05, "loss": 3.6144, "step": 890368 }, { "epoch": 0.02, "learning_rate": 3.5414691655916714e-05, "loss": 3.6143, "step": 890880 }, { "epoch": 0.02, "learning_rate": 3.5406305708406194e-05, "loss": 3.6101, "step": 891392 }, { "epoch": 0.02, "learning_rate": 3.5397919760895674e-05, "loss": 3.6092, "step": 891904 }, { "epoch": 0.02, "learning_rate": 3.538955019218888e-05, "loss": 3.604, "step": 892416 }, { "epoch": 0.02, "learning_rate": 3.538116424467837e-05, "loss": 3.6093, "step": 892928 }, { "epoch": 0.02, "learning_rate": 3.537277829716785e-05, "loss": 3.6085, "step": 893440 }, { "epoch": 0.02, "learning_rate": 3.536439234965733e-05, "loss": 3.6029, "step": 893952 }, { "epoch": 0.02, "learning_rate": 3.535602278095054e-05, "loss": 3.614, "step": 894464 }, { "epoch": 0.02, "learning_rate": 3.534763683344002e-05, "loss": 3.6123, "step": 894976 }, { "epoch": 0.02, "learning_rate": 3.53392508859295e-05, "loss": 3.6056, "step": 895488 }, { "epoch": 0.02, "learning_rate": 3.533086493841897e-05, "loss": 3.6117, "step": 896000 }, { "epoch": 0.02, "learning_rate": 3.532249536971219e-05, "loss": 3.6088, "step": 896512 }, { "epoch": 0.02, "learning_rate": 3.531410942220167e-05, "loss": 3.6155, "step": 897024 }, { "epoch": 0.02, "learning_rate": 3.530572347469115e-05, "loss": 3.6131, "step": 897536 }, { "epoch": 0.02, "learning_rate": 3.529733752718062e-05, "loss": 3.6092, "step": 898048 }, { "epoch": 0.02, "learning_rate": 3.528896795847384e-05, "loss": 3.6238, "step": 898560 }, { "epoch": 0.02, "learning_rate": 3.528058201096332e-05, "loss": 3.6201, "step": 899072 }, { "epoch": 0.02, "learning_rate": 3.52721960634528e-05, "loss": 3.6082, "step": 899584 }, { "epoch": 0.02, "learning_rate": 3.5263810115942276e-05, "loss": 3.6182, "step": 900096 }, { "epoch": 0.02, "learning_rate": 3.525544054723549e-05, "loss": 3.6018, "step": 900608 }, { "epoch": 0.02, "learning_rate": 3.524705459972497e-05, "loss": 3.614, "step": 901120 }, { "epoch": 0.02, "learning_rate": 3.5238668652214445e-05, "loss": 3.6077, "step": 901632 }, { "epoch": 0.02, "learning_rate": 3.5230282704703925e-05, "loss": 3.5974, "step": 902144 }, { "epoch": 0.02, "learning_rate": 3.522191313599714e-05, "loss": 3.6185, "step": 902656 }, { "epoch": 0.02, "learning_rate": 3.521352718848662e-05, "loss": 3.6158, "step": 903168 }, { "epoch": 0.02, "learning_rate": 3.5205141240976094e-05, "loss": 3.6136, "step": 903680 }, { "epoch": 0.02, "learning_rate": 3.5196755293465574e-05, "loss": 3.6121, "step": 904192 }, { "epoch": 0.02, "learning_rate": 3.518838572475879e-05, "loss": 3.603, "step": 904704 }, { "epoch": 0.02, "learning_rate": 3.517999977724828e-05, "loss": 3.6015, "step": 905216 }, { "epoch": 0.02, "learning_rate": 3.517161382973775e-05, "loss": 3.6192, "step": 905728 }, { "epoch": 0.02, "learning_rate": 3.516322788222723e-05, "loss": 3.6127, "step": 906240 }, { "epoch": 0.02, "learning_rate": 3.5154858313520446e-05, "loss": 3.6227, "step": 906752 }, { "epoch": 0.02, "learning_rate": 3.514647236600992e-05, "loss": 3.5951, "step": 907264 }, { "epoch": 0.02, "learning_rate": 3.51380864184994e-05, "loss": 3.6153, "step": 907776 }, { "epoch": 0.02, "learning_rate": 3.512970047098888e-05, "loss": 3.6105, "step": 908288 }, { "epoch": 0.02, "learning_rate": 3.5121330902282095e-05, "loss": 3.6195, "step": 908800 }, { "epoch": 0.02, "learning_rate": 3.511294495477157e-05, "loss": 3.6067, "step": 909312 }, { "epoch": 0.02, "learning_rate": 3.510455900726105e-05, "loss": 3.606, "step": 909824 }, { "epoch": 0.02, "learning_rate": 3.509617305975053e-05, "loss": 3.6137, "step": 910336 }, { "epoch": 0.02, "learning_rate": 3.5087803491043744e-05, "loss": 3.6303, "step": 910848 }, { "epoch": 0.02, "learning_rate": 3.5079417543533224e-05, "loss": 3.609, "step": 911360 }, { "epoch": 0.02, "learning_rate": 3.5071031596022704e-05, "loss": 3.6152, "step": 911872 }, { "epoch": 0.02, "learning_rate": 3.5062645648512184e-05, "loss": 3.6027, "step": 912384 }, { "epoch": 0.02, "learning_rate": 3.505427607980539e-05, "loss": 3.6129, "step": 912896 }, { "epoch": 0.02, "learning_rate": 3.504589013229487e-05, "loss": 3.6063, "step": 913408 }, { "epoch": 0.02, "learning_rate": 3.503750418478435e-05, "loss": 3.6071, "step": 913920 }, { "epoch": 0.02, "learning_rate": 3.502911823727383e-05, "loss": 3.6103, "step": 914432 }, { "epoch": 0.02, "learning_rate": 3.502073228976331e-05, "loss": 3.6104, "step": 914944 }, { "epoch": 0.02, "learning_rate": 3.501236272105652e-05, "loss": 3.6147, "step": 915456 }, { "epoch": 0.03, "eval_loss": 3.8646228313446045, "eval_runtime": 304.3615, "eval_samples_per_second": 1253.743, "eval_steps_per_second": 39.18, "step": 915840 }, { "epoch": 1.0, "learning_rate": 3.5003976773546e-05, "loss": 3.6125, "step": 915968 }, { "epoch": 1.0, "learning_rate": 3.499559082603548e-05, "loss": 3.5903, "step": 916480 }, { "epoch": 1.0, "learning_rate": 3.498720487852497e-05, "loss": 3.6123, "step": 916992 }, { "epoch": 1.0, "learning_rate": 3.497883530981818e-05, "loss": 3.6105, "step": 917504 }, { "epoch": 1.0, "learning_rate": 3.497044936230766e-05, "loss": 3.618, "step": 918016 }, { "epoch": 1.0, "learning_rate": 3.496206341479714e-05, "loss": 3.6147, "step": 918528 }, { "epoch": 1.0, "learning_rate": 3.495367746728662e-05, "loss": 3.6046, "step": 919040 }, { "epoch": 1.0, "learning_rate": 3.4945307898579827e-05, "loss": 3.61, "step": 919552 }, { "epoch": 1.0, "learning_rate": 3.4936921951069306e-05, "loss": 3.6025, "step": 920064 }, { "epoch": 1.0, "learning_rate": 3.4928536003558786e-05, "loss": 3.609, "step": 920576 }, { "epoch": 1.0, "learning_rate": 3.4920150056048266e-05, "loss": 3.6119, "step": 921088 }, { "epoch": 1.0, "learning_rate": 3.4911780487341476e-05, "loss": 3.6081, "step": 921600 }, { "epoch": 1.0, "learning_rate": 3.490341091863469e-05, "loss": 3.6169, "step": 922112 }, { "epoch": 1.0, "learning_rate": 3.489502497112417e-05, "loss": 3.5938, "step": 922624 }, { "epoch": 1.0, "learning_rate": 3.488663902361365e-05, "loss": 3.5955, "step": 923136 }, { "epoch": 1.0, "learning_rate": 3.487825307610313e-05, "loss": 3.5922, "step": 923648 }, { "epoch": 1.0, "learning_rate": 3.486986712859261e-05, "loss": 3.6076, "step": 924160 }, { "epoch": 1.0, "learning_rate": 3.486148118108209e-05, "loss": 3.5998, "step": 924672 }, { "epoch": 1.0, "learning_rate": 3.485309523357157e-05, "loss": 3.6006, "step": 925184 }, { "epoch": 1.0, "learning_rate": 3.484470928606105e-05, "loss": 3.6113, "step": 925696 }, { "epoch": 1.0, "learning_rate": 3.483632333855053e-05, "loss": 3.6221, "step": 926208 }, { "epoch": 1.0, "learning_rate": 3.482795376984374e-05, "loss": 3.6115, "step": 926720 }, { "epoch": 1.0, "learning_rate": 3.481956782233322e-05, "loss": 3.6064, "step": 927232 }, { "epoch": 1.0, "learning_rate": 3.48111818748227e-05, "loss": 3.608, "step": 927744 }, { "epoch": 1.0, "learning_rate": 3.480279592731218e-05, "loss": 3.6139, "step": 928256 }, { "epoch": 1.0, "learning_rate": 3.479442635860539e-05, "loss": 3.6018, "step": 928768 }, { "epoch": 1.0, "learning_rate": 3.478604041109487e-05, "loss": 3.6025, "step": 929280 }, { "epoch": 1.0, "learning_rate": 3.4777654463584356e-05, "loss": 3.6133, "step": 929792 }, { "epoch": 1.0, "learning_rate": 3.4769268516073836e-05, "loss": 3.5902, "step": 930304 }, { "epoch": 1.0, "learning_rate": 3.4760898947367045e-05, "loss": 3.5969, "step": 930816 }, { "epoch": 1.01, "learning_rate": 3.4752512999856525e-05, "loss": 3.6044, "step": 931328 }, { "epoch": 1.01, "learning_rate": 3.4744127052346005e-05, "loss": 3.6048, "step": 931840 }, { "epoch": 1.01, "learning_rate": 3.4735741104835485e-05, "loss": 3.612, "step": 932352 }, { "epoch": 1.01, "learning_rate": 3.4727371536128694e-05, "loss": 3.6086, "step": 932864 }, { "epoch": 1.01, "learning_rate": 3.4718985588618174e-05, "loss": 3.6022, "step": 933376 }, { "epoch": 1.01, "learning_rate": 3.4710599641107654e-05, "loss": 3.6005, "step": 933888 }, { "epoch": 1.01, "learning_rate": 3.4702213693597134e-05, "loss": 3.6034, "step": 934400 }, { "epoch": 1.01, "learning_rate": 3.469384412489034e-05, "loss": 3.5922, "step": 934912 }, { "epoch": 1.01, "learning_rate": 3.468545817737982e-05, "loss": 3.6047, "step": 935424 }, { "epoch": 1.01, "learning_rate": 3.467707222986931e-05, "loss": 3.5955, "step": 935936 }, { "epoch": 1.01, "learning_rate": 3.466868628235879e-05, "loss": 3.597, "step": 936448 }, { "epoch": 1.01, "learning_rate": 3.466030033484827e-05, "loss": 3.6035, "step": 936960 }, { "epoch": 1.01, "learning_rate": 3.465193076614148e-05, "loss": 3.6154, "step": 937472 }, { "epoch": 1.01, "learning_rate": 3.464354481863096e-05, "loss": 3.5973, "step": 937984 }, { "epoch": 1.01, "learning_rate": 3.463515887112044e-05, "loss": 3.6029, "step": 938496 }, { "epoch": 1.01, "learning_rate": 3.462677292360992e-05, "loss": 3.6044, "step": 939008 }, { "epoch": 1.01, "learning_rate": 3.461840335490313e-05, "loss": 3.595, "step": 939520 }, { "epoch": 1.01, "learning_rate": 3.461001740739261e-05, "loss": 3.6032, "step": 940032 }, { "epoch": 1.01, "learning_rate": 3.460163145988209e-05, "loss": 3.5874, "step": 940544 }, { "epoch": 1.01, "learning_rate": 3.459324551237157e-05, "loss": 3.6009, "step": 941056 }, { "epoch": 1.01, "learning_rate": 3.4584875943664776e-05, "loss": 3.5986, "step": 941568 }, { "epoch": 1.01, "learning_rate": 3.457648999615426e-05, "loss": 3.6034, "step": 942080 }, { "epoch": 1.01, "learning_rate": 3.456810404864374e-05, "loss": 3.5966, "step": 942592 }, { "epoch": 1.01, "learning_rate": 3.455971810113322e-05, "loss": 3.5867, "step": 943104 }, { "epoch": 1.01, "learning_rate": 3.455134853242643e-05, "loss": 3.5845, "step": 943616 }, { "epoch": 1.01, "learning_rate": 3.454296258491591e-05, "loss": 3.585, "step": 944128 }, { "epoch": 1.01, "learning_rate": 3.453457663740539e-05, "loss": 3.6161, "step": 944640 }, { "epoch": 1.01, "learning_rate": 3.452619068989487e-05, "loss": 3.5906, "step": 945152 }, { "epoch": 1.01, "learning_rate": 3.451782112118808e-05, "loss": 3.6098, "step": 945664 }, { "epoch": 1.01, "learning_rate": 3.450943517367756e-05, "loss": 3.6005, "step": 946176 }, { "epoch": 1.01, "learning_rate": 3.450104922616704e-05, "loss": 3.5831, "step": 946688 }, { "epoch": 1.01, "learning_rate": 3.449266327865652e-05, "loss": 3.5979, "step": 947200 }, { "epoch": 1.01, "learning_rate": 3.448429370994973e-05, "loss": 3.5881, "step": 947712 }, { "epoch": 1.01, "learning_rate": 3.447590776243922e-05, "loss": 3.5869, "step": 948224 }, { "epoch": 1.01, "learning_rate": 3.44675218149287e-05, "loss": 3.5966, "step": 948736 }, { "epoch": 1.01, "learning_rate": 3.445913586741818e-05, "loss": 3.6002, "step": 949248 }, { "epoch": 1.01, "learning_rate": 3.4450766298711386e-05, "loss": 3.5926, "step": 949760 }, { "epoch": 1.01, "learning_rate": 3.4442380351200866e-05, "loss": 3.5971, "step": 950272 }, { "epoch": 1.01, "learning_rate": 3.4433994403690346e-05, "loss": 3.5792, "step": 950784 }, { "epoch": 1.01, "learning_rate": 3.4425608456179826e-05, "loss": 3.5911, "step": 951296 }, { "epoch": 1.01, "learning_rate": 3.4417238887473035e-05, "loss": 3.5972, "step": 951808 }, { "epoch": 1.01, "learning_rate": 3.4408852939962515e-05, "loss": 3.6034, "step": 952320 }, { "epoch": 1.01, "learning_rate": 3.4400466992451995e-05, "loss": 3.6028, "step": 952832 }, { "epoch": 1.01, "learning_rate": 3.439208104494147e-05, "loss": 3.5972, "step": 953344 }, { "epoch": 1.01, "learning_rate": 3.4383711476234684e-05, "loss": 3.6025, "step": 953856 }, { "epoch": 1.01, "learning_rate": 3.437532552872417e-05, "loss": 3.5934, "step": 954368 }, { "epoch": 1.01, "learning_rate": 3.436693958121365e-05, "loss": 3.6047, "step": 954880 }, { "epoch": 1.01, "learning_rate": 3.4358553633703124e-05, "loss": 3.5883, "step": 955392 }, { "epoch": 1.01, "learning_rate": 3.435018406499634e-05, "loss": 3.5944, "step": 955904 }, { "epoch": 1.01, "learning_rate": 3.434179811748582e-05, "loss": 3.594, "step": 956416 }, { "epoch": 1.01, "learning_rate": 3.433341216997529e-05, "loss": 3.6026, "step": 956928 }, { "epoch": 1.01, "learning_rate": 3.432502622246477e-05, "loss": 3.6013, "step": 957440 }, { "epoch": 1.01, "learning_rate": 3.431665665375799e-05, "loss": 3.6031, "step": 957952 }, { "epoch": 1.01, "learning_rate": 3.430827070624747e-05, "loss": 3.5864, "step": 958464 }, { "epoch": 1.01, "learning_rate": 3.429988475873694e-05, "loss": 3.5743, "step": 958976 }, { "epoch": 1.01, "learning_rate": 3.429149881122642e-05, "loss": 3.5979, "step": 959488 }, { "epoch": 1.01, "learning_rate": 3.428312924251964e-05, "loss": 3.5992, "step": 960000 }, { "epoch": 1.01, "learning_rate": 3.4274743295009124e-05, "loss": 3.591, "step": 960512 }, { "epoch": 1.01, "learning_rate": 3.42663573474986e-05, "loss": 3.5987, "step": 961024 }, { "epoch": 1.01, "learning_rate": 3.425797139998808e-05, "loss": 3.5952, "step": 961536 }, { "epoch": 1.02, "learning_rate": 3.424960183128129e-05, "loss": 3.5883, "step": 962048 }, { "epoch": 1.02, "learning_rate": 3.4241215883770766e-05, "loss": 3.5934, "step": 962560 }, { "epoch": 1.02, "learning_rate": 3.4232829936260246e-05, "loss": 3.591, "step": 963072 }, { "epoch": 1.02, "learning_rate": 3.4224443988749726e-05, "loss": 3.5996, "step": 963584 }, { "epoch": 1.02, "learning_rate": 3.421607442004294e-05, "loss": 3.6066, "step": 964096 }, { "epoch": 1.02, "learning_rate": 3.4207688472532415e-05, "loss": 3.6089, "step": 964608 }, { "epoch": 1.02, "learning_rate": 3.4199302525021895e-05, "loss": 3.5842, "step": 965120 }, { "epoch": 1.02, "learning_rate": 3.4190916577511375e-05, "loss": 3.5951, "step": 965632 }, { "epoch": 1.02, "learning_rate": 3.418253063000086e-05, "loss": 3.5948, "step": 966144 }, { "epoch": 1.02, "learning_rate": 3.417416106129407e-05, "loss": 3.5951, "step": 966656 }, { "epoch": 1.02, "learning_rate": 3.416577511378355e-05, "loss": 3.5989, "step": 967168 }, { "epoch": 1.02, "learning_rate": 3.415738916627303e-05, "loss": 3.5928, "step": 967680 }, { "epoch": 1.02, "learning_rate": 3.414900321876251e-05, "loss": 3.5893, "step": 968192 }, { "epoch": 1.02, "learning_rate": 3.414063365005572e-05, "loss": 3.5884, "step": 968704 }, { "epoch": 1.02, "learning_rate": 3.41322477025452e-05, "loss": 3.5928, "step": 969216 }, { "epoch": 1.02, "learning_rate": 3.412386175503468e-05, "loss": 3.5898, "step": 969728 }, { "epoch": 1.02, "learning_rate": 3.411547580752416e-05, "loss": 3.5848, "step": 970240 }, { "epoch": 1.02, "learning_rate": 3.410710623881737e-05, "loss": 3.5976, "step": 970752 }, { "epoch": 1.02, "learning_rate": 3.409872029130685e-05, "loss": 3.5936, "step": 971264 }, { "epoch": 1.02, "learning_rate": 3.409033434379633e-05, "loss": 3.5876, "step": 971776 }, { "epoch": 1.02, "learning_rate": 3.408194839628581e-05, "loss": 3.5965, "step": 972288 }, { "epoch": 1.02, "learning_rate": 3.4073578827579025e-05, "loss": 3.5862, "step": 972800 }, { "epoch": 1.02, "learning_rate": 3.4065192880068505e-05, "loss": 3.5992, "step": 973312 }, { "epoch": 1.02, "learning_rate": 3.4056806932557985e-05, "loss": 3.5956, "step": 973824 }, { "epoch": 1.02, "learning_rate": 3.4048420985047465e-05, "loss": 3.5937, "step": 974336 }, { "epoch": 1.02, "learning_rate": 3.4040051416340674e-05, "loss": 3.6, "step": 974848 }, { "epoch": 1.02, "learning_rate": 3.4031665468830154e-05, "loss": 3.6047, "step": 975360 }, { "epoch": 1.02, "learning_rate": 3.4023279521319634e-05, "loss": 3.5908, "step": 975872 }, { "epoch": 1.02, "learning_rate": 3.4014893573809113e-05, "loss": 3.6003, "step": 976384 }, { "epoch": 1.02, "learning_rate": 3.400652400510232e-05, "loss": 3.5854, "step": 976896 }, { "epoch": 1.02, "learning_rate": 3.39981380575918e-05, "loss": 3.5958, "step": 977408 }, { "epoch": 1.02, "learning_rate": 3.398975211008128e-05, "loss": 3.591, "step": 977920 }, { "epoch": 1.02, "learning_rate": 3.398136616257076e-05, "loss": 3.5781, "step": 978432 }, { "epoch": 1.02, "learning_rate": 3.397299659386398e-05, "loss": 3.5952, "step": 978944 }, { "epoch": 1.02, "learning_rate": 3.396461064635346e-05, "loss": 3.6009, "step": 979456 }, { "epoch": 1.02, "learning_rate": 3.395622469884294e-05, "loss": 3.5978, "step": 979968 }, { "epoch": 1.02, "learning_rate": 3.394783875133242e-05, "loss": 3.5926, "step": 980480 }, { "epoch": 1.02, "learning_rate": 3.393946918262563e-05, "loss": 3.5837, "step": 980992 }, { "epoch": 1.02, "learning_rate": 3.393108323511511e-05, "loss": 3.5848, "step": 981504 }, { "epoch": 1.02, "learning_rate": 3.392269728760459e-05, "loss": 3.6017, "step": 982016 }, { "epoch": 1.02, "learning_rate": 3.391431134009407e-05, "loss": 3.5942, "step": 982528 }, { "epoch": 1.02, "learning_rate": 3.3905941771387276e-05, "loss": 3.6042, "step": 983040 }, { "epoch": 1.02, "learning_rate": 3.3897555823876756e-05, "loss": 3.5748, "step": 983552 }, { "epoch": 1.02, "learning_rate": 3.3889169876366236e-05, "loss": 3.598, "step": 984064 }, { "epoch": 1.02, "learning_rate": 3.3880783928855716e-05, "loss": 3.5937, "step": 984576 }, { "epoch": 1.02, "learning_rate": 3.387241436014893e-05, "loss": 3.5988, "step": 985088 }, { "epoch": 1.02, "learning_rate": 3.386402841263841e-05, "loss": 3.5879, "step": 985600 }, { "epoch": 1.02, "learning_rate": 3.385564246512789e-05, "loss": 3.5895, "step": 986112 }, { "epoch": 1.02, "learning_rate": 3.384725651761737e-05, "loss": 3.5928, "step": 986624 }, { "epoch": 1.02, "learning_rate": 3.383888694891058e-05, "loss": 3.6124, "step": 987136 }, { "epoch": 1.02, "learning_rate": 3.383050100140006e-05, "loss": 3.5915, "step": 987648 }, { "epoch": 1.02, "learning_rate": 3.382211505388954e-05, "loss": 3.5971, "step": 988160 }, { "epoch": 1.02, "learning_rate": 3.381372910637902e-05, "loss": 3.5883, "step": 988672 }, { "epoch": 1.02, "learning_rate": 3.380535953767223e-05, "loss": 3.5961, "step": 989184 }, { "epoch": 1.02, "learning_rate": 3.379697359016171e-05, "loss": 3.586, "step": 989696 }, { "epoch": 1.02, "learning_rate": 3.378858764265119e-05, "loss": 3.5947, "step": 990208 }, { "epoch": 1.02, "learning_rate": 3.378020169514067e-05, "loss": 3.5885, "step": 990720 }, { "epoch": 1.02, "learning_rate": 3.3771832126433886e-05, "loss": 3.5927, "step": 991232 }, { "epoch": 1.02, "learning_rate": 3.3763446178923366e-05, "loss": 3.5968, "step": 991744 }, { "epoch": 1.03, "eval_loss": 3.8638370037078857, "eval_runtime": 305.1306, "eval_samples_per_second": 1250.582, "eval_steps_per_second": 39.082, "step": 992160 }, { "epoch": 0.0, "learning_rate": 3.3755060231412846e-05, "loss": 3.5984, "step": 992256 }, { "epoch": 0.0, "learning_rate": 3.3746674283902326e-05, "loss": 3.5747, "step": 992768 }, { "epoch": 0.0, "learning_rate": 3.3738288336391805e-05, "loss": 3.5921, "step": 993280 }, { "epoch": 0.0, "learning_rate": 3.3729902388881285e-05, "loss": 3.5983, "step": 993792 }, { "epoch": 0.0, "learning_rate": 3.3721532820174495e-05, "loss": 3.5961, "step": 994304 }, { "epoch": 0.0, "learning_rate": 3.3713146872663974e-05, "loss": 3.5977, "step": 994816 }, { "epoch": 0.0, "learning_rate": 3.3704760925153454e-05, "loss": 3.5854, "step": 995328 }, { "epoch": 0.0, "learning_rate": 3.3696374977642934e-05, "loss": 3.5964, "step": 995840 }, { "epoch": 0.0, "learning_rate": 3.3688005408936143e-05, "loss": 3.5853, "step": 996352 }, { "epoch": 0.0, "learning_rate": 3.3679619461425623e-05, "loss": 3.5885, "step": 996864 }, { "epoch": 0.0, "learning_rate": 3.367123351391511e-05, "loss": 3.5902, "step": 997376 }, { "epoch": 0.0, "learning_rate": 3.366284756640459e-05, "loss": 3.5924, "step": 997888 }, { "epoch": 0.0, "learning_rate": 3.365449437650153e-05, "loss": 3.6027, "step": 998400 }, { "epoch": 0.0, "learning_rate": 3.364610842899101e-05, "loss": 3.5753, "step": 998912 }, { "epoch": 0.0, "learning_rate": 3.363772248148049e-05, "loss": 3.5759, "step": 999424 }, { "epoch": 0.0, "learning_rate": 3.362933653396997e-05, "loss": 3.5812, "step": 999936 }, { "epoch": 0.0, "learning_rate": 3.362095058645945e-05, "loss": 3.5896, "step": 1000448 }, { "epoch": 0.0, "learning_rate": 3.361256463894893e-05, "loss": 3.5809, "step": 1000960 }, { "epoch": 0.0, "learning_rate": 3.360417869143841e-05, "loss": 3.5835, "step": 1001472 }, { "epoch": 0.0, "learning_rate": 3.359579274392789e-05, "loss": 3.5949, "step": 1001984 }, { "epoch": 0.0, "learning_rate": 3.358740679641737e-05, "loss": 3.5983, "step": 1002496 }, { "epoch": 0.0, "learning_rate": 3.357903722771058e-05, "loss": 3.5979, "step": 1003008 }, { "epoch": 0.0, "learning_rate": 3.3570651280200064e-05, "loss": 3.5868, "step": 1003520 }, { "epoch": 0.0, "learning_rate": 3.3562265332689544e-05, "loss": 3.5895, "step": 1004032 }, { "epoch": 0.0, "learning_rate": 3.3553879385179024e-05, "loss": 3.5949, "step": 1004544 }, { "epoch": 0.0, "learning_rate": 3.354550981647223e-05, "loss": 3.5832, "step": 1005056 }, { "epoch": 0.0, "learning_rate": 3.353712386896171e-05, "loss": 3.5824, "step": 1005568 }, { "epoch": 0.0, "learning_rate": 3.352873792145119e-05, "loss": 3.5998, "step": 1006080 }, { "epoch": 0.0, "learning_rate": 3.352035197394067e-05, "loss": 3.5718, "step": 1006592 }, { "epoch": 0.0, "learning_rate": 3.351198240523388e-05, "loss": 3.5809, "step": 1007104 }, { "epoch": 0.01, "learning_rate": 3.350359645772336e-05, "loss": 3.5839, "step": 1007616 }, { "epoch": 0.01, "learning_rate": 3.349521051021284e-05, "loss": 3.5915, "step": 1008128 }, { "epoch": 0.01, "learning_rate": 3.3486824562702315e-05, "loss": 3.5936, "step": 1008640 }, { "epoch": 0.01, "learning_rate": 3.347845499399553e-05, "loss": 3.5902, "step": 1009152 }, { "epoch": 0.01, "learning_rate": 3.347006904648502e-05, "loss": 3.5882, "step": 1009664 }, { "epoch": 0.01, "learning_rate": 3.34616830989745e-05, "loss": 3.5843, "step": 1010176 }, { "epoch": 0.01, "learning_rate": 3.345329715146397e-05, "loss": 3.5843, "step": 1010688 }, { "epoch": 0.01, "learning_rate": 3.3444927582757187e-05, "loss": 3.5713, "step": 1011200 }, { "epoch": 0.01, "learning_rate": 3.3436541635246666e-05, "loss": 3.5912, "step": 1011712 }, { "epoch": 0.01, "learning_rate": 3.3428155687736146e-05, "loss": 3.5771, "step": 1012224 }, { "epoch": 0.01, "learning_rate": 3.341976974022562e-05, "loss": 3.5816, "step": 1012736 }, { "epoch": 0.01, "learning_rate": 3.34113837927151e-05, "loss": 3.5831, "step": 1013248 }, { "epoch": 0.01, "learning_rate": 3.3403014224008315e-05, "loss": 3.5973, "step": 1013760 }, { "epoch": 0.01, "learning_rate": 3.339462827649779e-05, "loss": 3.584, "step": 1014272 }, { "epoch": 0.01, "learning_rate": 3.338624232898727e-05, "loss": 3.5828, "step": 1014784 }, { "epoch": 0.01, "learning_rate": 3.3377856381476755e-05, "loss": 3.5857, "step": 1015296 }, { "epoch": 0.01, "learning_rate": 3.3369486812769964e-05, "loss": 3.5792, "step": 1015808 }, { "epoch": 0.01, "learning_rate": 3.3361100865259444e-05, "loss": 3.5812, "step": 1016320 }, { "epoch": 0.01, "learning_rate": 3.3352714917748924e-05, "loss": 3.572, "step": 1016832 }, { "epoch": 0.01, "learning_rate": 3.3344328970238404e-05, "loss": 3.5822, "step": 1017344 }, { "epoch": 0.01, "learning_rate": 3.333595940153162e-05, "loss": 3.5849, "step": 1017856 }, { "epoch": 0.01, "learning_rate": 3.332757345402109e-05, "loss": 3.5828, "step": 1018368 }, { "epoch": 0.01, "learning_rate": 