{ "best_metric": 4.0268874168396, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/pp-mod-subj2/lstm/2/checkpoints/checkpoint-2671200", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 2671200, "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": 10.8208, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 7.5693, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 7.0625, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 6.9896, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 6.9381, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 6.8335, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 6.6844, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 6.5822, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 6.4915, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 6.4177, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 6.3654, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 6.2956, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 6.2386, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989098268236324e-05, "loss": 6.1664, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988259673485272e-05, "loss": 6.1167, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.98742107873422e-05, "loss": 6.0504, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986582483983168e-05, "loss": 6.0234, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985743889232116e-05, "loss": 5.9688, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984905294481064e-05, "loss": 5.9251, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984066699730012e-05, "loss": 5.8929, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.8698, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 5.8234, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 5.8002, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.980713958606178e-05, "loss": 5.7636, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 5.7312, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 5.7138, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 5.6757, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 5.6632, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 5.6372, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 5.6086, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 5.595, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 5.5717, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 5.5581, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 5.5397, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 5.5194, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 5.5117, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 5.5037, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 5.4652, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 5.4555, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967306269871584e-05, "loss": 5.4422, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966467675120532e-05, "loss": 5.4262, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.96562908036948e-05, "loss": 5.4117, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964790485618428e-05, "loss": 5.4139, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963951890867376e-05, "loss": 5.3941, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.963113296116324e-05, "loss": 5.3779, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 5.3722, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 5.3603, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.9605991497435414e-05, "loss": 5.3545, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.9597605549924894e-05, "loss": 5.3298, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 5.3187, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 5.327, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 5.3167, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 5.3035, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 5.2791, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954728986486177e-05, "loss": 5.2889, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 5.2672, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 5.2829, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 5.2487, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951376245362342e-05, "loss": 5.2534, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950540926372037e-05, "loss": 5.2332, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949702331620985e-05, "loss": 5.2229, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948863736869932e-05, "loss": 5.2238, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 5.2078, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 5.2029, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 5.1953, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 5.2048, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 5.178, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 5.1667, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 5.1527, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 5.1512, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 5.1653, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 5.156, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 5.1355, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 5.1338, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 5.1339, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 5.1286, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 5.1056, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 5.1085, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 5.0949, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 5.0968, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 5.0926, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 5.082, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 5.0836, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 5.0745, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 5.058, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 5.0577, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 5.0622, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 5.0562, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 5.043, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925391273242342e-05, "loss": 5.0297, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 5.0339, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 5.0223, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 5.0313, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 5.0101, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 5.0054, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920362980496776e-05, "loss": 5.0232, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919524385745724e-05, "loss": 4.9905, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.9842, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.9905, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.9871, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.9874, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.9755, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.9698, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.963, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.9621, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.9468, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.9459, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.9489, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.9392, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.9316, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.9272, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.9179, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.9283, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.914, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.9101, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.9121, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.9063, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.902, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.8984, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.8983, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.8975, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.8775, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.8892, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.8784, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.8805, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.8607, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.8706, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.8555, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.8622, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.8394, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.8635, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.8673, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.8455, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.8343, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.8456, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886830655617308e-05, "loss": 4.8387, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.8372, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885153466115204e-05, "loss": 4.8317, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.8344, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.8244, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.8198, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.8045, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.8164, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.8137, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.8032, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.8155, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.7943, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.8049, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.8055, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.7935, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.80623722076416, "eval_runtime": 281.8309, "eval_samples_per_second": 1353.971, "eval_steps_per_second": 42.313, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.87425828587302e-05, "loss": 4.7818, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873419691121968e-05, "loss": 4.788, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.7903, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.7815, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.7816, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.7668, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.7705, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.7609, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.7655, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.7581, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.7652, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.7657, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642000625015155e-05, "loss": 4.751, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633614677504635e-05, "loss": 4.7488, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.7337, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.7455, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.7397, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860008726626628e-05, "loss": 4.732, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591701318755764e-05, "loss": 4.7315, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583315371245244e-05, "loss": 4.7577, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.7286, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.7315, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558157528713684e-05, "loss": 4.734, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.723, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.7231, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.7102, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.7181, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.7143, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.7014, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849947227494377e-05, "loss": 4.7099, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849108632743325e-05, "loss": 4.6989, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.7088, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847431443241221e-05, "loss": 4.7057, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846592848490169e-05, "loss": 4.6931, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.702, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.7111, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.6791, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.6907, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.6862, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841566193624977e-05, "loss": 4.6778, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.6804, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398906420032456e-05, "loss": 4.6885, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.8390520472521936e-05, "loss": 4.6823, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382134525011416e-05, "loss": 4.6767, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83737485775009e-05, "loss": 4.6779, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.6722, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.6765, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.6596, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834020478745882e-05, "loss": 4.6564, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331818839948295e-05, "loss": 4.6723, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832344927124151e-05, "loss": 4.6706, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.6605, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830667737622047e-05, "loss": 4.6501, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.6592, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289905481199424e-05, "loss": 4.6426, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.6683, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.6468, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.6565, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.6419, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.636, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.6389, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823123660623325e-05, "loss": 4.645, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822285065872273e-05, "loss": 4.6264, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821446471121221e-05, "loss": 4.6305, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820607876370169e-05, "loss": 4.6448, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.6247, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818932324748438e-05, "loss": 4.6166, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818093729997386e-05, "loss": 4.6161, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817255135246334e-05, "loss": 4.6146, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.6357, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155795836246034e-05, "loss": 4.6313, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147409888735514e-05, "loss": 4.6145, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8139023941224994e-05, "loss": 4.6194, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.622, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.6211, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.6054, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810549652998664e-05, "loss": 4.6169, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809711058247612e-05, "loss": 4.6049, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.6122, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808035506625881e-05, "loss": 4.6051, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807196911874829e-05, "loss": 4.604, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806358317123777e-05, "loss": 4.6053, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805519722372726e-05, "loss": 4.6083, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804681127621674e-05, "loss": 4.591, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803842532870622e-05, "loss": 4.5985, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.80300393811957e-05, "loss": 4.597, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802166981248891e-05, "loss": 4.6022, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801328386497839e-05, "loss": 4.5951, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800489791746787e-05, "loss": 4.582, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799651196995735e-05, "loss": 4.5928, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798812602244683e-05, "loss": 4.5838, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979772832543765e-05, "loss": 4.5954, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971386885033245e-05, "loss": 4.5756, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963000937522725e-05, "loss": 4.5802, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795461499001221e-05, "loss": 4.5928, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794622904250169e-05, "loss": 4.5814, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793784309499117e-05, "loss": 4.5622, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792945714748065e-05, "loss": 4.5757, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792107119997013e-05, "loss": 4.5809, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791270163126334e-05, "loss": 4.5807, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790431568375282e-05, "loss": 4.5716, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.78959297362423e-05, "loss": 4.5698, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887543788731774e-05, "loss": 4.5649, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787917422002499e-05, "loss": 4.569, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.787078827251447e-05, "loss": 4.5527, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.5607, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854032756297166e-05, "loss": 4.5645, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845646808786646e-05, "loss": 4.5631, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837260861276126e-05, "loss": 4.5455, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828874913765606e-05, "loss": 4.5568, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782048896625508e-05, "loss": 4.5443, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781210301874456e-05, "loss": 4.5606, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780371707123404e-05, "loss": 4.5466, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779534750252725e-05, "loss": 4.5381, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778696155501673e-05, "loss": 4.5571, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778591986309944e-05, "loss": 4.5502, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770206038799423e-05, "loss": 4.5444, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761820091288903e-05, "loss": 4.5477, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753434143778383e-05, "loss": 4.5452, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774504819626786e-05, "loss": 4.5499, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773667862756108e-05, "loss": 4.5282, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772829268005055e-05, "loss": 4.551, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771990673254003e-05, "loss": 4.5374, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771152078502951e-05, "loss": 4.5399, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770313483751899e-05, "loss": 4.53, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769474889000847e-05, "loss": 4.5355, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768636294249795e-05, "loss": 4.525, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767797699498743e-05, "loss": 4.5348, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766960742628064e-05, "loss": 4.5131, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766122147877012e-05, "loss": 4.545, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528355312596e-05, "loss": 4.5371, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764444958374909e-05, "loss": 4.5289, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763606363623857e-05, "loss": 4.5175, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762769406753178e-05, "loss": 4.5328, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761930812002126e-05, "loss": 4.531, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761092217251074e-05, "loss": 4.5239, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760253622500022e-05, "loss": 4.5178, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594166656293426e-05, "loss": 4.5274, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585797087586635e-05, "loss": 4.5199, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577411140076115e-05, "loss": 4.5273, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569025192565595e-05, "loss": 4.5028, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560639245055075e-05, "loss": 4.5188, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552253297544555e-05, "loss": 4.5162, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543867350034035e-05, "loss": 4.5102, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753548140252352e-05, "loss": 4.5237, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527095455013e-05, "loss": 4.503, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751872588630621e-05, "loss": 4.5141, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751033993879569e-05, "loss": 4.5109, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750195399128517e-05, "loss": 4.5109, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.527585983276367, "eval_runtime": 283.1798, "eval_samples_per_second": 1347.522, "eval_steps_per_second": 42.111, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749356804377465e-05, "loss": 4.499, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748518209626413e-05, "loss": 4.5054, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747679614875361e-05, "loss": 4.5109, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468410201243084e-05, "loss": 4.5074, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460024253732563e-05, "loss": 4.5052, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451638306222043e-05, "loss": 4.4891, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744325235871152e-05, "loss": 4.4967, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434866411201e-05, "loss": 4.4897, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742648046369049e-05, "loss": 4.4993, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.741809451617997e-05, "loss": 