3.331918750651057e-05, "loss": 3.5801, "step": 1018880 }, { "epoch": 0.01, "learning_rate": 3.331080155900005e-05, "loss": 3.5671, "step": 1019392 }, { "epoch": 0.01, "learning_rate": 3.330243199029326e-05, "loss": 3.5746, "step": 1019904 }, { "epoch": 0.01, "learning_rate": 3.329404604278274e-05, "loss": 3.5667, "step": 1020416 }, { "epoch": 0.01, "learning_rate": 3.328566009527222e-05, "loss": 3.6013, "step": 1020928 }, { "epoch": 0.01, "learning_rate": 3.327727414776171e-05, "loss": 3.5727, "step": 1021440 }, { "epoch": 0.01, "learning_rate": 3.326890457905492e-05, "loss": 3.5958, "step": 1021952 }, { "epoch": 0.01, "learning_rate": 3.32605186315444e-05, "loss": 3.5791, "step": 1022464 }, { "epoch": 0.01, "learning_rate": 3.325213268403388e-05, "loss": 3.5678, "step": 1022976 }, { "epoch": 0.01, "learning_rate": 3.324374673652336e-05, "loss": 3.5767, "step": 1023488 }, { "epoch": 0.01, "learning_rate": 3.323537716781657e-05, "loss": 3.5723, "step": 1024000 }, { "epoch": 0.01, "learning_rate": 3.322699122030605e-05, "loss": 3.5736, "step": 1024512 }, { "epoch": 0.01, "learning_rate": 3.321860527279553e-05, "loss": 3.574, "step": 1025024 }, { "epoch": 0.01, "learning_rate": 3.321021932528501e-05, "loss": 3.5865, "step": 1025536 }, { "epoch": 0.01, "learning_rate": 3.3201849756578216e-05, "loss": 3.5784, "step": 1026048 }, { "epoch": 0.01, "learning_rate": 3.3193463809067696e-05, "loss": 3.5761, "step": 1026560 }, { "epoch": 0.01, "learning_rate": 3.3185077861557176e-05, "loss": 3.5659, "step": 1027072 }, { "epoch": 0.01, "learning_rate": 3.3176691914046656e-05, "loss": 3.5741, "step": 1027584 }, { "epoch": 0.01, "learning_rate": 3.316832234533987e-05, "loss": 3.5753, "step": 1028096 }, { "epoch": 0.01, "learning_rate": 3.315993639782935e-05, "loss": 3.5871, "step": 1028608 }, { "epoch": 0.01, "learning_rate": 3.315155045031883e-05, "loss": 3.5859, "step": 1029120 }, { "epoch": 0.01, "learning_rate": 3.314316450280831e-05, "loss": 3.5836, "step": 1029632 }, { "epoch": 0.01, "learning_rate": 3.313479493410152e-05, "loss": 3.5835, "step": 1030144 }, { "epoch": 0.01, "learning_rate": 3.3126408986591e-05, "loss": 3.5781, "step": 1030656 }, { "epoch": 0.01, "learning_rate": 3.311802303908048e-05, "loss": 3.5848, "step": 1031168 }, { "epoch": 0.01, "learning_rate": 3.310963709156996e-05, "loss": 3.5722, "step": 1031680 }, { "epoch": 0.01, "learning_rate": 3.310126752286317e-05, "loss": 3.5802, "step": 1032192 }, { "epoch": 0.01, "learning_rate": 3.309288157535265e-05, "loss": 3.5758, "step": 1032704 }, { "epoch": 0.01, "learning_rate": 3.308449562784213e-05, "loss": 3.5834, "step": 1033216 }, { "epoch": 0.01, "learning_rate": 3.307610968033161e-05, "loss": 3.5876, "step": 1033728 }, { "epoch": 0.01, "learning_rate": 3.3067740111624825e-05, "loss": 3.5862, "step": 1034240 }, { "epoch": 0.01, "learning_rate": 3.3059354164114305e-05, "loss": 3.5715, "step": 1034752 }, { "epoch": 0.01, "learning_rate": 3.3050968216603785e-05, "loss": 3.5526, "step": 1035264 }, { "epoch": 0.01, "learning_rate": 3.3042582269093265e-05, "loss": 3.5828, "step": 1035776 }, { "epoch": 0.01, "learning_rate": 3.3034212700386474e-05, "loss": 3.5815, "step": 1036288 }, { "epoch": 0.01, "learning_rate": 3.3025826752875954e-05, "loss": 3.5769, "step": 1036800 }, { "epoch": 0.01, "learning_rate": 3.3017440805365434e-05, "loss": 3.5749, "step": 1037312 }, { "epoch": 0.01, "learning_rate": 3.3009054857854914e-05, "loss": 3.5822, "step": 1037824 }, { "epoch": 0.02, "learning_rate": 3.300068528914812e-05, "loss": 3.5695, "step": 1038336 }, { "epoch": 0.02, "learning_rate": 3.29922993416376e-05, "loss": 3.5764, "step": 1038848 }, { "epoch": 0.02, "learning_rate": 3.298391339412708e-05, "loss": 3.5733, "step": 1039360 }, { "epoch": 0.02, "learning_rate": 3.297552744661656e-05, "loss": 3.58, "step": 1039872 }, { "epoch": 0.02, "learning_rate": 3.296715787790978e-05, "loss": 3.5901, "step": 1040384 }, { "epoch": 0.02, "learning_rate": 3.295877193039926e-05, "loss": 3.5913, "step": 1040896 }, { "epoch": 0.02, "learning_rate": 3.295038598288874e-05, "loss": 3.5723, "step": 1041408 }, { "epoch": 0.02, "learning_rate": 3.294200003537822e-05, "loss": 3.5748, "step": 1041920 }, { "epoch": 0.02, "learning_rate": 3.293363046667143e-05, "loss": 3.5785, "step": 1042432 }, { "epoch": 0.02, "learning_rate": 3.292524451916091e-05, "loss": 3.5795, "step": 1042944 }, { "epoch": 0.02, "learning_rate": 3.291685857165039e-05, "loss": 3.5782, "step": 1043456 }, { "epoch": 0.02, "learning_rate": 3.290847262413987e-05, "loss": 3.5784, "step": 1043968 }, { "epoch": 0.02, "learning_rate": 3.290010305543308e-05, "loss": 3.5737, "step": 1044480 }, { "epoch": 0.02, "learning_rate": 3.289171710792256e-05, "loss": 3.5708, "step": 1044992 }, { "epoch": 0.02, "learning_rate": 3.288333116041204e-05, "loss": 3.5794, "step": 1045504 }, { "epoch": 0.02, "learning_rate": 3.287494521290152e-05, "loss": 3.5668, "step": 1046016 }, { "epoch": 0.02, "learning_rate": 3.286657564419473e-05, "loss": 3.571, "step": 1046528 }, { "epoch": 0.02, "learning_rate": 3.285818969668421e-05, "loss": 3.5787, "step": 1047040 }, { "epoch": 0.02, "learning_rate": 3.284980374917369e-05, "loss": 3.5731, "step": 1047552 }, { "epoch": 0.02, "learning_rate": 3.284141780166317e-05, "loss": 3.5746, "step": 1048064 }, { "epoch": 0.02, "learning_rate": 3.283304823295638e-05, "loss": 3.5841, "step": 1048576 }, { "epoch": 0.02, "learning_rate": 3.282466228544586e-05, "loss": 3.5683, "step": 1049088 }, { "epoch": 0.02, "learning_rate": 3.281627633793534e-05, "loss": 3.5807, "step": 1049600 }, { "epoch": 0.02, "learning_rate": 3.280789039042482e-05, "loss": 3.5784, "step": 1050112 }, { "epoch": 0.02, "learning_rate": 3.279952082171803e-05, "loss": 3.5759, "step": 1050624 }, { "epoch": 0.02, "learning_rate": 3.279113487420751e-05, "loss": 3.5819, "step": 1051136 }, { "epoch": 0.02, "learning_rate": 3.278274892669699e-05, "loss": 3.5884, "step": 1051648 }, { "epoch": 0.02, "learning_rate": 3.277436297918647e-05, "loss": 3.5763, "step": 1052160 }, { "epoch": 0.02, "learning_rate": 3.2765993410479686e-05, "loss": 3.5833, "step": 1052672 }, { "epoch": 0.02, "learning_rate": 3.2757607462969166e-05, "loss": 3.5689, "step": 1053184 }, { "epoch": 0.02, "learning_rate": 3.2749221515458646e-05, "loss": 3.5784, "step": 1053696 }, { "epoch": 0.02, "learning_rate": 3.2740835567948126e-05, "loss": 3.5736, "step": 1054208 }, { "epoch": 0.02, "learning_rate": 3.2732465999241335e-05, "loss": 3.567, "step": 1054720 }, { "epoch": 0.02, "learning_rate": 3.2724080051730815e-05, "loss": 3.5741, "step": 1055232 }, { "epoch": 0.02, "learning_rate": 3.2715694104220295e-05, "loss": 3.5856, "step": 1055744 }, { "epoch": 0.02, "learning_rate": 3.2707308156709775e-05, "loss": 3.5796, "step": 1056256 }, { "epoch": 0.02, "learning_rate": 3.2698938588002984e-05, "loss": 3.577, "step": 1056768 }, { "epoch": 0.02, "learning_rate": 3.2690552640492464e-05, "loss": 3.5674, "step": 1057280 }, { "epoch": 0.02, "learning_rate": 3.2682166692981944e-05, "loss": 3.5705, "step": 1057792 }, { "epoch": 0.02, "learning_rate": 3.2673780745471424e-05, "loss": 3.581, "step": 1058304 }, { "epoch": 0.02, "learning_rate": 3.266541117676464e-05, "loss": 3.5773, "step": 1058816 }, { "epoch": 0.02, "learning_rate": 3.265702522925412e-05, "loss": 3.5908, "step": 1059328 }, { "epoch": 0.02, "learning_rate": 3.26486392817436e-05, "loss": 3.562, "step": 1059840 }, { "epoch": 0.02, "learning_rate": 3.264025333423308e-05, "loss": 3.5801, "step": 1060352 }, { "epoch": 0.02, "learning_rate": 3.263188376552629e-05, "loss": 3.5777, "step": 1060864 }, { "epoch": 0.02, "learning_rate": 3.262349781801577e-05, "loss": 3.5791, "step": 1061376 }, { "epoch": 0.02, "learning_rate": 3.261511187050525e-05, "loss": 3.5697, "step": 1061888 }, { "epoch": 0.02, "learning_rate": 3.260672592299473e-05, "loss": 3.5718, "step": 1062400 }, { "epoch": 0.02, "learning_rate": 3.259835635428794e-05, "loss": 3.581, "step": 1062912 }, { "epoch": 0.02, "learning_rate": 3.258997040677742e-05, "loss": 3.5921, "step": 1063424 }, { "epoch": 0.02, "learning_rate": 3.25815844592669e-05, "loss": 3.5759, "step": 1063936 }, { "epoch": 0.02, "learning_rate": 3.257319851175638e-05, "loss": 3.5784, "step": 1064448 }, { "epoch": 0.02, "learning_rate": 3.2564828943049594e-05, "loss": 3.57, "step": 1064960 }, { "epoch": 0.02, "learning_rate": 3.2556442995539074e-05, "loss": 3.5782, "step": 1065472 }, { "epoch": 0.02, "learning_rate": 3.2548057048028554e-05, "loss": 3.5704, "step": 1065984 }, { "epoch": 0.02, "learning_rate": 3.2539671100518034e-05, "loss": 3.5794, "step": 1066496 }, { "epoch": 0.02, "learning_rate": 3.253130153181124e-05, "loss": 3.5694, "step": 1067008 }, { "epoch": 0.02, "learning_rate": 3.252291558430072e-05, "loss": 3.5759, "step": 1067520 }, { "epoch": 0.02, "learning_rate": 3.25145296367902e-05, "loss": 3.579, "step": 1068032 }, { "epoch": 0.03, "eval_loss": 3.8645758628845215, "eval_runtime": 350.3398, "eval_samples_per_second": 1089.202, "eval_steps_per_second": 34.038, "step": 1068480 }, { "epoch": 1.0, "learning_rate": 3.250614368927968e-05, "loss": 3.5751, "step": 1068544 }, { "epoch": 1.0, "learning_rate": 3.249777412057289e-05, "loss": 3.563, "step": 1069056 }, { "epoch": 1.0, "learning_rate": 3.248938817306237e-05, "loss": 3.5729, "step": 1069568 }, { "epoch": 1.0, "learning_rate": 3.248100222555185e-05, "loss": 3.5814, "step": 1070080 }, { "epoch": 1.0, "learning_rate": 3.247261627804133e-05, "loss": 3.5772, "step": 1070592 }, { "epoch": 1.0, "learning_rate": 3.246424670933455e-05, "loss": 3.584, "step": 1071104 }, { "epoch": 1.0, "learning_rate": 3.245586076182403e-05, "loss": 3.5672, "step": 1071616 }, { "epoch": 1.0, "learning_rate": 3.244747481431351e-05, "loss": 3.5794, "step": 1072128 }, { "epoch": 1.0, "learning_rate": 3.243908886680299e-05, "loss": 3.5691, "step": 1072640 }, { "epoch": 1.0, "learning_rate": 3.2430719298096196e-05, "loss": 3.5743, "step": 1073152 }, { "epoch": 1.0, "learning_rate": 3.2422333350585676e-05, "loss": 3.573, "step": 1073664 }, { "epoch": 1.0, "learning_rate": 3.2413947403075156e-05, "loss": 3.5779, "step": 1074176 }, { "epoch": 1.0, "learning_rate": 3.2405577834368365e-05, "loss": 3.5879, "step": 1074688 }, { "epoch": 1.0, "learning_rate": 3.2397191886857845e-05, "loss": 3.5628, "step": 1075200 }, { "epoch": 1.0, "learning_rate": 3.2388805939347325e-05, "loss": 3.5549, "step": 1075712 }, { "epoch": 1.0, "learning_rate": 3.2380419991836805e-05, "loss": 3.565, "step": 1076224 }, { "epoch": 1.0, "learning_rate": 3.2372034044326285e-05, "loss": 3.57, "step": 1076736 }, { "epoch": 1.0, "learning_rate": 3.2363648096815765e-05, "loss": 3.5671, "step": 1077248 }, { "epoch": 1.0, "learning_rate": 3.2355262149305245e-05, "loss": 3.5658, "step": 1077760 }, { "epoch": 1.0, "learning_rate": 3.2346876201794725e-05, "loss": 3.5771, "step": 1078272 }, { "epoch": 1.0, "learning_rate": 3.2338490254284205e-05, "loss": 3.5867, "step": 1078784 }, { "epoch": 1.0, "learning_rate": 3.2330120685577414e-05, "loss": 3.5745, "step": 1079296 }, { "epoch": 1.0, "learning_rate": 3.2321734738066894e-05, "loss": 3.5748, "step": 1079808 }, { "epoch": 1.0, "learning_rate": 3.2313348790556374e-05, "loss": 3.5733, "step": 1080320 }, { "epoch": 1.0, "learning_rate": 3.2304962843045854e-05, "loss": 3.5803, "step": 1080832 }, { "epoch": 1.0, "learning_rate": 3.229659327433906e-05, "loss": 3.5646, "step": 1081344 }, { "epoch": 1.0, "learning_rate": 3.228820732682854e-05, "loss": 3.5715, "step": 1081856 }, { "epoch": 1.0, "learning_rate": 3.227982137931802e-05, "loss": 3.579, "step": 1082368 }, { "epoch": 1.0, "learning_rate": 3.22714354318075e-05, "loss": 3.5579, "step": 1082880 }, { "epoch": 1.0, "learning_rate": 3.226306586310072e-05, "loss": 3.5618, "step": 1083392 }, { "epoch": 1.01, "learning_rate": 3.22546799155902e-05, "loss": 3.5665, "step": 1083904 }, { "epoch": 1.01, "learning_rate": 3.224629396807968e-05, "loss": 3.5742, "step": 1084416 }, { "epoch": 1.01, "learning_rate": 3.223790802056916e-05, "loss": 3.581, "step": 1084928 }, { "epoch": 1.01, "learning_rate": 3.222953845186237e-05, "loss": 3.5683, "step": 1085440 }, { "epoch": 1.01, "learning_rate": 3.222115250435185e-05, "loss": 3.577, "step": 1085952 }, { "epoch": 1.01, "learning_rate": 3.221276655684133e-05, "loss": 3.5673, "step": 1086464 }, { "epoch": 1.01, "learning_rate": 3.220438060933081e-05, "loss": 3.5624, "step": 1086976 }, { "epoch": 1.01, "learning_rate": 3.219601104062402e-05, "loss": 3.5598, "step": 1087488 }, { "epoch": 1.01, "learning_rate": 3.21876250931135e-05, "loss": 3.5739, "step": 1088000 }, { "epoch": 1.01, "learning_rate": 3.217923914560298e-05, "loss": 3.5585, "step": 1088512 }, { "epoch": 1.01, "learning_rate": 3.217085319809246e-05, "loss": 3.5649, "step": 1089024 }, { "epoch": 1.01, "learning_rate": 3.216248362938567e-05, "loss": 3.5698, "step": 1089536 }, { "epoch": 1.01, "learning_rate": 3.215409768187515e-05, "loss": 3.5821, "step": 1090048 }, { "epoch": 1.01, "learning_rate": 3.214571173436463e-05, "loss": 3.5649, "step": 1090560 }, { "epoch": 1.01, "learning_rate": 3.213732578685411e-05, "loss": 3.5688, "step": 1091072 }, { "epoch": 1.01, "learning_rate": 3.212893983934359e-05, "loss": 3.5707, "step": 1091584 }, { "epoch": 1.01, "learning_rate": 3.21205702706368e-05, "loss": 3.5613, "step": 1092096 }, { "epoch": 1.01, "learning_rate": 3.211218432312628e-05, "loss": 3.5685, "step": 1092608 }, { "epoch": 1.01, "learning_rate": 3.210379837561576e-05, "loss": 3.5548, "step": 1093120 }, { "epoch": 1.01, "learning_rate": 3.209541242810524e-05, "loss": 3.5637, "step": 1093632 }, { "epoch": 1.01, "learning_rate": 3.208704285939845e-05, "loss": 3.572, "step": 1094144 }, { "epoch": 1.01, "learning_rate": 3.207865691188793e-05, "loss": 3.5644, "step": 1094656 }, { "epoch": 1.01, "learning_rate": 3.207027096437741e-05, "loss": 3.5632, "step": 1095168 }, { "epoch": 1.01, "learning_rate": 3.20618850168669e-05, "loss": 3.5477, "step": 1095680 }, { "epoch": 1.01, "learning_rate": 3.2053515448160106e-05, "loss": 3.5624, "step": 1096192 }, { "epoch": 1.01, "learning_rate": 3.2045129500649586e-05, "loss": 3.5461, "step": 1096704 }, { "epoch": 1.01, "learning_rate": 3.2036743553139066e-05, "loss": 3.5845, "step": 1097216 }, { "epoch": 1.01, "learning_rate": 3.2028357605628546e-05, "loss": 3.5576, "step": 1097728 }, { "epoch": 1.01, "learning_rate": 3.2019988036921755e-05, "loss": 3.5813, "step": 1098240 }, { "epoch": 1.01, "learning_rate": 3.2011602089411235e-05, "loss": 3.5627, "step": 1098752 }, { "epoch": 1.01, "learning_rate": 3.2003216141900715e-05, "loss": 3.5484, "step": 1099264 }, { "epoch": 1.01, "learning_rate": 3.1994830194390195e-05, "loss": 3.5621, "step": 1099776 }, { "epoch": 1.01, "learning_rate": 3.1986460625683404e-05, "loss": 3.5633, "step": 1100288 }, { "epoch": 1.01, "learning_rate": 3.1978074678172884e-05, "loss": 3.5559, "step": 1100800 }, { "epoch": 1.01, "learning_rate": 3.1969688730662364e-05, "loss": 3.5505, "step": 1101312 }, { "epoch": 1.01, "learning_rate": 3.196130278315185e-05, "loss": 3.5738, "step": 1101824 }, { "epoch": 1.01, "learning_rate": 3.195293321444506e-05, "loss": 3.5664, "step": 1102336 }, { "epoch": 1.01, "learning_rate": 3.194454726693454e-05, "loss": 3.554, "step": 1102848 }, { "epoch": 1.01, "learning_rate": 3.193616131942402e-05, "loss": 3.5508, "step": 1103360 }, { "epoch": 1.01, "learning_rate": 3.19277753719135e-05, "loss": 3.5576, "step": 1103872 }, { "epoch": 1.01, "learning_rate": 3.191940580320671e-05, "loss": 3.561, "step": 1104384 }, { "epoch": 1.01, "learning_rate": 3.191101985569619e-05, "loss": 3.5723, "step": 1104896 }, { "epoch": 1.01, "learning_rate": 3.190263390818567e-05, "loss": 3.5692, "step": 1105408 }, { "epoch": 1.01, "learning_rate": 3.189424796067515e-05, "loss": 3.5683, "step": 1105920 }, { "epoch": 1.01, "learning_rate": 3.188587839196836e-05, "loss": 3.567, "step": 1106432 }, { "epoch": 1.01, "learning_rate": 3.187749244445784e-05, "loss": 3.5633, "step": 1106944 }, { "epoch": 1.01, "learning_rate": 3.186910649694732e-05, "loss": 3.5694, "step": 1107456 }, { "epoch": 1.01, "learning_rate": 3.1860720549436804e-05, "loss": 3.5564, "step": 1107968 }, { "epoch": 1.01, "learning_rate": 3.1852350980730013e-05, "loss": 3.5659, "step": 1108480 }, { "epoch": 1.01, "learning_rate": 3.1843965033219493e-05, "loss": 3.5599, "step": 1108992 }, { "epoch": 1.01, "learning_rate": 3.183557908570897e-05, "loss": 3.5637, "step": 1109504 }, { "epoch": 1.01, "learning_rate": 3.182719313819845e-05, "loss": 3.5709, "step": 1110016 }, { "epoch": 1.01, "learning_rate": 3.181882356949166e-05, "loss": 3.5722, "step": 1110528 }, { "epoch": 1.01, "learning_rate": 3.181043762198114e-05, "loss": 3.5556, "step": 1111040 }, { "epoch": 1.01, "learning_rate": 3.180205167447062e-05, "loss": 3.5386, "step": 1111552 }, { "epoch": 1.01, "learning_rate": 3.17936657269601e-05, "loss": 3.5675, "step": 1112064 }, { "epoch": 1.01, "learning_rate": 3.178529615825331e-05, "loss": 3.5603, "step": 1112576 }, { "epoch": 1.01, "learning_rate": 3.177691021074279e-05, "loss": 3.5658, "step": 1113088 }, { "epoch": 1.01, "learning_rate": 3.176852426323227e-05, "loss": 3.5596, "step": 1113600 }, { "epoch": 1.01, "learning_rate": 3.176013831572176e-05, "loss": 3.5663, "step": 1114112 }, { "epoch": 1.02, "learning_rate": 3.175176874701497e-05, "loss": 3.5586, "step": 1114624 }, { "epoch": 1.02, "learning_rate": 3.174338279950445e-05, "loss": 3.556, "step": 1115136 }, { "epoch": 1.02, "learning_rate": 3.173499685199393e-05, "loss": 3.5582, "step": 1115648 }, { "epoch": 1.02, "learning_rate": 3.1726627283287136e-05, "loss": 3.5639, "step": 1116160 }, { "epoch": 1.02, "learning_rate": 3.1718241335776616e-05, "loss": 3.574, "step": 1116672 }, { "epoch": 1.02, "learning_rate": 3.1709855388266096e-05, "loss": 3.5741, "step": 1117184 }, { "epoch": 1.02, "learning_rate": 3.1701469440755576e-05, "loss": 3.5576, "step": 1117696 }, { "epoch": 1.02, "learning_rate": 3.1693099872048785e-05, "loss": 3.5612, "step": 1118208 }, { "epoch": 1.02, "learning_rate": 3.1684713924538265e-05, "loss": 3.5644, "step": 1118720 }, { "epoch": 1.02, "learning_rate": 3.1676327977027745e-05, "loss": 3.5648, "step": 1119232 }, { "epoch": 1.02, "learning_rate": 3.1667942029517225e-05, "loss": 3.5603, "step": 1119744 }, { "epoch": 1.02, "learning_rate": 3.165957246081044e-05, "loss": 3.5634, "step": 1120256 }, { "epoch": 1.02, "learning_rate": 3.165118651329992e-05, "loss": 3.5565, "step": 1120768 }, { "epoch": 1.02, "learning_rate": 3.16428005657894e-05, "loss": 3.5541, "step": 1121280 }, { "epoch": 1.02, "learning_rate": 3.163441461827888e-05, "loss": 3.5669, "step": 1121792 }, { "epoch": 1.02, "learning_rate": 3.162602867076836e-05, "loss": 3.5474, "step": 1122304 }, { "epoch": 1.02, "learning_rate": 3.161765910206157e-05, "loss": 3.5529, "step": 1122816 }, { "epoch": 1.02, "learning_rate": 3.160927315455105e-05, "loss": 3.5687, "step": 1123328 }, { "epoch": 1.02, "learning_rate": 3.160088720704053e-05, "loss": 3.5552, "step": 1123840 }, { "epoch": 1.02, "learning_rate": 3.159250125953001e-05, "loss": 3.557, "step": 1124352 }, { "epoch": 1.02, "learning_rate": 3.158413169082322e-05, "loss": 3.5706, "step": 1124864 }, { "epoch": 1.02, "learning_rate": 3.15757457433127e-05, "loss": 3.5511, "step": 1125376 }, { "epoch": 1.02, "learning_rate": 3.156735979580218e-05, "loss": 3.5657, "step": 1125888 }, { "epoch": 1.02, "learning_rate": 3.155897384829166e-05, "loss": 3.5652, "step": 1126400 }, { "epoch": 1.02, "learning_rate": 3.1550604279584874e-05, "loss": 3.5627, "step": 1126912 }, { "epoch": 1.02, "learning_rate": 3.1542218332074354e-05, "loss": 3.5679, "step": 1127424 }, { "epoch": 1.02, "learning_rate": 3.1533832384563834e-05, "loss": 3.5697, "step": 1127936 }, { "epoch": 1.02, "learning_rate": 3.1525446437053314e-05, "loss": 3.5629, "step": 1128448 }, { "epoch": 1.02, "learning_rate": 3.1517076868346523e-05, "loss": 3.5634, "step": 1128960 }, { "epoch": 1.02, "learning_rate": 3.1508690920836e-05, "loss": 3.5565, "step": 1129472 }, { "epoch": 1.02, "learning_rate": 3.150030497332548e-05, "loss": 3.5637, "step": 1129984 }, { "epoch": 1.02, "learning_rate": 3.149191902581496e-05, "loss": 3.5566, "step": 1130496 }, { "epoch": 1.02, "learning_rate": 3.148354945710817e-05, "loss": 3.5552, "step": 1131008 }, { "epoch": 1.02, "learning_rate": 3.147516350959765e-05, "loss": 3.5573, "step": 1131520 }, { "epoch": 1.02, "learning_rate": 3.146677756208713e-05, "loss": 3.5692, "step": 1132032 }, { "epoch": 1.02, "learning_rate": 3.145839161457661e-05, "loss": 3.5627, "step": 1132544 }, { "epoch": 1.02, "learning_rate": 3.145002204586983e-05, "loss": 3.5628, "step": 1133056 }, { "epoch": 1.02, "learning_rate": 3.144163609835931e-05, "loss": 3.5551, "step": 1133568 }, { "epoch": 1.02, "learning_rate": 3.143325015084879e-05, "loss": 3.5546, "step": 1134080 }, { "epoch": 1.02, "learning_rate": 3.142486420333826e-05, "loss": 3.5626, "step": 1134592 }, { "epoch": 1.02, "learning_rate": 3.141649463463148e-05, "loss": 3.5655, "step": 1135104 }, { "epoch": 1.02, "learning_rate": 3.140810868712096e-05, "loss": 3.5705, "step": 1135616 }, { "epoch": 1.02, "learning_rate": 3.139972273961044e-05, "loss": 3.5481, "step": 1136128 }, { "epoch": 1.02, "learning_rate": 3.139133679209991e-05, "loss": 3.5671, "step": 1136640 }, { "epoch": 1.02, "learning_rate": 3.1382967223393126e-05, "loss": 3.5627, "step": 1137152 }, { "epoch": 1.02, "learning_rate": 3.1374581275882606e-05, "loss": 3.5646, "step": 1137664 }, { "epoch": 1.02, "learning_rate": 3.1366195328372086e-05, "loss": 3.554, "step": 1138176 }, { "epoch": 1.02, "learning_rate": 3.1357809380861566e-05, "loss": 3.5591, "step": 1138688 }, { "epoch": 1.02, "learning_rate": 3.134943981215478e-05, "loss": 3.5653, "step": 1139200 }, { "epoch": 1.02, "learning_rate": 3.134105386464426e-05, "loss": 3.5739, "step": 1139712 }, { "epoch": 1.02, "learning_rate": 3.1332667917133735e-05, "loss": 3.5596, "step": 1140224 }, { "epoch": 1.02, "learning_rate": 3.1324281969623215e-05, "loss": 3.5598, "step": 1140736 }, { "epoch": 1.02, "learning_rate": 3.131591240091643e-05, "loss": 3.558, "step": 1141248 }, { "epoch": 1.02, "learning_rate": 3.130752645340591e-05, "loss": 3.5587, "step": 1141760 }, { "epoch": 1.02, "learning_rate": 3.1299140505895384e-05, "loss": 3.5542, "step": 1142272 }, { "epoch": 1.02, "learning_rate": 3.1290754558384864e-05, "loss": 3.5677, "step": 1142784 }, { "epoch": 1.02, "learning_rate": 3.128238498967808e-05, "loss": 3.5505, "step": 1143296 }, { "epoch": 1.02, "learning_rate": 3.127399904216756e-05, "loss": 3.5692, "step": 1143808 }, { "epoch": 1.02, "learning_rate": 3.126561309465704e-05, "loss": 3.5567, "step": 1144320 }, { "epoch": 1.03, "eval_loss": 3.8662688732147217, "eval_runtime": 351.4006, "eval_samples_per_second": 1085.915, "eval_steps_per_second": 33.936, "step": 1144800 }, { "epoch": 0.0, "learning_rate": 3.125722714714652e-05, "loss": 3.5353, "step": 1144832 }, { "epoch": 0.0, "learning_rate": 3.1248841199636e-05, "loss": 3.5489, "step": 1145344 }, { "epoch": 0.0, "learning_rate": 3.124045525212548e-05, "loss": 3.5552, "step": 1145856 }, { "epoch": 0.0, "learning_rate": 3.123206930461496e-05, "loss": 3.5659, "step": 1146368 }, { "epoch": 0.0, "learning_rate": 3.122369973590817e-05, "loss": 3.5635, "step": 1146880 }, { "epoch": 0.0, "learning_rate": 3.121531378839765e-05, "loss": 3.5693, "step": 1147392 }, { "epoch": 0.0, "learning_rate": 3.120692784088713e-05, "loss": 3.5522, "step": 1147904 }, { "epoch": 0.0, "learning_rate": 3.119854189337661e-05, "loss": 3.5645, "step": 1148416 }, { "epoch": 0.0, "learning_rate": 3.119017232466982e-05, "loss": 3.5504, "step": 1148928 }, { "epoch": 0.0, "learning_rate": 3.1181802755963027e-05, "loss": 3.5594, "step": 1149440 }, { "epoch": 0.0, "learning_rate": 3.117341680845251e-05, "loss": 3.5564, "step": 1149952 }, { "epoch": 0.0, "learning_rate": 3.116503086094199e-05, "loss": 3.5643, "step": 1150464 }, { "epoch": 0.0, "learning_rate": 3.115664491343147e-05, "loss": 3.5661, "step": 1150976 }, { "epoch": 0.0, "learning_rate": 3.114825896592095e-05, "loss": 3.5578, "step": 1151488 }, { "epoch": 0.0, "learning_rate": 3.113987301841043e-05, "loss": 3.5431, "step": 1152000 }, { "epoch": 0.0, "learning_rate": 3.113148707089991e-05, "loss": 3.5521, "step": 1152512 }, { "epoch": 0.0, "learning_rate": 3.112310112338939e-05, "loss": 3.5462, "step": 1153024 }, { "epoch": 0.0, "learning_rate": 3.11147315546826e-05, "loss": 3.5518, "step": 1153536 }, { "epoch": 0.0, "learning_rate": 3.110634560717208e-05, "loss": 3.5553, "step": 1154048 }, { "epoch": 0.0, "learning_rate": 3.109795965966156e-05, "loss": 3.556, "step": 1154560 }, { "epoch": 0.0, "learning_rate": 3.108957371215104e-05, "loss": 3.5742, "step": 1155072 }, { "epoch": 0.0, "learning_rate": 3.108120414344425e-05, "loss": 3.5628, "step": 1155584 }, { "epoch": 0.0, "learning_rate": 3.107281819593373e-05, "loss": 3.559, "step": 1156096 }, { "epoch": 0.0, "learning_rate": 3.106443224842321e-05, "loss": 3.562, "step": 1156608 }, { "epoch": 0.0, "learning_rate": 3.10560463009127e-05, "loss": 3.5661, "step": 1157120 }, { "epoch": 0.0, "learning_rate": 3.104767673220591e-05, "loss": 3.5477, "step": 1157632 }, { "epoch": 0.0, "learning_rate": 3.103929078469539e-05, "loss": 3.5581, "step": 1158144 }, { "epoch": 0.0, "learning_rate": 3.103090483718487e-05, "loss": 3.5619, "step": 1158656 }, { "epoch": 0.0, "learning_rate": 3.102251888967435e-05, "loss": 3.5504, "step": 1159168 }, { "epoch": 0.0, "learning_rate": 3.1014149320967556e-05, "loss": 3.5402, "step": 1159680 }, { "epoch": 0.01, "learning_rate": 3.1005763373457036e-05, "loss": 3.5531, "step": 1160192 }, { "epoch": 0.01, "learning_rate": 3.0997377425946516e-05, "loss": 3.562, "step": 1160704 }, { "epoch": 0.01, "learning_rate": 3.0988991478435996e-05, "loss": 3.5616, "step": 1161216 }, { "epoch": 0.01, "learning_rate": 3.0980621909729205e-05, "loss": 3.5564, "step": 1161728 }, { "epoch": 0.01, "learning_rate": 3.0972235962218685e-05, "loss": 3.5593, "step": 1162240 }, { "epoch": 0.01, "learning_rate": 3.0963850014708165e-05, "loss": 3.5513, "step": 1162752 }, { "epoch": 0.01, "learning_rate": 3.095546406719765e-05, "loss": 3.547, "step": 1163264 }, { "epoch": 0.01, "learning_rate": 3.094709449849086e-05, "loss": 3.5441, "step": 1163776 }, { "epoch": 0.01, "learning_rate": 3.093870855098034e-05, "loss": 3.5594, "step": 1164288 }, { "epoch": 0.01, "learning_rate": 3.093032260346982e-05, "loss": 3.5452, "step": 1164800 }, { "epoch": 0.01, "learning_rate": 3.09219366559593e-05, "loss": 3.5518, "step": 1165312 }, { "epoch": 0.01, "learning_rate": 3.091356708725251e-05, "loss": 3.5509, "step": 1165824 }, { "epoch": 0.01, "learning_rate": 3.090518113974199e-05, "loss": 3.5695, "step": 1166336 }, { "epoch": 0.01, "learning_rate": 3.089679519223147e-05, "loss": 3.5494, "step": 1166848 }, { "epoch": 0.01, "learning_rate": 3.088840924472095e-05, "loss": 3.5541, "step": 1167360 }, { "epoch": 0.01, "learning_rate": 3.088003967601416e-05, "loss": 3.5576, "step": 1167872 }, { "epoch": 0.01, "learning_rate": 3.087165372850364e-05, "loss": 3.5453, "step": 1168384 }, { "epoch": 0.01, "learning_rate": 3.086326778099312e-05, "loss": 3.5558, "step": 1168896 }, { "epoch": 0.01, "learning_rate": 3.0854881833482605e-05, "loss": 3.5416, "step": 1169408 }, { "epoch": 0.01, "learning_rate": 3.0846512264775814e-05, "loss": 3.5501, "step": 1169920 }, { "epoch": 0.01, "learning_rate": 3.0838126317265294e-05, "loss": 3.5523, "step": 1170432 }, { "epoch": 0.01, "learning_rate": 3.0829740369754774e-05, "loss": 3.5504, "step": 1170944 }, { "epoch": 0.01, "learning_rate": 3.0821354422244254e-05, "loss": 3.5492, "step": 1171456 }, { "epoch": 0.01, "learning_rate": 3.081298485353746e-05, "loss": 3.5318, "step": 1171968 }, { "epoch": 0.01, "learning_rate": 3.080459890602694e-05, "loss": 3.5491, "step": 1172480 }, { "epoch": 0.01, "learning_rate": 3.079621295851642e-05, "loss": 3.5323, "step": 1172992 }, { "epoch": 0.01, "learning_rate": 3.07878270110059e-05, "loss": 3.5666, "step": 1173504 }, { "epoch": 0.01, "learning_rate": 3.077945744229911e-05, "loss": 3.5456, "step": 1174016 }, { "epoch": 0.01, "learning_rate": 3.077107149478859e-05, "loss": 3.5606, "step": 1174528 }, { "epoch": 0.01, "learning_rate": 3.076268554727807e-05, "loss": 3.5542, "step": 1175040 }, { "epoch": 0.01, "learning_rate": 3.075429959976755e-05, "loss": 3.534, "step": 1175552 }, { "epoch": 0.01, "learning_rate": 3.074593003106077e-05, "loss": 3.5438, "step": 1176064 }, { "epoch": 0.01, "learning_rate": 3.073754408355025e-05, "loss": 3.5474, "step": 1176576 }, { "epoch": 0.01, "learning_rate": 3.072915813603973e-05, "loss": 3.5404, "step": 1177088 }, { "epoch": 0.01, "learning_rate": 3.072077218852921e-05, "loss": 3.5338, "step": 1177600 }, { "epoch": 0.01, "learning_rate": 3.071240261982242e-05, "loss": 3.5597, "step": 1178112 }, { "epoch": 0.01, "learning_rate": 3.07040166723119e-05, "loss": 3.5563, "step": 1178624 }, { "epoch": 0.01, "learning_rate": 3.069563072480138e-05, "loss": 3.5413, "step": 1179136 }, { "epoch": 0.01, "learning_rate": 3.068724477729086e-05, "loss": 3.5326, "step": 1179648 }, { "epoch": 0.01, "learning_rate": 3.0678875208584066e-05, "loss": 3.5417, "step": 1180160 }, { "epoch": 0.01, "learning_rate": 3.0670489261073546e-05, "loss": 3.5449, "step": 1180672 }, { "epoch": 0.01, "learning_rate": 3.0662103313563026e-05, "loss": 3.5611, "step": 1181184 }, { "epoch": 0.01, "learning_rate": 3.0653717366052506e-05, "loss": 3.5516, "step": 1181696 }, { "epoch": 0.01, "learning_rate": 3.064534779734572e-05, "loss": 3.5551, "step": 1182208 }, { "epoch": 0.01, "learning_rate": 3.06369618498352e-05, "loss": 3.548, "step": 1182720 }, { "epoch": 0.01, "learning_rate": 3.062857590232468e-05, "loss": 3.5536, "step": 1183232 }, { "epoch": 0.01, "learning_rate": 3.062018995481416e-05, "loss": 3.551, "step": 1183744 }, { "epoch": 0.01, "learning_rate": 3.061182038610737e-05, "loss": 3.5421, "step": 1184256 }, { "epoch": 0.01, "learning_rate": 3.060343443859685e-05, "loss": 3.5548, "step": 1184768 }, { "epoch": 0.01, "learning_rate": 3.059504849108633e-05, "loss": 3.5432, "step": 1185280 }, { "epoch": 0.01, "learning_rate": 3.058666254357581e-05, "loss": 3.5521, "step": 1185792 }, { "epoch": 0.01, "learning_rate": 3.057829297486902e-05, "loss": 3.5556, "step": 1186304 }, { "epoch": 0.01, "learning_rate": 3.05699070273585e-05, "loss": 3.5532, "step": 1186816 }, { "epoch": 0.01, "learning_rate": 3.056152107984798e-05, "loss": 3.5416, "step": 1187328 }, { "epoch": 0.01, "learning_rate": 3.055313513233746e-05, "loss": 3.5267, "step": 1187840 }, { "epoch": 0.01, "learning_rate": 3.0544765563630675e-05, "loss": 3.5493, "step": 1188352 }, { "epoch": 0.01, "learning_rate": 3.0536379616120155e-05, "loss": 3.5499, "step": 1188864 }, { "epoch": 0.01, "learning_rate": 3.0527993668609635e-05, "loss": 3.5475, "step": 1189376 }, { "epoch": 0.01, "learning_rate": 3.051960772109911e-05, "loss": 3.5477, "step": 1189888 }, { "epoch": 0.01, "learning_rate": 3.0511238152392324e-05, "loss": 3.5507, "step": 1190400 }, { "epoch": 0.02, "learning_rate": 3.0502852204881804e-05, "loss": 3.5465, "step": 1190912 }, { "epoch": 0.02, "learning_rate": 3.0494466257371284e-05, "loss": 3.5387, "step": 1191424 }, { "epoch": 0.02, "learning_rate": 3.048608030986076e-05, "loss": 3.5417, "step": 1191936 }, { "epoch": 0.02, "learning_rate": 3.0477710741153977e-05, "loss": 3.5507, "step": 1192448 }, { "epoch": 0.02, "learning_rate": 3.0469324793643456e-05, "loss": 3.558, "step": 1192960 }, { "epoch": 0.02, "learning_rate": 3.0460938846132936e-05, "loss": 3.555, "step": 1193472 }, { "epoch": 0.02, "learning_rate": 3.045255289862241e-05, "loss": 3.5502, "step": 1193984 }, { "epoch": 0.02, "learning_rate": 3.0444183329915625e-05, "loss": 3.5426, "step": 1194496 }, { "epoch": 0.02, "learning_rate": 3.0435797382405105e-05, "loss": 3.549, "step": 1195008 }, { "epoch": 0.02, "learning_rate": 3.0427411434894582e-05, "loss": 3.5504, "step": 1195520 }, { "epoch": 0.02, "learning_rate": 3.0419025487384062e-05, "loss": 3.5467, "step": 1196032 }, { "epoch": 0.02, "learning_rate": 3.0410655918677278e-05, "loss": 3.5484, "step": 1196544 }, { "epoch": 0.02, "learning_rate": 3.0402269971166758e-05, "loss": 3.5435, "step": 1197056 }, { "epoch": 0.02, "learning_rate": 3.0393884023656234e-05, "loss": 3.534, "step": 1197568 }, { "epoch": 0.02, "learning_rate": 3.0385498076145714e-05, "loss": 3.5564, "step": 1198080 }, { "epoch": 0.02, "learning_rate": 3.037712850743893e-05, "loss": 3.5303, "step": 1198592 }, { "epoch": 0.02, "learning_rate": 3.0368742559928403e-05, "loss": 3.5408, "step": 1199104 }, { "epoch": 0.02, "learning_rate": 3.0360356612417883e-05, "loss": 3.5525, "step": 1199616 }, { "epoch": 0.02, "learning_rate": 3.0351970664907363e-05, "loss": 3.5443, "step": 1200128 }, { "epoch": 0.02, "learning_rate": 3.034360109620058e-05, "loss": 3.5435, "step": 1200640 }, { "epoch": 0.02, "learning_rate": 3.0335215148690056e-05, "loss": 3.5512, "step": 1201152 }, { "epoch": 0.02, "learning_rate": 3.0326829201179536e-05, "loss": 3.543, "step": 1201664 }, { "epoch": 0.02, "learning_rate": 3.0318443253669016e-05, "loss": 3.5484, "step": 1202176 }, { "epoch": 0.02, "learning_rate": 3.031007368496223e-05, "loss": 3.5494, "step": 1202688 }, { "epoch": 0.02, "learning_rate": 3.0301687737451705e-05, "loss": 3.5469, "step": 1203200 }, { "epoch": 0.02, "learning_rate": 3.0293301789941188e-05, "loss": 3.5534, "step": 1203712 }, { "epoch": 0.02, "learning_rate": 3.0284915842430668e-05, "loss": 3.5579, "step": 1204224 }, { "epoch": 0.02, "learning_rate": 3.0276546273723877e-05, "loss": 3.547, "step": 1204736 }, { "epoch": 0.02, "learning_rate": 3.0268160326213357e-05, "loss": 3.5494, "step": 1205248 }, { "epoch": 0.02, "learning_rate": 3.0259774378702837e-05, "loss": 3.5467, "step": 1205760 }, { "epoch": 0.02, "learning_rate": 3.0251388431192317e-05, "loss": 3.5468, "step": 1206272 }, { "epoch": 0.02, "learning_rate": 3.024301886248553e-05, "loss": 3.5372, "step": 1206784 }, { "epoch": 0.02, "learning_rate": 3.023463291497501e-05, "loss": 3.5417, "step": 1207296 }, { "epoch": 0.02, "learning_rate": 3.022624696746449e-05, "loss": 3.5432, "step": 1207808 }, { "epoch": 0.02, "learning_rate": 3.021786101995397e-05, "loss": 3.5549, "step": 1208320 }, { "epoch": 0.02, "learning_rate": 3.020949145124718e-05, "loss": 3.5472, "step": 1208832 }, { "epoch": 0.02, "learning_rate": 3.020110550373666e-05, "loss": 3.5488, "step": 1209344 }, { "epoch": 0.02, "learning_rate": 3.0192719556226142e-05, "loss": 3.5391, "step": 1209856 }, { "epoch": 0.02, "learning_rate": 3.018433360871562e-05, "loss": 3.5444, "step": 1210368 }, { "epoch": 0.02, "learning_rate": 3.017596404000883e-05, "loss": 3.5425, "step": 1210880 }, { "epoch": 0.02, "learning_rate": 3.016757809249831e-05, "loss": 3.5548, "step": 1211392 }, { "epoch": 0.02, "learning_rate": 3.015919214498779e-05, "loss": 3.555, "step": 1211904 }, { "epoch": 0.02, "learning_rate": 3.015080619747727e-05, "loss": 3.5342, "step": 1212416 }, { "epoch": 0.02, "learning_rate": 3.0142436628770483e-05, "loss": 3.5463, "step": 1212928 }, { "epoch": 0.02, "learning_rate": 3.0134050681259963e-05, "loss": 3.5522, "step": 1213440 }, { "epoch": 0.02, "learning_rate": 3.0125664733749443e-05, "loss": 3.5487, "step": 1213952 }, { "epoch": 0.02, "learning_rate": 3.0117278786238923e-05, "loss": 3.5398, "step": 1214464 }, { "epoch": 0.02, "learning_rate": 3.0108909217532132e-05, "loss": 3.5436, "step": 1214976 }, { "epoch": 0.02, "learning_rate": 3.0100523270021612e-05, "loss": 3.5521, "step": 1215488 }, { "epoch": 0.02, "learning_rate": 3.0092137322511092e-05, "loss": 3.5589, "step": 1216000 }, { "epoch": 0.02, "learning_rate": 3.0083751375000575e-05, "loss": 3.548, "step": 1216512 }, { "epoch": 0.02, "learning_rate": 3.0075381806293784e-05, "loss": 3.5473, "step": 1217024 }, { "epoch": 0.02, "learning_rate": 3.0066995858783264e-05, "loss": 3.544, "step": 1217536 }, { "epoch": 0.02, "learning_rate": 3.0058609911272744e-05, "loss": 3.5413, "step": 1218048 }, { "epoch": 0.02, "learning_rate": 3.0050223963762224e-05, "loss": 3.5403, "step": 1218560 }, { "epoch": 0.02, "learning_rate": 3.0041854395055437e-05, "loss": 3.5559, "step": 1219072 }, { "epoch": 0.02, "learning_rate": 3.0033468447544917e-05, "loss": 3.5381, "step": 1219584 }, { "epoch": 0.02, "learning_rate": 3.0025082500034397e-05, "loss": 3.5525, "step": 1220096 }, { "epoch": 0.02, "learning_rate": 3.0016696552523877e-05, "loss": 3.5437, "step": 1220608 }, { "epoch": 0.03, "learning_rate": 3.0008326983817086e-05, "loss": 3.5475, "step": 1221120 }, { "epoch": 0.03, "eval_loss": 3.8671066761016846, "eval_runtime": 304.4085, "eval_samples_per_second": 1253.549, "eval_steps_per_second": 39.174, "step": 1221120 }, { "epoch": 1.0, "learning_rate": 2.9999941036306566e-05, "loss": 3.5333, "step": 1221632 }, { "epoch": 1.0, "learning_rate": 2.9991555088796046e-05, "loss": 3.5398, "step": 1222144 }, { "epoch": 1.0, "learning_rate": 2.998316914128553e-05, "loss": 3.553, "step": 1222656 }, { "epoch": 1.0, "learning_rate": 2.9974799572578738e-05, "loss": 3.546, "step": 1223168 }, { "epoch": 1.0, "learning_rate": 2.9966413625068218e-05, "loss": 3.5591, "step": 1223680 }, { "epoch": 1.0, "learning_rate": 2.9958027677557698e-05, "loss": 3.5364, "step": 1224192 }, { "epoch": 1.0, "learning_rate": 2.9949641730047178e-05, "loss": 3.5496, "step": 1224704 }, { "epoch": 1.0, "learning_rate": 2.994127216134039e-05, "loss": 3.5393, "step": 1225216 }, { "epoch": 1.0, "learning_rate": 2.99329025926336e-05, "loss": 3.5454, "step": 1225728 }, { "epoch": 1.0, "learning_rate": 2.992451664512308e-05, "loss": 3.5426, "step": 1226240 }, { "epoch": 1.0, "learning_rate": 2.991613069761256e-05, "loss": 3.5457, "step": 1226752 }, { "epoch": 1.0, "learning_rate": 2.990774475010204e-05, "loss": 3.5516, "step": 1227264 }, { "epoch": 1.0, "learning_rate": 2.989935880259152e-05, "loss": 3.5396, "step": 1227776 }, { "epoch": 1.0, "learning_rate": 2.9890972855081e-05, "loss": 3.5292, "step": 1228288 }, { "epoch": 1.0, "learning_rate": 2.9882586907570483e-05, "loss": 3.5406, "step": 1228800 }, { "epoch": 1.0, "learning_rate": 2.9874200960059963e-05, "loss": 3.5285, "step": 1229312 }, { "epoch": 1.0, "learning_rate": 2.9865831391353172e-05, "loss": 3.5393, "step": 1229824 }, { "epoch": 1.0, "learning_rate": 2.985744544384265e-05, "loss": 3.541, "step": 1230336 }, { "epoch": 1.0, "learning_rate": 2.984905949633213e-05, "loss": 3.5408, "step": 1230848 }, { "epoch": 1.0, "learning_rate": 2.984067354882161e-05, "loss": 3.5608, "step": 1231360 }, { "epoch": 1.0, "learning_rate": 2.9832303980114824e-05, "loss": 3.5491, "step": 1231872 }, { "epoch": 1.0, "learning_rate": 2.9823918032604304e-05, "loss": 3.5466, "step": 1232384 }, { "epoch": 1.0, "learning_rate": 2.9815532085093784e-05, "loss": 3.5448, "step": 1232896 }, { "epoch": 1.0, "learning_rate": 2.9807146137583264e-05, "loss": 3.552, "step": 1233408 }, { "epoch": 1.0, "learning_rate": 2.9798776568876473e-05, "loss": 3.5392, "step": 1233920 }, { "epoch": 1.0, "learning_rate": 2.9790390621365953e-05, "loss": 3.5414, "step": 1234432 }, { "epoch": 1.0, "learning_rate": 2.9782004673855436e-05, "loss": 3.5489, "step": 1234944 }, { "epoch": 1.0, "learning_rate": 2.9773618726344916e-05, "loss": 3.5372, "step": 1235456 }, { "epoch": 1.0, "learning_rate": 2.9765249157638125e-05, "loss": 3.5229, "step": 1235968 }, { "epoch": 1.01, "learning_rate": 2.9756863210127605e-05, "loss": 3.5386, "step": 1236480 }, { "epoch": 1.01, "learning_rate": 2.9748477262617085e-05, "loss": 3.5463, "step": 1236992 }, { "epoch": 1.01, "learning_rate": 2.9740091315106565e-05, "loss": 3.5494, "step": 1237504 }, { "epoch": 1.01, "learning_rate": 2.9731721746399778e-05, "loss": 3.5442, "step": 1238016 }, { "epoch": 1.01, "learning_rate": 2.9723335798889258e-05, "loss": 3.5479, "step": 1238528 }, { "epoch": 1.01, "learning_rate": 2.9714949851378738e-05, "loss": 3.5337, "step": 1239040 }, { "epoch": 1.01, "learning_rate": 2.9706563903868218e-05, "loss": 3.5385, "step": 1239552 }, { "epoch": 1.01, "learning_rate": 2.9698194335161427e-05, "loss": 3.5264, "step": 1240064 }, { "epoch": 1.01, "learning_rate": 2.9689808387650907e-05, "loss": 3.543, "step": 1240576 }, { "epoch": 1.01, "learning_rate": 2.968142244014039e-05, "loss": 3.5332, "step": 1241088 }, { "epoch": 1.01, "learning_rate": 2.967303649262987e-05, "loss": 3.5392, "step": 1241600 }, { "epoch": 1.01, "learning_rate": 2.966466692392308e-05, "loss": 3.5381, "step": 1242112 }, { "epoch": 1.01, "learning_rate": 2.965628097641256e-05, "loss": 3.5483, "step": 1242624 }, { "epoch": 1.01, "learning_rate": 2.964789502890204e-05, "loss": 3.5434, "step": 1243136 }, { "epoch": 1.01, "learning_rate": 2.963950908139152e-05, "loss": 3.5361, "step": 1243648 }, { "epoch": 1.01, "learning_rate": 2.963113951268473e-05, "loss": 3.5436, "step": 1244160 }, { "epoch": 1.01, "learning_rate": 2.962275356517421e-05, "loss": 3.5341, "step": 1244672 }, { "epoch": 1.01, "learning_rate": 2.961436761766369e-05, "loss": 3.5423, "step": 1245184 }, { "epoch": 1.01, "learning_rate": 2.960598167015317e-05, "loss": 3.5271, "step": 1245696 }, { "epoch": 1.01, "learning_rate": 2.959761210144638e-05, "loss": 3.5357, "step": 1246208 }, { "epoch": 1.01, "learning_rate": 2.958922615393586e-05, "loss": 3.5418, "step": 1246720 }, { "epoch": 1.01, "learning_rate": 2.9580840206425344e-05, "loss": 3.5349, "step": 1247232 }, { "epoch": 1.01, "learning_rate": 2.9572454258914824e-05, "loss": 3.5384, "step": 1247744 }, { "epoch": 1.01, "learning_rate": 2.9564084690208033e-05, "loss": 3.5219, "step": 1248256 }, { "epoch": 1.01, "learning_rate": 2.9555698742697513e-05, "loss": 3.5346, "step": 1248768 }, { "epoch": 1.01, "learning_rate": 2.9547312795186993e-05, "loss": 3.516, "step": 1249280 }, { "epoch": 1.01, "learning_rate": 2.9538926847676473e-05, "loss": 3.5522, "step": 1249792 }, { "epoch": 1.01, "learning_rate": 2.9530557278969685e-05, "loss": 3.5303, "step": 1250304 }, { "epoch": 1.01, "learning_rate": 2.9522171331459165e-05, "loss": 3.5468, "step": 1250816 }, { "epoch": 1.01, "learning_rate": 2.9513785383948645e-05, "loss": 3.5411, "step": 1251328 }, { "epoch": 1.01, "learning_rate": 2.9505399436438125e-05, "loss": 3.5233, "step": 1251840 }, { "epoch": 1.01, "learning_rate": 2.9497029867731334e-05, "loss": 3.5271, "step": 1252352 }, { "epoch": 1.01, "learning_rate": 2.9488643920220814e-05, "loss": 3.5326, "step": 1252864 }, { "epoch": 1.01, "learning_rate": 2.9480257972710297e-05, "loss": 3.526, "step": 1253376 }, { "epoch": 1.01, "learning_rate": 2.9471872025199777e-05, "loss": 3.522, "step": 1253888 }, { "epoch": 1.01, "learning_rate": 2.9463502456492986e-05, "loss": 3.5461, "step": 1254400 }, { "epoch": 1.01, "learning_rate": 2.9455116508982466e-05, "loss": 3.5406, "step": 1254912 }, { "epoch": 1.01, "learning_rate": 2.9446730561471946e-05, "loss": 3.5277, "step": 1255424 }, { "epoch": 1.01, "learning_rate": 2.9438344613961426e-05, "loss": 3.5201, "step": 1255936 }, { "epoch": 1.01, "learning_rate": 2.942997504525464e-05, "loss": 3.5259, "step": 1256448 }, { "epoch": 1.01, "learning_rate": 2.942158909774412e-05, "loss": 3.5337, "step": 1256960 }, { "epoch": 1.01, "learning_rate": 2.94132031502336e-05, "loss": 3.5417, "step": 1257472 }, { "epoch": 1.01, "learning_rate": 2.940481720272308e-05, "loss": 3.5378, "step": 1257984 }, { "epoch": 1.01, "learning_rate": 2.9396447634016288e-05, "loss": 3.5401, "step": 1258496 }, { "epoch": 1.01, "learning_rate": 2.9388061686505768e-05, "loss": 3.5361, "step": 1259008 }, { "epoch": 1.01, "learning_rate": 2.9379675738995248e-05, "loss": 3.5401, "step": 1259520 }, { "epoch": 1.01, "learning_rate": 2.937128979148473e-05, "loss": 3.5336, "step": 1260032 }, { "epoch": 1.01, "learning_rate": 2.936292022277794e-05, "loss": 3.5322, "step": 1260544 }, { "epoch": 1.01, "learning_rate": 2.935453427526742e-05, "loss": 3.5392, "step": 1261056 }, { "epoch": 1.01, "learning_rate": 2.93461483277569e-05, "loss": 3.5315, "step": 1261568 }, { "epoch": 1.01, "learning_rate": 2.9337762380246377e-05, "loss": 3.5363, "step": 1262080 }, { "epoch": 1.01, "learning_rate": 2.9329392811539592e-05, "loss": 3.5408, "step": 1262592 }, { "epoch": 1.01, "learning_rate": 2.9321006864029072e-05, "loss": 3.5436, "step": 1263104 }, { "epoch": 1.01, "learning_rate": 2.9312620916518552e-05, "loss": 3.5265, "step": 1263616 }, { "epoch": 1.01, "learning_rate": 2.9304234969008025e-05, "loss": 3.5172, "step": 1264128 }, { "epoch": 1.01, "learning_rate": 2.929586540030124e-05, "loss": 3.5329, "step": 1264640 }, { "epoch": 1.01, "learning_rate": 2.928747945279072e-05, "loss": 3.5362, "step": 1265152 }, { "epoch": 1.01, "learning_rate": 2.92790935052802e-05, "loss": 3.5353, "step": 1265664 }, { "epoch": 1.01, "learning_rate": 2.9270707557769678e-05, "loss": 3.5323, "step": 1266176 }, { "epoch": 1.01, "learning_rate": 2.9262337989062894e-05, "loss": 3.5374, "step": 1266688 }, { "epoch": 1.02, "learning_rate": 2.9253952041552374e-05, "loss": 3.5296, "step": 1267200 }, { "epoch": 1.02, "learning_rate": 2.924556609404185e-05, "loss": 3.5239, "step": 1267712 }, { "epoch": 1.02, "learning_rate": 2.923718014653133e-05, "loss": 3.5302, "step": 1268224 }, { "epoch": 1.02, "learning_rate": 2.9228810577824546e-05, "loss": 3.5325, "step": 1268736 }, { "epoch": 1.02, "learning_rate": 2.9220424630314026e-05, "loss": 3.5428, "step": 1269248 }, { "epoch": 1.02, "learning_rate": 2.92120386828035e-05, "loss": 3.5455, "step": 1269760 }, { "epoch": 1.02, "learning_rate": 2.920365273529298e-05, "loss": 3.5426, "step": 1270272 }, { "epoch": 1.02, "learning_rate": 2.9195283166586195e-05, "loss": 3.5236, "step": 1270784 }, { "epoch": 1.02, "learning_rate": 2.9186897219075675e-05, "loss": 3.5368, "step": 1271296 }, { "epoch": 1.02, "learning_rate": 2.917851127156515e-05, "loss": 3.5361, "step": 1271808 }, { "epoch": 1.02, "learning_rate": 2.917012532405463e-05, "loss": 3.5357, "step": 1272320 }, { "epoch": 1.02, "learning_rate": 2.9161755755347847e-05, "loss": 3.5336, "step": 1272832 }, { "epoch": 1.02, "learning_rate": 2.915336980783732e-05, "loss": 3.5269, "step": 1273344 }, { "epoch": 1.02, "learning_rate": 2.91449838603268e-05, "loss": 3.5232, "step": 