4.4914, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740970856866945e-05, "loss": 4.5, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740132262115893e-05, "loss": 4.5028, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739295305245214e-05, "loss": 4.4846, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738456710494162e-05, "loss": 4.4897, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.73761811574311e-05, "loss": 4.4711, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736779520992058e-05, "loss": 4.4847, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735940926241006e-05, "loss": 4.4837, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735102331489954e-05, "loss": 4.4759, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734263736738902e-05, "loss": 4.4777, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.73342514198785e-05, "loss": 4.5024, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732586547236797e-05, "loss": 4.4818, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731747952485746e-05, "loss": 4.479, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309109956150674e-05, "loss": 4.4854, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.7300740387443884e-05, "loss": 4.4817, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292354439933364e-05, "loss": 4.4751, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7283968492422844e-05, "loss": 4.4645, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275582544912323e-05, "loss": 4.4758, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.72671965974018e-05, "loss": 4.4685, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258810649891277e-05, "loss": 4.4626, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250424702380757e-05, "loss": 4.4735, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7242038754870237e-05, "loss": 4.4629, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233652807359716e-05, "loss": 4.474, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225266859849196e-05, "loss": 4.4696, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216880912338676e-05, "loss": 4.4586, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720851134363189e-05, "loss": 4.4702, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720012539612137e-05, "loss": 4.4825, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719173944861085e-05, "loss": 4.4479, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718335350110033e-05, "loss": 4.4655, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717496755358981e-05, "loss": 4.4553, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716658160607929e-05, "loss": 4.4555, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.71582120373725e-05, "loss": 4.4519, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714982608986198e-05, "loss": 4.467, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714144014235146e-05, "loss": 4.4602, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713305419484094e-05, "loss": 4.4549, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712466824733042e-05, "loss": 4.457, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.71162822998199e-05, "loss": 4.4494, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710789635230938e-05, "loss": 4.4628, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709951040479886e-05, "loss": 4.4429, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709114083609208e-05, "loss": 4.4415, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708275488858156e-05, "loss": 4.4549, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074368941071037e-05, "loss": 4.4545, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7065982993560517e-05, "loss": 4.4459, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705759704604999e-05, "loss": 4.4409, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704921109853947e-05, "loss": 4.4488, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704082515102895e-05, "loss": 4.4313, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703243920351843e-05, "loss": 4.456, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702406963481164e-05, "loss": 4.44, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701568368730112e-05, "loss": 4.4482, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.70072977397906e-05, "loss": 4.444, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699891179228008e-05, "loss": 4.432, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990542223573294e-05, "loss": 4.4336, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982156276062774e-05, "loss": 4.443, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973770328552254e-05, "loss": 4.4219, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965384381041734e-05, "loss": 4.4307, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.6957014812334943e-05, "loss": 4.4398, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694862886482442e-05, "loss": 4.4319, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694027567492137e-05, "loss": 4.4179, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693188972741085e-05, "loss": 4.4191, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692350377990033e-05, "loss": 4.4165, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691511783238981e-05, "loss": 4.4433, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690673188487928e-05, "loss": 4.4332, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689834593736877e-05, "loss": 4.4227, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.688995998985825e-05, "loss": 4.4317, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688157404234773e-05, "loss": 4.4269, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687318809483721e-05, "loss": 4.4316, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686481852613042e-05, "loss": 4.4154, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.68564325786199e-05, "loss": 4.4297, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684804663110938e-05, "loss": 4.4215, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683966068359886e-05, "loss": 4.4225, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683127473608834e-05, "loss": 4.4163, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682288878857782e-05, "loss": 4.4203, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.68145028410673e-05, "loss": 4.4207, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806133272360506e-05, "loss": 4.4247, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797747324849986e-05, "loss": 4.4096, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789361377339466e-05, "loss": 4.4157, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678097542982895e-05, "loss": 4.4137, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677258948231843e-05, "loss": 4.4181, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676420353480791e-05, "loss": 4.4174, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675581758729739e-05, "loss": 4.4003, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674743163978687e-05, "loss": 4.4127, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673906207108008e-05, "loss": 4.4077, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673069250237329e-05, "loss": 4.4175, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672230655486277e-05, "loss": 4.3968, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671392060735225e-05, "loss": 4.4062, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670553465984173e-05, "loss": 4.4183, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669716509113494e-05, "loss": 4.4054, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668877914362442e-05, "loss": 4.3886, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680393196113906e-05, "loss": 4.4013, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6672007248603386e-05, "loss": 4.4092, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663621301092866e-05, "loss": 4.4093, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655235353582346e-05, "loss": 4.4021, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664684940607182e-05, "loss": 4.3957, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.66384634585613e-05, "loss": 4.3944, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630093889854515e-05, "loss": 4.4015, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621707942343995e-05, "loss": 4.3858, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661332199483347e-05, "loss": 4.3927, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6604952426126684e-05, "loss": 4.3971, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596566478616164e-05, "loss": 4.397, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588180531105644e-05, "loss": 4.378, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579794583595124e-05, "loss": 4.3952, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571408636084604e-05, "loss": 4.38, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6563022688574084e-05, "loss": 4.3931, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554636741063564e-05, "loss": 4.3877, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546250793553044e-05, "loss": 4.3782, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653788122484625e-05, "loss": 4.394, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652949527733573e-05, "loss": 4.3918, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652112570862894e-05, "loss": 4.3827, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651273976111842e-05, "loss": 4.3883, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.65043538136079e-05, "loss": 4.3865, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649596786609738e-05, "loss": 4.3864, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648758191858686e-05, "loss": 4.3754, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647919597107634e-05, "loss": 4.3906, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647081002356582e-05, "loss": 4.3807, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.646244045485904e-05, "loss": 4.3821, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645405450734852e-05, "loss": 4.3787, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445668559838e-05, "loss": 4.3849, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643728261232748e-05, "loss": 4.3667, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6428913043620687e-05, "loss": 4.3795, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420527096110166e-05, "loss": 4.3599, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412141148599646e-05, "loss": 4.39, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403755201089126e-05, "loss": 4.3814, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395369253578606e-05, "loss": 4.3786, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6386983306068086e-05, "loss": 4.3653, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378597358557566e-05, "loss": 4.3825, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370211411047046e-05, "loss": 4.3842, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636184184234026e-05, "loss": 4.3712, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635345589482974e-05, "loss": 4.3699, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634506994731922e-05, "loss": 4.3784, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.63366839998087e-05, "loss": 4.3707, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632829805229818e-05, "loss": 4.38, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6319912104787655e-05, "loss": 4.3594, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631154253608087e-05, "loss": 4.3707, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630315658857035e-05, "loss": 4.3709, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629477064105983e-05, "loss": 4.3638, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628640107235304e-05, "loss": 4.3798, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627801512484252e-05, "loss": 4.3577, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.6269629177332e-05, "loss": 4.3664, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626124322982148e-05, "loss": 4.3696, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625285728231096e-05, "loss": 4.364, "step": 228864 }, { "epoch": 0.03, "eval_loss": 4.3927435874938965, "eval_runtime": 308.9633, "eval_samples_per_second": 1235.069, "eval_steps_per_second": 38.597, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624447133480044e-05, "loss": 4.3649, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623608538728992e-05, "loss": 4.3612, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.62276994397794e-05, "loss": 4.3708, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621931349226888e-05, "loss": 4.3661, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621092754475836e-05, "loss": 4.3634, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620254159724784e-05, "loss": 4.353, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619415564973732e-05, "loss": 4.3589, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618578608103053e-05, "loss": 4.3448, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617740013352001e-05, "loss": 4.3692, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616901418600949e-05, "loss": 4.3518, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.61606446173027e-05, "loss": 4.3645, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.6152258669792184e-05, "loss": 4.3658, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6143889101085393e-05, "loss": 4.3529, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.613550315357487e-05, "loss": 4.3478, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.612711720606435e-05, "loss": 4.3428, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611873125855383e-05, "loss": 4.3424, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611034531104331e-05, "loss": 4.3537, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610195936353279e-05, "loss": 4.342, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609357341602227e-05, "loss": 4.3449, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.608518746851175e-05, "loss": 4.3669, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607680152100123e-05, "loss": 4.3488, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606841557349071e-05, "loss": 4.3474, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606002962598019e-05, "loss": 4.3529, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051643678469666e-05, "loss": 4.3497, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604327410976288e-05, "loss": 4.3448, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603488816225236e-05, "loss": 4.333, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602650221474184e-05, "loss": 4.3498, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601811626723132e-05, "loss": 4.3323, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.60097303197208e-05, "loss": 4.3367, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.600136075101402e-05, "loss": 4.3391, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599299118230723e-05, "loss": 4.3341, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598460523479671e-05, "loss": 4.3475, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597621928728619e-05, "loss": 4.3405, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596783333977567e-05, "loss": 4.3316, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.5959463771068876e-05, "loss": 4.3439, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.5951077823558356e-05, "loss": 4.3502, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.5942691876047836e-05, "loss": 4.3296, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.5934305928537316e-05, "loss": 4.3396, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.5925919981026796e-05, "loss": 4.3254, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.5917534033516276e-05, "loss": 4.341, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.5909148086005756e-05, "loss": 4.325, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.5900778517298965e-05, "loss": 4.344, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.5892392569788445e-05, "loss": 4.3371, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884006622277925e-05, "loss": 4.3326, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.5875620674767404e-05, "loss": 4.3367, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.5867234727256884e-05, "loss": 4.3276, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.5858848779746364e-05, "loss": 4.3398, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.5850462832235844e-05, "loss": 4.3223, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.5842076884725324e-05, "loss": 4.32, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.5833690937214804e-05, "loss": 4.3351, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.5825304989704284e-05, "loss": 4.3297, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581691904219377e-05, "loss": 4.332, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580853309468325e-05, "loss": 4.3177, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580016352597646e-05, "loss": 4.3275, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579177757846594e-05, "loss": 4.3142, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578339163095542e-05, "loss": 4.3347, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.57750056834449e-05, "loss": 4.3225, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576661973593438e-05, "loss": 4.3341, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.575823378842385e-05, "loss": 4.3285, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.574986421971707e-05, "loss": 4.3188, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574147827220655e-05, "loss": 4.3137, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573309232469602e-05, "loss": 4.3263, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572470637718551e-05, "loss": 4.3093, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716336808478725e-05, "loss": 4.3174, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5707950860968205e-05, "loss": 4.3219, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569956491345768e-05, "loss": 4.3204, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569117896594716e-05, "loss": 4.3003, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568279301843664e-05, "loss": 4.3083, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567440707092612e-05, "loss": 4.3013, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.56660211234156e-05, "loss": 4.3322, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565763517590508e-05, "loss": 4.3182, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564926560719829e-05, "loss": 4.3131, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5640896038491496e-05, "loss": 4.319, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632510090980976e-05, "loss": 4.3122, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562412414347046e-05, "loss": 4.3266, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561573819595994e-05, "loss": 4.3004, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.560735224844942e-05, "loss": 4.3223, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.55989663009389e-05, "loss": 4.3087, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.559058035342838e-05, "loss": 4.3122, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.558219440591786e-05, "loss": 4.3105, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.55738412160148e-05, "loss": 4.3061, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556545526850428e-05, "loss": 4.3166, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555706932099376e-05, "loss": 4.3107, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554868337348324e-05, "loss": 4.3004, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554029742597272e-05, "loss": 4.3106, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.55319114784622e-05, "loss": 4.3014, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552352553095168e-05, "loss": 4.3141, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551513958344116e-05, "loss": 4.308, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.5506770014734376e-05, "loss": 4.2936, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.5498384067223856e-05, "loss": 4.3078, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.5489998119713336e-05, "loss": 4.299, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.5481628551006545e-05, "loss": 4.308, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.5473242603496025e-05, "loss": 4.2935, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.5464856655985505e-05, "loss": 4.3026, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.5456470708474985e-05, "loss": 4.3124, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.5448101139768194e-05, "loss": 4.2969, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.5439715192257674e-05, "loss": 4.2894, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.5431329244747154e-05, "loss": 4.2978, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.5422943297236634e-05, "loss": 4.2973, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.5414557349726114e-05, "loss": 4.3108, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.5406171402215594e-05, "loss": 4.2969, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539780183350881e-05, "loss": 4.2938, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538941588599829e-05, "loss": 4.2912, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538102993848777e-05, "loss": 4.3015, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537264399097725e-05, "loss": 4.2802, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536425804346673e-05, "loss": 4.2934, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535588847475994e-05, "loss": 4.2924, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534750252724942e-05, "loss": 4.2972, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.53391165797389e-05, "loss": 4.274, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533073063222838e-05, "loss": 4.2937, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532234468471786e-05, "loss": 4.2862, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531395873720733e-05, "loss": 4.2843, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530557278969682e-05, "loss": 4.2927, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.52971868421863e-05, "loss": 4.2745, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.5288817273479514e-05, "loss": 4.2967, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.528043132596899e-05, "loss": 4.2904, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.52720617572622e-05, "loss": 4.2831, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526367580975168e-05, "loss": 