1273856 }, { "epoch": 1.02, "learning_rate": 2.9136597912816284e-05, "loss": 3.5426, "step": 1274368 }, { "epoch": 1.02, "learning_rate": 2.91282283441095e-05, "loss": 3.5157, "step": 1274880 }, { "epoch": 1.02, "learning_rate": 2.9119842396598973e-05, "loss": 3.5293, "step": 1275392 }, { "epoch": 1.02, "learning_rate": 2.9111456449088453e-05, "loss": 3.5383, "step": 1275904 }, { "epoch": 1.02, "learning_rate": 2.9103070501577933e-05, "loss": 3.526, "step": 1276416 }, { "epoch": 1.02, "learning_rate": 2.9094700932871145e-05, "loss": 3.5289, "step": 1276928 }, { "epoch": 1.02, "learning_rate": 2.9086314985360625e-05, "loss": 3.5371, "step": 1277440 }, { "epoch": 1.02, "learning_rate": 2.9077929037850105e-05, "loss": 3.5268, "step": 1277952 }, { "epoch": 1.02, "learning_rate": 2.9069543090339585e-05, "loss": 3.5371, "step": 1278464 }, { "epoch": 1.02, "learning_rate": 2.9061173521632794e-05, "loss": 3.5361, "step": 1278976 }, { "epoch": 1.02, "learning_rate": 2.9052787574122274e-05, "loss": 3.5328, "step": 1279488 }, { "epoch": 1.02, "learning_rate": 2.9044401626611754e-05, "loss": 3.5354, "step": 1280000 }, { "epoch": 1.02, "learning_rate": 2.9036015679101238e-05, "loss": 3.5475, "step": 1280512 }, { "epoch": 1.02, "learning_rate": 2.9027646110394447e-05, "loss": 3.534, "step": 1281024 }, { "epoch": 1.02, "learning_rate": 2.9019260162883927e-05, "loss": 3.5341, "step": 1281536 }, { "epoch": 1.02, "learning_rate": 2.9010874215373407e-05, "loss": 3.5343, "step": 1282048 }, { "epoch": 1.02, "learning_rate": 2.9002488267862886e-05, "loss": 3.5325, "step": 1282560 }, { "epoch": 1.02, "learning_rate": 2.89941186991561e-05, "loss": 3.528, "step": 1283072 }, { "epoch": 1.02, "learning_rate": 2.898573275164558e-05, "loss": 3.5245, "step": 1283584 }, { "epoch": 1.02, "learning_rate": 2.897734680413506e-05, "loss": 3.5305, "step": 1284096 }, { "epoch": 1.02, "learning_rate": 2.896896085662454e-05, "loss": 3.5415, "step": 1284608 }, { "epoch": 1.02, "learning_rate": 2.8960591287917748e-05, "loss": 3.5374, "step": 1285120 }, { "epoch": 1.02, "learning_rate": 2.8952205340407228e-05, "loss": 3.5356, "step": 1285632 }, { "epoch": 1.02, "learning_rate": 2.8943819392896708e-05, "loss": 3.5272, "step": 1286144 }, { "epoch": 1.02, "learning_rate": 2.893543344538619e-05, "loss": 3.5284, "step": 1286656 }, { "epoch": 1.02, "learning_rate": 2.89270638766794e-05, "loss": 3.5316, "step": 1287168 }, { "epoch": 1.02, "learning_rate": 2.891867792916888e-05, "loss": 3.5432, "step": 1287680 }, { "epoch": 1.02, "learning_rate": 2.891029198165836e-05, "loss": 3.5426, "step": 1288192 }, { "epoch": 1.02, "learning_rate": 2.890190603414784e-05, "loss": 3.5234, "step": 1288704 }, { "epoch": 1.02, "learning_rate": 2.8893536465441053e-05, "loss": 3.5327, "step": 1289216 }, { "epoch": 1.02, "learning_rate": 2.8885150517930533e-05, "loss": 3.5344, "step": 1289728 }, { "epoch": 1.02, "learning_rate": 2.8876764570420013e-05, "loss": 3.5294, "step": 1290240 }, { "epoch": 1.02, "learning_rate": 2.8868378622909493e-05, "loss": 3.5341, "step": 1290752 }, { "epoch": 1.02, "learning_rate": 2.88600090542027e-05, "loss": 3.5268, "step": 1291264 }, { "epoch": 1.02, "learning_rate": 2.885162310669218e-05, "loss": 3.5423, "step": 1291776 }, { "epoch": 1.02, "learning_rate": 2.884323715918166e-05, "loss": 3.542, "step": 1292288 }, { "epoch": 1.02, "learning_rate": 2.8834851211671145e-05, "loss": 3.5359, "step": 1292800 }, { "epoch": 1.02, "learning_rate": 2.8826481642964354e-05, "loss": 3.5339, "step": 1293312 }, { "epoch": 1.02, "learning_rate": 2.8818095695453834e-05, "loss": 3.5342, "step": 1293824 }, { "epoch": 1.02, "learning_rate": 2.8809709747943314e-05, "loss": 3.5276, "step": 1294336 }, { "epoch": 1.02, "learning_rate": 2.8801323800432794e-05, "loss": 3.5273, "step": 1294848 }, { "epoch": 1.02, "learning_rate": 2.8792954231726006e-05, "loss": 3.5431, "step": 1295360 }, { "epoch": 1.02, "learning_rate": 2.8784568284215486e-05, "loss": 3.5242, "step": 1295872 }, { "epoch": 1.02, "learning_rate": 2.8776182336704966e-05, "loss": 3.5369, "step": 1296384 }, { "epoch": 1.02, "learning_rate": 2.8767796389194446e-05, "loss": 3.5335, "step": 1296896 }, { "epoch": 1.02, "learning_rate": 2.8759426820487655e-05, "loss": 3.5315, "step": 1297408 }, { "epoch": 1.03, "eval_loss": 3.868220806121826, "eval_runtime": 302.9414, "eval_samples_per_second": 1259.62, "eval_steps_per_second": 39.364, "step": 1297440 }, { "epoch": 0.0, "learning_rate": 2.8751040872977135e-05, "loss": 3.5192, "step": 1297920 }, { "epoch": 0.0, "learning_rate": 2.8742654925466615e-05, "loss": 3.5285, "step": 1298432 }, { "epoch": 0.0, "learning_rate": 2.87342689779561e-05, "loss": 3.5414, "step": 1298944 }, { "epoch": 0.0, "learning_rate": 2.872588303044558e-05, "loss": 3.5291, "step": 1299456 }, { "epoch": 0.0, "learning_rate": 2.8717513461738788e-05, "loss": 3.5463, "step": 1299968 }, { "epoch": 0.0, "learning_rate": 2.8709127514228268e-05, "loss": 3.5193, "step": 1300480 }, { "epoch": 0.0, "learning_rate": 2.8700741566717747e-05, "loss": 3.5382, "step": 1300992 }, { "epoch": 0.0, "learning_rate": 2.869237199801096e-05, "loss": 3.524, "step": 1301504 }, { "epoch": 0.0, "learning_rate": 2.868400242930417e-05, "loss": 3.5323, "step": 1302016 }, { "epoch": 0.0, "learning_rate": 2.867561648179365e-05, "loss": 3.5319, "step": 1302528 }, { "epoch": 0.0, "learning_rate": 2.866723053428313e-05, "loss": 3.5291, "step": 1303040 }, { "epoch": 0.0, "learning_rate": 2.865884458677261e-05, "loss": 3.5375, "step": 1303552 }, { "epoch": 0.0, "learning_rate": 2.865045863926209e-05, "loss": 3.5253, "step": 1304064 }, { "epoch": 0.0, "learning_rate": 2.864207269175157e-05, "loss": 3.5207, "step": 1304576 }, { "epoch": 0.0, "learning_rate": 2.8633686744241052e-05, "loss": 3.5256, "step": 1305088 }, { "epoch": 0.0, "learning_rate": 2.8625300796730532e-05, "loss": 3.5198, "step": 1305600 }, { "epoch": 0.0, "learning_rate": 2.861693122802374e-05, "loss": 3.5218, "step": 1306112 }, { "epoch": 0.0, "learning_rate": 2.860854528051322e-05, "loss": 3.5277, "step": 1306624 }, { "epoch": 0.0, "learning_rate": 2.86001593330027e-05, "loss": 3.5257, "step": 1307136 }, { "epoch": 0.0, "learning_rate": 2.859177338549218e-05, "loss": 3.5494, "step": 1307648 }, { "epoch": 0.0, "learning_rate": 2.8583403816785394e-05, "loss": 3.5318, "step": 1308160 }, { "epoch": 0.0, "learning_rate": 2.8575017869274874e-05, "loss": 3.534, "step": 1308672 }, { "epoch": 0.0, "learning_rate": 2.8566631921764354e-05, "loss": 3.5304, "step": 1309184 }, { "epoch": 0.0, "learning_rate": 2.8558245974253833e-05, "loss": 3.5343, "step": 1309696 }, { "epoch": 0.0, "learning_rate": 2.8549876405547043e-05, "loss": 3.5264, "step": 1310208 }, { "epoch": 0.0, "learning_rate": 2.8541490458036523e-05, "loss": 3.5315, "step": 1310720 }, { "epoch": 0.0, "learning_rate": 2.8533104510526006e-05, "loss": 3.5325, "step": 1311232 }, { "epoch": 0.0, "learning_rate": 2.8524718563015486e-05, "loss": 3.5242, "step": 1311744 }, { "epoch": 0.0, "learning_rate": 2.8516348994308695e-05, "loss": 3.5073, "step": 1312256 }, { "epoch": 0.01, "learning_rate": 2.8507963046798175e-05, "loss": 3.5295, "step": 1312768 }, { "epoch": 0.01, "learning_rate": 2.8499577099287655e-05, "loss": 3.5306, "step": 1313280 }, { "epoch": 0.01, "learning_rate": 2.8491191151777135e-05, "loss": 3.5342, "step": 1313792 }, { "epoch": 0.01, "learning_rate": 2.8482821583070347e-05, "loss": 3.5327, "step": 1314304 }, { "epoch": 0.01, "learning_rate": 2.8474435635559827e-05, "loss": 3.5333, "step": 1314816 }, { "epoch": 0.01, "learning_rate": 2.8466049688049307e-05, "loss": 3.5216, "step": 1315328 }, { "epoch": 0.01, "learning_rate": 2.8457663740538787e-05, "loss": 3.5249, "step": 1315840 }, { "epoch": 0.01, "learning_rate": 2.8449294171831996e-05, "loss": 3.5145, "step": 1316352 }, { "epoch": 0.01, "learning_rate": 2.8440908224321476e-05, "loss": 3.5301, "step": 1316864 }, { "epoch": 0.01, "learning_rate": 2.8432522276810956e-05, "loss": 3.5223, "step": 1317376 }, { "epoch": 0.01, "learning_rate": 2.842413632930044e-05, "loss": 3.5203, "step": 1317888 }, { "epoch": 0.01, "learning_rate": 2.841576676059365e-05, "loss": 3.5259, "step": 1318400 }, { "epoch": 0.01, "learning_rate": 2.840738081308313e-05, "loss": 3.5343, "step": 1318912 }, { "epoch": 0.01, "learning_rate": 2.839899486557261e-05, "loss": 3.5305, "step": 1319424 }, { "epoch": 0.01, "learning_rate": 2.839060891806209e-05, "loss": 3.5266, "step": 1319936 }, { "epoch": 0.01, "learning_rate": 2.83822393493553e-05, "loss": 3.5331, "step": 1320448 }, { "epoch": 0.01, "learning_rate": 2.837385340184478e-05, "loss": 3.5183, "step": 1320960 }, { "epoch": 0.01, "learning_rate": 2.836546745433426e-05, "loss": 3.5263, "step": 1321472 }, { "epoch": 0.01, "learning_rate": 2.835708150682374e-05, "loss": 3.5154, "step": 1321984 }, { "epoch": 0.01, "learning_rate": 2.834871193811695e-05, "loss": 3.5177, "step": 1322496 }, { "epoch": 0.01, "learning_rate": 2.834032599060643e-05, "loss": 3.528, "step": 1323008 }, { "epoch": 0.01, "learning_rate": 2.833194004309591e-05, "loss": 3.5211, "step": 1323520 }, { "epoch": 0.01, "learning_rate": 2.8323554095585393e-05, "loss": 3.5223, "step": 1324032 }, { "epoch": 0.01, "learning_rate": 2.8315184526878602e-05, "loss": 3.5138, "step": 1324544 }, { "epoch": 0.01, "learning_rate": 2.8306798579368082e-05, "loss": 3.5196, "step": 1325056 }, { "epoch": 0.01, "learning_rate": 2.8298412631857562e-05, "loss": 3.5075, "step": 1325568 }, { "epoch": 0.01, "learning_rate": 2.8290026684347042e-05, "loss": 3.5342, "step": 1326080 }, { "epoch": 0.01, "learning_rate": 2.8281657115640255e-05, "loss": 3.5194, "step": 1326592 }, { "epoch": 0.01, "learning_rate": 2.8273271168129735e-05, "loss": 3.5294, "step": 1327104 }, { "epoch": 0.01, "learning_rate": 2.8264885220619215e-05, "loss": 3.5294, "step": 1327616 }, { "epoch": 0.01, "learning_rate": 2.8256499273108694e-05, "loss": 3.5115, "step": 1328128 }, { "epoch": 0.01, "learning_rate": 2.8248129704401904e-05, "loss": 3.513, "step": 1328640 }, { "epoch": 0.01, "learning_rate": 2.8239743756891384e-05, "loss": 3.5202, "step": 1329152 }, { "epoch": 0.01, "learning_rate": 2.8231357809380863e-05, "loss": 3.5142, "step": 1329664 }, { "epoch": 0.01, "learning_rate": 2.8222971861870347e-05, "loss": 3.5105, "step": 1330176 }, { "epoch": 0.01, "learning_rate": 2.8214602293163556e-05, "loss": 3.5288, "step": 1330688 }, { "epoch": 0.01, "learning_rate": 2.8206216345653036e-05, "loss": 3.53, "step": 1331200 }, { "epoch": 0.01, "learning_rate": 2.8197830398142516e-05, "loss": 3.5156, "step": 1331712 }, { "epoch": 0.01, "learning_rate": 2.8189444450631996e-05, "loss": 3.5086, "step": 1332224 }, { "epoch": 0.01, "learning_rate": 2.8181074881925208e-05, "loss": 3.5116, "step": 1332736 }, { "epoch": 0.01, "learning_rate": 2.8172688934414688e-05, "loss": 3.5216, "step": 1333248 }, { "epoch": 0.01, "learning_rate": 2.8164302986904168e-05, "loss": 3.5267, "step": 1333760 }, { "epoch": 0.01, "learning_rate": 2.815591703939364e-05, "loss": 3.5259, "step": 1334272 }, { "epoch": 0.01, "learning_rate": 2.8147547470686857e-05, "loss": 3.5288, "step": 1334784 }, { "epoch": 0.01, "learning_rate": 2.8139161523176337e-05, "loss": 3.5235, "step": 1335296 }, { "epoch": 0.01, "learning_rate": 2.8130775575665817e-05, "loss": 3.5297, "step": 1335808 }, { "epoch": 0.01, "learning_rate": 2.8122389628155294e-05, "loss": 3.5154, "step": 1336320 }, { "epoch": 0.01, "learning_rate": 2.811402005944851e-05, "loss": 3.5228, "step": 1336832 }, { "epoch": 0.01, "learning_rate": 2.810563411193799e-05, "loss": 3.5234, "step": 1337344 }, { "epoch": 0.01, "learning_rate": 2.809724816442747e-05, "loss": 3.5143, "step": 1337856 }, { "epoch": 0.01, "learning_rate": 2.8088862216916946e-05, "loss": 3.5292, "step": 1338368 }, { "epoch": 0.01, "learning_rate": 2.8080492648210162e-05, "loss": 3.5272, "step": 1338880 }, { "epoch": 0.01, "learning_rate": 2.8072106700699642e-05, "loss": 3.5308, "step": 1339392 }, { "epoch": 0.01, "learning_rate": 2.8063720753189115e-05, "loss": 3.509, "step": 1339904 }, { "epoch": 0.01, "learning_rate": 2.8055334805678595e-05, "loss": 3.5037, "step": 1340416 }, { "epoch": 0.01, "learning_rate": 2.804696523697181e-05, "loss": 3.5199, "step": 1340928 }, { "epoch": 0.01, "learning_rate": 2.803857928946129e-05, "loss": 3.5218, "step": 1341440 }, { "epoch": 0.01, "learning_rate": 2.8030193341950767e-05, "loss": 3.5235, "step": 1341952 }, { "epoch": 0.01, "learning_rate": 2.8021807394440247e-05, "loss": 3.5182, "step": 1342464 }, { "epoch": 0.01, "learning_rate": 2.8013437825733463e-05, "loss": 3.522, "step": 1342976 }, { "epoch": 0.02, "learning_rate": 2.8005051878222943e-05, "loss": 3.5198, "step": 1343488 }, { "epoch": 0.02, "learning_rate": 2.7996665930712416e-05, "loss": 3.5103, "step": 1344000 }, { "epoch": 0.02, "learning_rate": 2.79882799832019e-05, "loss": 3.5167, "step": 1344512 }, { "epoch": 0.02, "learning_rate": 2.7979910414495116e-05, "loss": 3.5196, "step": 1345024 }, { "epoch": 0.02, "learning_rate": 2.797152446698459e-05, "loss": 3.5293, "step": 1345536 }, { "epoch": 0.02, "learning_rate": 2.796313851947407e-05, "loss": 3.5319, "step": 1346048 }, { "epoch": 0.02, "learning_rate": 2.795475257196355e-05, "loss": 3.5291, "step": 1346560 }, { "epoch": 0.02, "learning_rate": 2.7946383003256765e-05, "loss": 3.5141, "step": 1347072 }, { "epoch": 0.02, "learning_rate": 2.793799705574624e-05, "loss": 3.5232, "step": 1347584 }, { "epoch": 0.02, "learning_rate": 2.792961110823572e-05, "loss": 3.5186, "step": 1348096 }, { "epoch": 0.02, "learning_rate": 2.79212251607252e-05, "loss": 3.5279, "step": 1348608 }, { "epoch": 0.02, "learning_rate": 2.7912855592018417e-05, "loss": 3.5157, "step": 1349120 }, { "epoch": 0.02, "learning_rate": 2.790446964450789e-05, "loss": 3.5136, "step": 1349632 }, { "epoch": 0.02, "learning_rate": 2.789608369699737e-05, "loss": 3.5114, "step": 1350144 }, { "epoch": 0.02, "learning_rate": 2.7887697749486853e-05, "loss": 3.5282, "step": 1350656 }, { "epoch": 0.02, "learning_rate": 2.7879328180780062e-05, "loss": 3.5036, "step": 1351168 }, { "epoch": 0.02, "learning_rate": 2.7870942233269542e-05, "loss": 3.5194, "step": 1351680 }, { "epoch": 0.02, "learning_rate": 2.7862556285759022e-05, "loss": 3.5236, "step": 1352192 }, { "epoch": 0.02, "learning_rate": 2.7854186717052238e-05, "loss": 3.5123, "step": 1352704 }, { "epoch": 0.02, "learning_rate": 2.7845800769541715e-05, "loss": 3.5175, "step": 1353216 }, { "epoch": 0.02, "learning_rate": 2.7837414822031195e-05, "loss": 3.5275, "step": 1353728 }, { "epoch": 0.02, "learning_rate": 2.7829028874520675e-05, "loss": 3.5143, "step": 1354240 }, { "epoch": 0.02, "learning_rate": 2.782065930581389e-05, "loss": 3.5204, "step": 1354752 }, { "epoch": 0.02, "learning_rate": 2.7812273358303364e-05, "loss": 3.5261, "step": 1355264 }, { "epoch": 0.02, "learning_rate": 2.7803887410792844e-05, "loss": 3.5164, "step": 1355776 }, { "epoch": 0.02, "learning_rate": 2.7795501463282324e-05, "loss": 3.5261, "step": 1356288 }, { "epoch": 0.02, "learning_rate": 2.7787131894575536e-05, "loss": 3.5334, "step": 1356800 }, { "epoch": 0.02, "learning_rate": 2.7778745947065016e-05, "loss": 3.5195, "step": 1357312 }, { "epoch": 0.02, "learning_rate": 2.7770359999554496e-05, "loss": 3.5218, "step": 1357824 }, { "epoch": 0.02, "learning_rate": 2.7761974052043976e-05, "loss": 3.5229, "step": 1358336 }, { "epoch": 0.02, "learning_rate": 2.7753604483337185e-05, "loss": 3.5154, "step": 1358848 }, { "epoch": 0.02, "learning_rate": 2.774521853582667e-05, "loss": 3.5141, "step": 1359360 }, { "epoch": 0.02, "learning_rate": 2.773683258831615e-05, "loss": 3.513, "step": 1359872 }, { "epoch": 0.02, "learning_rate": 2.772844664080563e-05, "loss": 3.5145, "step": 1360384 }, { "epoch": 0.02, "learning_rate": 2.7720077072098838e-05, "loss": 3.5307, "step": 1360896 }, { "epoch": 0.02, "learning_rate": 2.7711691124588317e-05, "loss": 3.5242, "step": 1361408 }, { "epoch": 0.02, "learning_rate": 2.7703305177077797e-05, "loss": 3.5214, "step": 1361920 }, { "epoch": 0.02, "learning_rate": 2.7694919229567277e-05, "loss": 3.5139, "step": 1362432 }, { "epoch": 0.02, "learning_rate": 2.768654966086049e-05, "loss": 3.5133, "step": 1362944 }, { "epoch": 0.02, "learning_rate": 2.767816371334997e-05, "loss": 3.5182, "step": 1363456 }, { "epoch": 0.02, "learning_rate": 2.766977776583945e-05, "loss": 3.531, "step": 1363968 }, { "epoch": 0.02, "learning_rate": 2.766139181832893e-05, "loss": 3.5307, "step": 1364480 }, { "epoch": 0.02, "learning_rate": 2.765302224962214e-05, "loss": 3.5091, "step": 1364992 }, { "epoch": 0.02, "learning_rate": 2.7644636302111622e-05, "loss": 3.5157, "step": 1365504 }, { "epoch": 0.02, "learning_rate": 2.7636250354601102e-05, "loss": 3.5232, "step": 1366016 }, { "epoch": 0.02, "learning_rate": 2.7627864407090582e-05, "loss": 3.5201, "step": 1366528 }, { "epoch": 0.02, "learning_rate": 2.761949483838379e-05, "loss": 3.5243, "step": 1367040 }, { "epoch": 0.02, "learning_rate": 2.761110889087327e-05, "loss": 3.514, "step": 1367552 }, { "epoch": 0.02, "learning_rate": 2.760272294336275e-05, "loss": 3.5256, "step": 1368064 }, { "epoch": 0.02, "learning_rate": 2.759433699585223e-05, "loss": 3.5275, "step": 1368576 }, { "epoch": 0.02, "learning_rate": 2.7585967427145444e-05, "loss": 3.521, "step": 1369088 }, { "epoch": 0.02, "learning_rate": 2.7577581479634923e-05, "loss": 3.5213, "step": 1369600 }, { "epoch": 0.02, "learning_rate": 2.7569195532124403e-05, "loss": 3.5235, "step": 1370112 }, { "epoch": 0.02, "learning_rate": 2.7560809584613883e-05, "loss": 3.5142, "step": 1370624 }, { "epoch": 0.02, "learning_rate": 2.7552440015907092e-05, "loss": 3.5155, "step": 1371136 }, { "epoch": 0.02, "learning_rate": 2.7544054068396576e-05, "loss": 3.527, "step": 1371648 }, { "epoch": 0.02, "learning_rate": 2.7535668120886056e-05, "loss": 3.5109, "step": 1372160 }, { "epoch": 0.02, "learning_rate": 2.7527282173375536e-05, "loss": 3.5228, "step": 1372672 }, { "epoch": 0.02, "learning_rate": 2.7518912604668745e-05, "loss": 3.5189, "step": 1373184 }, { "epoch": 0.02, "learning_rate": 2.7510526657158225e-05, "loss": 3.5161, "step": 1373696 }, { "epoch": 0.03, "eval_loss": 3.8701694011688232, "eval_runtime": 303.4006, "eval_samples_per_second": 1257.714, "eval_steps_per_second": 39.304, "step": 1373760 }, { "epoch": 1.0, "learning_rate": 2.7502140709647705e-05, "loss": 3.5094, "step": 1374208 }, { "epoch": 1.0, "learning_rate": 2.7493754762137185e-05, "loss": 3.5178, "step": 1374720 }, { "epoch": 1.0, "learning_rate": 2.7485385193430397e-05, "loss": 3.528, "step": 1375232 }, { "epoch": 1.0, "learning_rate": 2.7476999245919877e-05, "loss": 3.5098, "step": 1375744 }, { "epoch": 1.0, "learning_rate": 2.7468613298409357e-05, "loss": 3.5345, "step": 1376256 }, { "epoch": 1.0, "learning_rate": 2.7460227350898837e-05, "loss": 3.5092, "step": 1376768 }, { "epoch": 1.0, "learning_rate": 2.7451857782192046e-05, "loss": 3.5259, "step": 1377280 }, { "epoch": 1.0, "learning_rate": 2.744347183468153e-05, "loss": 3.5079, "step": 1377792 }, { "epoch": 1.0, "learning_rate": 2.743510226597474e-05, "loss": 3.5256, "step": 1378304 }, { "epoch": 1.0, "learning_rate": 2.742671631846422e-05, "loss": 3.5171, "step": 1378816 }, { "epoch": 1.0, "learning_rate": 2.74183303709537e-05, "loss": 3.5147, "step": 1379328 }, { "epoch": 1.0, "learning_rate": 2.740994442344318e-05, "loss": 3.5277, "step": 1379840 }, { "epoch": 1.0, "learning_rate": 2.740155847593266e-05, "loss": 3.5103, "step": 1380352 }, { "epoch": 1.0, "learning_rate": 2.739317252842214e-05, "loss": 3.5075, "step": 1380864 }, { "epoch": 1.0, "learning_rate": 2.738478658091162e-05, "loss": 3.5112, "step": 1381376 }, { "epoch": 1.0, "learning_rate": 2.73764006334011e-05, "loss": 3.5073, "step": 1381888 }, { "epoch": 1.0, "learning_rate": 2.736803106469431e-05, "loss": 3.5101, "step": 1382400 }, { "epoch": 1.0, "learning_rate": 2.735964511718379e-05, "loss": 3.5135, "step": 1382912 }, { "epoch": 1.0, "learning_rate": 2.735125916967327e-05, "loss": 3.5136, "step": 1383424 }, { "epoch": 1.0, "learning_rate": 2.734287322216275e-05, "loss": 3.5375, "step": 1383936 }, { "epoch": 1.0, "learning_rate": 2.7334503653455963e-05, "loss": 3.5208, "step": 1384448 }, { "epoch": 1.0, "learning_rate": 2.7326117705945443e-05, "loss": 3.5202, "step": 1384960 }, { "epoch": 1.0, "learning_rate": 2.7317731758434923e-05, "loss": 3.5181, "step": 1385472 }, { "epoch": 1.0, "learning_rate": 2.7309345810924403e-05, "loss": 3.5233, "step": 1385984 }, { "epoch": 1.0, "learning_rate": 2.7300976242217612e-05, "loss": 3.515, "step": 1386496 }, { "epoch": 1.0, "learning_rate": 2.7292590294707092e-05, "loss": 3.5167, "step": 1387008 }, { "epoch": 1.0, "learning_rate": 2.7284204347196572e-05, "loss": 3.5211, "step": 1387520 }, { "epoch": 1.0, "learning_rate": 2.7275818399686055e-05, "loss": 3.509, "step": 1388032 }, { "epoch": 1.0, "learning_rate": 2.7267448830979264e-05, "loss": 3.4958, "step": 1388544 }, { "epoch": 1.01, "learning_rate": 2.7259062883468744e-05, "loss": 3.5147, "step": 1389056 }, { "epoch": 1.01, "learning_rate": 2.7250676935958224e-05, "loss": 3.5209, "step": 1389568 }, { "epoch": 1.01, "learning_rate": 2.7242290988447704e-05, "loss": 3.5181, "step": 1390080 }, { "epoch": 1.01, "learning_rate": 2.7233921419740917e-05, "loss": 3.5224, "step": 1390592 }, { "epoch": 1.01, "learning_rate": 2.7225535472230397e-05, "loss": 3.5222, "step": 1391104 }, { "epoch": 1.01, "learning_rate": 2.7217149524719877e-05, "loss": 3.5083, "step": 1391616 }, { "epoch": 1.01, "learning_rate": 2.7208763577209357e-05, "loss": 3.5111, "step": 1392128 }, { "epoch": 1.01, "learning_rate": 2.7200394008502566e-05, "loss": 3.5065, "step": 1392640 }, { "epoch": 1.01, "learning_rate": 2.7192008060992046e-05, "loss": 3.5121, "step": 1393152 }, { "epoch": 1.01, "learning_rate": 2.7183622113481526e-05, "loss": 3.5096, "step": 1393664 }, { "epoch": 1.01, "learning_rate": 2.717523616597101e-05, "loss": 3.508, "step": 1394176 }, { "epoch": 1.01, "learning_rate": 2.7166866597264218e-05, "loss": 3.5153, "step": 1394688 }, { "epoch": 1.01, "learning_rate": 2.7158480649753698e-05, "loss": 3.5232, "step": 1395200 }, { "epoch": 1.01, "learning_rate": 2.7150094702243178e-05, "loss": 3.5122, "step": 1395712 }, { "epoch": 1.01, "learning_rate": 2.7141708754732658e-05, "loss": 3.5152, "step": 1396224 }, { "epoch": 1.01, "learning_rate": 2.713333918602587e-05, "loss": 3.5219, "step": 1396736 }, { "epoch": 1.01, "learning_rate": 2.712495323851535e-05, "loss": 3.5041, "step": 1397248 }, { "epoch": 1.01, "learning_rate": 2.711656729100483e-05, "loss": 3.5134, "step": 1397760 }, { "epoch": 1.01, "learning_rate": 2.710818134349431e-05, "loss": 3.5077, "step": 1398272 }, { "epoch": 1.01, "learning_rate": 2.709981177478752e-05, "loss": 3.5022, "step": 1398784 }, { "epoch": 1.01, "learning_rate": 2.7091425827277e-05, "loss": 3.5165, "step": 1399296 }, { "epoch": 1.01, "learning_rate": 2.708303987976648e-05, "loss": 3.5103, "step": 1399808 }, { "epoch": 1.01, "learning_rate": 2.7074653932255963e-05, "loss": 3.5087, "step": 1400320 }, { "epoch": 1.01, "learning_rate": 2.7066284363549172e-05, "loss": 3.5025, "step": 1400832 }, { "epoch": 1.01, "learning_rate": 2.7057898416038652e-05, "loss": 3.5091, "step": 1401344 }, { "epoch": 1.01, "learning_rate": 2.704951246852813e-05, "loss": 3.4919, "step": 1401856 }, { "epoch": 1.01, "learning_rate": 2.704112652101761e-05, "loss": 3.5186, "step": 1402368 }, { "epoch": 1.01, "learning_rate": 2.7032756952310824e-05, "loss": 3.5097, "step": 1402880 }, { "epoch": 1.01, "learning_rate": 2.7024371004800304e-05, "loss": 3.5167, "step": 1403392 }, { "epoch": 1.01, "learning_rate": 2.7015985057289784e-05, "loss": 3.5193, "step": 1403904 }, { "epoch": 1.01, "learning_rate": 2.7007599109779264e-05, "loss": 3.5011, "step": 1404416 }, { "epoch": 1.01, "learning_rate": 2.6999229541072473e-05, "loss": 3.4994, "step": 1404928 }, { "epoch": 1.01, "learning_rate": 2.6990843593561953e-05, "loss": 3.5106, "step": 1405440 }, { "epoch": 1.01, "learning_rate": 2.6982457646051433e-05, "loss": 3.4991, "step": 1405952 }, { "epoch": 1.01, "learning_rate": 2.697407169854091e-05, "loss": 3.4975, "step": 1406464 }, { "epoch": 1.01, "learning_rate": 2.6965702129834125e-05, "loss": 3.5172, "step": 1406976 }, { "epoch": 1.01, "learning_rate": 2.6957316182323605e-05, "loss": 3.5175, "step": 1407488 }, { "epoch": 1.01, "learning_rate": 2.6948930234813085e-05, "loss": 3.5025, "step": 1408000 }, { "epoch": 1.01, "learning_rate": 2.6940544287302562e-05, "loss": 3.4956, "step": 1408512 }, { "epoch": 1.01, "learning_rate": 2.6932174718595778e-05, "loss": 3.4997, "step": 1409024 }, { "epoch": 1.01, "learning_rate": 2.6923788771085258e-05, "loss": 3.506, "step": 1409536 }, { "epoch": 1.01, "learning_rate": 2.6915402823574738e-05, "loss": 3.514, "step": 1410048 }, { "epoch": 1.01, "learning_rate": 2.690701687606421e-05, "loss": 3.5114, "step": 1410560 }, { "epoch": 1.01, "learning_rate": 2.6898647307357427e-05, "loss": 3.5188, "step": 1411072 }, { "epoch": 1.01, "learning_rate": 2.6890261359846907e-05, "loss": 3.5086, "step": 1411584 }, { "epoch": 1.01, "learning_rate": 2.6881875412336383e-05, "loss": 3.5181, "step": 1412096 }, { "epoch": 1.01, "learning_rate": 2.6873489464825863e-05, "loss": 3.5044, "step": 1412608 }, { "epoch": 1.01, "learning_rate": 2.686511989611908e-05, "loss": 3.5092, "step": 1413120 }, { "epoch": 1.01, "learning_rate": 2.685673394860856e-05, "loss": 3.5115, "step": 1413632 }, { "epoch": 1.01, "learning_rate": 2.6848348001098032e-05, "loss": 3.4993, "step": 1414144 }, { "epoch": 1.01, "learning_rate": 2.6839962053587516e-05, "loss": 3.5159, "step": 1414656 }, { "epoch": 1.01, "learning_rate": 2.683159248488073e-05, "loss": 3.5174, "step": 1415168 }, { "epoch": 1.01, "learning_rate": 2.682320653737021e-05, "loss": 3.5168, "step": 1415680 }, { "epoch": 1.01, "learning_rate": 2.6814820589859685e-05, "loss": 3.4971, "step": 1416192 }, { "epoch": 1.01, "learning_rate": 2.6806434642349165e-05, "loss": 3.4929, "step": 1416704 }, { "epoch": 1.01, "learning_rate": 2.679806507364238e-05, "loss": 3.5076, "step": 1417216 }, { "epoch": 1.01, "learning_rate": 2.6789679126131857e-05, "loss": 3.5018, "step": 1417728 }, { "epoch": 1.01, "learning_rate": 2.6781293178621337e-05, "loss": 3.5151, "step": 1418240 }, { "epoch": 1.01, "learning_rate": 2.6772907231110817e-05, "loss": 3.5075, "step": 1418752 }, { "epoch": 1.01, "learning_rate": 2.6764537662404033e-05, "loss": 3.5104, "step": 1419264 }, { "epoch": 1.02, "learning_rate": 2.6756151714893506e-05, "loss": 3.5052, "step": 1419776 }, { "epoch": 1.02, "learning_rate": 2.6747765767382986e-05, "loss": 3.4976, "step": 1420288 }, { "epoch": 1.02, "learning_rate": 2.673937981987247e-05, "loss": 3.5063, "step": 1420800 }, { "epoch": 1.02, "learning_rate": 2.6731010251165685e-05, "loss": 3.5036, "step": 1421312 }, { "epoch": 1.02, "learning_rate": 2.672262430365516e-05, "loss": 3.5197, "step": 1421824 }, { "epoch": 1.02, "learning_rate": 2.6714238356144638e-05, "loss": 3.5213, "step": 1422336 }, { "epoch": 1.02, "learning_rate": 2.6705852408634118e-05, "loss": 3.5148, "step": 1422848 }, { "epoch": 1.02, "learning_rate": 2.669748283992733e-05, "loss": 3.4977, "step": 1423360 }, { "epoch": 1.02, "learning_rate": 2.668909689241681e-05, "loss": 3.5144, "step": 1423872 }, { "epoch": 1.02, "learning_rate": 2.668071094490629e-05, "loss": 3.5056, "step": 1424384 }, { "epoch": 1.02, "learning_rate": 2.667232499739577e-05, "loss": 3.5156, "step": 1424896 }, { "epoch": 1.02, "learning_rate": 2.666395542868898e-05, "loss": 3.5023, "step": 1425408 }, { "epoch": 1.02, "learning_rate": 2.665556948117846e-05, "loss": 3.5056, "step": 1425920 }, { "epoch": 1.02, "learning_rate": 2.664718353366794e-05, "loss": 3.4972, "step": 1426432 }, { "epoch": 1.02, "learning_rate": 2.6638797586157423e-05, "loss": 3.5145, "step": 1426944 }, { "epoch": 1.02, "learning_rate": 2.6630428017450632e-05, "loss": 3.4919, "step": 1427456 }, { "epoch": 1.02, "learning_rate": 2.6622042069940112e-05, "loss": 3.5091, "step": 1427968 }, { "epoch": 1.02, "learning_rate": 2.6613656122429592e-05, "loss": 3.502, "step": 1428480 }, { "epoch": 1.02, "learning_rate": 2.6605270174919072e-05, "loss": 3.5061, "step": 1428992 }, { "epoch": 1.02, "learning_rate": 2.6596900606212284e-05, "loss": 3.501, "step": 1429504 }, { "epoch": 1.02, "learning_rate": 2.6588514658701764e-05, "loss": 3.5137, "step": 1430016 }, { "epoch": 1.02, "learning_rate": 2.6580128711191244e-05, "loss": 3.5086, "step": 1430528 }, { "epoch": 1.02, "learning_rate": 2.6571742763680724e-05, "loss": 3.5029, "step": 1431040 }, { "epoch": 1.02, "learning_rate": 2.6563373194973933e-05, "loss": 3.5154, "step": 1431552 }, { "epoch": 1.02, "learning_rate": 2.6554987247463413e-05, "loss": 3.4999, "step": 1432064 }, { "epoch": 1.02, "learning_rate": 2.6546601299952893e-05, "loss": 3.5206, "step": 1432576 }, { "epoch": 1.02, "learning_rate": 2.6538215352442373e-05, "loss": 3.5253, "step": 1433088 }, { "epoch": 1.02, "learning_rate": 2.6529845783735586e-05, "loss": 3.5029, "step": 1433600 }, { "epoch": 1.02, "learning_rate": 2.6521459836225066e-05, "loss": 3.5075, "step": 1434112 }, { "epoch": 1.02, "learning_rate": 2.6513073888714546e-05, "loss": 3.508, "step": 1434624 }, { "epoch": 1.02, "learning_rate": 2.6504687941204026e-05, "loss": 3.5055, "step": 1435136 }, { "epoch": 1.02, "learning_rate": 2.6496318372497238e-05, "loss": 3.5022, "step": 1435648 }, { "epoch": 1.02, "learning_rate": 2.6487932424986718e-05, "loss": 3.5021, "step": 1436160 }, { "epoch": 1.02, "learning_rate": 2.6479546477476198e-05, "loss": 3.4999, "step": 1436672 }, { "epoch": 1.02, "learning_rate": 2.6471160529965678e-05, "loss": 3.5156, "step": 1437184 }, { "epoch": 1.02, "learning_rate": 2.6462790961258887e-05, "loss": 3.5125, "step": 1437696 }, { "epoch": 1.02, "learning_rate": 2.6454405013748367e-05, "loss": 3.5093, "step": 1438208 }, { "epoch": 1.02, "learning_rate": 2.6446019066237847e-05, "loss": 3.5007, "step": 1438720 }, { "epoch": 1.02, "learning_rate": 2.6437633118727327e-05, "loss": 3.503, "step": 1439232 }, { "epoch": 1.02, "learning_rate": 2.642926355002054e-05, "loss": 3.5006, "step": 1439744 }, { "epoch": 1.02, "learning_rate": 2.642087760251002e-05, "loss": 3.5198, "step": 1440256 }, { "epoch": 1.02, "learning_rate": 2.64124916549995e-05, "loss": 3.5176, "step": 1440768 }, { "epoch": 1.02, "learning_rate": 2.640410570748898e-05, "loss": 3.5038, "step": 1441280 }, { "epoch": 1.02, "learning_rate": 2.639573613878219e-05, "loss": 3.5001, "step": 1441792 }, { "epoch": 1.02, "learning_rate": 2.638735019127167e-05, "loss": 3.5121, "step": 1442304 }, { "epoch": 1.02, "learning_rate": 2.637896424376115e-05, "loss": 3.5026, "step": 1442816 }, { "epoch": 1.02, "learning_rate": 2.637057829625063e-05, "loss": 3.5165, "step": 1443328 }, { "epoch": 1.02, "learning_rate": 2.636220872754384e-05, "loss": 3.4974, "step": 1443840 }, { "epoch": 1.02, "learning_rate": 2.635382278003332e-05, "loss": 3.5178, "step": 1444352 }, { "epoch": 1.02, "learning_rate": 2.63454368325228e-05, "loss": 3.5099, "step": 1444864 }, { "epoch": 1.02, "learning_rate": 2.633705088501228e-05, "loss": 3.5119, "step": 1445376 }, { "epoch": 1.02, "learning_rate": 2.6328681316305493e-05, "loss": 3.5107, "step": 1445888 }, { "epoch": 1.02, "learning_rate": 2.6320295368794973e-05, "loss": 3.5094, "step": 1446400 }, { "epoch": 1.02, "learning_rate": 2.6311909421284453e-05, "loss": 3.501, "step": 1446912 }, { "epoch": 1.02, "learning_rate": 2.6303523473773933e-05, "loss": 3.5058, "step": 1447424 }, { "epoch": 1.02, "learning_rate": 2.6295153905067142e-05, "loss": 3.5138, "step": 1447936 }, { "epoch": 1.02, "learning_rate": 2.6286767957556625e-05, "loss": 3.5043, "step": 1448448 }, { "epoch": 1.02, "learning_rate": 2.6278382010046105e-05, "loss": 3.5057, "step": 1448960 }, { "epoch": 1.02, "learning_rate": 2.6269996062535585e-05, "loss": 3.506, "step": 1449472 }, { "epoch": 1.02, "learning_rate": 2.6261626493828794e-05, "loss": 3.5065, "step": 1449984 }, { "epoch": 1.03, "eval_loss": 3.870774269104004, "eval_runtime": 307.7686, "eval_samples_per_second": 1239.863, "eval_steps_per_second": 38.747, "step": 1450080 }, { "epoch": 0.0, "learning_rate": 2.6253240546318274e-05, "loss": 3.4938, "step": 1450496 }, { "epoch": 0.0, "learning_rate": 2.6244854598807754e-05, "loss": 3.5035, "step": 1451008 }, { "epoch": 0.0, "learning_rate": 2.6236468651297234e-05, "loss": 3.5143, "step": 1451520 }, { "epoch": 0.0, "learning_rate": 2.6228082703786718e-05, "loss": 3.4996, "step": 1452032 }, { "epoch": 0.0, "learning_rate": 2.6219713135079927e-05, "loss": 3.5242, "step": 1452544 }, { "epoch": 0.0, "learning_rate": 2.6211327187569407e-05, "loss": 3.4947, "step": 1453056 }, { "epoch": 0.0, "learning_rate": 2.6202941240058887e-05, "loss": 3.5143, "step": 1453568 }, { "epoch": 0.0, "learning_rate": 2.6194555292548367e-05, "loss": 3.497, "step": 1454080 }, { "epoch": 0.0, "learning_rate": 2.6186202102645308e-05, "loss": 3.5076, "step": 1454592 }, { "epoch": 0.0, "learning_rate": 2.6177816155134788e-05, "loss": 3.5055, "step": 1455104 }, { "epoch": 0.0, "learning_rate": 2.6169430207624268e-05, "loss": 3.5005, "step": 1455616 }, { "epoch": 0.0, "learning_rate": 2.6161044260113748e-05, "loss": 3.5144, "step": 1456128 }, { "epoch": 0.0, "learning_rate": 2.6152658312603228e-05, "loss": 3.5002, "step": 1456640 }, { "epoch": 0.0, "learning_rate": 2.6144272365092708e-05, "loss": 3.4952, "step": 1457152 }, { "epoch": 0.0, "learning_rate": 2.6135886417582188e-05, "loss": 3.5019, "step": 1457664 }, { "epoch": 0.0, "learning_rate": 2.612750047007167e-05, "loss": 3.4916, "step": 1458176 }, { "epoch": 0.0, "learning_rate": 2.611913090136488e-05, "loss": 3.4997, "step": 1458688 }, { "epoch": 0.0, "learning_rate": 2.611074495385436e-05, "loss": 3.5023, "step": 1459200 }, { "epoch": 0.0, "learning_rate": 2.610235900634384e-05, "loss": 3.5014, "step": 1459712 }, { "epoch": 0.0, "learning_rate": 2.609397305883332e-05, "loss": 3.5241, "step": 1460224 }, { "epoch": 0.0, "learning_rate": 2.6085603490126533e-05, "loss": 3.5105, "step": 1460736 }, { "epoch": 0.0, "learning_rate": 2.6077217542616013e-05, "loss": 3.5117, "step": 1461248 }, { "epoch": 0.0, "learning_rate": 2.6068831595105493e-05, "loss": 3.5039, "step": 1461760 }, { "epoch": 0.0, "learning_rate": 2.6060445647594973e-05, "loss": 3.508, "step": 1462272 }, { "epoch": 0.0, "learning_rate": 2.605207607888818e-05, "loss": 3.5007, "step": 1462784 }, { "epoch": 0.0, "learning_rate": 2.604369013137766e-05, "loss": 3.5031, "step": 1463296 }, { "epoch": 0.0, "learning_rate": 2.603530418386714e-05, "loss": 3.5098, "step": 1463808 }, { "epoch": 0.0, "learning_rate": 2.6026918236356625e-05, "loss": 3.497, "step": 1464320 }, { "epoch": 0.0, "learning_rate": 2.6018548667649834e-05, "loss": 3.4895, "step": 1464832 }, { "epoch": 0.01, "learning_rate": 2.6010162720139314e-05, "loss": 3.4967, "step": 1465344 }, { "epoch": 0.01, "learning_rate": 2.6001776772628794e-05, "loss": 3.5098, "step": 1465856 }, { "epoch": 0.01, "learning_rate": 2.5993390825118274e-05, "loss": 3.5085, "step": 1466368 }, { "epoch": 0.01, "learning_rate": 2.5985021256411486e-05, "loss": 3.5105, "step": 1466880 }, { "epoch": 0.01, "learning_rate": 2.5976635308900966e-05, "loss": 3.5129, "step": 1467392 }, { "epoch": 0.01, "learning_rate": 2.5968249361390446e-05, "loss": 3.4931, "step": 1467904 }, { "epoch": 0.01, "learning_rate": 2.5959863413879926e-05, "loss": 3.5, "step": 1468416 }, { "epoch": 0.01, "learning_rate": 2.5951493845173135e-05, "loss": 3.4972, "step": 1468928 }, { "epoch": 0.01, "learning_rate": 2.5943107897662615e-05, "loss": 3.4953, "step": 1469440 }, { "epoch": 0.01, "learning_rate": 2.5934721950152095e-05, "loss": 3.4964, "step": 1469952 }, { "epoch": 0.01, "learning_rate": 2.592633600264158e-05, "loss": 3.4939, "step": 1470464 }, { "epoch": 0.01, "learning_rate": 2.5917966433934788e-05, "loss": 3.5024, "step": 1470976 }, { "epoch": 0.01, "learning_rate": 2.5909580486424268e-05, "loss": 3.5091, "step": 1471488 }, { "epoch": 0.01, "learning_rate": 2.5901194538913748e-05, "loss": 3.5041, "step": 1472000 }, { "epoch": 0.01, "learning_rate": 2.5892808591403228e-05, "loss": 3.4981, "step": 1472512 }, { "epoch": 0.01, "learning_rate": 2.588443902269644e-05, "loss": 3.5087, "step": 1473024 }, { "epoch": 0.01, "learning_rate": 2.587605307518592e-05, "loss": 3.494, "step": 1473536 }, { "epoch": 0.01, "learning_rate": 2.58676671276754e-05, "loss": 3.5001, "step": 1474048 }, { "epoch": 0.01, "learning_rate": 2.585928118016488e-05, "loss": 3.4975, "step": 1474560 }, { "epoch": 0.01, "learning_rate": 2.585091161145809e-05, "loss": 3.4854, "step": 1475072 }, { "epoch": 0.01, "learning_rate": 2.584252566394757e-05, "loss": 3.5046, "step": 1475584 }, { "epoch": 0.01, "learning_rate": 2.583413971643705e-05, "loss": 3.4963, "step": 1476096 }, { "epoch": 0.01, "learning_rate": 2.5825753768926532e-05, "loss": 3.5002, "step": 1476608 }, { "epoch": 0.01, "learning_rate": 2.581738420021974e-05, "loss": 3.4887, "step": 1477120 }, { "epoch": 0.01, "learning_rate": 2.580899825270922e-05, "loss": 3.494, "step": 1477632 }, { "epoch": 0.01, "learning_rate": 2.58006123051987e-05, "loss": 3.4814, "step": 1478144 }, { "epoch": 0.01, "learning_rate": 2.5792226357688178e-05, "loss": 3.5041, "step": 1478656 }, { "epoch": 0.01, "learning_rate": 2.5783856788981394e-05, "loss": 3.4982, "step": 1479168 }, { "epoch": 0.01, "learning_rate": 2.5775470841470874e-05, "loss": 3.5018, "step": 1479680 }, { "epoch": 0.01, "learning_rate": 2.5767084893960354e-05, "loss": 3.5048, "step": 1480192 }, { "epoch": 0.01, "learning_rate": 2.5758698946449827e-05, "loss": 3.4886, "step": 1480704 }, { "epoch": 0.01, "learning_rate": 2.5750329377743043e-05, "loss": 3.487, "step": 1481216 }, { "epoch": 0.01, "learning_rate": 2.5741943430232523e-05, "loss": 3.501, "step": 1481728 }, { "epoch": 0.01, "learning_rate": 2.5733557482722003e-05, "loss": 3.4871, "step": 1482240 }, { "epoch": 0.01, "learning_rate": 2.572517153521148e-05, "loss": 3.4843, "step": 1482752 }, { "epoch": 0.01, "learning_rate": 2.5716801966504695e-05, "loss": 3.5056, "step": 1483264 }, { "epoch": 0.01, "learning_rate": 2.5708416018994175e-05, "loss": 3.5039, "step": 1483776 }, { "epoch": 0.01, "learning_rate": 2.5700030071483648e-05, "loss": 3.4902, "step": 1484288 }, { "epoch": 0.01, "learning_rate": 2.569164412397313e-05, "loss": 3.488, "step": 1484800 }, { "epoch": 0.01, "learning_rate": 2.5683274555266344e-05, "loss": 3.4816, "step": 1485312 }, { "epoch": 0.01, "learning_rate": 2.5674888607755827e-05, "loss": 3.4882, "step": 1485824 }, { "epoch": 0.01, "learning_rate": 2.56665026602453e-05, "loss": 3.5039, "step": 1486336 }, { "epoch": 0.01, "learning_rate": 2.565811671273478e-05, "loss": 3.5022, "step": 1486848 }, { "epoch": 0.01, "learning_rate": 2.5649747144027996e-05, "loss": 3.5067, "step": 1487360 }, { "epoch": 0.01, "learning_rate": 2.5641361196517476e-05, "loss": 3.4943, "step": 1487872 }, { "epoch": 0.01, "learning_rate": 2.5632975249006953e-05, "loss": 3.513, "step": 1488384 }, { "epoch": 0.01, "learning_rate": 2.5624589301496433e-05, "loss": 3.4897, "step": 1488896 }, { "epoch": 0.01, "learning_rate": 2.561621973278965e-05, "loss": 3.4998, "step": 1489408 }, { "epoch": 0.01, "learning_rate": 2.5607833785279122e-05, "loss": 3.4973, "step": 1489920 }, { "epoch": 0.01, "learning_rate": 2.5599447837768602e-05, "loss": 3.4838, "step": 1490432 }, { "epoch": 0.01, "learning_rate": 2.5591061890258082e-05, "loss": 3.5088, "step": 1490944 }, { "epoch": 0.01, "learning_rate": 2.5582692321551298e-05, "loss": 3.5039, "step": 1491456 }, { "epoch": 0.01, "learning_rate": 2.5574306374040774e-05, "loss": 3.5013, "step": 1491968 }, { "epoch": 0.01, "learning_rate": 2.5565920426530254e-05, "loss": 3.4885, "step": 1492480 }, { "epoch": 0.01, "learning_rate": 2.555755085782347e-05, "loss": 3.4828, "step": 1492992 }, { "epoch": 0.01, "learning_rate": 2.554916491031295e-05, "loss": 3.4955, "step": 1493504 }, { "epoch": 0.01, "learning_rate": 2.5540778962802427e-05, "loss": 3.4945, "step": 1494016 }, { "epoch": 0.01, "learning_rate": 2.5532393015291906e-05, "loss": 3.5024, "step": 1494528 }, { "epoch": 0.01, "learning_rate": 2.5524023446585122e-05, "loss": 3.4918, "step": 1495040 }, { "epoch": 0.01, "learning_rate": 2.5515637499074596e-05, "loss": 3.5005, "step": 1495552 }, { "epoch": 0.02, "learning_rate": 2.5507251551564075e-05, "loss": 3.4913, "step": 1496064 }, { "epoch": 0.02, "learning_rate": 2.5498865604053555e-05, "loss": 3.4909, "step": 1496576 }, { "epoch": 0.02, "learning_rate": 2.549049603534677e-05, "loss": 3.4904, "step": 1497088 }, { "epoch": 0.02, "learning_rate": 2.5482110087836248e-05, "loss": 3.4886, "step": 1497600 }, { "epoch": 0.02, "learning_rate": 2.5473724140325728e-05, "loss": 3.5117, "step": 1498112 }, { "epoch": 0.02, "learning_rate": 2.5465338192815208e-05, "loss": 3.5071, "step": 1498624 }, { "epoch": 0.02, "learning_rate": 2.5456968624108424e-05, "loss": 3.5061, "step": 1499136 }, { "epoch": 0.02, "learning_rate": 2.5448582676597897e-05, "loss": 3.483, "step": 1499648 }, { "epoch": 0.02, "learning_rate": 2.544019672908738e-05, "loss": 3.5018, "step": 1500160 }, { "epoch": 0.02, "learning_rate": 2.543181078157686e-05, "loss": 3.4915, "step": 1500672 }, { "epoch": 0.02, "learning_rate": 2.542344121287007e-05, "loss": 3.5001, "step": 1501184 }, { "epoch": 0.02, "learning_rate": 2.541505526535955e-05, "loss": 3.4934, "step": 1501696 }, { "epoch": 0.02, "learning_rate": 2.540666931784903e-05, "loss": 3.4905, "step": 1502208 }, { "epoch": 0.02, "learning_rate": 2.539828337033851e-05, "loss": 3.4873, "step": 1502720 }, { "epoch": 0.02, "learning_rate": 2.538991380163172e-05, "loss": 3.5031, "step": 1503232 }, { "epoch": 0.02, "learning_rate": 2.53815278541212e-05, "loss": 3.4808, "step": 1503744 }, { "epoch": 0.02, "learning_rate": 2.537314190661068e-05, "loss": 3.4945, "step": 1504256 }, { "epoch": 0.02, "learning_rate": 2.536475595910016e-05, "loss": 3.4912, "step": 1504768 }, { "epoch": 0.02, "learning_rate": 2.535638639039337e-05, "loss": 3.4914, "step": 1505280 }, { "epoch": 0.02, "learning_rate": 2.534800044288285e-05, "loss": 3.4886, "step": 1505792 }, { "epoch": 0.02, "learning_rate": 2.5339614495372334e-05, "loss": 3.5044, "step": 1506304 }, { "epoch": 0.02, "learning_rate": 2.5331228547861814e-05, "loss": 3.4939, "step": 1506816 }, { "epoch": 0.02, "learning_rate": 2.5322858979155023e-05, "loss": 3.4908, "step": 1507328 }, { "epoch": 0.02, "learning_rate": 2.5314473031644503e-05, "loss": 3.5057, "step": 1507840 }, { "epoch": 0.02, "learning_rate": 2.5306087084133983e-05, "loss": 3.4911, "step": 1508352 }, { "epoch": 0.02, "learning_rate": 2.5297701136623463e-05, "loss": 3.503, "step": 1508864 }, { "epoch": 0.02, "learning_rate": 2.5289331567916675e-05, "loss": 3.5103, "step": 1509376 }, { "epoch": 0.02, "learning_rate": 2.5280945620406155e-05, "loss": 3.4948, "step": 1509888 }, { "epoch": 0.02, "learning_rate": 2.5272559672895635e-05, "loss": 3.4966, "step": 1510400 }, { "epoch": 0.02, "learning_rate": 2.5264173725385115e-05, "loss": 3.4938, "step": 1510912 }, { "epoch": 0.02, "learning_rate": 2.5255804156678324e-05, "loss": 3.4894, "step": 1511424 }, { "epoch": 0.02, "learning_rate": 2.5247418209167804e-05, "loss": 3.4921, "step": 1511936 }, { "epoch": 0.02, "learning_rate": 2.5239032261657288e-05, "loss": 3.496, "step": 1512448 }, { "epoch": 0.02, "learning_rate": 2.5230646314146767e-05, "loss": 3.4814, "step": 1512960 }, { "epoch": 0.02, "learning_rate": 2.5222276745439977e-05, "loss": 3.5049, "step": 1513472 }, { "epoch": 0.02, "learning_rate": 2.5213890797929457e-05, "loss": 3.5023, "step": 1513984 }, { "epoch": 0.02, "learning_rate": 2.5205504850418936e-05, "loss": 3.5005, "step": 1514496 }, { "epoch": 0.02, "learning_rate": 2.5197118902908416e-05, "loss": 3.486, "step": 1515008 }, { "epoch": 0.02, "learning_rate": 2.518874933420163e-05, "loss": 3.4916, "step": 1515520 }, { "epoch": 0.02, "learning_rate": 2.518036338669111e-05, "loss": 3.4913, "step": 1516032 }, { "epoch": 0.02, "learning_rate": 2.517197743918059e-05, "loss": 3.5023, "step": 1516544 }, { "epoch": 0.02, "learning_rate": 2.516359149167007e-05, "loss": 3.5073, "step": 1517056 }, { "epoch": 0.02, "learning_rate": 2.5155221922963278e-05, "loss": 3.4948, "step": 1517568 }, { "epoch": 0.02, "learning_rate": 2.5146835975452758e-05, "loss": 3.483, "step": 1518080 }, { "epoch": 0.02, "learning_rate": 2.513845002794224e-05, "loss": 3.4986, "step": 1518592 }, { "epoch": 0.02, "learning_rate": 2.513006408043172e-05, "loss": 3.4913, "step": 1519104 }, { "epoch": 0.02, "learning_rate": 2.512169451172493e-05, "loss": 3.5038, "step": 1519616 }, { "epoch": 0.02, "learning_rate": 2.511330856421441e-05, "loss": 3.4854, "step": 1520128 }, { "epoch": 0.02, "learning_rate": 2.510492261670389e-05, "loss": 3.5009, "step": 1520640 }, { "epoch": 0.02, "learning_rate": 2.509653666919337e-05, "loss": 3.4994, "step": 1521152 }, { "epoch": 0.02, "learning_rate": 2.5088167100486583e-05, "loss": 3.5041, "step": 1521664 }, { "epoch": 0.02, "learning_rate": 2.5079781152976063e-05, "loss": 3.4988, "step": 1522176 }, { "epoch": 0.02, "learning_rate": 2.5071395205465543e-05, "loss": 3.4951, "step": 1522688 }, { "epoch": 0.02, "learning_rate": 2.5063009257955022e-05, "loss": 3.4883, "step": 1523200 }, { "epoch": 0.02, "learning_rate": 2.505463968924823e-05, "loss": 3.4927, "step": 1523712 }, { "epoch": 0.02, "learning_rate": 2.504625374173771e-05, "loss": 3.4991, "step": 1524224 }, { "epoch": 0.02, "learning_rate": 2.5037867794227195e-05, "loss": 3.4966, "step": 1524736 }, { "epoch": 0.02, "learning_rate": 2.5029481846716675e-05, "loss": 3.4947, "step": 1525248 }, { "epoch": 0.02, "learning_rate": 2.5021112278009884e-05, "loss": 3.4985, "step": 1525760 }, { "epoch": 0.02, "learning_rate": 2.5012726330499364e-05, "loss": 3.4897, "step": 1526272 }, { "epoch": 0.03, "eval_loss": 3.8728060722351074, "eval_runtime": 307.3128, "eval_samples_per_second": 1241.702, "eval_steps_per_second": 38.804, "step": 1526400 }, { "epoch": 0.0, "learning_rate": 2.5004340382988844e-05, "loss": 3.4807, "step": 1526784 }, { "epoch": 0.0, "learning_rate": 2.4995954435478324e-05, "loss": 3.4937, "step": 