4.2904, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525528986224116e-05, "loss": 4.2849, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5246903914730636e-05, "loss": 4.2899, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238517967220116e-05, "loss": 4.2719, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.5230132019709596e-05, "loss": 4.2968, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.5221762451002805e-05, "loss": 4.2825, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213376503492285e-05, "loss": 4.2821, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520499055598177e-05, "loss": 4.2812, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519660460847125e-05, "loss": 4.2899, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518821866096073e-05, "loss": 4.2756, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.517984909225394e-05, "loss": 4.2797, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517147952354716e-05, "loss": 4.2684, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516309357603663e-05, "loss": 4.292, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515470762852611e-05, "loss": 4.2851, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514632168101559e-05, "loss": 4.2832, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513793573350507e-05, "loss": 4.2713, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512954978599455e-05, "loss": 4.2861, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512116383848403e-05, "loss": 4.2862, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511279426977724e-05, "loss": 4.2769, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.5104408322266726e-05, "loss": 4.2742, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.5096022374756206e-05, "loss": 4.2843, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087636427245685e-05, "loss": 4.2796, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079250479735165e-05, "loss": 4.2829, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.5070864532224645e-05, "loss": 4.2669, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.5062478584714125e-05, "loss": 4.2775, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.5054092637203605e-05, "loss": 4.2753, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.5045723068496814e-05, "loss": 4.275, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.5037337120986294e-05, "loss": 4.2831, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.5028951173475774e-05, "loss": 4.2685, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.5020565225965254e-05, "loss": 4.2756, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.5012179278454734e-05, "loss": 4.2732, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500380970974794e-05, "loss": 4.2769, "step": 305152 }, { "epoch": 1.03, "eval_loss": 4.30879020690918, "eval_runtime": 307.4003, "eval_samples_per_second": 1241.349, "eval_steps_per_second": 38.793, "step": 305280 }, { "epoch": 2.0, "learning_rate": 4.499542376223742e-05, "loss": 4.2724, "step": 305664 }, { "epoch": 2.0, "learning_rate": 4.498703781472691e-05, "loss": 4.2725, "step": 306176 }, { "epoch": 2.0, "learning_rate": 4.497865186721639e-05, "loss": 4.2799, "step": 306688 }, { "epoch": 2.0, "learning_rate": 4.497029867731333e-05, "loss": 4.2736, "step": 307200 }, { "epoch": 2.0, "learning_rate": 4.496191272980281e-05, "loss": 4.2774, "step": 307712 }, { "epoch": 2.0, "learning_rate": 4.495352678229229e-05, "loss": 4.2616, "step": 308224 }, { "epoch": 2.0, "learning_rate": 4.494514083478177e-05, "loss": 4.2689, "step": 308736 }, { "epoch": 2.0, "learning_rate": 4.493675488727125e-05, "loss": 4.2565, "step": 309248 }, { "epoch": 2.0, "learning_rate": 4.492836893976073e-05, "loss": 4.2759, "step": 309760 }, { "epoch": 2.0, "learning_rate": 4.491998299225021e-05, "loss": 4.2691, "step": 310272 }, { "epoch": 2.0, "learning_rate": 4.491159704473969e-05, "loss": 4.2702, "step": 310784 }, { "epoch": 2.0, "learning_rate": 4.490321109722917e-05, "loss": 4.2721, "step": 311296 }, { "epoch": 2.0, "learning_rate": 4.489485790732611e-05, "loss": 4.263, "step": 311808 }, { "epoch": 2.0, "learning_rate": 4.488647195981559e-05, "loss": 4.2579, "step": 312320 }, { "epoch": 2.0, "learning_rate": 4.487808601230507e-05, "loss": 4.2592, "step": 312832 }, { "epoch": 2.0, "learning_rate": 4.486970006479455e-05, "loss": 4.2488, "step": 313344 }, { "epoch": 2.0, "learning_rate": 4.486133049608776e-05, "loss": 4.2662, "step": 313856 }, { "epoch": 2.0, "learning_rate": 4.485294454857724e-05, "loss": 4.2538, "step": 314368 }, { "epoch": 2.0, "learning_rate": 4.484455860106672e-05, "loss": 4.2556, "step": 314880 }, { "epoch": 2.0, "learning_rate": 4.48361726535562e-05, "loss": 4.2848, "step": 315392 }, { "epoch": 2.0, "learning_rate": 4.482778670604568e-05, "loss": 4.2588, "step": 315904 }, { "epoch": 2.0, "learning_rate": 4.481940075853516e-05, "loss": 4.2639, "step": 316416 }, { "epoch": 2.0, "learning_rate": 4.481101481102464e-05, "loss": 4.2675, "step": 316928 }, { "epoch": 2.0, "learning_rate": 4.4802628863514115e-05, "loss": 4.2629, "step": 317440 }, { "epoch": 2.0, "learning_rate": 4.479425929480733e-05, "loss": 4.2596, "step": 317952 }, { "epoch": 2.0, "learning_rate": 4.478587334729681e-05, "loss": 4.2496, "step": 318464 }, { "epoch": 2.0, "learning_rate": 4.47774873997863e-05, "loss": 4.2654, "step": 318976 }, { "epoch": 2.0, "learning_rate": 4.476910145227577e-05, "loss": 4.242, "step": 319488 }, { "epoch": 2.0, "learning_rate": 4.4760731883568986e-05, "loss": 4.2547, "step": 320000 }, { "epoch": 2.0, "learning_rate": 4.4752345936058466e-05, "loss": 4.2504, "step": 320512 }, { "epoch": 2.01, "learning_rate": 4.474395998854794e-05, "loss": 4.2527, "step": 321024 }, { "epoch": 2.01, "learning_rate": 4.473557404103742e-05, "loss": 4.2627, "step": 321536 }, { "epoch": 2.01, "learning_rate": 4.4727204472330635e-05, "loss": 4.2574, "step": 322048 }, { "epoch": 2.01, "learning_rate": 4.4718818524820115e-05, "loss": 4.25, "step": 322560 }, { "epoch": 2.01, "learning_rate": 4.4710448956113324e-05, "loss": 4.2586, "step": 323072 }, { "epoch": 2.01, "learning_rate": 4.4702063008602804e-05, "loss": 4.2653, "step": 323584 }, { "epoch": 2.01, "learning_rate": 4.4693677061092284e-05, "loss": 4.2484, "step": 324096 }, { "epoch": 2.01, "learning_rate": 4.4685291113581764e-05, "loss": 4.2571, "step": 324608 }, { "epoch": 2.01, "learning_rate": 4.4676905166071244e-05, "loss": 4.2433, "step": 325120 }, { "epoch": 2.01, "learning_rate": 4.4668519218560724e-05, "loss": 4.2595, "step": 325632 }, { "epoch": 2.01, "learning_rate": 4.466014964985394e-05, "loss": 4.2384, "step": 326144 }, { "epoch": 2.01, "learning_rate": 4.465176370234341e-05, "loss": 4.2652, "step": 326656 }, { "epoch": 2.01, "learning_rate": 4.464337775483289e-05, "loss": 4.2545, "step": 327168 }, { "epoch": 2.01, "learning_rate": 4.463499180732237e-05, "loss": 4.2496, "step": 327680 }, { "epoch": 2.01, "learning_rate": 4.462660585981185e-05, "loss": 4.2553, "step": 328192 }, { "epoch": 2.01, "learning_rate": 4.461821991230133e-05, "loss": 4.2463, "step": 328704 }, { "epoch": 2.01, "learning_rate": 4.460983396479081e-05, "loss": 4.256, "step": 329216 }, { "epoch": 2.01, "learning_rate": 4.460144801728029e-05, "loss": 4.2412, "step": 329728 }, { "epoch": 2.01, "learning_rate": 4.45930784485735e-05, "loss": 4.2391, "step": 330240 }, { "epoch": 2.01, "learning_rate": 4.458469250106299e-05, "loss": 4.2564, "step": 330752 }, { "epoch": 2.01, "learning_rate": 4.457630655355247e-05, "loss": 4.2492, "step": 331264 }, { "epoch": 2.01, "learning_rate": 4.456792060604195e-05, "loss": 4.2496, "step": 331776 }, { "epoch": 2.01, "learning_rate": 4.455955103733516e-05, "loss": 4.2407, "step": 332288 }, { "epoch": 2.01, "learning_rate": 4.455118146862837e-05, "loss": 4.2444, "step": 332800 }, { "epoch": 2.01, "learning_rate": 4.454279552111785e-05, "loss": 4.239, "step": 333312 }, { "epoch": 2.01, "learning_rate": 4.453440957360733e-05, "loss": 4.2517, "step": 333824 }, { "epoch": 2.01, "learning_rate": 4.452602362609681e-05, "loss": 4.2425, "step": 334336 }, { "epoch": 2.01, "learning_rate": 4.451763767858629e-05, "loss": 4.2557, "step": 334848 }, { "epoch": 2.01, "learning_rate": 4.450925173107577e-05, "loss": 4.2485, "step": 335360 }, { "epoch": 2.01, "learning_rate": 4.450086578356525e-05, "loss": 4.2371, "step": 335872 }, { "epoch": 2.01, "learning_rate": 4.4492479836054727e-05, "loss": 4.2385, "step": 336384 }, { "epoch": 2.01, "learning_rate": 4.4484093888544207e-05, "loss": 4.2451, "step": 336896 }, { "epoch": 2.01, "learning_rate": 4.447572431983742e-05, "loss": 4.23, "step": 337408 }, { "epoch": 2.01, "learning_rate": 4.44673383723269e-05, "loss": 4.2403, "step": 337920 }, { "epoch": 2.01, "learning_rate": 4.445895242481638e-05, "loss": 4.2421, "step": 338432 }, { "epoch": 2.01, "learning_rate": 4.445056647730586e-05, "loss": 4.2448, "step": 338944 }, { "epoch": 2.01, "learning_rate": 4.444219690859907e-05, "loss": 4.2231, "step": 339456 }, { "epoch": 2.01, "learning_rate": 4.443381096108855e-05, "loss": 4.2312, "step": 339968 }, { "epoch": 2.01, "learning_rate": 4.442542501357803e-05, "loss": 4.2261, "step": 340480 }, { "epoch": 2.01, "learning_rate": 4.441705544487124e-05, "loss": 4.2513, "step": 340992 }, { "epoch": 2.01, "learning_rate": 4.440866949736072e-05, "loss": 4.2403, "step": 341504 }, { "epoch": 2.01, "learning_rate": 4.44002835498502e-05, "loss": 4.2397, "step": 342016 }, { "epoch": 2.01, "learning_rate": 4.439189760233968e-05, "loss": 4.2412, "step": 342528 }, { "epoch": 2.01, "learning_rate": 4.438351165482916e-05, "loss": 4.2359, "step": 343040 }, { "epoch": 2.01, "learning_rate": 4.437512570731864e-05, "loss": 4.2539, "step": 343552 }, { "epoch": 2.01, "learning_rate": 4.436673975980813e-05, "loss": 4.2232, "step": 344064 }, { "epoch": 2.01, "learning_rate": 4.4358370191101336e-05, "loss": 4.2423, "step": 344576 }, { "epoch": 2.01, "learning_rate": 4.4349984243590816e-05, "loss": 4.2385, "step": 345088 }, { "epoch": 2.01, "learning_rate": 4.4341598296080296e-05, "loss": 4.2348, "step": 345600 }, { "epoch": 2.01, "learning_rate": 4.4333212348569776e-05, "loss": 4.2389, "step": 346112 }, { "epoch": 2.01, "learning_rate": 4.432482640105925e-05, "loss": 4.2337, "step": 346624 }, { "epoch": 2.01, "learning_rate": 4.431644045354873e-05, "loss": 4.2376, "step": 347136 }, { "epoch": 2.01, "learning_rate": 4.430805450603821e-05, "loss": 4.24, "step": 347648 }, { "epoch": 2.01, "learning_rate": 4.4299684937331425e-05, "loss": 4.2236, "step": 348160 }, { "epoch": 2.01, "learning_rate": 4.42912989898209e-05, "loss": 4.2372, "step": 348672 }, { "epoch": 2.01, "learning_rate": 4.428291304231038e-05, "loss": 4.2266, "step": 349184 }, { "epoch": 2.01, "learning_rate": 4.4274527094799865e-05, "loss": 4.2395, "step": 349696 }, { "epoch": 2.01, "learning_rate": 4.4266141147289345e-05, "loss": 4.2327, "step": 350208 }, { "epoch": 2.01, "learning_rate": 4.4257755199778825e-05, "loss": 4.2222, "step": 350720 }, { "epoch": 2.02, "learning_rate": 4.4249369252268305e-05, "loss": 4.2331, "step": 351232 }, { "epoch": 2.02, "learning_rate": 4.4240999683561514e-05, "loss": 4.2267, "step": 351744 }, { "epoch": 2.02, "learning_rate": 4.423263011485472e-05, "loss": 4.2368, "step": 352256 }, { "epoch": 2.02, "learning_rate": 4.42242441673442e-05, "loss": 4.2172, "step": 352768 }, { "epoch": 2.02, "learning_rate": 4.421585821983368e-05, "loss": 4.2302, "step": 353280 }, { "epoch": 2.02, "learning_rate": 4.420747227232316e-05, "loss": 4.2438, "step": 353792 }, { "epoch": 2.02, "learning_rate": 4.419908632481264e-05, "loss": 4.224, "step": 354304 }, { "epoch": 2.02, "learning_rate": 4.419070037730212e-05, "loss": 4.2139, "step": 354816 }, { "epoch": 2.02, "learning_rate": 4.41823144297916e-05, "loss": 4.2238, "step": 355328 }, { "epoch": 2.02, "learning_rate": 4.417392848228108e-05, "loss": 4.2305, "step": 355840 }, { "epoch": 2.02, "learning_rate": 4.416554253477056e-05, "loss": 4.2341, "step": 356352 }, { "epoch": 2.02, "learning_rate": 4.415715658726004e-05, "loss": 4.2275, "step": 356864 }, { "epoch": 2.02, "learning_rate": 4.414878701855326e-05, "loss": 4.223, "step": 357376 }, { "epoch": 2.02, "learning_rate": 4.414040107104274e-05, "loss": 4.2198, "step": 357888 }, { "epoch": 2.02, "learning_rate": 4.413201512353222e-05, "loss": 4.2301, "step": 358400 }, { "epoch": 2.02, "learning_rate": 4.41236291760217e-05, "loss": 4.2065, "step": 358912 }, { "epoch": 2.02, "learning_rate": 4.411524322851118e-05, "loss": 4.2209, "step": 359424 }, { "epoch": 2.02, "learning_rate": 4.410687365980439e-05, "loss": 4.2236, "step": 359936 }, { "epoch": 2.02, "learning_rate": 4.409848771229387e-05, "loss": 4.2265, "step": 360448 }, { "epoch": 2.02, "learning_rate": 4.409010176478335e-05, "loss": 4.2053, "step": 360960 }, { "epoch": 2.02, "learning_rate": 4.408171581727283e-05, "loss": 4.2236, "step": 361472 }, { "epoch": 2.02, "learning_rate": 4.407332986976231e-05, "loss": 4.2143, "step": 361984 }, { "epoch": 2.02, "learning_rate": 4.406494392225179e-05, "loss": 4.2176, "step": 362496 }, { "epoch": 2.02, "learning_rate": 4.405655797474127e-05, "loss": 4.2203, "step": 363008 }, { "epoch": 2.02, "learning_rate": 4.404817202723075e-05, "loss": 4.2081, "step": 363520 }, { "epoch": 2.02, "learning_rate": 4.403978607972023e-05, "loss": 4.2221, "step": 364032 }, { "epoch": 2.02, "learning_rate": 4.4031416511013436e-05, "loss": 4.2255, "step": 364544 }, { "epoch": 2.02, "learning_rate": 4.402304694230665e-05, "loss": 4.2127, "step": 365056 }, { "epoch": 2.02, "learning_rate": 4.401466099479613e-05, "loss": 4.2237, "step": 365568 }, { "epoch": 2.02, "learning_rate": 4.400627504728561e-05, "loss": 4.2139, "step": 366080 }, { "epoch": 2.02, "learning_rate": 4.3997889099775085e-05, "loss": 4.2247, "step": 366592 }, { "epoch": 2.02, "learning_rate": 4.3989503152264565e-05, "loss": 4.206, "step": 367104 }, { "epoch": 2.02, "learning_rate": 4.3981117204754045e-05, "loss": 4.2304, "step": 367616 }, { "epoch": 2.02, "learning_rate": 4.3972731257243525e-05, "loss": 4.2066, "step": 368128 }, { "epoch": 2.02, "learning_rate": 4.3964361688536734e-05, "loss": 4.2165, "step": 368640 }, { "epoch": 2.02, "learning_rate": 4.395597574102622e-05, "loss": 4.2079, "step": 369152 }, { "epoch": 2.02, "learning_rate": 4.39475897935157e-05, "loss": 4.2249, "step": 369664 }, { "epoch": 2.02, "learning_rate": 4.393920384600518e-05, "loss": 4.2125, "step": 370176 }, { "epoch": 2.02, "learning_rate": 4.393083427729839e-05, "loss": 4.2124, "step": 370688 }, { "epoch": 2.02, "learning_rate": 4.392244832978787e-05, "loss": 4.1969, "step": 371200 }, { "epoch": 2.02, "learning_rate": 4.391406238227735e-05, "loss": 4.2288, "step": 371712 }, { "epoch": 2.02, "learning_rate": 4.390567643476683e-05, "loss": 4.2122, "step": 372224 }, { "epoch": 2.02, "learning_rate": 4.389729048725631e-05, "loss": 4.2156, "step": 372736 }, { "epoch": 2.02, "learning_rate": 4.388890453974579e-05, "loss": 4.2026, "step": 373248 }, { "epoch": 2.02, "learning_rate": 4.388051859223527e-05, "loss": 4.2216, "step": 373760 }, { "epoch": 2.02, "learning_rate": 4.387213264472475e-05, "loss": 4.2245, "step": 374272 }, { "epoch": 2.02, "learning_rate": 4.386374669721423e-05, "loss": 4.208, "step": 374784 }, { "epoch": 2.02, "learning_rate": 4.385536074970371e-05, "loss": 4.2087, "step": 375296 }, { "epoch": 2.02, "learning_rate": 4.384699118099692e-05, "loss": 4.2188, "step": 375808 }, { "epoch": 2.02, "learning_rate": 4.3838605233486405e-05, "loss": 4.216, "step": 376320 }, { "epoch": 2.02, "learning_rate": 4.3830219285975885e-05, "loss": 4.2183, "step": 376832 }, { "epoch": 2.02, "learning_rate": 4.3821833338465365e-05, "loss": 4.1993, "step": 377344 }, { "epoch": 2.02, "learning_rate": 4.3813447390954845e-05, "loss": 4.2136, "step": 377856 }, { "epoch": 2.02, "learning_rate": 4.3805061443444325e-05, "loss": 4.2079, "step": 378368 }, { "epoch": 2.02, "learning_rate": 4.37966754959338e-05, "loss": 4.2106, "step": 378880 }, { "epoch": 2.02, "learning_rate": 4.378828954842328e-05, "loss": 4.2168, "step": 379392 }, { "epoch": 2.02, "learning_rate": 4.3779919979716494e-05, "loss": 4.2007, "step": 379904 }, { "epoch": 2.02, "learning_rate": 4.37715504110097e-05, "loss": 4.2177, "step": 380416 }, { "epoch": 2.02, "learning_rate": 4.376316446349918e-05, "loss": 4.2049, "step": 380928 }, { "epoch": 2.02, "learning_rate": 4.375477851598866e-05, "loss": 4.218, "step": 381440 }, { "epoch": 2.03, "eval_loss": 4.25235652923584, "eval_runtime": 308.0102, "eval_samples_per_second": 1238.891, "eval_steps_per_second": 38.716, "step": 381600 }, { "epoch": 0.0, "learning_rate": 4.374639256847814e-05, "loss": 4.2007, "step": 381952 }, { "epoch": 0.0, "learning_rate": 4.373800662096762e-05, "loss": 4.2113, "step": 382464 }, { "epoch": 0.0, "learning_rate": 4.37296206734571e-05, "loss": 4.2143, "step": 382976 }, { "epoch": 0.0, "learning_rate": 4.372123472594658e-05, "loss": 4.2089, "step": 383488 }, { "epoch": 0.0, "learning_rate": 4.371284877843606e-05, "loss": 4.2143, "step": 384000 }, { "epoch": 0.0, "learning_rate": 4.370446283092554e-05, "loss": 4.1994, "step": 384512 }, { "epoch": 0.0, "learning_rate": 4.369607688341502e-05, "loss": 4.2034, "step": 385024 }, { "epoch": 0.0, "learning_rate": 4.36876909359045e-05, "loss": 4.1948, "step": 385536 }, { "epoch": 0.0, "learning_rate": 4.367930498839398e-05, "loss": 4.2119, "step": 386048 }, { "epoch": 0.0, "learning_rate": 4.367091904088346e-05, "loss": 4.2081, "step": 386560 }, { "epoch": 0.0, "learning_rate": 4.366253309337294e-05, "loss": 4.2062, "step": 387072 }, { "epoch": 0.0, "learning_rate": 4.365414714586242e-05, "loss": 4.2113, "step": 387584 }, { "epoch": 0.0, "learning_rate": 4.36457611983519e-05, "loss": 4.1989, "step": 388096 }, { "epoch": 0.0, "learning_rate": 4.363737525084138e-05, "loss": 4.1988, "step": 388608 }, { "epoch": 0.0, "learning_rate": 4.362898930333086e-05, "loss": 4.1972, "step": 389120 }, { "epoch": 0.0, "learning_rate": 4.3620603355820335e-05, "loss": 4.187, "step": 389632 }, { "epoch": 0.0, "learning_rate": 4.361221740830982e-05, "loss": 4.2032, "step": 390144 }, { "epoch": 0.0, "learning_rate": 4.360384783960304e-05, "loss": 4.1913, "step": 390656 }, { "epoch": 0.0, "learning_rate": 4.359546189209251e-05, "loss": 4.1947, "step": 391168 }, { "epoch": 0.0, "learning_rate": 4.358707594458199e-05, "loss": 4.2298, "step": 391680 }, { "epoch": 0.0, "learning_rate": 4.357868999707147e-05, "loss": 4.1951, "step": 392192 }, { "epoch": 0.0, "learning_rate": 4.357030404956095e-05, "loss": 4.2032, "step": 392704 }, { "epoch": 0.0, "learning_rate": 4.356191810205043e-05, "loss": 4.2046, "step": 393216 }, { "epoch": 0.0, "learning_rate": 4.355354853334364e-05, "loss": 4.2035, "step": 393728 }, { "epoch": 0.0, "learning_rate": 4.354516258583312e-05, "loss": 4.1953, "step": 394240 }, { "epoch": 0.0, "learning_rate": 4.3536793017126336e-05, "loss": 4.1928, "step": 394752 }, { "epoch": 0.0, "learning_rate": 4.352840706961581e-05, "loss": 4.2005, "step": 395264 }, { "epoch": 0.0, "learning_rate": 4.352002112210529e-05, "loss": 4.1829, "step": 395776 }, { "epoch": 0.0, "learning_rate": 4.3511635174594776e-05, "loss": 4.1931, "step": 396288 }, { "epoch": 0.0, "learning_rate": 4.3503249227084256e-05, "loss": 4.1875, "step": 396800 }, { "epoch": 0.01, "learning_rate": 4.3494863279573736e-05, "loss": 4.1947, "step": 397312 }, { "epoch": 0.01, "learning_rate": 4.3486477332063216e-05, "loss": 4.1989, "step": 397824 }, { "epoch": 0.01, "learning_rate": 4.3478091384552696e-05, "loss": 4.1993, "step": 398336 }, { "epoch": 0.01, "learning_rate": 4.3469705437042175e-05, "loss": 4.1918, "step": 398848 }, { "epoch": 0.01, "learning_rate": 4.3461335868335385e-05, "loss": 4.1995, "step": 399360 }, { "epoch": 0.01, "learning_rate": 4.3452949920824865e-05, "loss": 4.202, "step": 399872 }, { "epoch": 0.01, "learning_rate": 4.3444563973314344e-05, "loss": 4.1874, "step": 400384 }, { "epoch": 0.01, "learning_rate": 4.3436178025803824e-05, "loss": 4.2003, "step": 400896 }, { "epoch": 0.01, "learning_rate": 4.3427792078293304e-05, "loss": 4.1808, "step": 401408 }, { "epoch": 0.01, "learning_rate": 4.3419422509586514e-05, "loss": 4.2024, "step": 401920 }, { "epoch": 0.01, "learning_rate": 4.3411036562075993e-05, "loss": 4.175, "step": 402432 }, { "epoch": 0.01, "learning_rate": 4.3402650614565473e-05, "loss": 4.2085, "step": 402944 }, { "epoch": 0.01, "learning_rate": 4.339426466705496e-05, "loss": 4.1957, "step": 403456 }, { "epoch": 0.01, "learning_rate": 4.338587871954444e-05, "loss": 4.1916, "step": 403968 }, { "epoch": 0.01, "learning_rate": 4.337750915083765e-05, "loss": 4.1957, "step": 404480 }, { "epoch": 0.01, "learning_rate": 4.336912320332713e-05, "loss": 4.1911, "step": 404992 }, { "epoch": 0.01, "learning_rate": 4.336073725581661e-05, "loss": 4.1947, "step": 405504 }, { "epoch": 0.01, "learning_rate": 4.335235130830609e-05, "loss": 4.181, "step": 406016 }, { "epoch": 0.01, "learning_rate": 4.334396536079557e-05, "loss": 4.1758, "step": 406528 }, { "epoch": 0.01, "learning_rate": 4.333557941328505e-05, "loss": 4.2031, "step": 407040 }, { "epoch": 0.01, "learning_rate": 4.332719346577452e-05, "loss": 4.1896, "step": 407552 }, { "epoch": 0.01, "learning_rate": 4.331882389706774e-05, "loss": 4.1971, "step": 408064 }, { "epoch": 0.01, "learning_rate": 4.331043794955722e-05, "loss": 4.183, "step": 408576 }, { "epoch": 0.01, "learning_rate": 4.33020520020467e-05, "loss": 4.187, "step": 409088 }, { "epoch": 0.01, "learning_rate": 4.329366605453618e-05, "loss": 4.1821, "step": 409600 }, { "epoch": 0.01, "learning_rate": 4.328528010702566e-05, "loss": 4.1923, "step": 410112 }, { "epoch": 0.01, "learning_rate": 4.327689415951514e-05, "loss": 4.1829, "step": 410624 }, { "epoch": 0.01, "learning_rate": 4.326850821200462e-05, "loss": 4.1965, "step": 411136 }, { "epoch": 0.01, "learning_rate": 4.32601222644941e-05, "loss": 4.1959, "step": 411648 }, { "epoch": 0.01, "learning_rate": 4.325175269578731e-05, "loss": 4.1775, "step": 412160 }, { "epoch": 0.01, "learning_rate": 4.324338312708052e-05, "loss": 4.1825, "step": 412672 }, { "epoch": 0.01, "learning_rate": 4.3234997179569996e-05, "loss": 4.1925, "step": 413184 }, { "epoch": 0.01, "learning_rate": 4.3226611232059476e-05, "loss": 4.1735, "step": 413696 }, { "epoch": 0.01, "learning_rate": 4.3218225284548956e-05, "loss": 4.1827, "step": 414208 }, { "epoch": 0.01, "learning_rate": 4.3209839337038436e-05, "loss": 4.1873, "step": 414720 }, { "epoch": 0.01, "learning_rate": 4.3201453389527916e-05, "loss": 4.1857, "step": 415232 }, { "epoch": 0.01, "learning_rate": 4.3193067442017396e-05, "loss": 4.1686, "step": 415744 }, { "epoch": 0.01, "learning_rate": 4.3184681494506876e-05, "loss": 4.1747, "step": 416256 }, { "epoch": 0.01, "learning_rate": 4.317631192580009e-05, "loss": 4.1693, "step": 416768 }, { "epoch": 0.01, "learning_rate": 4.31679423570933e-05, "loss": 4.1931, "step": 417280 }, { "epoch": 0.01, "learning_rate": 4.315955640958278e-05, "loss": 