1527296 }, { "epoch": 0.0, "learning_rate": 2.4987568487967804e-05, "loss": 3.4993, "step": 1527808 }, { "epoch": 0.0, "learning_rate": 2.4979182540457287e-05, "loss": 3.4895, "step": 1528320 }, { "epoch": 0.0, "learning_rate": 2.4970812971750496e-05, "loss": 3.5087, "step": 1528832 }, { "epoch": 0.0, "learning_rate": 2.4962427024239976e-05, "loss": 3.4891, "step": 1529344 }, { "epoch": 0.0, "learning_rate": 2.4954041076729456e-05, "loss": 3.4976, "step": 1529856 }, { "epoch": 0.0, "learning_rate": 2.4945655129218936e-05, "loss": 3.4865, "step": 1530368 }, { "epoch": 0.0, "learning_rate": 2.4937301939315878e-05, "loss": 3.4954, "step": 1530880 }, { "epoch": 0.0, "learning_rate": 2.4928915991805358e-05, "loss": 3.4943, "step": 1531392 }, { "epoch": 0.0, "learning_rate": 2.4920530044294838e-05, "loss": 3.4905, "step": 1531904 }, { "epoch": 0.0, "learning_rate": 2.4912144096784318e-05, "loss": 3.5018, "step": 1532416 }, { "epoch": 0.0, "learning_rate": 2.4903758149273797e-05, "loss": 3.4892, "step": 1532928 }, { "epoch": 0.0, "learning_rate": 2.4895372201763277e-05, "loss": 3.4828, "step": 1533440 }, { "epoch": 0.0, "learning_rate": 2.4886986254252757e-05, "loss": 3.4895, "step": 1533952 }, { "epoch": 0.0, "learning_rate": 2.4878600306742237e-05, "loss": 3.4804, "step": 1534464 }, { "epoch": 0.0, "learning_rate": 2.487023073803545e-05, "loss": 3.4873, "step": 1534976 }, { "epoch": 0.0, "learning_rate": 2.486184479052493e-05, "loss": 3.4881, "step": 1535488 }, { "epoch": 0.0, "learning_rate": 2.485345884301441e-05, "loss": 3.4881, "step": 1536000 }, { "epoch": 0.0, "learning_rate": 2.4845072895503886e-05, "loss": 3.5115, "step": 1536512 }, { "epoch": 0.0, "learning_rate": 2.4836703326797102e-05, "loss": 3.4964, "step": 1537024 }, { "epoch": 0.0, "learning_rate": 2.4828317379286582e-05, "loss": 3.5016, "step": 1537536 }, { "epoch": 0.0, "learning_rate": 2.481993143177606e-05, "loss": 3.4943, "step": 1538048 }, { "epoch": 0.0, "learning_rate": 2.481154548426554e-05, "loss": 3.4965, "step": 1538560 }, { "epoch": 0.0, "learning_rate": 2.480317591555875e-05, "loss": 3.4886, "step": 1539072 }, { "epoch": 0.0, "learning_rate": 2.479478996804823e-05, "loss": 3.4977, "step": 1539584 }, { "epoch": 0.0, "learning_rate": 2.478640402053771e-05, "loss": 3.4952, "step": 1540096 }, { "epoch": 0.0, "learning_rate": 2.477801807302719e-05, "loss": 3.486, "step": 1540608 }, { "epoch": 0.0, "learning_rate": 2.4769648504320404e-05, "loss": 3.4798, "step": 1541120 }, { "epoch": 0.0, "learning_rate": 2.4761262556809883e-05, "loss": 3.4835, "step": 1541632 }, { "epoch": 0.01, "learning_rate": 2.475287660929936e-05, "loss": 3.4934, "step": 1542144 }, { "epoch": 0.01, "learning_rate": 2.474449066178884e-05, "loss": 3.4971, "step": 1542656 }, { "epoch": 0.01, "learning_rate": 2.4736121093082052e-05, "loss": 3.4989, "step": 1543168 }, { "epoch": 0.01, "learning_rate": 2.4727735145571532e-05, "loss": 3.4987, "step": 1543680 }, { "epoch": 0.01, "learning_rate": 2.4719349198061012e-05, "loss": 3.4802, "step": 1544192 }, { "epoch": 0.01, "learning_rate": 2.4710963250550492e-05, "loss": 3.4898, "step": 1544704 }, { "epoch": 0.01, "learning_rate": 2.4702593681843705e-05, "loss": 3.4869, "step": 1545216 }, { "epoch": 0.01, "learning_rate": 2.469420773433318e-05, "loss": 3.4817, "step": 1545728 }, { "epoch": 0.01, "learning_rate": 2.4685821786822665e-05, "loss": 3.4868, "step": 1546240 }, { "epoch": 0.01, "learning_rate": 2.4677435839312145e-05, "loss": 3.4815, "step": 1546752 }, { "epoch": 0.01, "learning_rate": 2.4669066270605357e-05, "loss": 3.4949, "step": 1547264 }, { "epoch": 0.01, "learning_rate": 2.4660680323094834e-05, "loss": 3.4949, "step": 1547776 }, { "epoch": 0.01, "learning_rate": 2.4652294375584314e-05, "loss": 3.4936, "step": 1548288 }, { "epoch": 0.01, "learning_rate": 2.4643908428073794e-05, "loss": 3.4854, "step": 1548800 }, { "epoch": 0.01, "learning_rate": 2.4635538859367006e-05, "loss": 3.4998, "step": 1549312 }, { "epoch": 0.01, "learning_rate": 2.4627152911856486e-05, "loss": 3.4816, "step": 1549824 }, { "epoch": 0.01, "learning_rate": 2.4618766964345966e-05, "loss": 3.4907, "step": 1550336 }, { "epoch": 0.01, "learning_rate": 2.4610381016835446e-05, "loss": 3.4836, "step": 1550848 }, { "epoch": 0.01, "learning_rate": 2.4602011448128655e-05, "loss": 3.4723, "step": 1551360 }, { "epoch": 0.01, "learning_rate": 2.4593625500618135e-05, "loss": 3.4981, "step": 1551872 }, { "epoch": 0.01, "learning_rate": 2.458523955310762e-05, "loss": 3.4846, "step": 1552384 }, { "epoch": 0.01, "learning_rate": 2.45768536055971e-05, "loss": 3.4863, "step": 1552896 }, { "epoch": 0.01, "learning_rate": 2.4568484036890307e-05, "loss": 3.4814, "step": 1553408 }, { "epoch": 0.01, "learning_rate": 2.4560098089379787e-05, "loss": 3.479, "step": 1553920 }, { "epoch": 0.01, "learning_rate": 2.4551712141869267e-05, "loss": 3.4715, "step": 1554432 }, { "epoch": 0.01, "learning_rate": 2.4543326194358747e-05, "loss": 3.4855, "step": 1554944 }, { "epoch": 0.01, "learning_rate": 2.453495662565196e-05, "loss": 3.4896, "step": 1555456 }, { "epoch": 0.01, "learning_rate": 2.452657067814144e-05, "loss": 3.4894, "step": 1555968 }, { "epoch": 0.01, "learning_rate": 2.451818473063092e-05, "loss": 3.4939, "step": 1556480 }, { "epoch": 0.01, "learning_rate": 2.45097987831204e-05, "loss": 3.4812, "step": 1556992 }, { "epoch": 0.01, "learning_rate": 2.450142921441361e-05, "loss": 3.4731, "step": 1557504 }, { "epoch": 0.01, "learning_rate": 2.449304326690309e-05, "loss": 3.4909, "step": 1558016 }, { "epoch": 0.01, "learning_rate": 2.4484657319392572e-05, "loss": 3.4732, "step": 1558528 }, { "epoch": 0.01, "learning_rate": 2.4476271371882052e-05, "loss": 3.4711, "step": 1559040 }, { "epoch": 0.01, "learning_rate": 2.446790180317526e-05, "loss": 3.4962, "step": 1559552 }, { "epoch": 0.01, "learning_rate": 2.445951585566474e-05, "loss": 3.4884, "step": 1560064 }, { "epoch": 0.01, "learning_rate": 2.445112990815422e-05, "loss": 3.4813, "step": 1560576 }, { "epoch": 0.01, "learning_rate": 2.44427439606437e-05, "loss": 3.4761, "step": 1561088 }, { "epoch": 0.01, "learning_rate": 2.4434374391936913e-05, "loss": 3.4695, "step": 1561600 }, { "epoch": 0.01, "learning_rate": 2.4425988444426393e-05, "loss": 3.4787, "step": 1562112 }, { "epoch": 0.01, "learning_rate": 2.4417602496915873e-05, "loss": 3.4967, "step": 1562624 }, { "epoch": 0.01, "learning_rate": 2.4409216549405353e-05, "loss": 3.4879, "step": 1563136 }, { "epoch": 0.01, "learning_rate": 2.4400846980698562e-05, "loss": 3.4942, "step": 1563648 }, { "epoch": 0.01, "learning_rate": 2.4392461033188042e-05, "loss": 3.4824, "step": 1564160 }, { "epoch": 0.01, "learning_rate": 2.4384075085677526e-05, "loss": 3.503, "step": 1564672 }, { "epoch": 0.01, "learning_rate": 2.4375689138167006e-05, "loss": 3.4786, "step": 1565184 }, { "epoch": 0.01, "learning_rate": 2.4367319569460215e-05, "loss": 3.4897, "step": 1565696 }, { "epoch": 0.01, "learning_rate": 2.4358933621949695e-05, "loss": 3.4865, "step": 1566208 }, { "epoch": 0.01, "learning_rate": 2.4350547674439175e-05, "loss": 3.4666, "step": 1566720 }, { "epoch": 0.01, "learning_rate": 2.4342161726928655e-05, "loss": 3.5007, "step": 1567232 }, { "epoch": 0.01, "learning_rate": 2.4333792158221867e-05, "loss": 3.4914, "step": 1567744 }, { "epoch": 0.01, "learning_rate": 2.4325406210711347e-05, "loss": 3.4886, "step": 1568256 }, { "epoch": 0.01, "learning_rate": 2.4317020263200827e-05, "loss": 3.4774, "step": 1568768 }, { "epoch": 0.01, "learning_rate": 2.4308634315690307e-05, "loss": 3.4691, "step": 1569280 }, { "epoch": 0.01, "learning_rate": 2.4300264746983516e-05, "loss": 3.4835, "step": 1569792 }, { "epoch": 0.01, "learning_rate": 2.4291878799472996e-05, "loss": 3.4816, "step": 1570304 }, { "epoch": 0.01, "learning_rate": 2.4283492851962476e-05, "loss": 3.4907, "step": 1570816 }, { "epoch": 0.01, "learning_rate": 2.4275106904451956e-05, "loss": 3.4818, "step": 1571328 }, { "epoch": 0.01, "learning_rate": 2.426673733574517e-05, "loss": 3.4862, "step": 1571840 }, { "epoch": 0.02, "learning_rate": 2.425835138823465e-05, "loss": 3.4809, "step": 1572352 }, { "epoch": 0.02, "learning_rate": 2.424996544072413e-05, "loss": 3.4826, "step": 1572864 }, { "epoch": 0.02, "learning_rate": 2.4241579493213605e-05, "loss": 3.477, "step": 1573376 }, { "epoch": 0.02, "learning_rate": 2.423320992450682e-05, "loss": 3.4789, "step": 1573888 }, { "epoch": 0.02, "learning_rate": 2.42248239769963e-05, "loss": 3.4938, "step": 1574400 }, { "epoch": 0.02, "learning_rate": 2.421643802948578e-05, "loss": 3.4956, "step": 1574912 }, { "epoch": 0.02, "learning_rate": 2.4208052081975257e-05, "loss": 3.4992, "step": 1575424 }, { "epoch": 0.02, "learning_rate": 2.419968251326847e-05, "loss": 3.4714, "step": 1575936 }, { "epoch": 0.02, "learning_rate": 2.419129656575795e-05, "loss": 3.4898, "step": 1576448 }, { "epoch": 0.02, "learning_rate": 2.418291061824743e-05, "loss": 3.4825, "step": 1576960 }, { "epoch": 0.02, "learning_rate": 2.417452467073691e-05, "loss": 3.4875, "step": 1577472 }, { "epoch": 0.02, "learning_rate": 2.4166155102030122e-05, "loss": 3.4815, "step": 1577984 }, { "epoch": 0.02, "learning_rate": 2.4157769154519602e-05, "loss": 3.476, "step": 1578496 }, { "epoch": 0.02, "learning_rate": 2.414938320700908e-05, "loss": 3.4789, "step": 1579008 }, { "epoch": 0.02, "learning_rate": 2.414099725949856e-05, "loss": 3.4906, "step": 1579520 }, { "epoch": 0.02, "learning_rate": 2.4132627690791774e-05, "loss": 3.4692, "step": 1580032 }, { "epoch": 0.02, "learning_rate": 2.4124241743281254e-05, "loss": 3.4807, "step": 1580544 }, { "epoch": 0.02, "learning_rate": 2.411585579577073e-05, "loss": 3.4777, "step": 1581056 }, { "epoch": 0.02, "learning_rate": 2.410746984826021e-05, "loss": 3.487, "step": 1581568 }, { "epoch": 0.02, "learning_rate": 2.4099100279553423e-05, "loss": 3.4763, "step": 1582080 }, { "epoch": 0.02, "learning_rate": 2.4090714332042903e-05, "loss": 3.4889, "step": 1582592 }, { "epoch": 0.02, "learning_rate": 2.4082328384532383e-05, "loss": 3.4841, "step": 1583104 }, { "epoch": 0.02, "learning_rate": 2.4073942437021863e-05, "loss": 3.4786, "step": 1583616 }, { "epoch": 0.02, "learning_rate": 2.4065572868315076e-05, "loss": 3.4917, "step": 1584128 }, { "epoch": 0.02, "learning_rate": 2.4057186920804552e-05, "loss": 3.4797, "step": 1584640 }, { "epoch": 0.02, "learning_rate": 2.4048800973294032e-05, "loss": 3.4917, "step": 1585152 }, { "epoch": 0.02, "learning_rate": 2.4040415025783512e-05, "loss": 3.4965, "step": 1585664 }, { "epoch": 0.02, "learning_rate": 2.4032045457076728e-05, "loss": 3.4822, "step": 1586176 }, { "epoch": 0.02, "learning_rate": 2.4023659509566205e-05, "loss": 3.4835, "step": 1586688 }, { "epoch": 0.02, "learning_rate": 2.4015273562055685e-05, "loss": 3.4857, "step": 1587200 }, { "epoch": 0.02, "learning_rate": 2.4006903993348897e-05, "loss": 3.4794, "step": 1587712 }, { "epoch": 0.02, "learning_rate": 2.3998518045838374e-05, "loss": 3.4804, "step": 1588224 }, { "epoch": 0.02, "learning_rate": 2.3990132098327857e-05, "loss": 3.4823, "step": 1588736 }, { "epoch": 0.02, "learning_rate": 2.3981746150817337e-05, "loss": 3.4732, "step": 1589248 }, { "epoch": 0.02, "learning_rate": 2.397337658211055e-05, "loss": 3.492, "step": 1589760 }, { "epoch": 0.02, "learning_rate": 2.3964990634600026e-05, "loss": 3.4887, "step": 1590272 }, { "epoch": 0.02, "learning_rate": 2.3956604687089506e-05, "loss": 3.4898, "step": 1590784 }, { "epoch": 0.02, "learning_rate": 2.3948218739578986e-05, "loss": 3.4764, "step": 1591296 }, { "epoch": 0.02, "learning_rate": 2.39398491708722e-05, "loss": 3.4796, "step": 1591808 }, { "epoch": 0.02, "learning_rate": 2.393146322336168e-05, "loss": 3.4824, "step": 1592320 }, { "epoch": 0.02, "learning_rate": 2.392307727585116e-05, "loss": 3.4868, "step": 1592832 }, { "epoch": 0.02, "learning_rate": 2.391469132834064e-05, "loss": 3.4933, "step": 1593344 }, { "epoch": 0.02, "learning_rate": 2.3906321759633847e-05, "loss": 3.486, "step": 1593856 }, { "epoch": 0.02, "learning_rate": 2.3897935812123327e-05, "loss": 3.4698, "step": 1594368 }, { "epoch": 0.02, "learning_rate": 2.388954986461281e-05, "loss": 3.4901, "step": 1594880 }, { "epoch": 0.02, "learning_rate": 2.388116391710229e-05, "loss": 3.4802, "step": 1595392 }, { "epoch": 0.02, "learning_rate": 2.38727943483955e-05, "loss": 3.4912, "step": 1595904 }, { "epoch": 0.02, "learning_rate": 2.386440840088498e-05, "loss": 3.473, "step": 1596416 }, { "epoch": 0.02, "learning_rate": 2.385602245337446e-05, "loss": 3.4906, "step": 1596928 }, { "epoch": 0.02, "learning_rate": 2.384763650586394e-05, "loss": 3.4868, "step": 1597440 }, { "epoch": 0.02, "learning_rate": 2.3839266937157152e-05, "loss": 3.4952, "step": 1597952 }, { "epoch": 0.02, "learning_rate": 2.3830880989646632e-05, "loss": 3.4856, "step": 1598464 }, { "epoch": 0.02, "learning_rate": 2.3822495042136112e-05, "loss": 3.4841, "step": 1598976 }, { "epoch": 0.02, "learning_rate": 2.3814109094625592e-05, "loss": 3.4752, "step": 1599488 }, { "epoch": 0.02, "learning_rate": 2.38057395259188e-05, "loss": 3.4838, "step": 1600000 }, { "epoch": 0.02, "learning_rate": 2.379735357840828e-05, "loss": 3.4843, "step": 1600512 }, { "epoch": 0.02, "learning_rate": 2.378896763089776e-05, "loss": 3.486, "step": 1601024 }, { "epoch": 0.02, "learning_rate": 2.3780581683387244e-05, "loss": 3.4829, "step": 1601536 }, { "epoch": 0.02, "learning_rate": 2.3772212114680453e-05, "loss": 3.4807, "step": 1602048 }, { "epoch": 0.02, "learning_rate": 2.3763826167169933e-05, "loss": 3.4823, "step": 1602560 }, { "epoch": 0.03, "eval_loss": 3.8738698959350586, "eval_runtime": 315.4575, "eval_samples_per_second": 1209.643, "eval_steps_per_second": 37.802, "step": 1602720 }, { "epoch": 1.0, "learning_rate": 2.3755440219659413e-05, "loss": 3.4778, "step": 1603072 }, { "epoch": 1.0, "learning_rate": 2.3747054272148893e-05, "loss": 3.477, "step": 1603584 }, { "epoch": 1.0, "learning_rate": 2.3738684703442106e-05, "loss": 3.4902, "step": 1604096 }, { "epoch": 1.0, "learning_rate": 2.3730298755931586e-05, "loss": 3.4785, "step": 1604608 }, { "epoch": 1.0, "learning_rate": 2.3721912808421066e-05, "loss": 3.4938, "step": 1605120 }, { "epoch": 1.0, "learning_rate": 2.3713526860910546e-05, "loss": 3.479, "step": 1605632 }, { "epoch": 1.0, "learning_rate": 2.3705157292203755e-05, "loss": 3.4823, "step": 1606144 }, { "epoch": 1.0, "learning_rate": 2.3696771344693235e-05, "loss": 3.4789, "step": 1606656 }, { "epoch": 1.0, "learning_rate": 2.3688401775986447e-05, "loss": 3.4811, "step": 1607168 }, { "epoch": 1.0, "learning_rate": 2.3680015828475927e-05, "loss": 3.4815, "step": 1607680 }, { "epoch": 1.0, "learning_rate": 2.3671629880965407e-05, "loss": 3.484, "step": 1608192 }, { "epoch": 1.0, "learning_rate": 2.3663243933454887e-05, "loss": 3.488, "step": 1608704 }, { "epoch": 1.0, "learning_rate": 2.3654857985944367e-05, "loss": 3.4778, "step": 1609216 }, { "epoch": 1.0, "learning_rate": 2.3646472038433847e-05, "loss": 3.4706, "step": 1609728 }, { "epoch": 1.0, "learning_rate": 2.3638086090923327e-05, "loss": 3.481, "step": 1610240 }, { "epoch": 1.0, "learning_rate": 2.3629700143412807e-05, "loss": 3.4671, "step": 1610752 }, { "epoch": 1.0, "learning_rate": 2.362133057470602e-05, "loss": 3.4756, "step": 1611264 }, { "epoch": 1.0, "learning_rate": 2.36129446271955e-05, "loss": 3.4765, "step": 1611776 }, { "epoch": 1.0, "learning_rate": 2.3604558679684976e-05, "loss": 3.4769, "step": 1612288 }, { "epoch": 1.0, "learning_rate": 2.3596172732174456e-05, "loss": 3.5001, "step": 1612800 }, { "epoch": 1.0, "learning_rate": 2.358780316346767e-05, "loss": 3.4876, "step": 1613312 }, { "epoch": 1.0, "learning_rate": 2.357941721595715e-05, "loss": 3.4916, "step": 1613824 }, { "epoch": 1.0, "learning_rate": 2.3571031268446628e-05, "loss": 3.4797, "step": 1614336 }, { "epoch": 1.0, "learning_rate": 2.3562645320936108e-05, "loss": 3.4845, "step": 1614848 }, { "epoch": 1.0, "learning_rate": 2.355427575222932e-05, "loss": 3.4778, "step": 1615360 }, { "epoch": 1.0, "learning_rate": 2.3545889804718797e-05, "loss": 3.486, "step": 1615872 }, { "epoch": 1.0, "learning_rate": 2.353750385720828e-05, "loss": 3.481, "step": 1616384 }, { "epoch": 1.0, "learning_rate": 2.352911790969776e-05, "loss": 3.4778, "step": 1616896 }, { "epoch": 1.0, "learning_rate": 2.3520748340990973e-05, "loss": 3.4716, "step": 1617408 }, { "epoch": 1.0, "learning_rate": 2.351236239348045e-05, "loss": 3.4732, "step": 1617920 }, { "epoch": 1.01, "learning_rate": 2.350397644596993e-05, "loss": 3.4795, "step": 1618432 }, { "epoch": 1.01, "learning_rate": 2.349559049845941e-05, "loss": 3.4872, "step": 1618944 }, { "epoch": 1.01, "learning_rate": 2.3487220929752622e-05, "loss": 3.4831, "step": 1619456 }, { "epoch": 1.01, "learning_rate": 2.3478834982242102e-05, "loss": 3.4896, "step": 1619968 }, { "epoch": 1.01, "learning_rate": 2.3470449034731582e-05, "loss": 3.4695, "step": 1620480 }, { "epoch": 1.01, "learning_rate": 2.3462063087221062e-05, "loss": 3.4791, "step": 1620992 }, { "epoch": 1.01, "learning_rate": 2.345369351851427e-05, "loss": 3.4749, "step": 1621504 }, { "epoch": 1.01, "learning_rate": 2.344530757100375e-05, "loss": 3.47, "step": 1622016 }, { "epoch": 1.01, "learning_rate": 2.3436921623493234e-05, "loss": 3.4788, "step": 1622528 }, { "epoch": 1.01, "learning_rate": 2.3428535675982714e-05, "loss": 3.4644, "step": 1623040 }, { "epoch": 1.01, "learning_rate": 2.3420166107275923e-05, "loss": 3.482, "step": 1623552 }, { "epoch": 1.01, "learning_rate": 2.3411780159765403e-05, "loss": 3.4843, "step": 1624064 }, { "epoch": 1.01, "learning_rate": 2.3403394212254883e-05, "loss": 3.4835, "step": 1624576 }, { "epoch": 1.01, "learning_rate": 2.3395008264744363e-05, "loss": 3.4772, "step": 1625088 }, { "epoch": 1.01, "learning_rate": 2.3386638696037576e-05, "loss": 3.4886, "step": 1625600 }, { "epoch": 1.01, "learning_rate": 2.3378252748527056e-05, "loss": 3.4678, "step": 1626112 }, { "epoch": 1.01, "learning_rate": 2.3369866801016536e-05, "loss": 3.4815, "step": 1626624 }, { "epoch": 1.01, "learning_rate": 2.3361480853506016e-05, "loss": 3.4732, "step": 1627136 }, { "epoch": 1.01, "learning_rate": 2.3353111284799225e-05, "loss": 3.4554, "step": 1627648 }, { "epoch": 1.01, "learning_rate": 2.3344725337288705e-05, "loss": 3.4905, "step": 1628160 }, { "epoch": 1.01, "learning_rate": 2.3336339389778185e-05, "loss": 3.4711, "step": 1628672 }, { "epoch": 1.01, "learning_rate": 2.3327953442267668e-05, "loss": 3.4807, "step": 1629184 }, { "epoch": 1.01, "learning_rate": 2.3319583873560877e-05, "loss": 3.4659, "step": 1629696 }, { "epoch": 1.01, "learning_rate": 2.3311197926050357e-05, "loss": 3.4663, "step": 1630208 }, { "epoch": 1.01, "learning_rate": 2.3302811978539837e-05, "loss": 3.4641, "step": 1630720 }, { "epoch": 1.01, "learning_rate": 2.3294426031029317e-05, "loss": 3.472, "step": 1631232 }, { "epoch": 1.01, "learning_rate": 2.3286040083518797e-05, "loss": 3.4798, "step": 1631744 }, { "epoch": 1.01, "learning_rate": 2.3277654136008277e-05, "loss": 3.4753, "step": 1632256 }, { "epoch": 1.01, "learning_rate": 2.3269268188497757e-05, "loss": 3.484, "step": 1632768 }, { "epoch": 1.01, "learning_rate": 2.326089861979097e-05, "loss": 3.469, "step": 1633280 }, { "epoch": 1.01, "learning_rate": 2.325251267228045e-05, "loss": 3.4616, "step": 1633792 }, { "epoch": 1.01, "learning_rate": 2.3244126724769926e-05, "loss": 3.4792, "step": 1634304 }, { "epoch": 1.01, "learning_rate": 2.3235740777259406e-05, "loss": 3.4593, "step": 1634816 }, { "epoch": 1.01, "learning_rate": 2.322737120855262e-05, "loss": 3.4595, "step": 1635328 }, { "epoch": 1.01, "learning_rate": 2.32189852610421e-05, "loss": 3.4832, "step": 1635840 }, { "epoch": 1.01, "learning_rate": 2.3210599313531578e-05, "loss": 3.4783, "step": 1636352 }, { "epoch": 1.01, "learning_rate": 2.3202213366021058e-05, "loss": 3.4685, "step": 1636864 }, { "epoch": 1.01, "learning_rate": 2.319384379731427e-05, "loss": 3.4685, "step": 1637376 }, { "epoch": 1.01, "learning_rate": 2.318545784980375e-05, "loss": 3.4597, "step": 1637888 }, { "epoch": 1.01, "learning_rate": 2.317707190229323e-05, "loss": 3.4651, "step": 1638400 }, { "epoch": 1.01, "learning_rate": 2.316868595478271e-05, "loss": 3.4806, "step": 1638912 }, { "epoch": 1.01, "learning_rate": 2.3160316386075923e-05, "loss": 3.4766, "step": 1639424 }, { "epoch": 1.01, "learning_rate": 2.31519304385654e-05, "loss": 3.4814, "step": 1639936 }, { "epoch": 1.01, "learning_rate": 2.314354449105488e-05, "loss": 3.4728, "step": 1640448 }, { "epoch": 1.01, "learning_rate": 2.313515854354436e-05, "loss": 3.4869, "step": 1640960 }, { "epoch": 1.01, "learning_rate": 2.3126788974837575e-05, "loss": 3.4686, "step": 1641472 }, { "epoch": 1.01, "learning_rate": 2.3118403027327052e-05, "loss": 3.4792, "step": 1641984 }, { "epoch": 1.01, "learning_rate": 2.3110017079816532e-05, "loss": 3.473, "step": 1642496 }, { "epoch": 1.01, "learning_rate": 2.3101631132306012e-05, "loss": 3.4573, "step": 1643008 }, { "epoch": 1.01, "learning_rate": 2.309326156359922e-05, "loss": 3.4855, "step": 1643520 }, { "epoch": 1.01, "learning_rate": 2.3084875616088704e-05, "loss": 3.4814, "step": 1644032 }, { "epoch": 1.01, "learning_rate": 2.3076489668578184e-05, "loss": 3.4778, "step": 1644544 }, { "epoch": 1.01, "learning_rate": 2.3068103721067664e-05, "loss": 3.4691, "step": 1645056 }, { "epoch": 1.01, "learning_rate": 2.3059734152360873e-05, "loss": 3.4632, "step": 1645568 }, { "epoch": 1.01, "learning_rate": 2.3051348204850353e-05, "loss": 3.4664, "step": 1646080 }, { "epoch": 1.01, "learning_rate": 2.3042962257339833e-05, "loss": 3.4719, "step": 1646592 }, { "epoch": 1.01, "learning_rate": 2.3034576309829313e-05, "loss": 3.4811, "step": 1647104 }, { "epoch": 1.01, "learning_rate": 2.3026206741122526e-05, "loss": 3.4683, "step": 1647616 }, { "epoch": 1.01, "learning_rate": 2.3017820793612005e-05, "loss": 3.4762, "step": 1648128 }, { "epoch": 1.02, "learning_rate": 2.3009434846101485e-05, "loss": 3.4676, "step": 1648640 }, { "epoch": 1.02, "learning_rate": 2.3001048898590965e-05, "loss": 3.4731, "step": 1649152 }, { "epoch": 1.02, "learning_rate": 2.2992679329884174e-05, "loss": 3.4662, "step": 1649664 }, { "epoch": 1.02, "learning_rate": 2.2984293382373658e-05, "loss": 3.4684, "step": 1650176 }, { "epoch": 1.02, "learning_rate": 2.2975907434863138e-05, "loss": 3.4839, "step": 1650688 }, { "epoch": 1.02, "learning_rate": 2.2967521487352618e-05, "loss": 3.4864, "step": 1651200 }, { "epoch": 1.02, "learning_rate": 2.2959151918645827e-05, "loss": 3.4849, "step": 1651712 }, { "epoch": 1.02, "learning_rate": 2.2950765971135307e-05, "loss": 3.4582, "step": 1652224 }, { "epoch": 1.02, "learning_rate": 2.2942380023624787e-05, "loss": 3.4798, "step": 1652736 }, { "epoch": 1.02, "learning_rate": 2.2933994076114267e-05, "loss": 3.4673, "step": 1653248 }, { "epoch": 1.02, "learning_rate": 2.292562450740748e-05, "loss": 3.482, "step": 1653760 }, { "epoch": 1.02, "learning_rate": 2.291723855989696e-05, "loss": 3.4687, "step": 1654272 }, { "epoch": 1.02, "learning_rate": 2.290885261238644e-05, "loss": 3.4706, "step": 1654784 }, { "epoch": 1.02, "learning_rate": 