4.1846, "step": 417792 }, { "epoch": 0.01, "learning_rate": 4.315117046207226e-05, "loss": 4.1824, "step": 418304 }, { "epoch": 0.01, "learning_rate": 4.314278451456174e-05, "loss": 4.1878, "step": 418816 }, { "epoch": 0.01, "learning_rate": 4.313439856705122e-05, "loss": 4.1761, "step": 419328 }, { "epoch": 0.01, "learning_rate": 4.31260126195407e-05, "loss": 4.198, "step": 419840 }, { "epoch": 0.01, "learning_rate": 4.311764305083391e-05, "loss": 4.169, "step": 420352 }, { "epoch": 0.01, "learning_rate": 4.310925710332339e-05, "loss": 4.1855, "step": 420864 }, { "epoch": 0.01, "learning_rate": 4.310087115581287e-05, "loss": 4.1832, "step": 421376 }, { "epoch": 0.01, "learning_rate": 4.309248520830235e-05, "loss": 4.1804, "step": 421888 }, { "epoch": 0.01, "learning_rate": 4.308409926079183e-05, "loss": 4.1848, "step": 422400 }, { "epoch": 0.01, "learning_rate": 4.3075713313281316e-05, "loss": 4.1775, "step": 422912 }, { "epoch": 0.01, "learning_rate": 4.3067343744574525e-05, "loss": 4.1799, "step": 423424 }, { "epoch": 0.01, "learning_rate": 4.3058957797064005e-05, "loss": 4.1856, "step": 423936 }, { "epoch": 0.01, "learning_rate": 4.3050571849553485e-05, "loss": 4.1664, "step": 424448 }, { "epoch": 0.01, "learning_rate": 4.3042185902042965e-05, "loss": 4.1853, "step": 424960 }, { "epoch": 0.01, "learning_rate": 4.3033799954532445e-05, "loss": 4.1727, "step": 425472 }, { "epoch": 0.01, "learning_rate": 4.3025414007021925e-05, "loss": 4.1858, "step": 425984 }, { "epoch": 0.01, "learning_rate": 4.3017044438315134e-05, "loss": 4.1729, "step": 426496 }, { "epoch": 0.01, "learning_rate": 4.3008658490804614e-05, "loss": 4.1712, "step": 427008 }, { "epoch": 0.02, "learning_rate": 4.3000272543294094e-05, "loss": 4.1769, "step": 427520 }, { "epoch": 0.02, "learning_rate": 4.2991886595783574e-05, "loss": 4.1781, "step": 428032 }, { "epoch": 0.02, "learning_rate": 4.298351702707678e-05, "loss": 4.1799, "step": 428544 }, { "epoch": 0.02, "learning_rate": 4.297513107956627e-05, "loss": 4.1645, "step": 429056 }, { "epoch": 0.02, "learning_rate": 4.296674513205575e-05, "loss": 4.1776, "step": 429568 }, { "epoch": 0.02, "learning_rate": 4.295835918454523e-05, "loss": 4.1859, "step": 430080 }, { "epoch": 0.02, "learning_rate": 4.294997323703471e-05, "loss": 4.1731, "step": 430592 }, { "epoch": 0.02, "learning_rate": 4.294158728952418e-05, "loss": 4.1569, "step": 431104 }, { "epoch": 0.02, "learning_rate": 4.293320134201366e-05, "loss": 4.1714, "step": 431616 }, { "epoch": 0.02, "learning_rate": 4.292483177330688e-05, "loss": 4.1765, "step": 432128 }, { "epoch": 0.02, "learning_rate": 4.291644582579636e-05, "loss": 4.1786, "step": 432640 }, { "epoch": 0.02, "learning_rate": 4.290805987828583e-05, "loss": 4.1788, "step": 433152 }, { "epoch": 0.02, "learning_rate": 4.289967393077531e-05, "loss": 4.1693, "step": 433664 }, { "epoch": 0.02, "learning_rate": 4.289128798326479e-05, "loss": 4.1666, "step": 434176 }, { "epoch": 0.02, "learning_rate": 4.288290203575427e-05, "loss": 4.1766, "step": 434688 }, { "epoch": 0.02, "learning_rate": 4.287451608824375e-05, "loss": 4.1555, "step": 435200 }, { "epoch": 0.02, "learning_rate": 4.286613014073324e-05, "loss": 4.1693, "step": 435712 }, { "epoch": 0.02, "learning_rate": 4.285774419322272e-05, "loss": 4.1663, "step": 436224 }, { "epoch": 0.02, "learning_rate": 4.2849391003319656e-05, "loss": 4.1761, "step": 436736 }, { "epoch": 0.02, "learning_rate": 4.2841005055809136e-05, "loss": 4.1546, "step": 437248 }, { "epoch": 0.02, "learning_rate": 4.2832619108298616e-05, "loss": 4.1662, "step": 437760 }, { "epoch": 0.02, "learning_rate": 4.2824233160788096e-05, "loss": 4.1664, "step": 438272 }, { "epoch": 0.02, "learning_rate": 4.2815847213277576e-05, "loss": 4.1635, "step": 438784 }, { "epoch": 0.02, "learning_rate": 4.2807461265767056e-05, "loss": 4.1694, "step": 439296 }, { "epoch": 0.02, "learning_rate": 4.2799091697060265e-05, "loss": 4.156, "step": 439808 }, { "epoch": 0.02, "learning_rate": 4.2790722128353474e-05, "loss": 4.1706, "step": 440320 }, { "epoch": 0.02, "learning_rate": 4.278233618084296e-05, "loss": 4.1717, "step": 440832 }, { "epoch": 0.02, "learning_rate": 4.277395023333244e-05, "loss": 4.1594, "step": 441344 }, { "epoch": 0.02, "learning_rate": 4.276556428582192e-05, "loss": 4.1748, "step": 441856 }, { "epoch": 0.02, "learning_rate": 4.275719471711513e-05, "loss": 4.1599, "step": 442368 }, { "epoch": 0.02, "learning_rate": 4.274880876960461e-05, "loss": 4.1744, "step": 442880 }, { "epoch": 0.02, "learning_rate": 4.274042282209409e-05, "loss": 4.1591, "step": 443392 }, { "epoch": 0.02, "learning_rate": 4.273203687458357e-05, "loss": 4.1739, "step": 443904 }, { "epoch": 0.02, "learning_rate": 4.272365092707305e-05, "loss": 4.1545, "step": 444416 }, { "epoch": 0.02, "learning_rate": 4.271528135836626e-05, "loss": 4.1662, "step": 444928 }, { "epoch": 0.02, "learning_rate": 4.270689541085574e-05, "loss": 4.1605, "step": 445440 }, { "epoch": 0.02, "learning_rate": 4.269850946334522e-05, "loss": 4.1692, "step": 445952 }, { "epoch": 0.02, "learning_rate": 4.26901235158347e-05, "loss": 4.1596, "step": 446464 }, { "epoch": 0.02, "learning_rate": 4.268173756832418e-05, "loss": 4.167, "step": 446976 }, { "epoch": 0.02, "learning_rate": 4.2673367999617395e-05, "loss": 4.1442, "step": 447488 }, { "epoch": 0.02, "learning_rate": 4.2664982052106875e-05, "loss": 4.1782, "step": 448000 }, { "epoch": 0.02, "learning_rate": 4.2656596104596355e-05, "loss": 4.1597, "step": 448512 }, { "epoch": 0.02, "learning_rate": 4.2648210157085835e-05, "loss": 4.1659, "step": 449024 }, { "epoch": 0.02, "learning_rate": 4.2639824209575315e-05, "loss": 4.1525, "step": 449536 }, { "epoch": 0.02, "learning_rate": 4.2631438262064795e-05, "loss": 4.1706, "step": 450048 }, { "epoch": 0.02, "learning_rate": 4.2623052314554274e-05, "loss": 4.1714, "step": 450560 }, { "epoch": 0.02, "learning_rate": 4.2614666367043754e-05, "loss": 4.1583, "step": 451072 }, { "epoch": 0.02, "learning_rate": 4.2606280419533234e-05, "loss": 4.1611, "step": 451584 }, { "epoch": 0.02, "learning_rate": 4.2597894472022714e-05, "loss": 4.1673, "step": 452096 }, { "epoch": 0.02, "learning_rate": 4.258950852451219e-05, "loss": 4.1647, "step": 452608 }, { "epoch": 0.02, "learning_rate": 4.258112257700167e-05, "loss": 4.1747, "step": 453120 }, { "epoch": 0.02, "learning_rate": 4.257275300829488e-05, "loss": 4.1454, "step": 453632 }, { "epoch": 0.02, "learning_rate": 4.256438343958809e-05, "loss": 4.1673, "step": 454144 }, { "epoch": 0.02, "learning_rate": 4.255599749207758e-05, "loss": 4.1552, "step": 454656 }, { "epoch": 0.02, "learning_rate": 4.254761154456706e-05, "loss": 4.1656, "step": 455168 }, { "epoch": 0.02, "learning_rate": 4.253922559705654e-05, "loss": 4.1643, "step": 455680 }, { "epoch": 0.02, "learning_rate": 4.253083964954602e-05, "loss": 4.1488, "step": 456192 }, { "epoch": 0.02, "learning_rate": 4.252247008083923e-05, "loss": 4.1707, "step": 456704 }, { "epoch": 0.02, "learning_rate": 4.251410051213244e-05, "loss": 4.1614, "step": 457216 }, { "epoch": 0.02, "learning_rate": 4.250571456462192e-05, "loss": 4.1632, "step": 457728 }, { "epoch": 0.03, "eval_loss": 4.210960865020752, "eval_runtime": 303.7152, "eval_samples_per_second": 1256.41, "eval_steps_per_second": 39.264, "step": 457920 }, { "epoch": 1.0, "learning_rate": 4.24973286171114e-05, "loss": 4.1566, "step": 458240 }, { "epoch": 1.0, "learning_rate": 4.248894266960088e-05, "loss": 4.1565, "step": 458752 }, { "epoch": 1.0, "learning_rate": 4.248055672209036e-05, "loss": 4.1662, "step": 459264 }, { "epoch": 1.0, "learning_rate": 4.247217077457984e-05, "loss": 4.1619, "step": 459776 }, { "epoch": 1.0, "learning_rate": 4.246378482706932e-05, "loss": 4.1629, "step": 460288 }, { "epoch": 1.0, "learning_rate": 4.24553988795588e-05, "loss": 4.1558, "step": 460800 }, { "epoch": 1.0, "learning_rate": 4.244702931085201e-05, "loss": 4.148, "step": 461312 }, { "epoch": 1.0, "learning_rate": 4.243864336334149e-05, "loss": 4.1497, "step": 461824 }, { "epoch": 1.0, "learning_rate": 4.2430257415830966e-05, "loss": 4.1593, "step": 462336 }, { "epoch": 1.0, "learning_rate": 4.2421871468320446e-05, "loss": 4.1629, "step": 462848 }, { "epoch": 1.0, "learning_rate": 4.2413485520809926e-05, "loss": 4.157, "step": 463360 }, { "epoch": 1.0, "learning_rate": 4.2405099573299406e-05, "loss": 4.1624, "step": 463872 }, { "epoch": 1.0, "learning_rate": 4.2396730004592615e-05, "loss": 4.1473, "step": 464384 }, { "epoch": 1.0, "learning_rate": 4.2388344057082095e-05, "loss": 4.1524, "step": 464896 }, { "epoch": 1.0, "learning_rate": 4.2379958109571575e-05, "loss": 4.1514, "step": 465408 }, { "epoch": 1.0, "learning_rate": 4.2371572162061055e-05, "loss": 4.1394, "step": 465920 }, { "epoch": 1.0, "learning_rate": 4.2363186214550535e-05, "loss": 4.1567, "step": 466432 }, { "epoch": 1.0, "learning_rate": 4.2354833024647487e-05, "loss": 4.1408, "step": 466944 }, { "epoch": 1.0, "learning_rate": 4.2346447077136966e-05, "loss": 4.1469, "step": 467456 }, { "epoch": 1.0, "learning_rate": 4.233806112962644e-05, "loss": 4.1819, "step": 467968 }, { "epoch": 1.0, "learning_rate": 4.232967518211592e-05, "loss": 4.1482, "step": 468480 }, { "epoch": 1.0, "learning_rate": 4.23212892346054e-05, "loss": 4.1522, "step": 468992 }, { "epoch": 1.0, "learning_rate": 4.231290328709488e-05, "loss": 4.1548, "step": 469504 }, { "epoch": 1.0, "learning_rate": 4.230451733958436e-05, "loss": 4.1608, "step": 470016 }, { "epoch": 1.0, "learning_rate": 4.229613139207384e-05, "loss": 4.1406, "step": 470528 }, { "epoch": 1.0, "learning_rate": 4.228774544456332e-05, "loss": 4.1468, "step": 471040 }, { "epoch": 1.0, "learning_rate": 4.22793594970528e-05, "loss": 4.1527, "step": 471552 }, { "epoch": 1.0, "learning_rate": 4.227097354954228e-05, "loss": 4.1408, "step": 472064 }, { "epoch": 1.0, "learning_rate": 4.226258760203176e-05, "loss": 4.1471, "step": 472576 }, { "epoch": 1.0, "learning_rate": 4.225421803332497e-05, "loss": 4.14, "step": 473088 }, { "epoch": 1.01, "learning_rate": 4.2245832085814455e-05, "loss": 4.1483, "step": 473600 }, { "epoch": 1.01, "learning_rate": 4.2237446138303935e-05, "loss": 4.1542, "step": 474112 }, { "epoch": 1.01, "learning_rate": 4.2229060190793415e-05, "loss": 4.1504, "step": 474624 }, { "epoch": 1.01, "learning_rate": 4.2220690622086624e-05, "loss": 4.1438, "step": 475136 }, { "epoch": 1.01, "learning_rate": 4.221232105337983e-05, "loss": 4.1504, "step": 475648 }, { "epoch": 1.01, "learning_rate": 4.220395148467304e-05, "loss": 4.1547, "step": 476160 }, { "epoch": 1.01, "learning_rate": 4.219556553716252e-05, "loss": 4.1402, "step": 476672 }, { "epoch": 1.01, "learning_rate": 4.2187179589652e-05, "loss": 4.1591, "step": 477184 }, { "epoch": 1.01, "learning_rate": 4.217879364214148e-05, "loss": 4.133, "step": 477696 }, { "epoch": 1.01, "learning_rate": 4.217040769463096e-05, "loss": 4.1531, "step": 478208 }, { "epoch": 1.01, "learning_rate": 4.216202174712044e-05, "loss": 4.1301, "step": 478720 }, { "epoch": 1.01, "learning_rate": 4.215365217841366e-05, "loss": 4.1621, "step": 479232 }, { "epoch": 1.01, "learning_rate": 4.214526623090314e-05, "loss": 4.1466, "step": 479744 }, { "epoch": 1.01, "learning_rate": 4.213688028339262e-05, "loss": 4.149, "step": 480256 }, { "epoch": 1.01, "learning_rate": 4.21284943358821e-05, "loss": 4.1478, "step": 480768 }, { "epoch": 1.01, "learning_rate": 4.212010838837158e-05, "loss": 4.1457, "step": 481280 }, { "epoch": 1.01, "learning_rate": 4.211172244086106e-05, "loss": 4.15, "step": 481792 }, { "epoch": 1.01, "learning_rate": 4.210333649335054e-05, "loss": 4.1378, "step": 482304 }, { "epoch": 1.01, "learning_rate": 4.209495054584002e-05, "loss": 4.1261, "step": 482816 }, { "epoch": 1.01, "learning_rate": 4.20865645983295e-05, "loss": 4.1605, "step": 483328 }, { "epoch": 1.01, "learning_rate": 4.207817865081897e-05, "loss": 4.1408, "step": 483840 }, { "epoch": 1.01, "learning_rate": 4.206979270330845e-05, "loss": 4.1556, "step": 484352 }, { "epoch": 1.01, "learning_rate": 4.206140675579793e-05, "loss": 4.1361, "step": 484864 }, { "epoch": 1.01, "learning_rate": 4.2053037187091147e-05, "loss": 4.1416, "step": 485376 }, { "epoch": 1.01, "learning_rate": 4.2044651239580626e-05, "loss": 4.133, "step": 485888 }, { "epoch": 1.01, "learning_rate": 4.2036265292070106e-05, "loss": 4.1492, "step": 486400 }, { "epoch": 1.01, "learning_rate": 4.2027879344559586e-05, "loss": 4.1403, "step": 486912 }, { "epoch": 1.01, "learning_rate": 4.2019509775852796e-05, "loss": 4.152, "step": 487424 }, { "epoch": 1.01, "learning_rate": 4.2011123828342275e-05, "loss": 4.1502, "step": 487936 }, { "epoch": 1.01, "learning_rate": 4.200275425963549e-05, "loss": 4.1324, "step": 488448 }, { "epoch": 1.01, "learning_rate": 4.199436831212497e-05, "loss": 4.1344, "step": 488960 }, { "epoch": 1.01, "learning_rate": 4.1985982364614444e-05, "loss": 4.154, "step": 489472 }, { "epoch": 1.01, "learning_rate": 4.1977596417103924e-05, "loss": 4.1282, "step": 489984 }, { "epoch": 1.01, "learning_rate": 4.1969210469593404e-05, "loss": 4.1371, "step": 490496 }, { "epoch": 1.01, "learning_rate": 4.196084090088662e-05, "loss": 4.1408, "step": 491008 }, { "epoch": 1.01, "learning_rate": 4.19524549533761e-05, "loss": 4.1467, "step": 491520 }, { "epoch": 1.01, "learning_rate": 4.194406900586558e-05, "loss": 4.1242, "step": 492032 }, { "epoch": 1.01, "learning_rate": 4.193568305835506e-05, "loss": 4.1293, "step": 492544 }, { "epoch": 1.01, "learning_rate": 4.192729711084454e-05, "loss": 4.1303, "step": 493056 }, { "epoch": 1.01, "learning_rate": 4.191891116333402e-05, "loss": 4.1392, "step": 493568 }, { "epoch": 1.01, "learning_rate": 4.19105252158235e-05, "loss": 4.1427, "step": 494080 }, { "epoch": 1.01, "learning_rate": 4.190213926831298e-05, "loss": 4.1404, "step": 494592 }, { "epoch": 1.01, "learning_rate": 4.189376969960619e-05, "loss": 4.1443, "step": 495104 }, { "epoch": 1.01, "learning_rate": 4.188538375209567e-05, "loss": 4.1325, "step": 495616 }, { "epoch": 1.01, "learning_rate": 4.187699780458515e-05, "loss": 4.1571, "step": 496128 }, { "epoch": 1.01, "learning_rate": 4.186862823587836e-05, "loss": 4.1261, "step": 496640 }, { "epoch": 1.01, "learning_rate": 4.186024228836784e-05, "loss": 4.1397, "step": 497152 }, { "epoch": 1.01, "learning_rate": 4.185185634085732e-05, "loss": 4.14, "step": 497664 }, { "epoch": 1.01, "learning_rate": 4.18434703933468e-05, "loss": 4.1352, "step": 498176 }, { "epoch": 1.01, "learning_rate": 4.183508444583628e-05, "loss": 4.1434, "step": 498688 }, { "epoch": 1.01, "learning_rate": 4.1826698498325765e-05, "loss": 4.1349, "step": 499200 }, { "epoch": 1.01, "learning_rate": 4.1818328929618974e-05, "loss": 4.1327, "step": 499712 }, { "epoch": 1.01, "learning_rate": 4.1809942982108454e-05, "loss": 4.1441, "step": 500224 }, { "epoch": 1.01, "learning_rate": 4.1801557034597934e-05, "loss": 4.1273, "step": 500736 }, { "epoch": 1.01, "learning_rate": 4.1793171087087414e-05, "loss": 4.138, "step": 501248 }, { "epoch": 1.01, "learning_rate": 4.1784785139576894e-05, "loss": 4.132, "step": 501760 }, { "epoch": 1.01, "learning_rate": 4.1776399192066373e-05, "loss": 4.1428, "step": 502272 }, { "epoch": 1.01, "learning_rate": 4.176802962335958e-05, "loss": 4.13, "step": 502784 }, { "epoch": 1.01, "learning_rate": 4.175964367584906e-05, "loss": 4.1265, "step": 503296 }, { "epoch": 1.02, "learning_rate": 4.175125772833854e-05, "loss": 4.1327, "step": 503808 }, { "epoch": 1.02, "learning_rate": 4.174288815963175e-05, "loss": 4.1376, "step": 504320 }, { "epoch": 1.02, "learning_rate": 4.173450221212123e-05, "loss": 4.1374, "step": 504832 }, { "epoch": 1.02, "learning_rate": 4.172611626461072e-05, "loss": 4.1222, "step": 505344 }, { "epoch": 1.02, "learning_rate": 4.17177303171002e-05, "loss": 4.1357, "step": 505856 }, { "epoch": 1.02, "learning_rate": 4.170934436958968e-05, "loss": 4.1411, "step": 506368 }, { "epoch": 1.02, "learning_rate": 4.170095842207916e-05, "loss": 4.1326, "step": 506880 }, { "epoch": 1.02, "learning_rate": 4.169257247456863e-05, "loss": 4.1153, "step": 507392 }, { "epoch": 1.02, "learning_rate": 4.168418652705811e-05, "loss": 4.1297, "step": 507904 }, { "epoch": 1.02, "learning_rate": 4.167580057954759e-05, "loss": 4.128, "step": 508416 }, { "epoch": 1.02, "learning_rate": 4.166741463203707e-05, "loss": 4.1402, "step": 508928 }, { "epoch": 1.02, "learning_rate": 4.165902868452655e-05, "loss": 4.1368, "step": 509440 }, { "epoch": 1.02, "learning_rate": 4.165064273701603e-05, "loss": 4.1247, "step": 509952 }, { "epoch": 1.02, "learning_rate": 4.164225678950551e-05, "loss": 4.1243, "step": 510464 }, { "epoch": 1.02, "learning_rate": 4.163388722079872e-05, "loss": 4.134, "step": 510976 }, { "epoch": 1.02, "learning_rate": 4.1625517652091936e-05, "loss": 4.1138, "step": 511488 }, { "epoch": 1.02, "learning_rate": 4.1617131704581416e-05, "loss": 4.1321, "step": 512000 }, { "epoch": 1.02, "learning_rate": 4.1608745757070896e-05, "loss": 4.1201, "step": 512512 }, { "epoch": 1.02, "learning_rate": 4.1600359809560376e-05, "loss": 4.1399, "step": 513024 }, { "epoch": 1.02, "learning_rate": 4.1591973862049856e-05, "loss": 4.1126, "step": 513536 }, { "epoch": 1.02, "learning_rate": 4.1583587914539336e-05, "loss": 4.1231, "step": 514048 }, { "epoch": 1.02, "learning_rate": 4.1575218345832545e-05, "loss": 4.1222, "step": 514560 }, { "epoch": 1.02, "learning_rate": 4.1566832398322025e-05, "loss": 4.1286, "step": 515072 }, { "epoch": 1.02, "learning_rate": 4.1558446450811505e-05, "loss": 4.1231, "step": 515584 }, { "epoch": 1.02, "learning_rate": 4.1550060503300985e-05, "loss": 4.1177, "step": 516096 }, { "epoch": 1.02, "learning_rate": 4.1541674555790465e-05, "loss": 4.128, "step": 516608 }, { "epoch": 1.02, "learning_rate": 4.1533288608279945e-05, "loss": 4.1309, "step": 517120 }, { "epoch": 1.02, "learning_rate": 4.1524902660769425e-05, "loss": 4.1188, "step": 517632 }, { "epoch": 1.02, "learning_rate": 4.1516516713258905e-05, "loss": 4.1368, "step": 518144 }, { "epoch": 1.02, "learning_rate": 4.1508130765748385e-05, "loss": 4.1157, "step": 518656 }, { "epoch": 1.02, "learning_rate": 4.14997611970416e-05, "loss": 4.1261, "step": 519168 }, { "epoch": 1.02, "learning_rate": 4.149137524953108e-05, "loss": 4.1206, "step": 519680 }, { "epoch": 1.02, "learning_rate": 4.148298930202056e-05, "loss": 4.1306, "step": 520192 }, { "epoch": 1.02, "learning_rate": 4.147460335451004e-05, "loss": 4.1169, "step": 520704 }, { "epoch": 1.02, "learning_rate": 4.146623378580325e-05, "loss": 4.1232, "step": 521216 }, { "epoch": 1.02, "learning_rate": 4.145784783829273e-05, "loss": 4.1251, "step": 521728 }, { "epoch": 1.02, "learning_rate": 4.144946189078221e-05, "loss": 4.1237, "step": 522240 }, { "epoch": 1.02, "learning_rate": 4.144107594327169e-05, "loss": 4.1175, "step": 522752 }, { "epoch": 1.02, "learning_rate": 4.14327063745649e-05, "loss": 4.1271, "step": 523264 }, { "epoch": 1.02, "learning_rate": 4.142432042705438e-05, "loss": 4.1077, "step": 523776 }, { "epoch": 1.02, "learning_rate": 4.141593447954386e-05, "loss": 4.1354, "step": 524288 }, { "epoch": 1.02, "learning_rate": 4.140754853203334e-05, "loss": 4.1223, "step": 524800 }, { "epoch": 1.02, "learning_rate": 4.1399178963326554e-05, "loss": 4.1251, "step": 525312 }, { "epoch": 1.02, "learning_rate": 4.1390793015816034e-05, "loss": 4.1136, "step": 525824 }, { "epoch": 1.02, "learning_rate": 4.1382407068305514e-05, "loss": 4.1338, "step": 526336 }, { "epoch": 1.02, "learning_rate": 4.1374021120794994e-05, "loss": 4.1254, "step": 526848 }, { "epoch": 1.02, "learning_rate": 4.136563517328447e-05, "loss": 4.1194, "step": 527360 }, { "epoch": 1.02, "learning_rate": 4.135724922577395e-05, "loss": 4.1198, "step": 527872 }, { "epoch": 1.02, "learning_rate": 4.134886327826343e-05, "loss": 4.1256, "step": 528384 }, { "epoch": 1.02, "learning_rate": 4.134047733075291e-05, "loss": 4.1215, "step": 528896 }, { "epoch": 1.02, "learning_rate": 4.1332107762046116e-05, "loss": 4.1343, "step": 529408 }, { "epoch": 1.02, "learning_rate": 4.1323721814535596e-05, "loss": 4.1048, "step": 529920 }, { "epoch": 1.02, "learning_rate": 4.1315335867025076e-05, "loss": 4.1269, "step": 530432 }, { "epoch": 1.02, "learning_rate": 4.1306949919514556e-05, "loss": 4.1169, "step": 530944 }, { "epoch": 1.02, "learning_rate": 4.129856397200404e-05, "loss": 4.1258, "step": 531456 }, { "epoch": 1.02, "learning_rate": 4.129017802449352e-05, "loss": 4.1194, "step": 531968 }, { "epoch": 1.02, "learning_rate": 4.128180845578673e-05, "loss": 4.1139, "step": 532480 }, { "epoch": 1.02, "learning_rate": 4.127342250827621e-05, "loss": 4.1275, "step": 532992 }, { "epoch": 1.02, "learning_rate": 4.126503656076569e-05, "loss": 4.1215, "step": 533504 }, { "epoch": 1.02, "learning_rate": 4.125665061325517e-05, "loss": 4.122, "step": 534016 }, { "epoch": 1.03, "eval_loss": 4.178958415985107, "eval_runtime": 303.5491, "eval_samples_per_second": 1257.098, "eval_steps_per_second": 39.285, "step": 534240 }, { "epoch": 0.0, "learning_rate": 4.124826466574465e-05, "loss": 4.1201, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.123987871823413e-05, "loss": 4.1158, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.123149277072361e-05, "loss": 4.1258, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.122310682321309e-05, "loss": 4.1248, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.121472087570257e-05, "loss": 4.126, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.120633492819205e-05, "loss": 4.1135, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.119794898068153e-05, "loss": 4.1106, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.118956303317101e-05, "loss": 4.1071, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.118117708566049e-05, "loss": 4.1227, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.117279113814997e-05, "loss": 4.1279, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.116440519063945e-05, "loss": 4.1143, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.115601924312893e-05, "loss": 4.1216, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.114764967442214e-05, "loss": 4.1125, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.113926372691162e-05, "loss": 4.1125, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.11308777794011e-05, "loss": 4.1109, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.112249183189058e-05, "loss": 4.1061, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.111410588438006e-05, "loss": 4.1135, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.110571993686954e-05, "loss": 4.1072, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109733398935902e-05, "loss": 4.1072, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.10889480418485e-05, "loss": 4.1392, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108056209433798e-05, "loss": 4.1155, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.107217614682746e-05, "loss": 4.1133, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.1063806578120676e-05, "loss": 4.1161, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.1055420630610156e-05, "loss": 4.121, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.1047034683099636e-05, "loss": 4.1042, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.1038648735589115e-05, "loss": 4.111, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.1030262788078595e-05, "loss": 4.1138, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.102187684056807e-05, "loss": 4.1052, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.101349089305755e-05, "loss": 4.103, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.100510494554703e-05, "loss": 4.1035, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.0996751755643974e-05, "loss": 4.1105, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.0988365808133454e-05, "loss": 4.1183, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.0979979860622933e-05, "loss": 4.114, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.097161029191615e-05, "loss": 4.1058, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.096322434440563e-05, "loss": 4.1125, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.095485477569884e-05, "loss": 4.1156, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.094646882818832e-05, "loss": 4.109, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.09380828806778e-05, "loss": 4.1145, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.092969693316728e-05, "loss": 4.0993, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.092131098565676e-05, "loss": 4.1146, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.091292503814624e-05, "loss": 4.0964, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.090453909063572e-05, "loss": 4.1228, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.089615314312519e-05, "loss": 4.1117, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.088776719561467e-05, "loss": 4.1123, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.087938124810415e-05, "loss": 4.1148, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.087099530059363e-05, "loss": 4.1066, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.086260935308311e-05, "loss": 4.1152, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.08542234055726e-05, "loss": 4.1018, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.084583745806208e-05, "loss": 4.0851, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.083745151055156e-05, "loss": 4.1222, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.082906556304104e-05, "loss": 4.1048, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.082069599433425e-05, "loss": 4.1183, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.0812326425627456e-05, "loss": 4.1029, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.0803940478116936e-05, "loss": 4.1046, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.0795554530606416e-05, "loss": 4.0943, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.0787168583095896e-05, "loss": 4.1129, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.0778782635585376e-05, "loss": 4.1052, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.0770413066878585e-05, "loss": 4.1116, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.0762027119368065e-05, "loss": 4.1198, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.075364117185755e-05, "loss": 4.0976, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.074525522434703e-05, "loss": 4.0988, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.073686927683651e-05, "loss": 4.1168, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.072848332932599e-05, "loss": 4.0942, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.072009738181547e-05, "loss": 4.0983, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.071172781310868e-05, "loss": 4.1058, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.070334186559816e-05, "loss": 4.1097, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.069495591808764e-05, "loss": 4.0902, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.068656997057712e-05, "loss": 4.0948, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.06781840230666e-05, "loss": 4.0894, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.066979807555608e-05, "loss": 4.1051, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.0661412128045553e-05, "loss": 4.1091, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.065304255933877e-05, "loss": 4.1057, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.064465661182825e-05, "loss": 4.1029, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.063627066431773e-05, "loss": 4.1015, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.062788471680721e-05, "loss": 4.1209, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.061949876929669e-05, "loss": 4.0901, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.061111282178617e-05, "loss": 4.1101, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.060272687427565e-05, "loss": 4.1052, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.059434092676513e-05, "loss": 4.0949, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.058597135805834e-05, "loss": 4.1105, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.0577601789351554e-05, "loss": 4.1007, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.056921584184103e-05, "loss": 4.1005, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.056082989433051e-05, "loss": 4.1085, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.055244394681999e-05, "loss": 4.0925, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.0544057999309474e-05, "loss": 4.0999, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.0535672051798954e-05, "loss": 4.0992, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.0527286104288434e-05, "loss": 4.1073, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.0518900156777914e-05, "loss": 4.0951, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.0510514209267394e-05, "loss": 4.0976, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.0502128261756874e-05, "loss": 4.0916, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.049375869305008e-05, "loss": 4.1038, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.048538912434329e-05, "loss": 4.1038, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.047700317683277e-05, "loss": 4.0861, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.046861722932225e-05, "loss": 4.1064, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.046023128181173e-05, "loss": 4.1067, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.045184533430121e-05, "loss": 4.0968, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.044345938679069e-05, "loss": 4.0818, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.043507343928017e-05, "loss": 4.0963, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.042668749176965e-05, "loss": 4.0927, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.041830154425914e-05, "loss": 4.1078, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.040991559674862e-05, "loss": 4.1029, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.040152964923809e-05, "loss": 4.0914, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.039316008053131e-05, "loss": 4.0932, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.038477413302079e-05, "loss": 4.0934, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.037638818551027e-05, "loss": 4.0859, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.036800223799974e-05, "loss": 4.0946, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.035961629048922e-05, "loss": 4.087, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.03512303429787e-05, "loss": 4.1062, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.034286077427191e-05, "loss": 4.0785, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.033447482676139e-05, "loss": 4.0899, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.0326088879250876e-05, "loss": 4.0871, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.0317702931740356e-05, "loss": 4.098, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.0309316984229836e-05, "loss": 4.0875, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.0300931036719316e-05, "loss": 4.0848, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.0292545089208796e-05, "loss": 4.0961, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.0284159141698276e-05, "loss": 4.1005, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.0275805951795214e-05, "loss": 4.0828, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.0267420004284694e-05, "loss": 4.1, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.0259034056774174e-05, "loss": 4.0877, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.0250648109263654e-05, "loss": 4.0924, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.0242262161753134e-05, "loss": 4.0892, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.023389259304634e-05, "loss": 4.0952, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.022550664553583e-05, "loss": 4.0858, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.021712069802531e-05, "loss": 4.0954, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.020873475051479e-05, "loss": 4.0932, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.020034880300427e-05, "loss": 4.0914, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.019196285549375e-05, "loss": 4.0857, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.018357690798323e-05, "loss": 4.0922, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.017519096047271e-05, "loss": 4.0743, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.016682139176592e-05, "loss": 4.1063, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.015846820186286e-05, "loss": 4.085, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.015008225435234e-05, "loss": 4.0928, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.0141696306841817e-05, "loss": 4.08, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.0133310359331297e-05, "loss": 4.0995, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012492441182078e-05, "loss": 4.0937, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011653846431026e-05, "loss": 4.0883, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.010815251679974e-05, "loss": 4.0905, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.009976656928922e-05, "loss": 4.0903, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.00913806217787e-05, "loss": 4.092, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008299467426818e-05, "loss": 4.1067, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.007460872675766e-05, "loss": 4.0711, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.006622277924714e-05, "loss": 4.0983, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.005785321054035e-05, "loss": 4.0854, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.004946726302983e-05, "loss": 4.0929, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.004108131551931e-05, "loss": 4.0853, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.003269536800879e-05, "loss": 4.0873, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.002430942049827e-05, "loss": 4.0936, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.001592347298775e-05, "loss": 4.0909, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.000753752547723e-05, "loss": 4.0898, "step": 610304 }, { "epoch": 0.03, "eval_loss": 4.156386852264404, "eval_runtime": 298.9841, "eval_samples_per_second": 1276.292, "eval_steps_per_second": 39.885, "step": 610560 }, { "epoch": 1.0, "learning_rate": 3.999915157796671e-05, "loss": 4.0888, "step": 610816 }, { "epoch": 1.0, "learning_rate": 3.999079838806366e-05, "loss": 4.0844, "step": 611328 }, { "epoch": 1.0, "learning_rate": 3.998241244055314e-05, "loss": 4.0932, "step": 611840 }, { "epoch": 1.0, "learning_rate": 3.997402649304262e-05, "loss": 4.0906, "step": 612352 }, { "epoch": 1.0, "learning_rate": 3.99656405455321e-05, "loss": 4.0978, "step": 612864 }, { "epoch": 1.0, "learning_rate": 3.9957254598021577e-05, "loss": 4.081, "step": 613376 }, { "epoch": 1.0, "learning_rate": 3.994886865051105e-05, "loss": 4.0794, "step": 613888 }, { "epoch": 1.0, "learning_rate": 3.994048270300053e-05, "loss": 4.0809, "step": 614400 }, { "epoch": 1.0, "learning_rate": 3.993209675549001e-05, "loss": 4.0883, "step": 614912 }, { "epoch": 1.0, "learning_rate": 3.992372718678322e-05, "loss": 4.0958, "step": 615424 }, { "epoch": 1.0, "learning_rate": 3.9915341239272706e-05, "loss": 4.0822, "step": 615936 }, { "epoch": 1.0, "learning_rate": 3.9906955291762185e-05, "loss": 4.0896, "step": 616448 }, { "epoch": 1.0, "learning_rate": 3.98985857230554e-05, "loss": 4.087, "step": 616960 }, { "epoch": 1.0, "learning_rate": 3.9890199775544875e-05, "loss": 4.0778, "step": 617472 }, { "epoch": 1.0, "learning_rate": 3.9881813828034354e-05, "loss": 4.084, "step": 617984 }, { "epoch": 1.0, "learning_rate": 3.9873427880523834e-05, "loss": 4.0709, "step": 618496 }, { "epoch": 1.0, "learning_rate": 3.9865041933013314e-05, "loss": 4.083, "step": 619008 }, { "epoch": 1.0, "learning_rate": 3.9856655985502794e-05, "loss": 4.0744, "step": 619520 }, { "epoch": 1.0, "learning_rate": 3.9848270037992274e-05, "loss": 4.0785, "step": 620032 }, { "epoch": 1.0, "learning_rate": 3.9839884090481754e-05, "loss": 4.1032, "step": 620544 }, { "epoch": 1.0, "learning_rate": 3.9831498142971234e-05, "loss": 4.0904, "step": 621056 }, { "epoch": 1.0, "learning_rate": 3.9823112195460714e-05, "loss": 4.083, "step": 621568 }, { "epoch": 1.0, "learning_rate": 3.9814726247950194e-05, "loss": 4.0849, "step": 622080 }, { "epoch": 1.0, "learning_rate": 3.98063566792434e-05, "loss": 4.0926, "step": 622592 }, { "epoch": 1.0, "learning_rate": 3.979797073173288e-05, "loss": 4.068, "step": 623104 }, { "epoch": 1.0, "learning_rate": 3.978958478422237e-05, "loss": 4.0819, "step": 623616 }, { "epoch": 1.0, "learning_rate": 3.978119883671185e-05, "loss": 4.0859, "step": 624128 }, { "epoch": 1.0, "learning_rate": 3.977281288920133e-05, "loss": 4.0707, "step": 624640 }, { "epoch": 1.0, "learning_rate": 3.976442694169081e-05, "loss": 4.0718, "step": 625152 }, { "epoch": 1.0, "learning_rate": 3.975605737298402e-05, "loss": 4.0746, "step": 625664 }, { "epoch": 1.01, "learning_rate": 3.97476714254735e-05, "loss": 4.0784, "step": 626176 }, { "epoch": 1.01, "learning_rate": 3.973928547796298e-05, "loss": 4.0903, "step": 626688 }, { "epoch": 1.01, "learning_rate": 3.973089953045246e-05, "loss": 4.0815, "step": 627200 }, { "epoch": 1.01, "learning_rate": 3.972251358294193e-05, "loss": 4.0781, "step": 627712 }, { "epoch": 1.01, "learning_rate": 3.971412763543141e-05, "loss": 4.0828, "step": 628224 }, { "epoch": 1.01, "learning_rate": 3.970574168792089e-05, "loss": 4.0855, "step": 628736 }, { "epoch": 1.01, "learning_rate": 3.969737211921411e-05, "loss": 4.0796, "step": 629248 }, { "epoch": 1.01, "learning_rate": 3.968898617170359e-05, "loss": 4.0834, "step": 629760 }, { "epoch": 1.01, "learning_rate": 3.968060022419307e-05, "loss": 4.069, "step": 630272 }, { "epoch": 1.01, "learning_rate": 3.967221427668255e-05, "loss": 4.0831, "step": 630784 }, { "epoch": 1.01, "learning_rate": 3.966382832917203e-05, "loss": 4.0695, "step": 631296 }, { "epoch": 1.01, "learning_rate": 3.965544238166151e-05, "loss": 4.0902, "step": 631808 }, { "epoch": 1.01, "learning_rate": 3.964705643415099e-05, "loss": 4.082, "step": 632320 }, { "epoch": 1.01, "learning_rate": 3.963867048664047e-05, "loss": 4.0792, "step": 632832 }, { "epoch": 1.01, "learning_rate": 3.9630300917933676e-05, "loss": 4.085, "step": 633344 }, { "epoch": 1.01, "learning_rate": 3.9621931349226886e-05, "loss": 4.0776, "step": 633856 }, { "epoch": 1.01, "learning_rate": 3.9613545401716366e-05, "loss": 4.0865, "step": 634368 }, { "epoch": 1.01, "learning_rate": 3.9605159454205845e-05, "loss": 4.0738, "step": 634880 }, { "epoch": 1.01, "learning_rate": 3.9596773506695325e-05, "loss": 4.0507, "step": 635392 }, { "epoch": 1.01, "learning_rate": 3.9588387559184805e-05, "loss": 4.0925, "step": 635904 }, { "epoch": 1.01, "learning_rate": 3.958000161167429e-05, "loss": 4.0756, "step": 636416 }, { "epoch": 1.01, "learning_rate": 3.95716320429675e-05, "loss": 4.0919, "step": 636928 }, { "epoch": 1.01, "learning_rate": 3.956324609545698e-05, "loss": 4.0743, "step": 637440 }, { "epoch": 1.01, "learning_rate": 3.955486014794646e-05, "loss": 4.072, "step": 637952 }, { "epoch": 1.01, "learning_rate": 3.954647420043594e-05, "loss": 4.0675, "step": 638464 }, { "epoch": 1.01, "learning_rate": 3.953810463172915e-05, "loss": 4.0817, "step": 638976 }, { "epoch": 1.01, "learning_rate": 3.952971868421863e-05, "loss": 4.0793, "step": 639488 }, { "epoch": 1.01, "learning_rate": 3.952133273670811e-05, "loss": 4.0784, "step": 640000 }, { "epoch": 1.01, "learning_rate": 3.951294678919759e-05, "loss": 4.0909, "step": 640512 }, { "epoch": 1.01, "learning_rate": 3.950456084168707e-05, "loss": 4.0713, "step": 641024 }, { "epoch": 1.01, "learning_rate": 3.949617489417655e-05, "loss": 4.0657, "step": 641536 }, { "epoch": 1.01, "learning_rate": 3.948778894666603e-05, "loss": 4.0894, "step": 642048 }, { "epoch": 1.01, "learning_rate": 3.947940299915551e-05, "loss": 4.0631, "step": 642560 }, { "epoch": 1.01, "learning_rate": 3.9471033430448726e-05, "loss": 4.0695, "step": 643072 }, { "epoch": 1.01, "learning_rate": 3.9462663861741935e-05, "loss": 4.0748, "step": 643584 }, { "epoch": 1.01, "learning_rate": 3.9454277914231415e-05, "loss": 4.0827, "step": 644096 }, { "epoch": 1.01, "learning_rate": 3.9445891966720895e-05, "loss": 4.0617, "step": 644608 }, { "epoch": 1.01, "learning_rate": 3.9437506019210375e-05, "loss": 4.0668, "step": 645120 }, { "epoch": 1.01, "learning_rate": 3.9429120071699855e-05, "loss": 4.0608, "step": 645632 }, { "epoch": 1.01, "learning_rate": 3.9420734124189335e-05, "loss": 4.0717, "step": 646144 }, { "epoch": 1.01, "learning_rate": 3.9412348176678815e-05, "loss": 4.0812, "step": 646656 }, { "epoch": 1.01, "learning_rate": 3.9403978607972024e-05, "loss": 4.0708, "step": 647168 }, { "epoch": 1.01, "learning_rate": 3.9395592660461504e-05, "loss": 4.0746, "step": 647680 }, { "epoch": 1.01, "learning_rate": 3.9387206712950984e-05, "loss": 4.0716, "step": 648192 }, { "epoch": 1.01, "learning_rate": 3.9378820765440464e-05, "loss": 4.0932, "step": 648704 }, { "epoch": 1.01, "learning_rate": 3.937045119673368e-05, "loss": 4.0634, "step": 649216 }, { "epoch": 1.01, "learning_rate": 3.936206524922316e-05, "loss": 4.0769, "step": 649728 }, { "epoch": 1.01, "learning_rate": 3.935367930171264e-05, "loss": 4.0764, "step": 650240 }, { "epoch": 1.01, "learning_rate": 3.934529335420212e-05, "loss": 4.0669, "step": 650752 }, { "epoch": 1.01, "learning_rate": 3.933690740669159e-05, "loss": 4.0789, "step": 651264 }, { "epoch": 1.01, "learning_rate": 3.932853783798481e-05, "loss": 4.0742, "step": 651776 }, { "epoch": 1.01, "learning_rate": 3.932015189047429e-05, "loss": 4.0725, "step": 652288 }, { "epoch": 1.01, "learning_rate": 3.931176594296377e-05, "loss": 4.0758, "step": 652800 }, { "epoch": 1.01, "learning_rate": 3.930337999545324e-05, "loss": 4.0667, "step": 653312 }, { "epoch": 1.01, "learning_rate": 3.929499404794272e-05, "loss": 4.0684, "step": 653824 }, { "epoch": 1.01, "learning_rate": 3.92866081004322e-05, "loss": 4.0715, "step": 654336 }, { "epoch": 1.01, "learning_rate": 3.927822215292168e-05, "loss": 4.0797, "step": 654848 }, { "epoch": 1.01, "learning_rate": 3.926983620541116e-05, "loss": 4.0654, "step": 655360 }, { "epoch": 1.01, "learning_rate": 3.926146663670438e-05, "loss": 4.0687, "step": 655872 }, { "epoch": 1.02, "learning_rate": 3.925308068919386e-05, "loss": 4.0632, "step": 656384 }, { "epoch": 1.02, "learning_rate": 3.924469474168334e-05, "loss": 4.0778, "step": 656896 }, { "epoch": 1.02, "learning_rate": 3.923630879417282e-05, "loss": 4.0726, "step": 657408 }, { "epoch": 1.02, "learning_rate": 3.9227939225466026e-05, "loss": 4.0594, "step": 657920 }, { "epoch": 1.02, "learning_rate": 3.9219553277955506e-05, "loss": 4.0753, "step": 658432 }, { "epoch": 1.02, "learning_rate": 3.9211167330444986e-05, "loss": 4.0766, "step": 658944 }, { "epoch": 1.02, "learning_rate": 3.9202781382934466e-05, "loss": 4.0703, "step": 659456 }, { "epoch": 1.02, "learning_rate": 3.9194395435423946e-05, "loss": 4.0516, "step": 659968 }, { "epoch": 1.02, "learning_rate": 3.9186025866717155e-05, "loss": 4.0668, "step": 660480 }, { "epoch": 1.02, "learning_rate": 3.9177639919206635e-05, "loss": 4.0618, "step": 660992 }, { "epoch": 1.02, "learning_rate": 3.9169253971696115e-05, "loss": 4.0781, "step": 661504 }, { "epoch": 1.02, "learning_rate": 3.91608680241856e-05, "loss": 4.0733, "step": 662016 }, { "epoch": 1.02, "learning_rate": 3.915248207667508e-05, "loss": 4.0716, "step": 662528 }, { "epoch": 1.02, "learning_rate": 3.914409612916456e-05, "loss": 4.0634, "step": 663040 }, { "epoch": 1.02, "learning_rate": 3.913571018165404e-05, "loss": 4.0628, "step": 663552 }, { "epoch": 1.02, "learning_rate": 3.912732423414352e-05, "loss": 4.0598, "step": 664064 }, { "epoch": 1.02, "learning_rate": 3.9118938286633e-05, "loss": 4.0648, "step": 664576 }, { "epoch": 1.02, "learning_rate": 3.911056871792621e-05, "loss": 4.0594, "step": 665088 }, { "epoch": 1.02, "learning_rate": 3.910218277041569e-05, "loss": 4.0773, "step": 665600 }, { "epoch": 1.02, "learning_rate": 3.909379682290517e-05, "loss": 4.0538, "step": 666112 }, { "epoch": 1.02, "learning_rate": 3.908541087539465e-05, "loss": 4.0564, "step": 666624 }, { "epoch": 1.02, "learning_rate": 3.907704130668786e-05, "loss": 4.0617, "step": 667136 }, { "epoch": 1.02, "learning_rate": 3.906865535917734e-05, "loss": 4.063, "step": 667648 }, { "epoch": 1.02, "learning_rate": 3.906026941166682e-05, "loss": 4.0635, "step": 668160 }, { "epoch": 1.02, "learning_rate": 3.90518834641563e-05, "loss": 4.0573, "step": 668672 }, { "epoch": 1.02, "learning_rate": 3.9043513895449515e-05, "loss": 4.066, "step": 669184 }, { "epoch": 1.02, "learning_rate": 3.9035127947938995e-05, "loss": 4.0745, "step": 669696 }, { "epoch": 1.02, "learning_rate": 3.9026742000428475e-05, "loss": 4.0544, "step": 670208 }, { "epoch": 1.02, "learning_rate": 3.9018356052917955e-05, "loss": 4.0693, "step": 670720 }, { "epoch": 1.02, "learning_rate": 3.900997010540743e-05, "loss": 4.0597, "step": 671232 }, { "epoch": 1.02, "learning_rate": 3.9001600536700644e-05, "loss": 4.0652, "step": 671744 }, { "epoch": 1.02, "learning_rate": 3.8993214589190124e-05, "loss": 4.0636, "step": 672256 }, { "epoch": 1.02, "learning_rate": 3.898484502048333e-05, "loss": 4.0631, "step": 672768 }, { "epoch": 1.02, "learning_rate": 3.897645907297281e-05, "loss": 4.059, "step": 673280 }, { "epoch": 1.02, "learning_rate": 3.896807312546229e-05, "loss": 4.0677, "step": 673792 }, { "epoch": 1.02, "learning_rate": 3.895968717795177e-05, "loss": 4.0649, "step": 674304 }, { "epoch": 1.02, "learning_rate": 3.895130123044125e-05, "loss": 4.0621, "step": 674816 }, { "epoch": 1.02, "learning_rate": 3.894291528293073e-05, "loss": 4.0585, "step": 675328 }, { "epoch": 1.02, "learning_rate": 3.893454571422395e-05, "loss": 4.0633, "step": 675840 }, { "epoch": 1.02, "learning_rate": 3.892615976671343e-05, "loss": 4.0474, "step": 676352 }, { "epoch": 1.02, "learning_rate": 3.89177738192029e-05, "loss": 4.0772, "step": 676864 }, { "epoch": 1.02, "learning_rate": 3.890938787169238e-05, "loss": 4.0558, "step": 677376 }, { "epoch": 1.02, "learning_rate": 3.890100192418186e-05, "loss": 4.0687, "step": 677888 }, { "epoch": 1.02, "learning_rate": 3.889261597667134e-05, "loss": 4.051, "step": 678400 }, { "epoch": 1.02, "learning_rate": 3.888423002916082e-05, "loss": 4.0743, "step": 678912 }, { "epoch": 1.02, "learning_rate": 3.88758440816503e-05, "loss": 4.067, "step": 679424 }, { "epoch": 1.02, "learning_rate": 3.886747451294351e-05, "loss": 4.0599, "step": 679936 }, { "epoch": 1.02, "learning_rate": 3.885910494423673e-05, "loss": 4.0626, "step": 680448 }, { "epoch": 1.02, "learning_rate": 3.885071899672621e-05, "loss": 4.0638, "step": 680960 }, { "epoch": 1.02, "learning_rate": 3.884233304921569e-05, "loss": 4.0652, "step": 681472 }, { "epoch": 1.02, "learning_rate": 3.8833947101705167e-05, "loss": 4.0762, "step": 681984 }, { "epoch": 1.02, "learning_rate": 3.8825561154194647e-05, "loss": 4.044, "step": 682496 }, { "epoch": 1.02, "learning_rate": 3.8817175206684127e-05, "loss": 4.0727, "step": 683008 }, { "epoch": 1.02, "learning_rate": 3.8808789259173606e-05, "loss": 4.0539, "step": 683520 }, { "epoch": 1.02, "learning_rate": 3.8800419690466816e-05, "loss": 4.0674, "step": 684032 }, { "epoch": 1.02, "learning_rate": 3.8792033742956296e-05, "loss": 4.0606, "step": 684544 }, { "epoch": 1.02, "learning_rate": 3.8783647795445775e-05, "loss": 4.0584, "step": 685056 }, { "epoch": 1.02, "learning_rate": 3.8775261847935255e-05, "loss": 4.0658, "step": 685568 }, { "epoch": 1.02, "learning_rate": 3.8766875900424735e-05, "loss": 4.0654, "step": 686080 }, { "epoch": 1.02, "learning_rate": 3.8758489952914215e-05, "loss": 4.061, "step": 686592 }, { "epoch": 1.03, "eval_loss": 4.136733531951904, "eval_runtime": 304.7383, "eval_samples_per_second": 1252.192, "eval_steps_per_second": 39.132, "step": 686880 }, { "epoch": 0.0, "learning_rate": 3.8750104005403695e-05, "loss": 4.0573, "step": 687104 }, { "epoch": 0.0, "learning_rate": 3.8741718057893175e-05, "loss": 4.0608, "step": 687616 }, { "epoch": 0.0, "learning_rate": 3.8733332110382655e-05, "loss": 4.067, "step": 688128 }, { "epoch": 0.0, "learning_rate": 3.872494616287214e-05, "loss": 4.0627, "step": 688640 }, { "epoch": 0.0, "learning_rate": 3.8716560215361615e-05, "loss": 4.0686, "step": 689152 }, { "epoch": 0.0, "learning_rate": 3.8708174267851095e-05, "loss": 4.0554, "step": 689664 }, { "epoch": 0.0, "learning_rate": 3.8699788320340575e-05, "loss": 4.0564, "step": 690176 }, { "epoch": 0.0, "learning_rate": 3.8691402372830055e-05, "loss": 4.055, "step": 690688 }, { "epoch": 0.0, "learning_rate": 3.8683016425319535e-05, "loss": 4.0601, "step": 691200 }, { "epoch": 0.0, "learning_rate": 3.8674630477809015e-05, "loss": 4.0676, "step": 691712 }, { "epoch": 0.0, "learning_rate": 3.8666244530298495e-05, "loss": 4.0582, "step": 692224 }, { "epoch": 0.0, "learning_rate": 3.8657858582787975e-05, "loss": 4.0603, "step": 692736 }, { "epoch": 0.0, "learning_rate": 3.8649489014081184e-05, "loss": 4.0636, "step": 693248 }, { "epoch": 0.0, "learning_rate": 3.8641103066570664e-05, "loss": 4.0498, "step": 693760 }, { "epoch": 0.0, "learning_rate": 3.8632717119060144e-05, "loss": 4.0563, "step": 694272 }, { "epoch": 0.0, "learning_rate": 3.8624331171549624e-05, "loss": 4.0456, "step": 694784 }, { "epoch": 0.0, "learning_rate": 3.861594522403911e-05, "loss": 4.0532, "step": 695296 }, { "epoch": 0.0, "learning_rate": 3.860755927652859e-05, "loss": 4.0488, "step": 695808 }, { "epoch": 0.0, "learning_rate": 3.859917332901807e-05, "loss": 4.0523, "step": 696320 }, { "epoch": 0.0, "learning_rate": 3.859078738150755e-05, "loss": 4.0718, "step": 696832 }, { "epoch": 0.0, "learning_rate": 3.858240143399703e-05, "loss": 4.0638, "step": 697344 }, { "epoch": 0.0, "learning_rate": 3.8574015486486503e-05, "loss": 4.0596, "step": 697856 }, { "epoch": 0.0, "learning_rate": 3.8565629538975983e-05, "loss": 4.0564, "step": 698368 }, { "epoch": 0.0, "learning_rate": 3.8557243591465463e-05, "loss": 4.0668, "step": 698880 }, { "epoch": 0.0, "learning_rate": 3.854887402275868e-05, "loss": 4.0428, "step": 699392 }, { "epoch": 0.0, "learning_rate": 3.854048807524815e-05, "loss": 4.0555, "step": 699904 }, { "epoch": 0.0, "learning_rate": 3.853210212773763e-05, "loss": 4.0589, "step": 700416 }, { "epoch": 0.0, "learning_rate": 3.852371618022711e-05, "loss": 4.0399, "step": 700928 }, { "epoch": 0.0, "learning_rate": 3.851534661152033e-05, "loss": 4.0529, "step": 701440 }, { "epoch": 0.0, "learning_rate": 3.8506977042813544e-05, "loss": 4.0481, "step": 701952 }, { "epoch": 0.01, "learning_rate": 3.8498591095303024e-05, "loss": 4.0538, "step": 702464 }, { "epoch": 0.01, "learning_rate": 3.8490205147792504e-05, "loss": 4.0582, "step": 702976 }, { "epoch": 0.01, "learning_rate": 3.848181920028198e-05, "loss": 4.0553, "step": 703488 }, { "epoch": 0.01, "learning_rate": 3.847344963157519e-05, "loss": 4.059, "step": 704000 }, { "epoch": 0.01, "learning_rate": 3.84650800628684e-05, "loss": 4.0509, "step": 704512 }, { "epoch": 0.01, "learning_rate": 3.845669411535788e-05, "loss": 4.0586, "step": 705024 }, { "epoch": 0.01, "learning_rate": 3.844830816784736e-05, "loss": 4.0601, "step": 705536 }, { "epoch": 0.01, "learning_rate": 3.843992222033684e-05, "loss": 4.0517, "step": 706048 }, { "epoch": 0.01, "learning_rate": 3.843153627282632e-05, "loss": 4.0439, "step": 706560 }, { "epoch": 0.01, "learning_rate": 3.84231503253158e-05, "loss": 4.0577, "step": 707072 }, { "epoch": 0.01, "learning_rate": 3.841476437780528e-05, "loss": 4.0428, "step": 707584 }, { "epoch": 0.01, "learning_rate": 3.840637843029476e-05, "loss": 4.0658, "step": 708096 }, { "epoch": 0.01, "learning_rate": 3.839799248278424e-05, "loss": 4.0573, "step": 708608 }, { "epoch": 0.01, "learning_rate": 3.838962291407745e-05, "loss": 4.0506, "step": 709120 }, { "epoch": 0.01, "learning_rate": 3.838123696656693e-05, "loss": 4.0588, "step": 709632 }, { "epoch": 0.01, "learning_rate": 3.837285101905641e-05, "loss": 4.0518, "step": 710144 }, { "epoch": 0.01, "learning_rate": 3.836446507154589e-05, "loss": 4.0582, "step": 710656 }, { "epoch": 0.01, "learning_rate": 3.83560955028391e-05, "loss": 4.0545, "step": 711168 }, { "epoch": 0.01, "learning_rate": 3.834770955532858e-05, "loss": 4.0216, "step": 711680 }, { "epoch": 0.01, "learning_rate": 3.833932360781806e-05, "loss": 4.065, "step": 712192 }, { "epoch": 0.01, "learning_rate": 3.833093766030754e-05, "loss": 4.0511, "step": 712704 }, { "epoch": 0.01, "learning_rate": 3.832255171279702e-05, "loss": 4.0613, "step": 713216 }, { "epoch": 0.01, "learning_rate": 3.8314182144090236e-05, "loss": 4.0494, "step": 713728 }, { "epoch": 0.01, "learning_rate": 3.8305796196579716e-05, "loss": 4.047, "step": 714240 }, { "epoch": 0.01, "learning_rate": 3.8297410249069195e-05, "loss": 4.0408, "step": 714752 }, { "epoch": 0.01, "learning_rate": 3.8289024301558675e-05, "loss": 4.0569, "step": 715264 }, { "epoch": 0.01, "learning_rate": 3.8280638354048155e-05, "loss": 4.0522, "step": 715776 }, { "epoch": 0.01, "learning_rate": 3.8272268785341364e-05, "loss": 4.0509, "step": 716288 }, { "epoch": 0.01, "learning_rate": 3.8263882837830844e-05, "loss": 4.0693, "step": 716800 }, { "epoch": 0.01, "learning_rate": 3.8255496890320324e-05, "loss": 4.0467, "step": 717312 }, { "epoch": 0.01, "learning_rate": 3.8247110942809804e-05, "loss": 4.0372, "step": 717824 }, { "epoch": 0.01, "learning_rate": 3.8238741374103013e-05, "loss": 4.0648, "step": 718336 }, { "epoch": 0.01, "learning_rate": 3.8230355426592493e-05, "loss": 4.0383, "step": 718848 }, { "epoch": 0.01, "learning_rate": 3.822196947908197e-05, "loss": 4.0385, "step": 719360 }, { "epoch": 0.01, "learning_rate": 3.821358353157145e-05, "loss": 4.0574, "step": 719872 }, { "epoch": 0.01, "learning_rate": 3.820521396286467e-05, "loss": 4.0542, "step": 720384 }, { "epoch": 0.01, "learning_rate": 3.819682801535415e-05, "loss": 4.0383, "step": 720896 }, { "epoch": 0.01, "learning_rate": 3.818844206784363e-05, "loss": 4.0403, "step": 721408 }, { "epoch": 0.01, "learning_rate": 3.818007249913684e-05, "loss": 4.0342, "step": 721920 }, { "epoch": 0.01, "learning_rate": 3.817168655162632e-05, "loss": 4.0459, "step": 722432 }, { "epoch": 0.01, "learning_rate": 3.81633006041158e-05, "loss": 4.0586, "step": 722944 }, { "epoch": 0.01, "learning_rate": 3.815491465660528e-05, "loss": 4.0471, "step": 723456 }, { "epoch": 0.01, "learning_rate": 3.814652870909476e-05, "loss": 4.0528, "step": 723968 }, { "epoch": 0.01, "learning_rate": 3.813814276158424e-05, "loss": 4.042, "step": 724480 }, { "epoch": 0.01, "learning_rate": 3.812975681407372e-05, "loss": 4.0663, "step": 724992 }, { "epoch": 0.01, "learning_rate": 3.81213708665632e-05, "loss": 4.0398, "step": 725504 }, { "epoch": 0.01, "learning_rate": 3.811298491905268e-05, "loss": 4.0545, "step": 726016 }, { "epoch": 0.01, "learning_rate": 3.810461535034589e-05, "loss": 4.0496, "step": 726528 }, { "epoch": 0.01, "learning_rate": 3.8096229402835374e-05, "loss": 4.0449, "step": 727040 }, { "epoch": 0.01, "learning_rate": 3.8087843455324854e-05, "loss": 4.0505, "step": 727552 }, { "epoch": 0.01, "learning_rate": 3.8079457507814334e-05, "loss": 4.0527, "step": 728064 }, { "epoch": 0.01, "learning_rate": 3.8071071560303814e-05, "loss": 4.0438, "step": 728576 }, { "epoch": 0.01, "learning_rate": 3.806268561279329e-05, "loss": 4.0531, "step": 729088 }, { "epoch": 0.01, "learning_rate": 3.805429966528277e-05, "loss": 4.0437, "step": 729600 }, { "epoch": 0.01, "learning_rate": 3.804591371777225e-05, "loss": 4.0422, "step": 730112 }, { "epoch": 0.01, "learning_rate": 3.803754414906546e-05, "loss": 4.0466, "step": 730624 }, { "epoch": 0.01, "learning_rate": 3.802917458035867e-05, "loss": 4.0496, "step": 731136 }, { "epoch": 0.01, "learning_rate": 3.802078863284815e-05, "loss": 4.0404, "step": 731648 }, { "epoch": 0.01, "learning_rate": 3.801240268533763e-05, "loss": 4.0467, "step": 732160 }, { "epoch": 0.02, "learning_rate": 3.800401673782711e-05, "loss": 4.0422, "step": 732672 }, { "epoch": 0.02, "learning_rate": 3.799563079031659e-05, "loss": 4.0484, "step": 733184 }, { "epoch": 0.02, "learning_rate": 3.798726122160981e-05, "loss": 4.0484, "step": 733696 }, { "epoch": 0.02, "learning_rate": 3.797887527409929e-05, "loss": 4.034, "step": 734208 }, { "epoch": 0.02, "learning_rate": 3.797048932658876e-05, "loss": 4.0533, "step": 734720 }, { "epoch": 0.02, "learning_rate": 3.7962119757881976e-05, "loss": 4.0489, "step": 735232 }, { "epoch": 0.02, "learning_rate": 3.7953733810371456e-05, "loss": 4.0504, "step": 735744 }, { "epoch": 0.02, "learning_rate": 3.7945347862860936e-05, "loss": 4.0267, "step": 736256 }, { "epoch": 0.02, "learning_rate": 3.793696191535041e-05, "loss": 4.0397, "step": 736768 }, { "epoch": 0.02, "learning_rate": 3.792857596783989e-05, "loss": 4.0396, "step": 737280 }, { "epoch": 0.02, "learning_rate": 3.792019002032937e-05, "loss": 4.0544, "step": 737792 }, { "epoch": 0.02, "learning_rate": 3.791180407281885e-05, "loss": 4.0486, "step": 738304 }, { "epoch": 0.02, "learning_rate": 3.790341812530833e-05, "loss": 4.0484, "step": 738816 }, { "epoch": 0.02, "learning_rate": 3.789503217779781e-05, "loss": 4.0408, "step": 739328 }, { "epoch": 0.02, "learning_rate": 3.7886646230287296e-05, "loss": 4.0372, "step": 739840 }, { "epoch": 0.02, "learning_rate": 3.7878260282776776e-05, "loss": 4.0326, "step": 740352 }, { "epoch": 0.02, "learning_rate": 3.7869890714069985e-05, "loss": 4.0443, "step": 740864 }, { "epoch": 0.02, "learning_rate": 3.7861504766559465e-05, "loss": 4.0368, "step": 741376 }, { "epoch": 0.02, "learning_rate": 3.7853118819048945e-05, "loss": 4.0476, "step": 741888 }, { "epoch": 0.02, "learning_rate": 3.7844732871538425e-05, "loss": 4.0329, "step": 742400 }, { "epoch": 0.02, "learning_rate": 3.7836346924027905e-05, "loss": 4.0309, "step": 742912 }, { "epoch": 0.02, "learning_rate": 3.7827977355321114e-05, "loss": 4.0352, "step": 743424 }, { "epoch": 0.02, "learning_rate": 3.7819591407810594e-05, "loss": 4.0414, "step": 743936 }, { "epoch": 0.02, "learning_rate": 3.7811205460300074e-05, "loss": 4.0379, "step": 744448 }, { "epoch": 0.02, "learning_rate": 3.780283589159328e-05, "loss": 4.032, "step": 744960 }, { "epoch": 0.02, "learning_rate": 3.779444994408276e-05, "loss": 4.0481, "step": 745472 }, { "epoch": 0.02, "learning_rate": 3.778608037537598e-05, "loss": 4.0484, "step": 745984 }, { "epoch": 0.02, "learning_rate": 3.777769442786546e-05, "loss": 4.0313, "step": 746496 }, { "epoch": 0.02, "learning_rate": 3.776930848035494e-05, "loss": 4.0433, "step": 747008 }, { "epoch": 0.02, "learning_rate": 3.776092253284442e-05, "loss": 4.04, "step": 747520 }, { "epoch": 0.02, "learning_rate": 3.775255296413763e-05, "loss": 4.0401, "step": 748032 }, { "epoch": 0.02, "learning_rate": 3.774416701662711e-05, "loss": 4.042, "step": 748544 }, { "epoch": 0.02, "learning_rate": 3.773578106911659e-05, "loss": 4.0374, "step": 749056 }, { "epoch": 0.02, "learning_rate": 3.772739512160607e-05, "loss": 4.0383, "step": 749568 }, { "epoch": 0.02, "learning_rate": 3.771900917409555e-05, "loss": 4.0391, "step": 750080 }, { "epoch": 0.02, "learning_rate": 3.771062322658503e-05, "loss": 4.0436, "step": 750592 }, { "epoch": 0.02, "learning_rate": 3.770223727907451e-05, "loss": 4.0402, "step": 751104 }, { "epoch": 0.02, "learning_rate": 3.769385133156399e-05, "loss": 4.0313, "step": 751616 }, { "epoch": 0.02, "learning_rate": 3.76854817628572e-05, "loss": 4.0412, "step": 752128 }, { "epoch": 0.02, "learning_rate": 3.767709581534668e-05, "loss": 4.0237, "step": 752640 }, { "epoch": 0.02, "learning_rate": 3.766870986783616e-05, "loss": 4.0523, "step": 753152 }, { "epoch": 0.02, "learning_rate": 3.766034029912937e-05, "loss": 4.0333, "step": 753664 }, { "epoch": 0.02, "learning_rate": 3.765195435161885e-05, "loss": 4.0492, "step": 754176 }, { "epoch": 0.02, "learning_rate": 3.764356840410833e-05, "loss": 4.0281, "step": 754688 }, { "epoch": 0.02, "learning_rate": 3.763518245659781e-05, "loss": 4.0494, "step": 755200 }, { "epoch": 0.02, "learning_rate": 3.762679650908729e-05, "loss": 4.0454, "step": 755712 }, { "epoch": 0.02, "learning_rate": 3.761841056157677e-05, "loss": 4.036, "step": 756224 }, { "epoch": 0.02, "learning_rate": 3.7610024614066245e-05, "loss": 4.0415, "step": 756736 }, { "epoch": 0.02, "learning_rate": 3.7601638666555725e-05, "loss": 4.0358, "step": 757248 }, { "epoch": 0.02, "learning_rate": 3.7593252719045205e-05, "loss": 4.0455, "step": 757760 }, { "epoch": 0.02, "learning_rate": 3.7584866771534685e-05, "loss": 4.0499, "step": 758272 }, { "epoch": 0.02, "learning_rate": 3.7576480824024165e-05, "loss": 4.0238, "step": 758784 }, { "epoch": 0.02, "learning_rate": 3.756809487651365e-05, "loss": 4.0436, "step": 759296 }, { "epoch": 0.02, "learning_rate": 3.755970892900313e-05, "loss": 4.0363, "step": 759808 }, { "epoch": 0.02, "learning_rate": 3.755132298149261e-05, "loss": 4.044, "step": 760320 }, { "epoch": 0.02, "learning_rate": 3.754295341278582e-05, "loss": 4.0376, "step": 760832 }, { "epoch": 0.02, "learning_rate": 3.753458384407903e-05, "loss": 4.0407, "step": 761344 }, { "epoch": 0.02, "learning_rate": 3.752619789656851e-05, "loss": 4.0406, "step": 761856 }, { "epoch": 0.02, "learning_rate": 3.751781194905799e-05, "loss": 4.041, "step": 762368 }, { "epoch": 0.02, "learning_rate": 3.750942600154747e-05, "loss": 4.0412, "step": 762880 }, { "epoch": 0.03, "eval_loss": 4.120935440063477, "eval_runtime": 294.229, "eval_samples_per_second": 1296.919, "eval_steps_per_second": 40.53, "step": 763200 }, { "epoch": 1.0, "learning_rate": 3.750104005403695e-05, "loss": 4.0322, "step": 763392 }, { "epoch": 1.0, "learning_rate": 3.749265410652643e-05, "loss": 4.0342, "step": 763904 }, { "epoch": 1.0, "learning_rate": 3.748426815901591e-05, "loss": 4.0434, "step": 764416 }, { "epoch": 1.0, "learning_rate": 3.747588221150539e-05, "loss": 4.0407, "step": 764928 }, { "epoch": 1.0, "learning_rate": 3.746749626399487e-05, "loss": 4.0465, "step": 765440 }, { "epoch": 1.0, "learning_rate": 3.7459126695288085e-05, "loss": 4.0357, "step": 765952 }, { "epoch": 1.0, "learning_rate": 3.7450740747777565e-05, "loss": 4.0327, "step": 766464 }, { "epoch": 1.0, "learning_rate": 3.7442354800267045e-05, "loss": 4.0321, "step": 766976 }, { "epoch": 1.0, "learning_rate": 3.7433985231560254e-05, "loss": 4.0354, "step": 767488 }, { "epoch": 1.0, "learning_rate": 3.7425599284049734e-05, "loss": 4.0463, "step": 768000 }, { "epoch": 1.0, "learning_rate": 3.7417213336539214e-05, "loss": 4.0338, "step": 768512 }, { "epoch": 1.0, "learning_rate": 3.7408827389028694e-05, "loss": 4.034, "step": 769024 }, { "epoch": 1.0, "learning_rate": 3.74004578203219e-05, "loss": 4.0426, "step": 769536 }, { "epoch": 1.0, "learning_rate": 3.739207187281138e-05, "loss": 4.0259, "step": 770048 }, { "epoch": 1.0, "learning_rate": 3.738368592530086e-05, "loss": 4.0353, "step": 770560 }, { "epoch": 1.0, "learning_rate": 3.737529997779034e-05, "loss": 4.0224, "step": 771072 }, { "epoch": 1.0, "learning_rate": 3.736691403027982e-05, "loss": 4.0308, "step": 771584 }, { "epoch": 1.0, "learning_rate": 3.73585280827693e-05, "loss": 4.03, "step": 772096 }, { "epoch": 1.0, "learning_rate": 3.735014213525878e-05, "loss": 4.0263, "step": 772608 }, { "epoch": 1.0, "learning_rate": 3.734175618774826e-05, "loss": 4.0486, "step": 773120 }, { "epoch": 1.0, "learning_rate": 3.733337024023774e-05, "loss": 4.0459, "step": 773632 }, { "epoch": 1.0, "learning_rate": 3.732498429272722e-05, "loss": 4.0376, "step": 774144 }, { "epoch": 1.0, "learning_rate": 3.73165983452167e-05, "loss": 4.0341, "step": 774656 }, { "epoch": 1.0, "learning_rate": 3.730822877650991e-05, "loss": 4.0412, "step": 775168 }, { "epoch": 1.0, "learning_rate": 3.729984282899939e-05, "loss": 4.0266, "step": 775680 }, { "epoch": 1.0, "learning_rate": 3.729145688148887e-05, "loss": 4.0323, "step": 776192 }, { "epoch": 1.0, "learning_rate": 3.728307093397835e-05, "loss": 4.0349, "step": 776704 }, { "epoch": 1.0, "learning_rate": 3.727468498646783e-05, "loss": 4.0185, "step": 777216 }, { "epoch": 1.0, "learning_rate": 3.726629903895731e-05, "loss": 4.0266, "step": 777728 }, { "epoch": 1.0, "learning_rate": 3.725791309144679e-05, "loss": 4.0256, "step": 778240 }, { "epoch": 1.01, "learning_rate": 3.724952714393627e-05, "loss": 4.0341, "step": 778752 }, { "epoch": 1.01, "learning_rate": 3.724115757522949e-05, "loss": 4.0344, "step": 779264 }, { "epoch": 1.01, "learning_rate": 3.72327880065227e-05, "loss": 4.034, "step": 779776 }, { "epoch": 1.01, "learning_rate": 3.722440205901218e-05, "loss": 4.0375, "step": 780288 }, { "epoch": 1.01, "learning_rate": 3.7216032490305386e-05, "loss": 4.0254, "step": 780800 }, { "epoch": 1.01, "learning_rate": 3.7207646542794866e-05, "loss": 4.0395, "step": 781312 }, { "epoch": 1.01, "learning_rate": 3.7199260595284346e-05, "loss": 4.0404, "step": 781824 }, { "epoch": 1.01, "learning_rate": 3.7190874647773826e-05, "loss": 4.0244, "step": 782336 }, { "epoch": 1.01, "learning_rate": 3.7182488700263306e-05, "loss": 4.0281, "step": 782848 }, { "epoch": 1.01, "learning_rate": 3.7174102752752785e-05, "loss": 4.0299, "step": 783360 }, { "epoch": 1.01, "learning_rate": 3.7165716805242265e-05, "loss": 4.0245, "step": 783872 }, { "epoch": 1.01, "learning_rate": 3.7157330857731745e-05, "loss": 4.0422, "step": 784384 }, { "epoch": 1.01, "learning_rate": 3.7148944910221225e-05, "loss": 4.0339, "step": 784896 }, { "epoch": 1.01, "learning_rate": 3.7140558962710705e-05, "loss": 4.0312, "step": 785408 }, { "epoch": 1.01, "learning_rate": 3.713217301520019e-05, "loss": 4.0359, "step": 785920 }, { "epoch": 1.01, "learning_rate": 3.71238034464934e-05, "loss": 4.0316, "step": 786432 }, { "epoch": 1.01, "learning_rate": 3.711541749898288e-05, "loss": 4.0351, "step": 786944 }, { "epoch": 1.01, "learning_rate": 3.710703155147236e-05, "loss": 4.0334, "step": 787456 }, { "epoch": 1.01, "learning_rate": 3.709864560396184e-05, "loss": 4.0038, "step": 787968 }, { "epoch": 1.01, "learning_rate": 3.709025965645132e-05, "loss": 4.0429, "step": 788480 }, { "epoch": 1.01, "learning_rate": 3.7081873708940794e-05, "loss": 4.0262, "step": 788992 }, { "epoch": 1.01, "learning_rate": 3.7073487761430274e-05, "loss": 4.0383, "step": 789504 }, { "epoch": 1.01, "learning_rate": 3.7065101813919754e-05, "loss": 4.0312, "step": 790016 }, { "epoch": 1.01, "learning_rate": 3.705673224521296e-05, "loss": 4.0241, "step": 790528 }, { "epoch": 1.01, "learning_rate": 3.704836267650618e-05, "loss": 4.0213, "step": 791040 }, { "epoch": 1.01, "learning_rate": 3.703997672899566e-05, "loss": 4.0328, "step": 791552 }, { "epoch": 1.01, "learning_rate": 3.7031590781485146e-05, "loss": 4.0325, "step": 792064 }, { "epoch": 1.01, "learning_rate": 3.702320483397462e-05, "loss": 4.0279, "step": 792576 }, { "epoch": 1.01, "learning_rate": 3.70148188864641e-05, "loss": 4.0487, "step": 793088 }, { "epoch": 1.01, "learning_rate": 3.700643293895358e-05, "loss": 4.0317, "step": 793600 }, { "epoch": 1.01, "learning_rate": 3.699804699144306e-05, "loss": 4.0074, "step": 794112 }, { "epoch": 1.01, "learning_rate": 3.698967742273627e-05, "loss": 4.0412, "step": 794624 }, { "epoch": 1.01, "learning_rate": 3.6981307854029484e-05, "loss": 4.0177, "step": 795136 }, { "epoch": 1.01, "learning_rate": 3.6972921906518964e-05, "loss": 4.0205, "step": 795648 }, { "epoch": 1.01, "learning_rate": 3.696453595900844e-05, "loss": 4.0348, "step": 796160 }, { "epoch": 1.01, "learning_rate": 3.695615001149792e-05, "loss": 4.0324, "step": 796672 }, { "epoch": 1.01, "learning_rate": 3.69477640639874e-05, "loss": 4.018, "step": 797184 }, { "epoch": 1.01, "learning_rate": 3.6939378116476884e-05, "loss": 4.0189, "step": 797696 }, { "epoch": 1.01, "learning_rate": 3.6930992168966363e-05, "loss": 4.0137, "step": 798208 }, { "epoch": 1.01, "learning_rate": 3.6922606221455843e-05, "loss": 4.0234, "step": 798720 }, { "epoch": 1.01, "learning_rate": 3.691422027394532e-05, "loss": 4.0344, "step": 799232 }, { "epoch": 1.01, "learning_rate": 3.69058343264348e-05, "loss": 4.0285, "step": 799744 }, { "epoch": 1.01, "learning_rate": 3.689744837892428e-05, "loss": 4.0301, "step": 800256 }, { "epoch": 1.01, "learning_rate": 3.688906243141376e-05, "loss": 4.0189, "step": 800768 }, { "epoch": 1.01, "learning_rate": 3.688067648390324e-05, "loss": 4.0434, "step": 801280 }, { "epoch": 1.01, "learning_rate": 3.687230691519645e-05, "loss": 4.021, "step": 801792 }, { "epoch": 1.01, "learning_rate": 3.686392096768593e-05, "loss": 4.0344, "step": 802304 }, { "epoch": 1.01, "learning_rate": 3.685555139897914e-05, "loss": 4.0228, "step": 802816 }, { "epoch": 1.01, "learning_rate": 3.684716545146862e-05, "loss": 4.0255, "step": 803328 }, { "epoch": 1.01, "learning_rate": 3.68387795039581e-05, "loss": 4.0307, "step": 803840 }, { "epoch": 1.01, "learning_rate": 3.683039355644758e-05, "loss": 4.0322, "step": 804352 }, { "epoch": 1.01, "learning_rate": 3.682200760893707e-05, "loss": 4.0222, "step": 804864 }, { "epoch": 1.01, "learning_rate": 3.681362166142655e-05, "loss": 4.0366, "step": 805376 }, { "epoch": 1.01, "learning_rate": 3.680523571391603e-05, "loss": 4.0149, "step": 805888 }, { "epoch": 1.01, "learning_rate": 3.679686614520924e-05, "loss": 4.0235, "step": 806400 }, { "epoch": 1.01, "learning_rate": 3.678848019769872e-05, "loss": 4.0268, "step": 806912 }, { "epoch": 1.01, "learning_rate": 3.67800942501882e-05, "loss": 4.0321, "step": 807424 }, { "epoch": 1.01, "learning_rate": 3.677170830267768e-05, "loss": 4.0192, "step": 807936 }, { "epoch": 1.01, "learning_rate": 3.676332235516715e-05, "loss": 4.0227, "step": 808448 }, { "epoch": 1.01, "learning_rate": 3.675493640765663e-05, "loss": 4.02, "step": 808960 }, { "epoch": 1.02, "learning_rate": 3.674655046014611e-05, "loss": 4.026, "step": 809472 }, { "epoch": 1.02, "learning_rate": 3.673816451263559e-05, "loss": 4.028, "step": 809984 }, { "epoch": 1.02, "learning_rate": 3.6729794943928806e-05, "loss": 4.0137, "step": 810496 }, { "epoch": 1.02, "learning_rate": 3.6721408996418286e-05, "loss": 4.0302, "step": 811008 }, { "epoch": 1.02, "learning_rate": 3.67130394277115e-05, "loss": 4.0296, "step": 811520 }, { "epoch": 1.02, "learning_rate": 3.670465348020098e-05, "loss": 4.0308, "step": 812032 }, { "epoch": 1.02, "learning_rate": 3.6696267532690455e-05, "loss": 4.0032, "step": 812544 }, { "epoch": 1.02, "learning_rate": 3.6687881585179935e-05, "loss": 4.0211, "step": 813056 }, { "epoch": 1.02, "learning_rate": 3.6679495637669415e-05, "loss": 4.0174, "step": 813568 }, { "epoch": 1.02, "learning_rate": 3.6671109690158895e-05, "loss": 4.0309, "step": 814080 }, { "epoch": 1.02, "learning_rate": 3.6662740121452104e-05, "loss": 4.0316, "step": 814592 }, { "epoch": 1.02, "learning_rate": 3.6654354173941584e-05, "loss": 4.0221, "step": 815104 }, { "epoch": 1.02, "learning_rate": 3.6645968226431064e-05, "loss": 4.0179, "step": 815616 }, { "epoch": 1.02, "learning_rate": 3.6637582278920544e-05, "loss": 4.021, "step": 816128 }, { "epoch": 1.02, "learning_rate": 3.6629196331410023e-05, "loss": 4.0129, "step": 816640 }, { "epoch": 1.02, "learning_rate": 3.6620810383899503e-05, "loss": 4.0231, "step": 817152 }, { "epoch": 1.02, "learning_rate": 3.6612424436388983e-05, "loss": 4.0169, "step": 817664 }, { "epoch": 1.02, "learning_rate": 3.66040548676822e-05, "loss": 4.0254, "step": 818176 }, { "epoch": 1.02, "learning_rate": 3.659566892017168e-05, "loss": 4.0136, "step": 818688 }, { "epoch": 1.02, "learning_rate": 3.658728297266116e-05, "loss": 4.0109, "step": 819200 }, { "epoch": 1.02, "learning_rate": 3.657889702515064e-05, "loss": 4.0119, "step": 819712 }, { "epoch": 1.02, "learning_rate": 3.657051107764012e-05, "loss": 4.0168, "step": 820224 }, { "epoch": 1.02, "learning_rate": 3.65621251301296e-05, "loss": 4.022, "step": 820736 }, { "epoch": 1.02, "learning_rate": 3.655373918261908e-05, "loss": 4.0131, "step": 821248 }, { "epoch": 1.02, "learning_rate": 3.654535323510856e-05, "loss": 4.0216, "step": 821760 }, { "epoch": 1.02, "learning_rate": 3.653696728759804e-05, "loss": 4.0245, "step": 822272 }, { "epoch": 1.02, "learning_rate": 3.652859771889125e-05, "loss": 4.0137, "step": 822784 }, { "epoch": 1.02, "learning_rate": 3.652021177138073e-05, "loss": 4.0251, "step": 823296 }, { "epoch": 1.02, "learning_rate": 3.651182582387021e-05, "loss": 4.0171, "step": 823808 }, { "epoch": 1.02, "learning_rate": 3.650343987635969e-05, "loss": 4.0204, "step": 824320 }, { "epoch": 1.02, "learning_rate": 3.6495070307652904e-05, "loss": 4.0168, "step": 824832 }, { "epoch": 1.02, "learning_rate": 3.648670073894611e-05, "loss": 4.016, "step": 825344 }, { "epoch": 1.02, "learning_rate": 3.647831479143559e-05, "loss": 4.0198, "step": 825856 }, { "epoch": 1.02, "learning_rate": 3.646992884392507e-05, "loss": 4.0153, "step": 826368 }, { "epoch": 1.02, "learning_rate": 3.646154289641455e-05, "loss": 4.0238, "step": 826880 }, { "epoch": 1.02, "learning_rate": 3.645315694890403e-05, "loss": 4.0213, "step": 827392 }, { "epoch": 1.02, "learning_rate": 3.644477100139351e-05, "loss": 4.009, "step": 827904 }, { "epoch": 1.02, "learning_rate": 3.6436385053882986e-05, "loss": 4.0164, "step": 828416 }, { "epoch": 1.02, "learning_rate": 3.6427999106372466e-05, "loss": 4.006, "step": 828928 }, { "epoch": 1.02, "learning_rate": 3.641962953766568e-05, "loss": 4.0296, "step": 829440 }, { "epoch": 1.02, "learning_rate": 3.641124359015516e-05, "loss": 4.0104, "step": 829952 }, { "epoch": 1.02, "learning_rate": 3.640285764264464e-05, "loss": 4.0263, "step": 830464 }, { "epoch": 1.02, "learning_rate": 3.639447169513412e-05, "loss": 4.0124, "step": 830976 }, { "epoch": 1.02, "learning_rate": 3.63860857476236e-05, "loss": 4.0253, "step": 831488 }, { "epoch": 1.02, "learning_rate": 3.637771617891681e-05, "loss": 4.0245, "step": 832000 }, { "epoch": 1.02, "learning_rate": 3.636933023140629e-05, "loss": 4.0129, "step": 832512 }, { "epoch": 1.02, "learning_rate": 3.636094428389577e-05, "loss": 4.024, "step": 833024 }, { "epoch": 1.02, "learning_rate": 3.635255833638525e-05, "loss": 4.0124, "step": 833536 }, { "epoch": 1.02, "learning_rate": 3.634418876767846e-05, "loss": 4.0283, "step": 834048 }, { "epoch": 1.02, "learning_rate": 3.633580282016794e-05, "loss": 4.0228, "step": 834560 }, { "epoch": 1.02, "learning_rate": 3.632741687265742e-05, "loss": 4.0092, "step": 835072 }, { "epoch": 1.02, "learning_rate": 3.63190309251469e-05, "loss": 4.0192, "step": 835584 }, { "epoch": 1.02, "learning_rate": 3.631064497763638e-05, "loss": 4.0178, "step": 836096 }, { "epoch": 1.02, "learning_rate": 3.630225903012586e-05, "loss": 4.0258, "step": 836608 }, { "epoch": 1.02, "learning_rate": 3.6293889461419075e-05, "loss": 4.0137, "step": 837120 }, { "epoch": 1.02, "learning_rate": 3.6285503513908555e-05, "loss": 4.0249, "step": 837632 }, { "epoch": 1.02, "learning_rate": 3.6277117566398035e-05, "loss": 4.0117, "step": 838144 }, { "epoch": 1.02, "learning_rate": 3.6268731618887515e-05, "loss": 4.0248, "step": 838656 }, { "epoch": 1.02, "learning_rate": 3.6260345671376995e-05, "loss": 4.017, "step": 839168 }, { "epoch": 1.03, "eval_loss": 4.106806755065918, "eval_runtime": 295.9875, "eval_samples_per_second": 1289.213, "eval_steps_per_second": 40.289, "step": 839520 }, { "epoch": 2.0, "learning_rate": 3.6251959723866475e-05, "loss": 4.0155, "step": 839680 }, { "epoch": 2.0, "learning_rate": 3.6243573776355955e-05, "loss": 4.0141, "step": 840192 }, { "epoch": 2.0, "learning_rate": 3.6235187828845435e-05, "loss": 4.0198, "step": 840704 }, { "epoch": 2.0, "learning_rate": 3.622683463894237e-05, "loss": 4.0235, "step": 841216 }, { "epoch": 2.0, "learning_rate": 3.621844869143185e-05, "loss": 4.0284, "step": 841728 }, { "epoch": 2.0, "learning_rate": 3.621006274392133e-05, "loss": 4.0119, "step": 842240 }, { "epoch": 2.0, "learning_rate": 3.620167679641081e-05, "loss": 4.0134, "step": 842752 }, { "epoch": 2.0, "learning_rate": 3.61932908489003e-05, "loss": 4.0139, "step": 843264 }, { "epoch": 2.0, "learning_rate": 3.618490490138978e-05, "loss": 4.0178, "step": 843776 }, { "epoch": 2.0, "learning_rate": 3.617651895387926e-05, "loss": 4.0238, "step": 844288 }, { "epoch": 2.0, "learning_rate": 3.616814938517247e-05, "loss": 4.0136, "step": 844800 }, { "epoch": 2.0, "learning_rate": 3.615976343766195e-05, "loss": 4.0148, "step": 845312 }, { "epoch": 2.0, "learning_rate": 3.615137749015143e-05, "loss": 4.0269, "step": 845824 }, { "epoch": 2.0, "learning_rate": 3.614299154264091e-05, "loss": 4.0076, "step": 846336 }, { "epoch": 2.0, "learning_rate": 3.613460559513039e-05, "loss": 4.0108, "step": 846848 }, { "epoch": 2.0, "learning_rate": 3.612621964761987e-05, "loss": 4.0039, "step": 847360 }, { "epoch": 2.0, "learning_rate": 3.611783370010935e-05, "loss": 4.007, "step": 847872 }, { "epoch": 2.0, "learning_rate": 3.610944775259882e-05, "loss": 4.0127, "step": 848384 }, { "epoch": 2.0, "learning_rate": 3.610109456269577e-05, "loss": 4.0118, "step": 848896 }, { "epoch": 2.0, "learning_rate": 3.609270861518525e-05, "loss": 4.0253, "step": 849408 }, { "epoch": 2.0, "learning_rate": 3.608432266767473e-05, "loss": 4.0249, "step": 849920 }, { "epoch": 2.0, "learning_rate": 3.607593672016421e-05, "loss": 4.0169, "step": 850432 }, { "epoch": 2.0, "learning_rate": 3.606755077265369e-05, "loss": 4.0159, "step": 850944 }, { "epoch": 2.0, "learning_rate": 3.605916482514317e-05, "loss": 4.0201, "step": 851456 }, { "epoch": 2.0, "learning_rate": 3.6050778877632646e-05, "loss": 4.0013, "step": 851968 }, { "epoch": 2.0, "learning_rate": 3.6042392930122126e-05, "loss": 4.0189, "step": 852480 }, { "epoch": 2.0, "learning_rate": 3.603402336141534e-05, "loss": 4.0138, "step": 852992 }, { "epoch": 2.0, "learning_rate": 3.602563741390482e-05, "loss": 3.9977, "step": 853504 }, { "epoch": 2.0, "learning_rate": 3.6017251466394295e-05, "loss": 4.0097, "step": 854016 }, { "epoch": 2.0, "learning_rate": 3.6008865518883775e-05, "loss": 4.0074, "step": 854528 }, { "epoch": 2.01, "learning_rate": 3.6000479571373255e-05, "loss": 4.0101, "step": 855040 }, { "epoch": 2.01, "learning_rate": 3.599212638147021e-05, "loss": 4.0132, "step": 855552 }, { "epoch": 2.01, "learning_rate": 3.598374043395969e-05, "loss": 4.0203, "step": 856064 }, { "epoch": 2.01, "learning_rate": 3.597535448644917e-05, "loss": 4.0145, "step": 856576 }, { "epoch": 2.01, "learning_rate": 3.596696853893865e-05, "loss": 4.0048, "step": 857088 }, { "epoch": 2.01, "learning_rate": 3.5958598970231856e-05, "loss": 4.0209, "step": 857600 }, { "epoch": 2.01, "learning_rate": 3.5950213022721336e-05, "loss": 4.0221, "step": 858112 }, { "epoch": 2.01, "learning_rate": 3.5941827075210816e-05, "loss": 4.0064, "step": 858624 }, { "epoch": 2.01, "learning_rate": 3.5933441127700296e-05, "loss": 4.0104, "step": 859136 }, { "epoch": 2.01, "learning_rate": 3.5925071558993505e-05, "loss": 4.0099, "step": 859648 }, { "epoch": 2.01, "learning_rate": 3.5916685611482985e-05, "loss": 4.0018, "step": 860160 }, { "epoch": 2.01, "learning_rate": 3.5908299663972465e-05, "loss": 4.0205, "step": 860672 }, { "epoch": 2.01, "learning_rate": 3.5899913716461945e-05, "loss": 4.0141, "step": 861184 }, { "epoch": 2.01, "learning_rate": 3.5891527768951425e-05, "loss": 4.0195, "step": 861696 }, { "epoch": 2.01, "learning_rate": 3.5883141821440905e-05, "loss": 4.0111, "step": 862208 }, { "epoch": 2.01, "learning_rate": 3.5874755873930385e-05, "loss": 4.014, "step": 862720 }, { "epoch": 2.01, "learning_rate": 3.5866369926419865e-05, "loss": 4.0148, "step": 863232 }, { "epoch": 2.01, "learning_rate": 3.5857983978909345e-05, "loss": 4.0129, "step": 863744 }, { "epoch": 2.01, "learning_rate": 3.5849598031398825e-05, "loss": 3.9858, "step": 864256 }, { "epoch": 2.01, "learning_rate": 3.5841212083888305e-05, "loss": 4.021, "step": 864768 }, { "epoch": 2.01, "learning_rate": 3.5832826136377784e-05, "loss": 4.0077, "step": 865280 }, { "epoch": 2.01, "learning_rate": 3.5824456567670994e-05, "loss": 4.0216, "step": 865792 }, { "epoch": 2.01, "learning_rate": 3.58160869989642e-05, "loss": 4.0092, "step": 866304 }, { "epoch": 2.01, "learning_rate": 3.580770105145368e-05, "loss": 4.0062, "step": 866816 }, { "epoch": 2.01, "learning_rate": 3.579931510394316e-05, "loss": 4.0013, "step": 867328 }, { "epoch": 2.01, "learning_rate": 3.579092915643264e-05, "loss": 4.0087, "step": 867840 }, { "epoch": 2.01, "learning_rate": 3.578254320892212e-05, "loss": 4.0205, "step": 868352 }, { "epoch": 2.01, "learning_rate": 3.577417364021534e-05, "loss": 4.0067, "step": 868864 }, { "epoch": 2.01, "learning_rate": 3.576578769270482e-05, "loss": 4.027, "step": 869376 }, { "epoch": 2.01, "learning_rate": 3.57574017451943e-05, "loss": 4.0114, "step": 869888 }, { "epoch": 2.01, "learning_rate": 3.574901579768378e-05, "loss": 3.9905, "step": 870400 }, { "epoch": 2.01, "learning_rate": 3.574062985017326e-05, "loss": 4.0229, "step": 870912 }, { "epoch": 2.01, "learning_rate": 3.573224390266274e-05, "loss": 4.0015, "step": 871424 }, { "epoch": 2.01, "learning_rate": 3.572385795515222e-05, "loss": 4.0029, "step": 871936 }, { "epoch": 2.01, "learning_rate": 3.57154720076417e-05, "loss": 4.0117, "step": 872448 }, { "epoch": 2.01, "learning_rate": 3.570710243893491e-05, "loss": 4.0148, "step": 872960 }, { "epoch": 2.01, "learning_rate": 3.569871649142439e-05, "loss": 3.9956, "step": 873472 }, { "epoch": 2.01, "learning_rate": 3.569033054391387e-05, "loss": 4.0038, "step": 873984 }, { "epoch": 2.01, "learning_rate": 3.5681960975207076e-05, "loss": 3.9924, "step": 874496 }, { "epoch": 2.01, "learning_rate": 3.567357502769656e-05, "loss": 4.0081, "step": 875008 }, { "epoch": 2.01, "learning_rate": 3.566518908018604e-05, "loss": 4.0132, "step": 875520 }, { "epoch": 2.01, "learning_rate": 3.565680313267552e-05, "loss": 4.0066, "step": 876032 }, { "epoch": 2.01, "learning_rate": 3.564843356396873e-05, "loss": 4.0147, "step": 876544 }, { "epoch": 2.01, "learning_rate": 3.564004761645821e-05, "loss": 4.0012, "step": 877056 }, { "epoch": 2.01, "learning_rate": 3.563166166894769e-05, "loss": 4.02, "step": 877568 }, { "epoch": 2.01, "learning_rate": 3.56232921002409e-05, "loss": 4.0084, "step": 878080 }, { "epoch": 2.01, "learning_rate": 3.561490615273038e-05, "loss": 4.0152, "step": 878592 }, { "epoch": 2.01, "learning_rate": 3.560652020521986e-05, "loss": 4.0035, "step": 879104 }, { "epoch": 2.01, "learning_rate": 3.559813425770934e-05, "loss": 4.0076, "step": 879616 }, { "epoch": 2.01, "learning_rate": 3.558974831019882e-05, "loss": 4.0104, "step": 880128 }, { "epoch": 2.01, "learning_rate": 3.55813623626883e-05, "loss": 4.0119, "step": 880640 }, { "epoch": 2.01, "learning_rate": 3.557297641517778e-05, "loss": 4.0066, "step": 881152 }, { "epoch": 2.01, "learning_rate": 3.556459046766726e-05, "loss": 4.0174, "step": 881664 }, { "epoch": 2.01, "learning_rate": 3.555620452015674e-05, "loss": 3.9971, "step": 882176 }, { "epoch": 2.01, "learning_rate": 3.554781857264622e-05, "loss": 4.0038, "step": 882688 }, { "epoch": 2.01, "learning_rate": 3.55394326251357e-05, "loss": 4.006, "step": 883200 }, { "epoch": 2.01, "learning_rate": 3.553106305642891e-05, "loss": 4.0162, "step": 883712 }, { "epoch": 2.01, "learning_rate": 3.5522693487722125e-05, "loss": 3.9981, "step": 884224 }, { "epoch": 2.01, "learning_rate": 3.5514307540211605e-05, "loss": 4.0023, "step": 884736 }, { "epoch": 2.01, "learning_rate": 3.550592159270108e-05, "loss": 4.0059, "step": 885248 }, { "epoch": 2.02, "learning_rate": 3.549753564519056e-05, "loss": 4.0061, "step": 885760 }, { "epoch": 2.02, "learning_rate": 3.548914969768004e-05, "loss": 4.0087, "step": 886272 }, { "epoch": 2.02, "learning_rate": 3.548076375016952e-05, "loss": 3.9978, "step": 886784 }, { "epoch": 2.02, "learning_rate": 3.5472377802659e-05, "loss": 4.009, "step": 887296 }, { "epoch": 2.02, "learning_rate": 3.5463991855148485e-05, "loss": 4.013, "step": 887808 }, { "epoch": 2.02, "learning_rate": 3.5455605907637965e-05, "loss": 4.0125, "step": 888320 }, { "epoch": 2.02, "learning_rate": 3.5447219960127445e-05, "loss": 3.989, "step": 888832 }, { "epoch": 2.02, "learning_rate": 3.5438834012616925e-05, "loss": 4.0015, "step": 889344 }, { "epoch": 2.02, "learning_rate": 3.5430448065106405e-05, "loss": 3.9985, "step": 889856 }, { "epoch": 2.02, "learning_rate": 3.5422078496399614e-05, "loss": 4.0145, "step": 890368 }, { "epoch": 2.02, "learning_rate": 3.5413692548889094e-05, "loss": 4.0142, "step": 890880 }, { "epoch": 2.02, "learning_rate": 3.5405306601378574e-05, "loss": 4.0039, "step": 891392 }, { "epoch": 2.02, "learning_rate": 3.5396920653868054e-05, "loss": 4.0015, "step": 891904 }, { "epoch": 2.02, "learning_rate": 3.538855108516126e-05, "loss": 4.0025, "step": 892416 }, { "epoch": 2.02, "learning_rate": 3.538016513765074e-05, "loss": 3.9946, "step": 892928 }, { "epoch": 2.02, "learning_rate": 3.537177919014022e-05, "loss": 4.0036, "step": 893440 }, { "epoch": 2.02, "learning_rate": 3.53633932426297e-05, "loss": 4.0012, "step": 893952 }, { "epoch": 2.02, "learning_rate": 3.535500729511918e-05, "loss": 4.0063, "step": 894464 }, { "epoch": 2.02, "learning_rate": 3.53466377264124e-05, "loss": 3.9984, "step": 894976 }, { "epoch": 2.02, "learning_rate": 3.533825177890188e-05, "loss": 3.9939, "step": 895488 }, { "epoch": 2.02, "learning_rate": 3.532986583139136e-05, "loss": 3.9943, "step": 896000 }, { "epoch": 2.02, "learning_rate": 3.532147988388084e-05, "loss": 3.9984, "step": 896512 }, { "epoch": 2.02, "learning_rate": 3.531309393637032e-05, "loss": 4.0054, "step": 897024 }, { "epoch": 2.02, "learning_rate": 3.530472436766353e-05, "loss": 3.9954, "step": 897536 }, { "epoch": 2.02, "learning_rate": 3.529633842015301e-05, "loss": 4.0053, "step": 898048 }, { "epoch": 2.02, "learning_rate": 3.528795247264249e-05, "loss": 4.004, "step": 898560 }, { "epoch": 2.02, "learning_rate": 3.527956652513197e-05, "loss": 4.0014, "step": 899072 }, { "epoch": 2.02, "learning_rate": 3.5271196956425177e-05, "loss": 4.0077, "step": 899584 }, { "epoch": 2.02, "learning_rate": 3.5262811008914657e-05, "loss": 3.9992, "step": 900096 }, { "epoch": 2.02, "learning_rate": 3.5254425061404136e-05, "loss": 4.0061, "step": 900608 }, { "epoch": 2.02, "learning_rate": 3.5246039113893616e-05, "loss": 4.001, "step": 901120 }, { "epoch": 2.02, "learning_rate": 3.5237653166383096e-05, "loss": 3.9985, "step": 901632 }, { "epoch": 2.02, "learning_rate": 3.522928359767631e-05, "loss": 4.0031, "step": 902144 }, { "epoch": 2.02, "learning_rate": 3.522091402896952e-05, "loss": 4.0005, "step": 902656 }, { "epoch": 2.02, "learning_rate": 3.5212528081459e-05, "loss": 4.0057, "step": 903168 }, { "epoch": 2.02, "learning_rate": 3.520414213394848e-05, "loss": 4.0019, "step": 903680 }, { "epoch": 2.02, "learning_rate": 3.519575618643796e-05, "loss": 3.9952, "step": 904192 }, { "epoch": 2.02, "learning_rate": 3.5187370238927434e-05, "loss": 3.9988, "step": 904704 }, { "epoch": 2.02, "learning_rate": 3.5178984291416914e-05, "loss": 3.9917, "step": 905216 }, { "epoch": 2.02, "learning_rate": 3.5170598343906394e-05, "loss": 4.0104, "step": 905728 }, { "epoch": 2.02, "learning_rate": 3.5162212396395874e-05, "loss": 3.9993, "step": 906240 }, { "epoch": 2.02, "learning_rate": 3.5153826448885354e-05, "loss": 4.0104, "step": 906752 }, { "epoch": 2.02, "learning_rate": 3.514544050137484e-05, "loss": 3.994, "step": 907264 }, { "epoch": 2.02, "learning_rate": 3.513705455386432e-05, "loss": 4.0092, "step": 907776 }, { "epoch": 2.02, "learning_rate": 3.51286686063538e-05, "loss": 4.0071, "step": 908288 }, { "epoch": 2.02, "learning_rate": 3.512029903764701e-05, "loss": 3.9992, "step": 908800 }, { "epoch": 2.02, "learning_rate": 3.511191309013649e-05, "loss": 4.0018, "step": 909312 }, { "epoch": 2.02, "learning_rate": 3.510352714262597e-05, "loss": 3.9969, "step": 909824 }, { "epoch": 2.02, "learning_rate": 3.509515757391918e-05, "loss": 4.0112, "step": 910336 }, { "epoch": 2.02, "learning_rate": 3.508677162640866e-05, "loss": 4.0103, "step": 910848 }, { "epoch": 2.02, "learning_rate": 3.507838567889814e-05, "loss": 3.9953, "step": 911360 }, { "epoch": 2.02, "learning_rate": 3.506999973138762e-05, "loss": 3.9975, "step": 911872 }, { "epoch": 2.02, "learning_rate": 3.50616137838771e-05, "loss": 4.004, "step": 912384 }, { "epoch": 2.02, "learning_rate": 3.505322783636658e-05, "loss": 4.0087, "step": 912896 }, { "epoch": 2.02, "learning_rate": 3.504484188885606e-05, "loss": 3.9941, "step": 913408 }, { "epoch": 2.02, "learning_rate": 3.503645594134554e-05, "loss": 4.0086, "step": 913920 }, { "epoch": 2.02, "learning_rate": 3.5028069993835025e-05, "loss": 3.9966, "step": 914432 }, { "epoch": 2.02, "learning_rate": 3.5019700425128234e-05, "loss": 4.009, "step": 914944 }, { "epoch": 2.02, "learning_rate": 3.5011314477617714e-05, "loss": 4.0005, "step": 915456 }, { "epoch": 2.03, "eval_loss": 4.096757888793945, "eval_runtime": 295.5602, "eval_samples_per_second": 1291.077, "eval_steps_per_second": 40.347, "step": 915840 }, { "epoch": 0.0, "learning_rate": 3.5002928530107194e-05, "loss": 4.0078, "step": 915968 }, { "epoch": 0.0, "learning_rate": 3.4994542582596674e-05, "loss": 3.9955, "step": 916480 }, { "epoch": 0.0, "learning_rate": 3.4986156635086154e-05, "loss": 4.0013, "step": 916992 }, { "epoch": 0.0, "learning_rate": 3.497777068757563e-05, "loss": 4.0084, "step": 917504 }, { "epoch": 0.0, "learning_rate": 3.496938474006511e-05, "loss": 4.0104, "step": 918016 }, { "epoch": 0.0, "learning_rate": 3.496099879255459e-05, "loss": 3.9995, "step": 918528 }, { "epoch": 0.0, "learning_rate": 3.495261284504407e-05, "loss": 3.9964, "step": 919040 }, { "epoch": 0.0, "learning_rate": 3.494422689753355e-05, "loss": 3.9991, "step": 919552 }, { "epoch": 0.0, "learning_rate": 3.493584095002303e-05, "loss": 3.9992, "step": 920064 }, { "epoch": 0.0, "learning_rate": 3.492745500251251e-05, "loss": 4.0039, "step": 920576 }, { "epoch": 0.0, "learning_rate": 3.491906905500199e-05, "loss": 4.0003, "step": 921088 }, { "epoch": 0.0, "learning_rate": 3.4910683107491474e-05, "loss": 3.9995, "step": 921600 }, { "epoch": 0.0, "learning_rate": 3.490231353878468e-05, "loss": 4.011, "step": 922112 }, { "epoch": 0.0, "learning_rate": 3.489392759127416e-05, "loss": 3.9895, "step": 922624 }, { "epoch": 0.0, "learning_rate": 3.488554164376364e-05, "loss": 3.9938, "step": 923136 }, { "epoch": 0.0, "learning_rate": 3.487715569625312e-05, "loss": 3.9876, "step": 923648 }, { "epoch": 0.0, "learning_rate": 3.48687697487426e-05, "loss": 3.99, "step": 924160 }, { "epoch": 0.0, "learning_rate": 3.486038380123208e-05, "loss": 3.9962, "step": 924672 }, { "epoch": 0.0, "learning_rate": 3.485199785372156e-05, "loss": 3.9942, "step": 925184 }, { "epoch": 0.0, "learning_rate": 3.484361190621104e-05, "loss": 4.0059, "step": 925696 }, { "epoch": 0.0, "learning_rate": 3.4835225958700516e-05, "loss": 4.0109, "step": 926208 }, { "epoch": 0.0, "learning_rate": 3.4826840011189996e-05, "loss": 4.0002, "step": 926720 }, { "epoch": 0.0, "learning_rate": 3.481847044248321e-05, "loss": 4.0005, "step": 927232 }, { "epoch": 0.0, "learning_rate": 3.481008449497269e-05, "loss": 4.0043, "step": 927744 }, { "epoch": 0.0, "learning_rate": 3.480169854746217e-05, "loss": 3.9847, "step": 928256 }, { "epoch": 0.0, "learning_rate": 3.479331259995165e-05, "loss": 4.0054, "step": 928768 }, { "epoch": 0.0, "learning_rate": 3.478494303124487e-05, "loss": 3.9927, "step": 929280 }, { "epoch": 0.0, "learning_rate": 3.477655708373434e-05, "loss": 3.9858, "step": 929792 }, { "epoch": 0.0, "learning_rate": 3.476817113622382e-05, "loss": 3.9943, "step": 930304 }, { "epoch": 0.0, "learning_rate": 3.47597851887133e-05, "loss": 3.9894, "step": 930816 }, { "epoch": 0.01, "learning_rate": 3.475139924120278e-05, "loss": 3.9944, "step": 931328 }, { "epoch": 0.01, "learning_rate": 