2.290046666487592e-05, "loss": 3.4639, "step": 1655296 }, { "epoch": 1.02, "learning_rate": 2.2892097096169128e-05, "loss": 3.478, "step": 1655808 }, { "epoch": 1.02, "learning_rate": 2.2883711148658608e-05, "loss": 3.4595, "step": 1656320 }, { "epoch": 1.02, "learning_rate": 2.287532520114809e-05, "loss": 3.4736, "step": 1656832 }, { "epoch": 1.02, "learning_rate": 2.286693925363757e-05, "loss": 3.4606, "step": 1657344 }, { "epoch": 1.02, "learning_rate": 2.285856968493078e-05, "loss": 3.4776, "step": 1657856 }, { "epoch": 1.02, "learning_rate": 2.285018373742026e-05, "loss": 3.4686, "step": 1658368 }, { "epoch": 1.02, "learning_rate": 2.284179778990974e-05, "loss": 3.4734, "step": 1658880 }, { "epoch": 1.02, "learning_rate": 2.283341184239922e-05, "loss": 3.472, "step": 1659392 }, { "epoch": 1.02, "learning_rate": 2.2825042273692433e-05, "loss": 3.4737, "step": 1659904 }, { "epoch": 1.02, "learning_rate": 2.2816656326181913e-05, "loss": 3.4756, "step": 1660416 }, { "epoch": 1.02, "learning_rate": 2.2808270378671393e-05, "loss": 3.4712, "step": 1660928 }, { "epoch": 1.02, "learning_rate": 2.2799884431160873e-05, "loss": 3.4751, "step": 1661440 }, { "epoch": 1.02, "learning_rate": 2.2791514862454082e-05, "loss": 3.4906, "step": 1661952 }, { "epoch": 1.02, "learning_rate": 2.2783128914943562e-05, "loss": 3.4714, "step": 1662464 }, { "epoch": 1.02, "learning_rate": 2.2774742967433045e-05, "loss": 3.4696, "step": 1662976 }, { "epoch": 1.02, "learning_rate": 2.2766357019922525e-05, "loss": 3.4748, "step": 1663488 }, { "epoch": 1.02, "learning_rate": 2.2757987451215734e-05, "loss": 3.469, "step": 1664000 }, { "epoch": 1.02, "learning_rate": 2.2749601503705214e-05, "loss": 3.4631, "step": 1664512 }, { "epoch": 1.02, "learning_rate": 2.2741215556194694e-05, "loss": 3.4742, "step": 1665024 }, { "epoch": 1.02, "learning_rate": 2.2732829608684174e-05, "loss": 3.4605, "step": 1665536 }, { "epoch": 1.02, "learning_rate": 2.2724460039977387e-05, "loss": 3.4809, "step": 1666048 }, { "epoch": 1.02, "learning_rate": 2.2716074092466866e-05, "loss": 3.4807, "step": 1666560 }, { "epoch": 1.02, "learning_rate": 2.2707688144956346e-05, "loss": 3.4756, "step": 1667072 }, { "epoch": 1.02, "learning_rate": 2.2699318576249556e-05, "loss": 3.4694, "step": 1667584 }, { "epoch": 1.02, "learning_rate": 2.2690932628739035e-05, "loss": 3.4672, "step": 1668096 }, { "epoch": 1.02, "learning_rate": 2.2682546681228515e-05, "loss": 3.471, "step": 1668608 }, { "epoch": 1.02, "learning_rate": 2.2674160733718e-05, "loss": 3.4772, "step": 1669120 }, { "epoch": 1.02, "learning_rate": 2.2665791165011208e-05, "loss": 3.4772, "step": 1669632 }, { "epoch": 1.02, "learning_rate": 2.2657405217500688e-05, "loss": 3.4812, "step": 1670144 }, { "epoch": 1.02, "learning_rate": 2.2649019269990168e-05, "loss": 3.4567, "step": 1670656 }, { "epoch": 1.02, "learning_rate": 2.2640633322479648e-05, "loss": 3.4777, "step": 1671168 }, { "epoch": 1.02, "learning_rate": 2.263226375377286e-05, "loss": 3.4704, "step": 1671680 }, { "epoch": 1.02, "learning_rate": 2.262387780626234e-05, "loss": 3.4801, "step": 1672192 }, { "epoch": 1.02, "learning_rate": 2.261549185875182e-05, "loss": 3.4632, "step": 1672704 }, { "epoch": 1.02, "learning_rate": 2.2607105911241297e-05, "loss": 3.4814, "step": 1673216 }, { "epoch": 1.02, "learning_rate": 2.259873634253451e-05, "loss": 3.4729, "step": 1673728 }, { "epoch": 1.02, "learning_rate": 2.259035039502399e-05, "loss": 3.4861, "step": 1674240 }, { "epoch": 1.02, "learning_rate": 2.258196444751347e-05, "loss": 3.4682, "step": 1674752 }, { "epoch": 1.02, "learning_rate": 2.257357850000295e-05, "loss": 3.4814, "step": 1675264 }, { "epoch": 1.02, "learning_rate": 2.256520893129616e-05, "loss": 3.4596, "step": 1675776 }, { "epoch": 1.02, "learning_rate": 2.255682298378564e-05, "loss": 3.4749, "step": 1676288 }, { "epoch": 1.02, "learning_rate": 2.2548437036275118e-05, "loss": 3.4756, "step": 1676800 }, { "epoch": 1.02, "learning_rate": 2.2540051088764598e-05, "loss": 3.4708, "step": 1677312 }, { "epoch": 1.02, "learning_rate": 2.2531681520057814e-05, "loss": 3.477, "step": 1677824 }, { "epoch": 1.02, "learning_rate": 2.2523295572547294e-05, "loss": 3.4665, "step": 1678336 }, { "epoch": 1.02, "learning_rate": 2.251490962503677e-05, "loss": 3.4733, "step": 1678848 }, { "epoch": 1.03, "eval_loss": 3.875396251678467, "eval_runtime": 310.3677, "eval_samples_per_second": 1229.48, "eval_steps_per_second": 38.422, "step": 1679040 }, { "epoch": 0.0, "learning_rate": 2.250652367752625e-05, "loss": 3.4665, "step": 1679360 }, { "epoch": 0.0, "learning_rate": 2.249813773001573e-05, "loss": 3.4658, "step": 1679872 }, { "epoch": 0.0, "learning_rate": 2.248975178250521e-05, "loss": 3.4751, "step": 1680384 }, { "epoch": 0.0, "learning_rate": 2.248136583499469e-05, "loss": 3.4685, "step": 1680896 }, { "epoch": 0.0, "learning_rate": 2.2472996266287903e-05, "loss": 3.4833, "step": 1681408 }, { "epoch": 0.0, "learning_rate": 2.2464610318777383e-05, "loss": 3.4668, "step": 1681920 }, { "epoch": 0.0, "learning_rate": 2.2456224371266863e-05, "loss": 3.4717, "step": 1682432 }, { "epoch": 0.0, "learning_rate": 2.2447838423756343e-05, "loss": 3.4707, "step": 1682944 }, { "epoch": 0.0, "learning_rate": 2.2439485233853284e-05, "loss": 3.4689, "step": 1683456 }, { "epoch": 0.0, "learning_rate": 2.2431099286342768e-05, "loss": 3.4712, "step": 1683968 }, { "epoch": 0.0, "learning_rate": 2.2422713338832244e-05, "loss": 3.4714, "step": 1684480 }, { "epoch": 0.0, "learning_rate": 2.2414327391321724e-05, "loss": 3.476, "step": 1684992 }, { "epoch": 0.0, "learning_rate": 2.2405941443811204e-05, "loss": 3.4681, "step": 1685504 }, { "epoch": 0.0, "learning_rate": 2.2397555496300684e-05, "loss": 3.4601, "step": 1686016 }, { "epoch": 0.0, "learning_rate": 2.2389169548790164e-05, "loss": 3.4696, "step": 1686528 }, { "epoch": 0.0, "learning_rate": 2.2380783601279644e-05, "loss": 3.4537, "step": 1687040 }, { "epoch": 0.0, "learning_rate": 2.2372414032572856e-05, "loss": 3.4633, "step": 1687552 }, { "epoch": 0.0, "learning_rate": 2.2364028085062336e-05, "loss": 3.4653, "step": 1688064 }, { "epoch": 0.0, "learning_rate": 2.2355642137551816e-05, "loss": 3.4624, "step": 1688576 }, { "epoch": 0.0, "learning_rate": 2.2347256190041296e-05, "loss": 3.4895, "step": 1689088 }, { "epoch": 0.0, "learning_rate": 2.2338886621334505e-05, "loss": 3.4794, "step": 1689600 }, { "epoch": 0.0, "learning_rate": 2.2330500673823985e-05, "loss": 3.483, "step": 1690112 }, { "epoch": 0.0, "learning_rate": 2.232211472631347e-05, "loss": 3.4653, "step": 1690624 }, { "epoch": 0.0, "learning_rate": 2.231372877880295e-05, "loss": 3.4717, "step": 1691136 }, { "epoch": 0.0, "learning_rate": 2.2305359210096158e-05, "loss": 3.4693, "step": 1691648 }, { "epoch": 0.0, "learning_rate": 2.2296973262585638e-05, "loss": 3.4762, "step": 1692160 }, { "epoch": 0.0, "learning_rate": 2.2288587315075118e-05, "loss": 3.4681, "step": 1692672 }, { "epoch": 0.0, "learning_rate": 2.2280201367564598e-05, "loss": 3.4707, "step": 1693184 }, { "epoch": 0.0, "learning_rate": 2.227183179885781e-05, "loss": 3.4547, "step": 1693696 }, { "epoch": 0.0, "learning_rate": 2.226344585134729e-05, "loss": 3.4637, "step": 1694208 }, { "epoch": 0.01, "learning_rate": 2.225505990383677e-05, "loss": 3.4636, "step": 1694720 }, { "epoch": 0.01, "learning_rate": 2.2246673956326247e-05, "loss": 3.4773, "step": 1695232 }, { "epoch": 0.01, "learning_rate": 2.223830438761946e-05, "loss": 3.4741, "step": 1695744 }, { "epoch": 0.01, "learning_rate": 2.222991844010894e-05, "loss": 3.4787, "step": 1696256 }, { "epoch": 0.01, "learning_rate": 2.2221532492598422e-05, "loss": 3.4591, "step": 1696768 }, { "epoch": 0.01, "learning_rate": 2.22131465450879e-05, "loss": 3.4622, "step": 1697280 }, { "epoch": 0.01, "learning_rate": 2.220477697638111e-05, "loss": 3.4687, "step": 1697792 }, { "epoch": 0.01, "learning_rate": 2.219639102887059e-05, "loss": 3.4585, "step": 1698304 }, { "epoch": 0.01, "learning_rate": 2.218800508136007e-05, "loss": 3.4649, "step": 1698816 }, { "epoch": 0.01, "learning_rate": 2.217961913384955e-05, "loss": 3.4564, "step": 1699328 }, { "epoch": 0.01, "learning_rate": 2.2171249565142764e-05, "loss": 3.4674, "step": 1699840 }, { "epoch": 0.01, "learning_rate": 2.2162863617632244e-05, "loss": 3.4743, "step": 1700352 }, { "epoch": 0.01, "learning_rate": 2.215447767012172e-05, "loss": 3.4721, "step": 1700864 }, { "epoch": 0.01, "learning_rate": 2.21460917226112e-05, "loss": 3.4654, "step": 1701376 }, { "epoch": 0.01, "learning_rate": 2.2137722153904413e-05, "loss": 3.474, "step": 1701888 }, { "epoch": 0.01, "learning_rate": 2.2129336206393893e-05, "loss": 3.462, "step": 1702400 }, { "epoch": 0.01, "learning_rate": 2.2120950258883373e-05, "loss": 3.4682, "step": 1702912 }, { "epoch": 0.01, "learning_rate": 2.2112564311372853e-05, "loss": 3.4613, "step": 1703424 }, { "epoch": 0.01, "learning_rate": 2.2104194742666065e-05, "loss": 3.4432, "step": 1703936 }, { "epoch": 0.01, "learning_rate": 2.2095808795155545e-05, "loss": 3.4844, "step": 1704448 }, { "epoch": 0.01, "learning_rate": 2.208742284764502e-05, "loss": 3.4559, "step": 1704960 }, { "epoch": 0.01, "learning_rate": 2.2079036900134505e-05, "loss": 3.4697, "step": 1705472 }, { "epoch": 0.01, "learning_rate": 2.2070667331427717e-05, "loss": 3.451, "step": 1705984 }, { "epoch": 0.01, "learning_rate": 2.2062281383917194e-05, "loss": 3.4596, "step": 1706496 }, { "epoch": 0.01, "learning_rate": 2.2053895436406674e-05, "loss": 3.448, "step": 1707008 }, { "epoch": 0.01, "learning_rate": 2.2045509488896154e-05, "loss": 3.4616, "step": 1707520 }, { "epoch": 0.01, "learning_rate": 2.2037139920189366e-05, "loss": 3.4675, "step": 1708032 }, { "epoch": 0.01, "learning_rate": 2.2028753972678846e-05, "loss": 3.467, "step": 1708544 }, { "epoch": 0.01, "learning_rate": 2.2020368025168326e-05, "loss": 3.4724, "step": 1709056 }, { "epoch": 0.01, "learning_rate": 2.2011982077657806e-05, "loss": 3.4584, "step": 1709568 }, { "epoch": 0.01, "learning_rate": 2.200361250895102e-05, "loss": 3.4515, "step": 1710080 }, { "epoch": 0.01, "learning_rate": 2.1995226561440495e-05, "loss": 3.4727, "step": 1710592 }, { "epoch": 0.01, "learning_rate": 2.1986840613929975e-05, "loss": 3.4478, "step": 1711104 }, { "epoch": 0.01, "learning_rate": 2.1978454666419455e-05, "loss": 3.4498, "step": 1711616 }, { "epoch": 0.01, "learning_rate": 2.1970085097712668e-05, "loss": 3.4714, "step": 1712128 }, { "epoch": 0.01, "learning_rate": 2.1961699150202148e-05, "loss": 3.4663, "step": 1712640 }, { "epoch": 0.01, "learning_rate": 2.1953313202691628e-05, "loss": 3.4572, "step": 1713152 }, { "epoch": 0.01, "learning_rate": 2.1944927255181108e-05, "loss": 3.459, "step": 1713664 }, { "epoch": 0.01, "learning_rate": 2.1936557686474317e-05, "loss": 3.4489, "step": 1714176 }, { "epoch": 0.01, "learning_rate": 2.19281717389638e-05, "loss": 3.4544, "step": 1714688 }, { "epoch": 0.01, "learning_rate": 2.191978579145328e-05, "loss": 3.4677, "step": 1715200 }, { "epoch": 0.01, "learning_rate": 2.191141622274649e-05, "loss": 3.4656, "step": 1715712 }, { "epoch": 0.01, "learning_rate": 2.190303027523597e-05, "loss": 3.4728, "step": 1716224 }, { "epoch": 0.01, "learning_rate": 2.189464432772545e-05, "loss": 3.4631, "step": 1716736 }, { "epoch": 0.01, "learning_rate": 2.188625838021493e-05, "loss": 3.4738, "step": 1717248 }, { "epoch": 0.01, "learning_rate": 2.187788881150814e-05, "loss": 3.4561, "step": 1717760 }, { "epoch": 0.01, "learning_rate": 2.186950286399762e-05, "loss": 3.4695, "step": 1718272 }, { "epoch": 0.01, "learning_rate": 2.18611169164871e-05, "loss": 3.4587, "step": 1718784 }, { "epoch": 0.01, "learning_rate": 2.185273096897658e-05, "loss": 3.4518, "step": 1719296 }, { "epoch": 0.01, "learning_rate": 2.184436140026979e-05, "loss": 3.4711, "step": 1719808 }, { "epoch": 0.01, "learning_rate": 2.183597545275927e-05, "loss": 3.4743, "step": 1720320 }, { "epoch": 0.01, "learning_rate": 2.1827589505248754e-05, "loss": 3.4667, "step": 1720832 }, { "epoch": 0.01, "learning_rate": 2.1819203557738234e-05, "loss": 3.4586, "step": 1721344 }, { "epoch": 0.01, "learning_rate": 2.1810833989031443e-05, "loss": 3.4486, "step": 1721856 }, { "epoch": 0.01, "learning_rate": 2.1802448041520923e-05, "loss": 3.4542, "step": 1722368 }, { "epoch": 0.01, "learning_rate": 2.1794062094010403e-05, "loss": 3.4616, "step": 1722880 }, { "epoch": 0.01, "learning_rate": 2.1785676146499883e-05, "loss": 3.4711, "step": 1723392 }, { "epoch": 0.01, "learning_rate": 2.1777306577793095e-05, "loss": 3.4569, "step": 1723904 }, { "epoch": 0.01, "learning_rate": 2.1768920630282575e-05, "loss": 3.466, "step": 1724416 }, { "epoch": 0.02, "learning_rate": 2.1760534682772055e-05, "loss": 3.4509, "step": 1724928 }, { "epoch": 0.02, "learning_rate": 2.1752148735261535e-05, "loss": 3.465, "step": 1725440 }, { "epoch": 0.02, "learning_rate": 2.1743779166554744e-05, "loss": 3.455, "step": 1725952 }, { "epoch": 0.02, "learning_rate": 2.1735393219044224e-05, "loss": 3.4588, "step": 1726464 }, { "epoch": 0.02, "learning_rate": 2.1727007271533707e-05, "loss": 3.4718, "step": 1726976 }, { "epoch": 0.02, "learning_rate": 2.1718621324023187e-05, "loss": 3.4741, "step": 1727488 }, { "epoch": 0.02, "learning_rate": 2.1710251755316396e-05, "loss": 3.4757, "step": 1728000 }, { "epoch": 0.02, "learning_rate": 2.1701865807805876e-05, "loss": 3.449, "step": 1728512 }, { "epoch": 0.02, "learning_rate": 2.1693479860295356e-05, "loss": 3.4686, "step": 1729024 }, { "epoch": 0.02, "learning_rate": 2.1685093912784836e-05, "loss": 3.4535, "step": 1729536 }, { "epoch": 0.02, "learning_rate": 2.167672434407805e-05, "loss": 3.4699, "step": 1730048 }, { "epoch": 0.02, "learning_rate": 2.166833839656753e-05, "loss": 3.4579, "step": 1730560 }, { "epoch": 0.02, "learning_rate": 2.165995244905701e-05, "loss": 3.4626, "step": 1731072 }, { "epoch": 0.02, "learning_rate": 2.165156650154649e-05, "loss": 3.4521, "step": 1731584 }, { "epoch": 0.02, "learning_rate": 2.1643196932839698e-05, "loss": 3.4642, "step": 1732096 }, { "epoch": 0.02, "learning_rate": 2.1634810985329178e-05, "loss": 3.4516, "step": 1732608 }, { "epoch": 0.02, "learning_rate": 2.162642503781866e-05, "loss": 3.4627, "step": 1733120 }, { "epoch": 0.02, "learning_rate": 2.161803909030814e-05, "loss": 3.4489, "step": 1733632 }, { "epoch": 0.02, "learning_rate": 2.160966952160135e-05, "loss": 3.4682, "step": 1734144 }, { "epoch": 0.02, "learning_rate": 2.160128357409083e-05, "loss": 3.4574, "step": 1734656 }, { "epoch": 0.02, "learning_rate": 2.159289762658031e-05, "loss": 3.4628, "step": 1735168 }, { "epoch": 0.02, "learning_rate": 2.158451167906979e-05, "loss": 3.4594, "step": 1735680 }, { "epoch": 0.02, "learning_rate": 2.1576142110363002e-05, "loss": 3.4649, "step": 1736192 }, { "epoch": 0.02, "learning_rate": 2.1567756162852482e-05, "loss": 3.4641, "step": 1736704 }, { "epoch": 0.02, "learning_rate": 2.1559370215341962e-05, "loss": 3.4606, "step": 1737216 }, { "epoch": 0.02, "learning_rate": 2.1550984267831442e-05, "loss": 3.467, "step": 1737728 }, { "epoch": 0.02, "learning_rate": 2.154261469912465e-05, "loss": 3.4752, "step": 1738240 }, { "epoch": 0.02, "learning_rate": 2.153422875161413e-05, "loss": 3.4644, "step": 1738752 }, { "epoch": 0.02, "learning_rate": 2.1525842804103615e-05, "loss": 3.4617, "step": 1739264 }, { "epoch": 0.02, "learning_rate": 2.151745685659309e-05, "loss": 3.4609, "step": 1739776 }, { "epoch": 0.02, "learning_rate": 2.1509087287886304e-05, "loss": 3.4626, "step": 1740288 }, { "epoch": 0.02, "learning_rate": 2.1500701340375784e-05, "loss": 3.4512, "step": 1740800 }, { "epoch": 0.02, "learning_rate": 2.1492315392865264e-05, "loss": 3.4643, "step": 1741312 }, { "epoch": 0.02, "learning_rate": 2.148392944535474e-05, "loss": 3.4449, "step": 1741824 }, { "epoch": 0.02, "learning_rate": 2.1475559876647956e-05, "loss": 3.472, "step": 1742336 }, { "epoch": 0.02, "learning_rate": 2.1467173929137436e-05, "loss": 3.466, "step": 1742848 }, { "epoch": 0.02, "learning_rate": 2.1458787981626916e-05, "loss": 3.465, "step": 1743360 }, { "epoch": 0.02, "learning_rate": 2.1450402034116393e-05, "loss": 3.4581, "step": 1743872 }, { "epoch": 0.02, "learning_rate": 2.1442032465409605e-05, "loss": 3.4574, "step": 1744384 }, { "epoch": 0.02, "learning_rate": 2.1433646517899085e-05, "loss": 3.4609, "step": 1744896 }, { "epoch": 0.02, "learning_rate": 2.1425260570388565e-05, "loss": 3.469, "step": 1745408 }, { "epoch": 0.02, "learning_rate": 2.1416874622878045e-05, "loss": 3.4653, "step": 1745920 }, { "epoch": 0.02, "learning_rate": 2.1408505054171257e-05, "loss": 3.4656, "step": 1746432 }, { "epoch": 0.02, "learning_rate": 2.1400119106660737e-05, "loss": 3.4497, "step": 1746944 }, { "epoch": 0.02, "learning_rate": 2.1391733159150214e-05, "loss": 3.4663, "step": 1747456 }, { "epoch": 0.02, "learning_rate": 2.138336359044343e-05, "loss": 3.4583, "step": 1747968 }, { "epoch": 0.02, "learning_rate": 2.137497764293291e-05, "loss": 3.4707, "step": 1748480 }, { "epoch": 0.02, "learning_rate": 2.136659169542239e-05, "loss": 3.4497, "step": 1748992 }, { "epoch": 0.02, "learning_rate": 2.1358205747911866e-05, "loss": 3.469, "step": 1749504 }, { "epoch": 0.02, "learning_rate": 2.134983617920508e-05, "loss": 3.4582, "step": 1750016 }, { "epoch": 0.02, "learning_rate": 2.134145023169456e-05, "loss": 3.4792, "step": 1750528 }, { "epoch": 0.02, "learning_rate": 2.133306428418404e-05, "loss": 3.4567, "step": 1751040 }, { "epoch": 0.02, "learning_rate": 2.132467833667352e-05, "loss": 3.4691, "step": 1751552 }, { "epoch": 0.02, "learning_rate": 2.131630876796673e-05, "loss": 3.4487, "step": 1752064 }, { "epoch": 0.02, "learning_rate": 2.130792282045621e-05, "loss": 3.4644, "step": 1752576 }, { "epoch": 0.02, "learning_rate": 2.1299536872945688e-05, "loss": 3.4619, "step": 1753088 }, { "epoch": 0.02, "learning_rate": 2.1291150925435168e-05, "loss": 3.4581, "step": 1753600 }, { "epoch": 0.02, "learning_rate": 2.1282781356728383e-05, "loss": 3.4702, "step": 1754112 }, { "epoch": 0.02, "learning_rate": 2.1274395409217863e-05, "loss": 3.4518, "step": 1754624 }, { "epoch": 0.02, "learning_rate": 2.126600946170734e-05, "loss": 3.4682, "step": 1755136 }, { "epoch": 0.03, "eval_loss": 3.876676082611084, "eval_runtime": 305.517, "eval_samples_per_second": 1249.001, "eval_steps_per_second": 39.032, "step": 1755360 }, { "epoch": 0.0, "learning_rate": 2.125762351419682e-05, "loss": 3.4543, "step": 1755648 }, { "epoch": 0.0, "learning_rate": 2.12492375666863e-05, "loss": 3.4514, "step": 1756160 }, { "epoch": 0.0, "learning_rate": 2.124085161917578e-05, "loss": 3.4645, "step": 1756672 }, { "epoch": 0.0, "learning_rate": 2.123246567166526e-05, "loss": 3.4572, "step": 1757184 }, { "epoch": 0.0, "learning_rate": 2.1224096102958472e-05, "loss": 3.4713, "step": 1757696 }, { "epoch": 0.0, "learning_rate": 2.1215710155447952e-05, "loss": 3.4582, "step": 1758208 }, { "epoch": 0.0, "learning_rate": 2.1207324207937432e-05, "loss": 3.4606, "step": 1758720 }, { "epoch": 0.0, "learning_rate": 2.1198938260426912e-05, "loss": 3.4624, "step": 1759232 }, { "epoch": 0.0, "learning_rate": 2.1190585070523854e-05, "loss": 3.4568, "step": 1759744 }, { "epoch": 0.0, "learning_rate": 2.1182199123013334e-05, "loss": 3.4598, "step": 1760256 }, { "epoch": 0.0, "learning_rate": 2.1173813175502814e-05, "loss": 3.4598, "step": 1760768 }, { "epoch": 0.0, "learning_rate": 2.1165427227992294e-05, "loss": 3.465, "step": 1761280 }, { "epoch": 0.0, "learning_rate": 2.1157041280481774e-05, "loss": 3.4591, "step": 1761792 }, { "epoch": 0.0, "learning_rate": 2.1148655332971254e-05, "loss": 3.4476, "step": 1762304 }, { "epoch": 0.0, "learning_rate": 2.1140269385460733e-05, "loss": 3.4552, "step": 1762816 }, { "epoch": 0.0, "learning_rate": 2.1131883437950213e-05, "loss": 3.4468, "step": 1763328 }, { "epoch": 0.0, "learning_rate": 2.1123513869243426e-05, "loss": 3.4515, "step": 1763840 }, { "epoch": 0.0, "learning_rate": 2.1115127921732906e-05, "loss": 3.4599, "step": 1764352 }, { "epoch": 0.0, "learning_rate": 2.1106741974222386e-05, "loss": 3.45, "step": 1764864 }, { "epoch": 0.0, "learning_rate": 2.1098356026711866e-05, "loss": 3.4768, "step": 1765376 }, { "epoch": 0.0, "learning_rate": 2.1089986458005075e-05, "loss": 3.468, "step": 1765888 }, { "epoch": 0.0, "learning_rate": 2.1081600510494555e-05, "loss": 3.4702, "step": 1766400 }, { "epoch": 0.0, "learning_rate": 2.1073214562984038e-05, "loss": 3.4552, "step": 1766912 }, { "epoch": 0.0, "learning_rate": 2.1064828615473515e-05, "loss": 3.4587, "step": 1767424 }, { "epoch": 0.0, "learning_rate": 2.1056459046766727e-05, "loss": 3.4637, "step": 1767936 }, { "epoch": 0.0, "learning_rate": 2.1048073099256207e-05, "loss": 3.4589, "step": 1768448 }, { "epoch": 0.0, "learning_rate": 2.1039687151745687e-05, "loss": 3.4577, "step": 1768960 }, { "epoch": 0.0, "learning_rate": 2.1031301204235164e-05, "loss": 3.4658, "step": 1769472 }, { "epoch": 0.0, "learning_rate": 2.102293163552838e-05, "loss": 3.4422, "step": 1769984 }, { "epoch": 0.0, "learning_rate": 2.101454568801786e-05, "loss": 3.451, "step": 1770496 }, { "epoch": 0.01, "learning_rate": 2.100615974050734e-05, "loss": 3.4558, "step": 1771008 }, { "epoch": 0.01, "learning_rate": 2.0997773792996816e-05, "loss": 3.4622, "step": 1771520 }, { "epoch": 0.01, "learning_rate": 2.098940422429003e-05, "loss": 3.4676, "step": 1772032 }, { "epoch": 0.01, "learning_rate": 2.098101827677951e-05, "loss": 3.4648, "step": 1772544 }, { "epoch": 0.01, "learning_rate": 2.097263232926899e-05, "loss": 3.4483, "step": 1773056 }, { "epoch": 0.01, "learning_rate": 2.096424638175847e-05, "loss": 3.4511, "step": 1773568 }, { "epoch": 0.01, "learning_rate": 2.095587681305168e-05, "loss": 3.4602, "step": 1774080 }, { "epoch": 0.01, "learning_rate": 2.094749086554116e-05, "loss": 3.4492, "step": 1774592 }, { "epoch": 0.01, "learning_rate": 2.0939104918030637e-05, "loss": 3.4563, "step": 1775104 }, { "epoch": 0.01, "learning_rate": 2.0930718970520117e-05, "loss": 3.4439, "step": 1775616 }, { "epoch": 0.01, "learning_rate": 2.0922349401813333e-05, "loss": 3.4594, "step": 1776128 }, { "epoch": 0.01, "learning_rate": 2.0913963454302813e-05, "loss": 3.457, "step": 1776640 }, { "epoch": 0.01, "learning_rate": 2.090557750679229e-05, "loss": 3.4615, "step": 1777152 }, { "epoch": 0.01, "learning_rate": 2.089719155928177e-05, "loss": 3.4603, "step": 1777664 }, { "epoch": 0.01, "learning_rate": 2.0888821990574982e-05, "loss": 3.4588, "step": 1778176 }, { "epoch": 0.01, "learning_rate": 2.0880436043064462e-05, "loss": 3.4545, "step": 1778688 }, { "epoch": 0.01, "learning_rate": 2.0872050095553942e-05, "loss": 3.4589, "step": 1779200 }, { "epoch": 0.01, "learning_rate": 2.0863664148043422e-05, "loss": 3.4494, "step": 1779712 }, { "epoch": 0.01, "learning_rate": 2.0855294579336635e-05, "loss": 3.4351, "step": 1780224 }, { "epoch": 0.01, "learning_rate": 2.084690863182611e-05, "loss": 3.4706, "step": 1780736 }, { "epoch": 0.01, "learning_rate": 2.083852268431559e-05, "loss": 3.444, "step": 1781248 }, { "epoch": 0.01, "learning_rate": 2.083013673680507e-05, "loss": 3.4599, "step": 1781760 }, { "epoch": 0.01, "learning_rate": 2.0821767168098287e-05, "loss": 3.4479, "step": 1782272 }, { "epoch": 0.01, "learning_rate": 2.0813381220587763e-05, "loss": 3.4452, "step": 1782784 }, { "epoch": 0.01, "learning_rate": 2.0804995273077243e-05, "loss": 3.437, "step": 1783296 }, { "epoch": 0.01, "learning_rate": 2.0796609325566723e-05, "loss": 3.4501, "step": 1783808 }, { "epoch": 0.01, "learning_rate": 2.0788239756859932e-05, "loss": 3.4603, "step": 1784320 }, { "epoch": 0.01, "learning_rate": 2.0779853809349416e-05, "loss": 3.4544, "step": 1784832 }, { "epoch": 0.01, "learning_rate": 2.0771467861838896e-05, "loss": 3.4636, "step": 1785344 }, { "epoch": 0.01, "learning_rate": 2.0763081914328376e-05, "loss": 3.4539, "step": 1785856 }, { "epoch": 0.01, "learning_rate": 2.0754712345621585e-05, "loss": 3.4354, "step": 1786368 }, { "epoch": 0.01, "learning_rate": 2.0746326398111065e-05, "loss": 3.4582, "step": 1786880 }, { "epoch": 0.01, "learning_rate": 2.0737940450600545e-05, "loss": 3.4401, "step": 1787392 }, { "epoch": 0.01, "learning_rate": 2.0729554503090025e-05, "loss": 3.4358, "step": 1787904 }, { "epoch": 0.01, "learning_rate": 2.0721184934383237e-05, "loss": 3.466, "step": 1788416 }, { "epoch": 0.01, "learning_rate": 2.0712798986872717e-05, "loss": 3.4529, "step": 1788928 }, { "epoch": 0.01, "learning_rate": 2.0704413039362197e-05, "loss": 3.4456, "step": 1789440 }, { "epoch": 0.01, "learning_rate": 2.0696043470655406e-05, "loss": 3.4498, "step": 1789952 }, { "epoch": 0.01, "learning_rate": 2.0687657523144886e-05, "loss": 3.4409, "step": 1790464 }, { "epoch": 0.01, "learning_rate": 2.067927157563437e-05, "loss": 3.4438, "step": 1790976 }, { "epoch": 0.01, "learning_rate": 2.067088562812385e-05, "loss": 3.4552, "step": 1791488 }, { "epoch": 0.01, "learning_rate": 2.066251605941706e-05, "loss": 3.454, "step": 1792000 }, { "epoch": 0.01, "learning_rate": 2.065413011190654e-05, "loss": 3.4619, "step": 1792512 }, { "epoch": 0.01, "learning_rate": 2.064574416439602e-05, "loss": 3.4504, "step": 1793024 }, { "epoch": 0.01, "learning_rate": 2.06373582168855e-05, "loss": 3.4642, "step": 1793536 }, { "epoch": 0.01, "learning_rate": 2.062898864817871e-05, "loss": 3.4437, "step": 1794048 }, { "epoch": 0.01, "learning_rate": 2.062060270066819e-05, "loss": 3.4625, "step": 1794560 }, { "epoch": 0.01, "learning_rate": 2.061221675315767e-05, "loss": 3.4451, "step": 1795072 }, { "epoch": 0.01, "learning_rate": 2.060383080564715e-05, "loss": 3.4435, "step": 1795584 }, { "epoch": 0.01, "learning_rate": 2.059546123694036e-05, "loss": 3.4601, "step": 1796096 }, { "epoch": 0.01, "learning_rate": 2.058707528942984e-05, "loss": 3.4642, "step": 1796608 }, { "epoch": 0.01, "learning_rate": 2.0578689341919323e-05, "loss": 3.4555, "step": 1797120 }, { "epoch": 0.01, "learning_rate": 2.0570303394408803e-05, "loss": 3.4543, "step": 1797632 }, { "epoch": 0.01, "learning_rate": 2.0561933825702012e-05, "loss": 3.4352, "step": 1798144 }, { "epoch": 0.01, "learning_rate": 2.0553547878191492e-05, "loss": 3.4431, "step": 1798656 }, { "epoch": 0.01, "learning_rate": 2.0545161930680972e-05, "loss": 3.4518, "step": 1799168 }, { "epoch": 0.01, "learning_rate": 2.0536775983170452e-05, "loss": 3.4585, "step": 1799680 }, { "epoch": 0.01, "learning_rate": 2.0528406414463665e-05, "loss": 3.4497, "step": 1800192 }, { "epoch": 0.01, "learning_rate": 2.0520020466953145e-05, "loss": 3.4548, "step": 1800704 }, { "epoch": 0.02, "learning_rate": 2.0511634519442624e-05, "loss": 3.4413, "step": 1801216 }, { "epoch": 0.02, "learning_rate": 2.0503248571932104e-05, "loss": 3.4538, "step": 1801728 }, { "epoch": 0.02, "learning_rate": 2.0494879003225314e-05, "loss": 3.4458, "step": 1802240 }, { "epoch": 0.02, "learning_rate": 2.0486493055714793e-05, "loss": 3.4475, "step": 1802752 }, { "epoch": 0.02, "learning_rate": 2.0478107108204277e-05, "loss": 3.4581, "step": 1803264 }, { "epoch": 0.02, "learning_rate": 2.0469721160693757e-05, "loss": 3.4612, "step": 1803776 }, { "epoch": 0.02, "learning_rate": 2.0461351591986966e-05, "loss": 3.4651, "step": 1804288 }, { "epoch": 0.02, "learning_rate": 2.0452965644476446e-05, "loss": 3.4409, "step": 1804800 }, { "epoch": 0.02, "learning_rate": 2.0444579696965926e-05, "loss": 3.4537, "step": 1805312 }, { "epoch": 0.02, "learning_rate": 2.0436193749455406e-05, "loss": 3.4465, "step": 1805824 }, { "epoch": 0.02, "learning_rate": 2.0427824180748618e-05, "loss": 3.4553, "step": 1806336 }, { "epoch": 0.02, "learning_rate": 2.0419438233238098e-05, "loss": 3.4469, "step": 1806848 }, { "epoch": 0.02, "learning_rate": 2.0411052285727578e-05, "loss": 3.4542, "step": 1807360 }, { "epoch": 0.02, "learning_rate": 2.0402666338217058e-05, "loss": 3.441, "step": 1807872 }, { "epoch": 0.02, "learning_rate": 2.0394296769510267e-05, "loss": 3.4504, "step": 1808384 }, { "epoch": 0.02, "learning_rate": 2.0385910821999747e-05, "loss": 3.4465, "step": 1808896 }, { "epoch": 0.02, "learning_rate": 2.037752487448923e-05, "loss": 3.4483, "step": 1809408 }, { "epoch": 0.02, "learning_rate": 2.036913892697871e-05, "loss": 3.4358, "step": 1809920 }, { "epoch": 0.02, "learning_rate": 2.036076935827192e-05, "loss": 3.4572, "step": 1810432 }, { "epoch": 0.02, "learning_rate": 2.03523834107614e-05, "loss": 3.4479, "step": 1810944 }, { "epoch": 0.02, "learning_rate": 2.034399746325088e-05, "loss": 3.4525, "step": 1811456 }, { "epoch": 0.02, "learning_rate": 2.0335611515740356e-05, "loss": 3.4489, "step": 1811968 }, { "epoch": 0.02, "learning_rate": 2.0327241947033572e-05, "loss": 3.4518, "step": 1812480 }, { "epoch": 0.02, "learning_rate": 2.0318855999523052e-05, "loss": 3.4548, "step": 1812992 }, { "epoch": 0.02, "learning_rate": 2.0310470052012532e-05, "loss": 3.4509, "step": 1813504 }, { "epoch": 0.02, "learning_rate": 2.030208410450201e-05, "loss": 3.4565, "step": 1814016 }, { "epoch": 0.02, "learning_rate": 2.029371453579522e-05, "loss": 3.4628, "step": 1814528 }, { "epoch": 0.02, "learning_rate": 2.02853285882847e-05, "loss": 3.4479, "step": 1815040 }, { "epoch": 0.02, "learning_rate": 2.0276959019577913e-05, "loss": 3.4565, "step": 1815552 }, { "epoch": 0.02, "learning_rate": 2.0268573072067393e-05, "loss": 3.4487, "step": 1816064 }, { "epoch": 0.02, "learning_rate": 2.0260187124556873e-05, "loss": 3.4473, "step": 1816576 }, { "epoch": 0.02, "learning_rate": 2.0251801177046353e-05, "loss": 3.4498, "step": 1817088 }, { "epoch": 0.02, "learning_rate": 2.024341522953583e-05, "loss": 3.451, "step": 1817600 }, { "epoch": 0.02, "learning_rate": 2.023502928202531e-05, "loss": 3.434, "step": 1818112 }, { "epoch": 0.02, "learning_rate": 2.0226643334514793e-05, "loss": 3.4581, "step": 1818624 }, { "epoch": 0.02, "learning_rate": 2.0218257387004273e-05, "loss": 3.4557, "step": 1819136 }, { "epoch": 0.02, "learning_rate": 2.0209887818297482e-05, "loss": 3.4567, "step": 1819648 }, { "epoch": 0.02, "learning_rate": 2.0201501870786962e-05, "loss": 3.447, "step": 1820160 }, { "epoch": 0.02, "learning_rate": 2.0193115923276442e-05, "loss": 3.4435, "step": 1820672 }, { "epoch": 0.02, "learning_rate": 2.0184729975765922e-05, "loss": 3.4476, "step": 1821184 }, { "epoch": 0.02, "learning_rate": 2.0176360407059134e-05, "loss": 3.4571, "step": 1821696 }, { "epoch": 0.02, "learning_rate": 2.0167974459548614e-05, "loss": 3.4547, "step": 1822208 }, { "epoch": 0.02, "learning_rate": 2.0159588512038094e-05, "loss": 3.4601, "step": 1822720 }, { "epoch": 0.02, "learning_rate": 2.0151202564527574e-05, "loss": 3.4353, "step": 1823232 }, { "epoch": 0.02, "learning_rate": 2.0142832995820783e-05, "loss": 3.4557, "step": 1823744 }, { "epoch": 0.02, "learning_rate": 2.0134447048310263e-05, "loss": 3.4476, "step": 1824256 }, { "epoch": 0.02, "learning_rate": 2.0126061100799747e-05, "loss": 3.4621, "step": 1824768 }, { "epoch": 0.02, "learning_rate": 2.0117675153289227e-05, "loss": 3.4416, "step": 1825280 }, { "epoch": 0.02, "learning_rate": 2.0109305584582436e-05, "loss": 3.4552, "step": 1825792 }, { "epoch": 0.02, "learning_rate": 2.0100919637071916e-05, "loss": 3.4465, "step": 1826304 }, { "epoch": 0.02, "learning_rate": 2.0092533689561396e-05, "loss": 3.4689, "step": 1826816 }, { "epoch": 0.02, "learning_rate": 2.0084147742050876e-05, "loss": 3.4461, "step": 1827328 }, { "epoch": 0.02, "learning_rate": 2.0075778173344088e-05, "loss": 3.4567, "step": 1827840 }, { "epoch": 0.02, "learning_rate": 2.0067392225833568e-05, "loss": 3.4413, "step": 1828352 }, { "epoch": 0.02, "learning_rate": 2.0059006278323048e-05, "loss": 3.4546, "step": 1828864 }, { "epoch": 0.02, "learning_rate": 2.0050620330812528e-05, "loss": 3.4472, "step": 1829376 }, { "epoch": 0.02, "learning_rate": 2.0042250762105737e-05, "loss": 3.4462, "step": 1829888 }, { "epoch": 0.02, "learning_rate": 2.0033864814595217e-05, "loss": 3.4587, "step": 1830400 }, { "epoch": 0.02, "learning_rate": 2.00254788670847e-05, "loss": 3.4358, "step": 1830912 }, { "epoch": 0.02, "learning_rate": 2.001709291957418e-05, "loss": 3.4618, "step": 1831424 }, { "epoch": 0.03, "eval_loss": 3.8798234462738037, "eval_runtime": 312.8359, "eval_samples_per_second": 1219.78, "eval_steps_per_second": 38.119, "step": 1831680 }, { "epoch": 0.0, "learning_rate": 2.000872335086739e-05, "loss": 3.444, "step": 1831936 }, { "epoch": 0.0, "learning_rate": 2.000033740335687e-05, "loss": 3.4428, "step": 1832448 }, { "epoch": 0.0, "learning_rate": 1.999195145584635e-05, "loss": 3.4509, "step": 1832960 }, { "epoch": 0.0, "learning_rate": 1.998356550833583e-05, "loss": 3.4466, "step": 1833472 }, { "epoch": 0.0, "learning_rate": 1.9975195939629042e-05, "loss": 3.4609, "step": 1833984 }, { "epoch": 0.0, "learning_rate": 1.9966809992118522e-05, "loss": 3.4478, "step": 1834496 }, { "epoch": 0.0, "learning_rate": 1.9958424044608002e-05, "loss": 3.4512, "step": 1835008 }, { "epoch": 0.0, "learning_rate": 1.995003809709748e-05, "loss": 3.4511, "step": 1835520 }, { "epoch": 0.0, "learning_rate": 1.994166852839069e-05, "loss": 3.4453, "step": 1836032 }, { "epoch": 0.0, "learning_rate": 1.9933298959683903e-05, "loss": 3.4515, "step": 1836544 }, { "epoch": 0.0, "learning_rate": 1.9924913012173383e-05, "loss": 3.4496, "step": 1837056 }, { "epoch": 0.0, "learning_rate": 1.9916527064662863e-05, "loss": 3.4522, "step": 1837568 }, { "epoch": 0.0, "learning_rate": 1.9908141117152343e-05, "loss": 3.4526, "step": 1838080 }, { "epoch": 0.0, "learning_rate": 1.9899755169641823e-05, "loss": 3.4331, "step": 1838592 }, { "epoch": 0.0, "learning_rate": 1.9891369222131303e-05, "loss": 3.4462, "step": 1839104 }, { "epoch": 0.0, "learning_rate": 1.988298327462078e-05, "loss": 3.4319, "step": 1839616 }, { "epoch": 0.0, "learning_rate": 1.9874613705913995e-05, "loss": 3.4438, "step": 1840128 }, { "epoch": 0.0, "learning_rate": 1.9866227758403475e-05, "loss": 3.4471, "step": 1840640 }, { "epoch": 0.0, "learning_rate": 1.9857841810892955e-05, "loss": 3.4401, "step": 1841152 }, { "epoch": 0.0, "learning_rate": 1.9849455863382432e-05, "loss": 3.4655, "step": 1841664 }, { "epoch": 0.0, "learning_rate": 1.9841086294675644e-05, "loss": 3.4591, "step": 1842176 }, { "epoch": 0.0, "learning_rate": 1.9832700347165124e-05, "loss": 3.4594, "step": 1842688 }, { "epoch": 0.0, "learning_rate": 1.9824314399654604e-05, "loss": 3.4469, "step": 1843200 }, { "epoch": 0.0, "learning_rate": 1.9815928452144084e-05, "loss": 3.4492, "step": 1843712 }, { "epoch": 0.0, "learning_rate": 1.9807558883437297e-05, "loss": 3.4532, "step": 1844224 }, { "epoch": 0.0, "learning_rate": 1.9799172935926777e-05, "loss": 3.4476, "step": 1844736 }, { "epoch": 0.0, "learning_rate": 1.9790786988416253e-05, "loss": 3.4466, "step": 1845248 }, { "epoch": 0.0, "learning_rate": 1.9782401040905733e-05, "loss": 3.4522, "step": 1845760 }, { "epoch": 0.0, "learning_rate": 1.977403147219895e-05, "loss": 3.4352, "step": 1846272 }, { "epoch": 0.0, "learning_rate": 1.976564552468843e-05, "loss": 3.4365, "step": 1846784 }, { "epoch": 0.01, "learning_rate": 1.9757259577177906e-05, "loss": 3.4484, "step": 1847296 }, { "epoch": 0.01, "learning_rate": 1.9748873629667386e-05, "loss": 3.4512, "step": 1847808 }, { "epoch": 0.01, "learning_rate": 1.9740504060960598e-05, "loss": 3.4482, "step": 1848320 }, { "epoch": 0.01, "learning_rate": 1.9732118113450078e-05, "loss": 3.4615, "step": 1848832 }, { "epoch": 0.01, "learning_rate": 1.9723732165939558e-05, "loss": 3.4388, "step": 1849344 }, { "epoch": 0.01, "learning_rate": 1.9715346218429038e-05, "loss": 3.4389, "step": 1849856 }, { "epoch": 0.01, "learning_rate": 1.970697664972225e-05, "loss": 3.4487, "step": 1850368 }, { "epoch": 0.01, "learning_rate": 1.9698590702211727e-05, "loss": 3.4357, "step": 1850880 }, { "epoch": 0.01, "learning_rate": 1.9690204754701207e-05, "loss": 3.4477, "step": 1851392 }, { "epoch": 0.01, "learning_rate": 1.9681818807190687e-05, "loss": 3.4377, "step": 1851904 }, { "epoch": 0.01, "learning_rate": 1.9673449238483903e-05, "loss": 3.4447, "step": 1852416 }, { "epoch": 0.01, "learning_rate": 1.966506329097338e-05, "loss": 3.4474, "step": 1852928 }, { "epoch": 0.01, "learning_rate": 1.965667734346286e-05, "loss": 3.4492, "step": 1853440 }, { "epoch": 0.01, "learning_rate": 1.964829139595234e-05, "loss": 3.4499, "step": 1853952 }, { "epoch": 0.01, "learning_rate": 1.9639921827245552e-05, "loss": 3.4473, "step": 1854464 }, { "epoch": 0.01, "learning_rate": 1.9631535879735032e-05, "loss": 3.4449, "step": 1854976 }, { "epoch": 0.01, "learning_rate": 1.962314993222451e-05, "loss": 3.4419, "step": 1855488 }, { "epoch": 0.01, "learning_rate": 1.961476398471399e-05, "loss": 3.4452, "step": 1856000 }, { "epoch": 0.01, "learning_rate": 1.96063944160072e-05, "loss": 3.4226, "step": 1856512 }, { "epoch": 0.01, "learning_rate": 1.959800846849668e-05, "loss": 3.4583, "step": 1857024 }, { "epoch": 0.01, "learning_rate": 1.958962252098616e-05, "loss": 3.4322, "step": 1857536 }, { "epoch": 0.01, "learning_rate": 1.958123657347564e-05, "loss": 3.4504, "step": 1858048 }, { "epoch": 0.01, "learning_rate": 1.9572867004768853e-05, "loss": 3.4374, "step": 1858560 }, { "epoch": 0.01, "learning_rate": 1.9564481057258333e-05, "loss": 3.4343, "step": 1859072 }, { "epoch": 0.01, "learning_rate": 1.9556095109747813e-05, "loss": 3.4307, "step": 1859584 }, { "epoch": 0.01, "learning_rate": 1.9547709162237293e-05, "loss": 3.4332, "step": 1860096 }, { "epoch": 0.01, "learning_rate": 1.9539323214726773e-05, "loss": 3.4538, "step": 1860608 }, { "epoch": 0.01, "learning_rate": 1.9530937267216253e-05, "loss": 3.4374, "step": 1861120 }, { "epoch": 0.01, "learning_rate": 1.9522551319705733e-05, "loss": 3.4579, "step": 1861632 }, { "epoch": 0.01, "learning_rate": 1.9514165372195213e-05, "loss": 3.4433, "step": 1862144 }, { "epoch": 0.01, "learning_rate": 1.9505795803488425e-05, "loss": 3.4259, "step": 1862656 }, { "epoch": 0.01, "learning_rate": 1.9497409855977905e-05, "loss": 3.4442, "step": 1863168 }, { "epoch": 0.01, "learning_rate": 1.9489023908467382e-05, "loss": 3.4348, "step": 1863680 }, { "epoch": 0.01, "learning_rate": 1.9480637960956862e-05, "loss": 3.4236, "step": 1864192 }, { "epoch": 0.01, "learning_rate": 1.9472268392250078e-05, "loss": 3.4525, "step": 1864704 }, { "epoch": 0.01, "learning_rate": 1.9463882444739558e-05, "loss": 3.4445, "step": 1865216 }, { "epoch": 0.01, "learning_rate": 1.9455496497229034e-05, "loss": 3.4351, "step": 1865728 }, { "epoch": 0.01, "learning_rate": 1.9447110549718514e-05, "loss": 3.44, "step": 1866240 }, { "epoch": 0.01, "learning_rate": 1.9438740981011727e-05, "loss": 3.4249, "step": 1866752 }, { "epoch": 0.01, "learning_rate": 1.9430355033501207e-05, "loss": 3.4355, "step": 1867264 }, { "epoch": 0.01, "learning_rate": 1.9421969085990686e-05, "loss": 3.443, "step": 1867776 }, { "epoch": 0.01, "learning_rate": 1.9413583138480166e-05, "loss": 3.4416, "step": 1868288 }, { "epoch": 0.01, "learning_rate": 1.940521356977338e-05, "loss": 3.4544, "step": 1868800 }, { "epoch": 0.01, "learning_rate": 1.9396827622262855e-05, "loss": 3.4388, "step": 1869312 }, { "epoch": 0.01, "learning_rate": 1.9388441674752335e-05, "loss": 3.4519, "step": 1869824 }, { "epoch": 0.01, "learning_rate": 1.9380072106045548e-05, "loss": 3.4377, "step": 1870336 }, { "epoch": 0.01, "learning_rate": 1.9371686158535028e-05, "loss": 3.4499, "step": 1870848 }, { "epoch": 0.01, "learning_rate": 1.9363300211024508e-05, "loss": 3.4319, "step": 1871360 }, { "epoch": 0.01, "learning_rate": 1.9354914263513988e-05, "loss": 3.4318, "step": 1871872 }, { "epoch": 0.01, "learning_rate": 1.93465446948072e-05, "loss": 3.4505, "step": 1872384 }, { "epoch": 0.01, "learning_rate": 1.933815874729668e-05, "loss": 3.4536, "step": 1872896 }, { "epoch": 0.01, "learning_rate": 1.9329772799786157e-05, "loss": 3.4426, "step": 1873408 }, { "epoch": 0.01, "learning_rate": 1.932138685227564e-05, "loss": 3.4455, "step": 1873920 }, { "epoch": 0.01, "learning_rate": 1.9313017283568853e-05, "loss": 3.4231, "step": 1874432 }, { "epoch": 0.01, "learning_rate": 1.930463133605833e-05, "loss": 3.4309, "step": 1874944 }, { "epoch": 0.01, "learning_rate": 1.929624538854781e-05, "loss": 3.4426, "step": 1875456 }, { "epoch": 0.01, "learning_rate": 1.928785944103729e-05, "loss": 3.4478, "step": 1875968 }, { "epoch": 0.01, "learning_rate": 1.92794898723305e-05, "loss": 3.4368, "step": 1876480 }, { "epoch": 0.01, "learning_rate": 1.927110392481998e-05, "loss": 3.443, "step": 1876992 }, { "epoch": 0.02, "learning_rate": 1.926271797730946e-05, "loss": 3.4333, "step": 1877504 }, { "epoch": 0.02, "learning_rate": 1.925433202979894e-05, "loss": 3.4424, "step": 1878016 }, { "epoch": 0.02, "learning_rate": 1.924596246109215e-05, "loss": 3.4342, "step": 1878528 }, { "epoch": 0.02, "learning_rate": 1.923757651358163e-05, "loss": 3.4368, "step": 1879040 }, { "epoch": 0.02, "learning_rate": 1.922919056607111e-05, "loss": 3.4472, "step": 1879552 }, { "epoch": 0.02, "learning_rate": 1.9220804618560594e-05, "loss": 3.4515, "step": 1880064 }, { "epoch": 0.02, "learning_rate": 1.9212435049853803e-05, "loss": 3.4541, "step": 1880576 }, { "epoch": 0.02, "learning_rate": 1.9204049102343283e-05, "loss": 3.431, "step": 1881088 }, { "epoch": 0.02, "learning_rate": 1.9195663154832763e-05, "loss": 3.4434, "step": 1881600 }, { "epoch": 0.02, "learning_rate": 1.9187277207322243e-05, "loss": 3.438, "step": 1882112 }, { "epoch": 0.02, "learning_rate": 1.9178907638615455e-05, "loss": 3.4439, "step": 1882624 }, { "epoch": 0.02, "learning_rate": 1.9170521691104935e-05, "loss": 3.4365, "step": 1883136 }, { "epoch": 0.02, "learning_rate": 1.9162135743594415e-05, "loss": 3.4416, "step": 1883648 }, { "epoch": 0.02, "learning_rate": 1.9153749796083895e-05, "loss": 3.4347, "step": 1884160 }, { "epoch": 0.02, "learning_rate": 1.9145380227377104e-05, "loss": 3.4367, "step": 1884672 }, { "epoch": 0.02, "learning_rate": 1.9136994279866584e-05, "loss": 3.4346, "step": 1885184 }, { "epoch": 0.02, "learning_rate": 1.9128608332356064e-05, "loss": 3.4363, "step": 1885696 }, { "epoch": 0.02, "learning_rate": 1.9120222384845547e-05, "loss": 3.4263, "step": 1886208 }, { "epoch": 0.02, "learning_rate": 1.9111852816138757e-05, "loss": 3.447, "step": 1886720 }, { "epoch": 0.02, "learning_rate": 1.9103466868628237e-05, "loss": 3.4387, "step": 1887232 }, { "epoch": 0.02, "learning_rate": 1.9095080921117716e-05, "loss": 3.4391, "step": 1887744 }, { "epoch": 0.02, "learning_rate": 1.9086694973607196e-05, "loss": 3.4419, "step": 1888256 }, { "epoch": 0.02, "learning_rate": 1.907832540490041e-05, "loss": 3.4376, "step": 1888768 }, { "epoch": 0.02, "learning_rate": 1.906993945738989e-05, "loss": 3.4454, "step": 1889280 }, { "epoch": 0.02, "learning_rate": 1.906155350987937e-05, "loss": 3.4378, "step": 1889792 }, { "epoch": 0.02, "learning_rate": 1.905316756236885e-05, "loss": 3.4466, "step": 1890304 }, { "epoch": 0.02, "learning_rate": 1.9044797993662058e-05, "loss": 3.4531, "step": 1890816 }, { "epoch": 0.02, "learning_rate": 1.9036412046151538e-05, "loss": 3.4401, "step": 1891328 }, { "epoch": 0.02, "learning_rate": 1.9028026098641018e-05, "loss": 3.4431, "step": 1891840 }, { "epoch": 0.02, "learning_rate": 1.90196401511305e-05, "loss": 3.4412, "step": 1892352 }, { "epoch": 0.02, "learning_rate": 1.901127058242371e-05, "loss": 3.434, "step": 1892864 }, { "epoch": 0.02, "learning_rate": 1.900288463491319e-05, "loss": 3.4397, "step": 1893376 }, { "epoch": 0.02, "learning_rate": 1.899449868740267e-05, "loss": 3.4435, "step": 1893888 }, { "epoch": 0.02, "learning_rate": 1.898611273989215e-05, "loss": 3.4214, "step": 1894400 }, { "epoch": 0.02, "learning_rate": 1.8977743171185363e-05, "loss": 3.4492, "step": 1894912 }, { "epoch": 0.02, "learning_rate": 1.8969357223674843e-05, "loss": 3.4428, "step": 1895424 }, { "epoch": 0.02, "learning_rate": 1.8960971276164322e-05, "loss": 3.4465, "step": 1895936 }, { "epoch": 0.02, "learning_rate": 1.8952585328653802e-05, "loss": 3.4391, "step": 1896448 }, { "epoch": 0.02, "learning_rate": 1.894421575994701e-05, "loss": 3.433, "step": 1896960 }, { "epoch": 0.02, "learning_rate": 1.893582981243649e-05, "loss": 3.4362, "step": 1897472 }, { "epoch": 0.02, "learning_rate": 1.892744386492597e-05, "loss": 3.4458, "step": 1897984 }, { "epoch": 0.02, "learning_rate": 1.891905791741545e-05, "loss": 3.4461, "step": 1898496 }, { "epoch": 0.02, "learning_rate": 1.8910688348708664e-05, "loss": 3.4494, "step": 1899008 }, { "epoch": 0.02, "learning_rate": 1.8902302401198144e-05, "loss": 3.4236, "step": 1899520 }, { "epoch": 0.02, "learning_rate": 1.8893916453687624e-05, "loss": 3.4485, "step": 1900032 }, { "epoch": 0.02, "learning_rate": 1.8885546884980833e-05, "loss": 3.4365, "step": 1900544 }, { "epoch": 0.02, "learning_rate": 1.8877160937470313e-05, "loss": 3.4529, "step": 1901056 }, { "epoch": 0.02, "learning_rate": 1.8868774989959796e-05, "loss": 3.4318, "step": 1901568 }, { "epoch": 0.02, "learning_rate": 1.8860389042449276e-05, "loss": 3.4417, "step": 1902080 }, { "epoch": 0.02, "learning_rate": 1.8852019473742485e-05, "loss": 3.4382, "step": 1902592 }, { "epoch": 0.02, "learning_rate": 1.8843633526231965e-05, "loss": 3.4581, "step": 1903104 }, { "epoch": 0.02, "learning_rate": 1.8835247578721445e-05, "loss": 3.4357, "step": 1903616 }, { "epoch": 0.02, "learning_rate": 1.8826861631210925e-05, "loss": 3.4455, "step": 1904128 }, { "epoch": 0.02, "learning_rate": 1.8818492062504138e-05, "loss": 3.4333, "step": 1904640 }, { "epoch": 0.02, "learning_rate": 1.8810106114993618e-05, "loss": 3.4473, "step": 1905152 }, { "epoch": 0.02, "learning_rate": 1.8801720167483098e-05, "loss": 3.4338, "step": 1905664 }, { "epoch": 0.02, "learning_rate": 1.8793334219972577e-05, "loss": 3.4352, "step": 1906176 }, { "epoch": 0.02, "learning_rate": 1.8784964651265787e-05, "loss": 3.4447, "step": 1906688 }, { "epoch": 0.02, "learning_rate": 1.8776578703755267e-05, "loss": 3.4311, "step": 1907200 }, { "epoch": 0.02, "learning_rate": 1.876819275624475e-05, "loss": 3.4486, "step": 1907712 }, { "epoch": 0.03, "eval_loss": 3.8796281814575195, "eval_runtime": 304.68, "eval_samples_per_second": 1252.432, "eval_steps_per_second": 39.139, "step": 1908000 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.320703854882048e+18, "trial_name": null, "trial_params": null }