3.474301329369226e-05, "loss": 3.9953, "step": 931840 }, { "epoch": 0.01, "learning_rate": 3.473462734618174e-05, "loss": 4.0065, "step": 932352 }, { "epoch": 0.01, "learning_rate": 3.472624139867122e-05, "loss": 3.9966, "step": 932864 }, { "epoch": 0.01, "learning_rate": 3.47178554511607e-05, "loss": 3.9901, "step": 933376 }, { "epoch": 0.01, "learning_rate": 3.470948588245391e-05, "loss": 4.0014, "step": 933888 }, { "epoch": 0.01, "learning_rate": 3.4701099934943396e-05, "loss": 4.0061, "step": 934400 }, { "epoch": 0.01, "learning_rate": 3.4692730366236605e-05, "loss": 3.9905, "step": 934912 }, { "epoch": 0.01, "learning_rate": 3.4684344418726085e-05, "loss": 3.99, "step": 935424 }, { "epoch": 0.01, "learning_rate": 3.4675958471215565e-05, "loss": 3.9936, "step": 935936 }, { "epoch": 0.01, "learning_rate": 3.4667572523705045e-05, "loss": 3.9886, "step": 936448 }, { "epoch": 0.01, "learning_rate": 3.4659186576194525e-05, "loss": 4.001, "step": 936960 }, { "epoch": 0.01, "learning_rate": 3.4650817007487734e-05, "loss": 3.9983, "step": 937472 }, { "epoch": 0.01, "learning_rate": 3.464244743878094e-05, "loss": 4.0052, "step": 937984 }, { "epoch": 0.01, "learning_rate": 3.463406149127042e-05, "loss": 3.9974, "step": 938496 }, { "epoch": 0.01, "learning_rate": 3.46256755437599e-05, "loss": 3.9964, "step": 939008 }, { "epoch": 0.01, "learning_rate": 3.461728959624938e-05, "loss": 3.9985, "step": 939520 }, { "epoch": 0.01, "learning_rate": 3.460890364873886e-05, "loss": 3.9955, "step": 940032 }, { "epoch": 0.01, "learning_rate": 3.460053408003208e-05, "loss": 3.9725, "step": 940544 }, { "epoch": 0.01, "learning_rate": 3.459214813252156e-05, "loss": 4.0024, "step": 941056 }, { "epoch": 0.01, "learning_rate": 3.458376218501104e-05, "loss": 3.9938, "step": 941568 }, { "epoch": 0.01, "learning_rate": 3.457537623750052e-05, "loss": 4.0047, "step": 942080 }, { "epoch": 0.01, "learning_rate": 3.456699028999e-05, "loss": 3.9935, "step": 942592 }, { "epoch": 0.01, "learning_rate": 3.455860434247948e-05, "loss": 3.9936, "step": 943104 }, { "epoch": 0.01, "learning_rate": 3.455021839496896e-05, "loss": 3.9827, "step": 943616 }, { "epoch": 0.01, "learning_rate": 3.454183244745844e-05, "loss": 3.9906, "step": 944128 }, { "epoch": 0.01, "learning_rate": 3.453344649994792e-05, "loss": 4.0078, "step": 944640 }, { "epoch": 0.01, "learning_rate": 3.45250605524374e-05, "loss": 3.992, "step": 945152 }, { "epoch": 0.01, "learning_rate": 3.451667460492687e-05, "loss": 4.0084, "step": 945664 }, { "epoch": 0.01, "learning_rate": 3.450830503622009e-05, "loss": 3.9962, "step": 946176 }, { "epoch": 0.01, "learning_rate": 3.449991908870957e-05, "loss": 3.9708, "step": 946688 }, { "epoch": 0.01, "learning_rate": 3.4491549520002783e-05, "loss": 4.0103, "step": 947200 }, { "epoch": 0.01, "learning_rate": 3.4483163572492263e-05, "loss": 3.9826, "step": 947712 }, { "epoch": 0.01, "learning_rate": 3.447477762498174e-05, "loss": 3.9854, "step": 948224 }, { "epoch": 0.01, "learning_rate": 3.446639167747122e-05, "loss": 3.9969, "step": 948736 }, { "epoch": 0.01, "learning_rate": 3.44580057299607e-05, "loss": 3.9972, "step": 949248 }, { "epoch": 0.01, "learning_rate": 3.4449619782450176e-05, "loss": 3.9849, "step": 949760 }, { "epoch": 0.01, "learning_rate": 3.4441233834939656e-05, "loss": 3.986, "step": 950272 }, { "epoch": 0.01, "learning_rate": 3.4432847887429136e-05, "loss": 3.9811, "step": 950784 }, { "epoch": 0.01, "learning_rate": 3.4424461939918616e-05, "loss": 3.9859, "step": 951296 }, { "epoch": 0.01, "learning_rate": 3.4416075992408096e-05, "loss": 4.0028, "step": 951808 }, { "epoch": 0.01, "learning_rate": 3.4407690044897576e-05, "loss": 3.993, "step": 952320 }, { "epoch": 0.01, "learning_rate": 3.4399304097387056e-05, "loss": 3.995, "step": 952832 }, { "epoch": 0.01, "learning_rate": 3.4390950907484e-05, "loss": 3.9867, "step": 953344 }, { "epoch": 0.01, "learning_rate": 3.438256495997348e-05, "loss": 4.004, "step": 953856 }, { "epoch": 0.01, "learning_rate": 3.437417901246296e-05, "loss": 3.9936, "step": 954368 }, { "epoch": 0.01, "learning_rate": 3.436579306495244e-05, "loss": 3.9991, "step": 954880 }, { "epoch": 0.01, "learning_rate": 3.435740711744192e-05, "loss": 3.9872, "step": 955392 }, { "epoch": 0.01, "learning_rate": 3.43490211699314e-05, "loss": 3.9948, "step": 955904 }, { "epoch": 0.01, "learning_rate": 3.434063522242088e-05, "loss": 3.9967, "step": 956416 }, { "epoch": 0.01, "learning_rate": 3.433224927491036e-05, "loss": 3.9938, "step": 956928 }, { "epoch": 0.01, "learning_rate": 3.432387970620357e-05, "loss": 3.9922, "step": 957440 }, { "epoch": 0.01, "learning_rate": 3.431549375869305e-05, "loss": 4.0027, "step": 957952 }, { "epoch": 0.01, "learning_rate": 3.430710781118253e-05, "loss": 3.9842, "step": 958464 }, { "epoch": 0.01, "learning_rate": 3.429872186367201e-05, "loss": 3.9859, "step": 958976 }, { "epoch": 0.01, "learning_rate": 3.429035229496522e-05, "loss": 3.9921, "step": 959488 }, { "epoch": 0.01, "learning_rate": 3.4281966347454706e-05, "loss": 3.9972, "step": 960000 }, { "epoch": 0.01, "learning_rate": 3.4273580399944186e-05, "loss": 3.9852, "step": 960512 }, { "epoch": 0.01, "learning_rate": 3.4265210831237395e-05, "loss": 3.9919, "step": 961024 }, { "epoch": 0.01, "learning_rate": 3.4256824883726875e-05, "loss": 3.9877, "step": 961536 }, { "epoch": 0.02, "learning_rate": 3.4248438936216355e-05, "loss": 3.9895, "step": 962048 }, { "epoch": 0.02, "learning_rate": 3.4240052988705835e-05, "loss": 3.9947, "step": 962560 }, { "epoch": 0.02, "learning_rate": 3.4231667041195315e-05, "loss": 3.9844, "step": 963072 }, { "epoch": 0.02, "learning_rate": 3.4223281093684794e-05, "loss": 3.9935, "step": 963584 }, { "epoch": 0.02, "learning_rate": 3.4214895146174274e-05, "loss": 3.9978, "step": 964096 }, { "epoch": 0.02, "learning_rate": 3.4206509198663754e-05, "loss": 4.0013, "step": 964608 }, { "epoch": 0.02, "learning_rate": 3.4198139629956964e-05, "loss": 3.9683, "step": 965120 }, { "epoch": 0.02, "learning_rate": 3.4189753682446443e-05, "loss": 3.9886, "step": 965632 }, { "epoch": 0.02, "learning_rate": 3.4181367734935923e-05, "loss": 3.9822, "step": 966144 }, { "epoch": 0.02, "learning_rate": 3.417299816622914e-05, "loss": 3.9995, "step": 966656 }, { "epoch": 0.02, "learning_rate": 3.416461221871862e-05, "loss": 4.0008, "step": 967168 }, { "epoch": 0.02, "learning_rate": 3.41562262712081e-05, "loss": 3.9852, "step": 967680 }, { "epoch": 0.02, "learning_rate": 3.414784032369758e-05, "loss": 3.9864, "step": 968192 }, { "epoch": 0.02, "learning_rate": 3.413945437618706e-05, "loss": 3.9879, "step": 968704 }, { "epoch": 0.02, "learning_rate": 3.413106842867654e-05, "loss": 3.9828, "step": 969216 }, { "epoch": 0.02, "learning_rate": 3.412268248116601e-05, "loss": 3.9853, "step": 969728 }, { "epoch": 0.02, "learning_rate": 3.411431291245923e-05, "loss": 3.984, "step": 970240 }, { "epoch": 0.02, "learning_rate": 3.410592696494871e-05, "loss": 3.9908, "step": 970752 }, { "epoch": 0.02, "learning_rate": 3.409754101743818e-05, "loss": 3.9835, "step": 971264 }, { "epoch": 0.02, "learning_rate": 3.408915506992766e-05, "loss": 3.9792, "step": 971776 }, { "epoch": 0.02, "learning_rate": 3.408076912241714e-05, "loss": 3.9801, "step": 972288 }, { "epoch": 0.02, "learning_rate": 3.407238317490663e-05, "loss": 3.98, "step": 972800 }, { "epoch": 0.02, "learning_rate": 3.406401360619984e-05, "loss": 3.9915, "step": 973312 }, { "epoch": 0.02, "learning_rate": 3.405562765868932e-05, "loss": 3.9789, "step": 973824 }, { "epoch": 0.02, "learning_rate": 3.40472417111788e-05, "loss": 3.9913, "step": 974336 }, { "epoch": 0.02, "learning_rate": 3.403885576366828e-05, "loss": 3.9886, "step": 974848 }, { "epoch": 0.02, "learning_rate": 3.403046981615776e-05, "loss": 3.9868, "step": 975360 }, { "epoch": 0.02, "learning_rate": 3.4022100247450966e-05, "loss": 3.988, "step": 975872 }, { "epoch": 0.02, "learning_rate": 3.4013714299940446e-05, "loss": 3.9846, "step": 976384 }, { "epoch": 0.02, "learning_rate": 3.4005328352429926e-05, "loss": 3.9902, "step": 976896 }, { "epoch": 0.02, "learning_rate": 3.3996958783723135e-05, "loss": 3.9826, "step": 977408 }, { "epoch": 0.02, "learning_rate": 3.3988572836212615e-05, "loss": 3.9825, "step": 977920 }, { "epoch": 0.02, "learning_rate": 3.3980186888702095e-05, "loss": 3.9879, "step": 978432 }, { "epoch": 0.02, "learning_rate": 3.397180094119158e-05, "loss": 3.9849, "step": 978944 }, { "epoch": 0.02, "learning_rate": 3.396341499368106e-05, "loss": 3.9884, "step": 979456 }, { "epoch": 0.02, "learning_rate": 3.395502904617054e-05, "loss": 3.9837, "step": 979968 }, { "epoch": 0.02, "learning_rate": 3.394664309866002e-05, "loss": 3.9816, "step": 980480 }, { "epoch": 0.02, "learning_rate": 3.39382571511495e-05, "loss": 3.9846, "step": 980992 }, { "epoch": 0.02, "learning_rate": 3.392987120363898e-05, "loss": 3.9777, "step": 981504 }, { "epoch": 0.02, "learning_rate": 3.392150163493219e-05, "loss": 3.9891, "step": 982016 }, { "epoch": 0.02, "learning_rate": 3.391311568742167e-05, "loss": 3.9861, "step": 982528 }, { "epoch": 0.02, "learning_rate": 3.390472973991115e-05, "loss": 3.9969, "step": 983040 }, { "epoch": 0.02, "learning_rate": 3.389634379240063e-05, "loss": 3.979, "step": 983552 }, { "epoch": 0.02, "learning_rate": 3.388795784489011e-05, "loss": 3.9883, "step": 984064 }, { "epoch": 0.02, "learning_rate": 3.387957189737959e-05, "loss": 3.9927, "step": 984576 }, { "epoch": 0.02, "learning_rate": 3.387118594986907e-05, "loss": 3.9862, "step": 985088 }, { "epoch": 0.02, "learning_rate": 3.386280000235855e-05, "loss": 3.9835, "step": 985600 }, { "epoch": 0.02, "learning_rate": 3.385441405484803e-05, "loss": 3.9834, "step": 986112 }, { "epoch": 0.02, "learning_rate": 3.3846044486141246e-05, "loss": 3.9969, "step": 986624 }, { "epoch": 0.02, "learning_rate": 3.3837674917434455e-05, "loss": 3.994, "step": 987136 }, { "epoch": 0.02, "learning_rate": 3.3829288969923935e-05, "loss": 3.9846, "step": 987648 }, { "epoch": 0.02, "learning_rate": 3.3820903022413415e-05, "loss": 3.9796, "step": 988160 }, { "epoch": 0.02, "learning_rate": 3.3812517074902895e-05, "loss": 3.9889, "step": 988672 }, { "epoch": 0.02, "learning_rate": 3.380413112739237e-05, "loss": 3.992, "step": 989184 }, { "epoch": 0.02, "learning_rate": 3.3795761558685584e-05, "loss": 3.9763, "step": 989696 }, { "epoch": 0.02, "learning_rate": 3.378739198997879e-05, "loss": 4.0017, "step": 990208 }, { "epoch": 0.02, "learning_rate": 3.377900604246827e-05, "loss": 3.9784, "step": 990720 }, { "epoch": 0.02, "learning_rate": 3.377062009495775e-05, "loss": 3.9928, "step": 991232 }, { "epoch": 0.02, "learning_rate": 3.376223414744723e-05, "loss": 3.9871, "step": 991744 }, { "epoch": 0.03, "eval_loss": 4.088620662689209, "eval_runtime": 350.5963, "eval_samples_per_second": 1088.406, "eval_steps_per_second": 34.013, "step": 992160 }, { "epoch": 1.0, "learning_rate": 3.375384819993671e-05, "loss": 3.9874, "step": 992256 }, { "epoch": 1.0, "learning_rate": 3.374547863122993e-05, "loss": 3.9801, "step": 992768 }, { "epoch": 1.0, "learning_rate": 3.373709268371941e-05, "loss": 3.9848, "step": 993280 }, { "epoch": 1.0, "learning_rate": 3.372870673620889e-05, "loss": 3.9963, "step": 993792 }, { "epoch": 1.0, "learning_rate": 3.372032078869837e-05, "loss": 3.988, "step": 994304 }, { "epoch": 1.0, "learning_rate": 3.371193484118784e-05, "loss": 3.9888, "step": 994816 }, { "epoch": 1.0, "learning_rate": 3.370354889367732e-05, "loss": 3.9809, "step": 995328 }, { "epoch": 1.0, "learning_rate": 3.36951629461668e-05, "loss": 3.9801, "step": 995840 }, { "epoch": 1.0, "learning_rate": 3.368677699865628e-05, "loss": 3.984, "step": 996352 }, { "epoch": 1.0, "learning_rate": 3.367839105114576e-05, "loss": 3.991, "step": 996864 }, { "epoch": 1.0, "learning_rate": 3.367000510363524e-05, "loss": 3.9833, "step": 997376 }, { "epoch": 1.0, "learning_rate": 3.366161915612472e-05, "loss": 3.9892, "step": 997888 }, { "epoch": 1.0, "learning_rate": 3.365324958741794e-05, "loss": 3.9945, "step": 998400 }, { "epoch": 1.0, "learning_rate": 3.364486363990742e-05, "loss": 3.972, "step": 998912 }, { "epoch": 1.0, "learning_rate": 3.36364776923969e-05, "loss": 3.983, "step": 999424 }, { "epoch": 1.0, "learning_rate": 3.3628108123690106e-05, "loss": 3.9696, "step": 999936 }, { "epoch": 1.0, "learning_rate": 3.3619722176179586e-05, "loss": 3.9724, "step": 1000448 }, { "epoch": 1.0, "learning_rate": 3.3611336228669066e-05, "loss": 3.9848, "step": 1000960 }, { "epoch": 1.0, "learning_rate": 3.3602950281158546e-05, "loss": 3.9755, "step": 1001472 }, { "epoch": 1.0, "learning_rate": 3.3594564333648026e-05, "loss": 3.9884, "step": 1001984 }, { "epoch": 1.0, "learning_rate": 3.3586178386137506e-05, "loss": 3.9955, "step": 1002496 }, { "epoch": 1.0, "learning_rate": 3.3577792438626986e-05, "loss": 3.983, "step": 1003008 }, { "epoch": 1.0, "learning_rate": 3.3569406491116466e-05, "loss": 3.9892, "step": 1003520 }, { "epoch": 1.0, "learning_rate": 3.3561020543605946e-05, "loss": 3.9897, "step": 1004032 }, { "epoch": 1.0, "learning_rate": 3.3552634596095426e-05, "loss": 3.9717, "step": 1004544 }, { "epoch": 1.0, "learning_rate": 3.3544265027388635e-05, "loss": 3.9868, "step": 1005056 }, { "epoch": 1.0, "learning_rate": 3.353587907987812e-05, "loss": 3.9802, "step": 1005568 }, { "epoch": 1.0, "learning_rate": 3.35274931323676e-05, "loss": 3.9726, "step": 1006080 }, { "epoch": 1.0, "learning_rate": 3.351910718485708e-05, "loss": 3.9823, "step": 1006592 }, { "epoch": 1.0, "learning_rate": 3.351072123734656e-05, "loss": 3.9722, "step": 1007104 }, { "epoch": 1.01, "learning_rate": 3.3502335289836035e-05, "loss": 3.9778, "step": 1007616 }, { "epoch": 1.01, "learning_rate": 3.349396572112925e-05, "loss": 3.9825, "step": 1008128 }, { "epoch": 1.01, "learning_rate": 3.348557977361873e-05, "loss": 3.9888, "step": 1008640 }, { "epoch": 1.01, "learning_rate": 3.3477193826108204e-05, "loss": 3.981, "step": 1009152 }, { "epoch": 1.01, "learning_rate": 3.3468807878597684e-05, "loss": 3.9779, "step": 1009664 }, { "epoch": 1.01, "learning_rate": 3.34604383098909e-05, "loss": 3.9815, "step": 1010176 }, { "epoch": 1.01, "learning_rate": 3.345205236238038e-05, "loss": 3.9942, "step": 1010688 }, { "epoch": 1.01, "learning_rate": 3.344366641486986e-05, "loss": 3.9769, "step": 1011200 }, { "epoch": 1.01, "learning_rate": 3.343528046735934e-05, "loss": 3.9756, "step": 1011712 }, { "epoch": 1.01, "learning_rate": 3.342689451984882e-05, "loss": 3.9772, "step": 1012224 }, { "epoch": 1.01, "learning_rate": 3.34185085723383e-05, "loss": 3.9788, "step": 1012736 }, { "epoch": 1.01, "learning_rate": 3.341013900363151e-05, "loss": 3.9799, "step": 1013248 }, { "epoch": 1.01, "learning_rate": 3.340175305612099e-05, "loss": 3.9866, "step": 1013760 }, { "epoch": 1.01, "learning_rate": 3.339336710861047e-05, "loss": 3.9867, "step": 1014272 }, { "epoch": 1.01, "learning_rate": 3.338498116109995e-05, "loss": 3.9843, "step": 1014784 }, { "epoch": 1.01, "learning_rate": 3.337661159239316e-05, "loss": 3.9809, "step": 1015296 }, { "epoch": 1.01, "learning_rate": 3.336822564488264e-05, "loss": 3.9811, "step": 1015808 }, { "epoch": 1.01, "learning_rate": 3.335983969737212e-05, "loss": 3.9806, "step": 1016320 }, { "epoch": 1.01, "learning_rate": 3.33514537498616e-05, "loss": 3.9625, "step": 1016832 }, { "epoch": 1.01, "learning_rate": 3.334306780235108e-05, "loss": 3.9863, "step": 1017344 }, { "epoch": 1.01, "learning_rate": 3.333469823364429e-05, "loss": 3.98, "step": 1017856 }, { "epoch": 1.01, "learning_rate": 3.332631228613377e-05, "loss": 3.9905, "step": 1018368 }, { "epoch": 1.01, "learning_rate": 3.331792633862325e-05, "loss": 3.9767, "step": 1018880 }, { "epoch": 1.01, "learning_rate": 3.330954039111273e-05, "loss": 3.9785, "step": 1019392 }, { "epoch": 1.01, "learning_rate": 3.330115444360221e-05, "loss": 3.9722, "step": 1019904 }, { "epoch": 1.01, "learning_rate": 3.329276849609169e-05, "loss": 3.9703, "step": 1020416 }, { "epoch": 1.01, "learning_rate": 3.328438254858117e-05, "loss": 3.991, "step": 1020928 }, { "epoch": 1.01, "learning_rate": 3.327599660107065e-05, "loss": 3.9735, "step": 1021440 }, { "epoch": 1.01, "learning_rate": 3.326761065356013e-05, "loss": 4.0001, "step": 1021952 }, { "epoch": 1.01, "learning_rate": 3.325924108485334e-05, "loss": 3.9781, "step": 1022464 }, { "epoch": 1.01, "learning_rate": 3.325085513734282e-05, "loss": 3.9651, "step": 1022976 }, { "epoch": 1.01, "learning_rate": 3.32424691898323e-05, "loss": 3.9959, "step": 1023488 }, { "epoch": 1.01, "learning_rate": 3.323408324232178e-05, "loss": 3.9716, "step": 1024000 }, { "epoch": 1.01, "learning_rate": 3.322569729481126e-05, "loss": 3.967, "step": 1024512 }, { "epoch": 1.01, "learning_rate": 3.321731134730074e-05, "loss": 3.9792, "step": 1025024 }, { "epoch": 1.01, "learning_rate": 3.320894177859396e-05, "loss": 3.9872, "step": 1025536 }, { "epoch": 1.01, "learning_rate": 3.320055583108344e-05, "loss": 3.9663, "step": 1026048 }, { "epoch": 1.01, "learning_rate": 3.319216988357292e-05, "loss": 3.9726, "step": 1026560 }, { "epoch": 1.01, "learning_rate": 3.318378393606239e-05, "loss": 3.9664, "step": 1027072 }, { "epoch": 1.01, "learning_rate": 3.317539798855187e-05, "loss": 3.9686, "step": 1027584 }, { "epoch": 1.01, "learning_rate": 3.3167028419845087e-05, "loss": 3.9919, "step": 1028096 }, { "epoch": 1.01, "learning_rate": 3.3158642472334567e-05, "loss": 3.9801, "step": 1028608 }, { "epoch": 1.01, "learning_rate": 3.315025652482404e-05, "loss": 3.9794, "step": 1029120 }, { "epoch": 1.01, "learning_rate": 3.314187057731352e-05, "loss": 3.9711, "step": 1029632 }, { "epoch": 1.01, "learning_rate": 3.3133484629803e-05, "loss": 3.9903, "step": 1030144 }, { "epoch": 1.01, "learning_rate": 3.312509868229248e-05, "loss": 3.9788, "step": 1030656 }, { "epoch": 1.01, "learning_rate": 3.3116729113585695e-05, "loss": 3.9865, "step": 1031168 }, { "epoch": 1.01, "learning_rate": 3.3108343166075175e-05, "loss": 3.9731, "step": 1031680 }, { "epoch": 1.01, "learning_rate": 3.3099957218564655e-05, "loss": 3.9793, "step": 1032192 }, { "epoch": 1.01, "learning_rate": 3.3091571271054135e-05, "loss": 3.9845, "step": 1032704 }, { "epoch": 1.01, "learning_rate": 3.3083185323543615e-05, "loss": 3.9777, "step": 1033216 }, { "epoch": 1.01, "learning_rate": 3.3074815754836824e-05, "loss": 3.9783, "step": 1033728 }, { "epoch": 1.01, "learning_rate": 3.3066429807326304e-05, "loss": 3.9869, "step": 1034240 }, { "epoch": 1.01, "learning_rate": 3.3058043859815784e-05, "loss": 3.976, "step": 1034752 }, { "epoch": 1.01, "learning_rate": 3.3049657912305264e-05, "loss": 3.9694, "step": 1035264 }, { "epoch": 1.01, "learning_rate": 3.3041271964794744e-05, "loss": 3.9753, "step": 1035776 }, { "epoch": 1.01, "learning_rate": 3.303290239608795e-05, "loss": 3.9832, "step": 1036288 }, { "epoch": 1.01, "learning_rate": 3.302451644857743e-05, "loss": 3.9739, "step": 1036800 }, { "epoch": 1.01, "learning_rate": 3.301613050106691e-05, "loss": 3.9752, "step": 1037312 }, { "epoch": 1.01, "learning_rate": 3.30077445535564e-05, "loss": 3.9721, "step": 1037824 }, { "epoch": 1.02, "learning_rate": 3.299935860604588e-05, "loss": 3.9748, "step": 1038336 }, { "epoch": 1.02, "learning_rate": 3.299098903733909e-05, "loss": 3.9765, "step": 1038848 }, { "epoch": 1.02, "learning_rate": 3.298260308982857e-05, "loss": 3.9741, "step": 1039360 }, { "epoch": 1.02, "learning_rate": 3.297421714231805e-05, "loss": 3.9784, "step": 1039872 }, { "epoch": 1.02, "learning_rate": 3.296583119480753e-05, "loss": 3.9822, "step": 1040384 }, { "epoch": 1.02, "learning_rate": 3.295744524729701e-05, "loss": 3.9864, "step": 1040896 }, { "epoch": 1.02, "learning_rate": 3.294905929978649e-05, "loss": 3.9551, "step": 1041408 }, { "epoch": 1.02, "learning_rate": 3.294067335227597e-05, "loss": 3.9712, "step": 1041920 }, { "epoch": 1.02, "learning_rate": 3.293228740476545e-05, "loss": 3.9697, "step": 1042432 }, { "epoch": 1.02, "learning_rate": 3.292391783605866e-05, "loss": 3.9823, "step": 1042944 }, { "epoch": 1.02, "learning_rate": 3.291553188854814e-05, "loss": 3.9865, "step": 1043456 }, { "epoch": 1.02, "learning_rate": 3.290714594103762e-05, "loss": 3.972, "step": 1043968 }, { "epoch": 1.02, "learning_rate": 3.28987599935271e-05, "loss": 3.9715, "step": 1044480 }, { "epoch": 1.02, "learning_rate": 3.2890390424820314e-05, "loss": 3.9738, "step": 1044992 }, { "epoch": 1.02, "learning_rate": 3.2882004477309793e-05, "loss": 3.9714, "step": 1045504 }, { "epoch": 1.02, "learning_rate": 3.2873618529799273e-05, "loss": 3.9694, "step": 1046016 }, { "epoch": 1.02, "learning_rate": 3.286524896109248e-05, "loss": 3.9704, "step": 1046528 }, { "epoch": 1.02, "learning_rate": 3.285686301358196e-05, "loss": 3.9774, "step": 1047040 }, { "epoch": 1.02, "learning_rate": 3.284847706607144e-05, "loss": 3.969, "step": 1047552 }, { "epoch": 1.02, "learning_rate": 3.284009111856092e-05, "loss": 3.9657, "step": 1048064 }, { "epoch": 1.02, "learning_rate": 3.28317051710504e-05, "loss": 3.9686, "step": 1048576 }, { "epoch": 1.02, "learning_rate": 3.2823319223539876e-05, "loss": 3.9597, "step": 1049088 }, { "epoch": 1.02, "learning_rate": 3.2814933276029355e-05, "loss": 3.9759, "step": 1049600 }, { "epoch": 1.02, "learning_rate": 3.2806547328518835e-05, "loss": 3.9704, "step": 1050112 }, { "epoch": 1.02, "learning_rate": 3.279816138100832e-05, "loss": 3.97, "step": 1050624 }, { "epoch": 1.02, "learning_rate": 3.27897754334978e-05, "loss": 3.9767, "step": 1051136 }, { "epoch": 1.02, "learning_rate": 3.278138948598728e-05, "loss": 3.9756, "step": 1051648 }, { "epoch": 1.02, "learning_rate": 3.277301991728049e-05, "loss": 3.9738, "step": 1052160 }, { "epoch": 1.02, "learning_rate": 3.276463396976997e-05, "loss": 3.9685, "step": 1052672 }, { "epoch": 1.02, "learning_rate": 3.275624802225945e-05, "loss": 3.9782, "step": 1053184 }, { "epoch": 1.02, "learning_rate": 3.274786207474893e-05, "loss": 3.9693, "step": 1053696 }, { "epoch": 1.02, "learning_rate": 3.273949250604214e-05, "loss": 3.9646, "step": 1054208 }, { "epoch": 1.02, "learning_rate": 3.273110655853162e-05, "loss": 3.9763, "step": 1054720 }, { "epoch": 1.02, "learning_rate": 3.27227206110211e-05, "loss": 3.9732, "step": 1055232 }, { "epoch": 1.02, "learning_rate": 3.271433466351058e-05, "loss": 3.9733, "step": 1055744 }, { "epoch": 1.02, "learning_rate": 3.270594871600006e-05, "loss": 3.9686, "step": 1056256 }, { "epoch": 1.02, "learning_rate": 3.269756276848954e-05, "loss": 3.9715, "step": 1056768 }, { "epoch": 1.02, "learning_rate": 3.268917682097902e-05, "loss": 3.9709, "step": 1057280 }, { "epoch": 1.02, "learning_rate": 3.2680807252272236e-05, "loss": 3.9653, "step": 1057792 }, { "epoch": 1.02, "learning_rate": 3.2672421304761716e-05, "loss": 3.965, "step": 1058304 }, { "epoch": 1.02, "learning_rate": 3.2664035357251196e-05, "loss": 3.9796, "step": 1058816 }, { "epoch": 1.02, "learning_rate": 3.2655649409740676e-05, "loss": 3.9839, "step": 1059328 }, { "epoch": 1.02, "learning_rate": 3.2647263462230156e-05, "loss": 3.9622, "step": 1059840 }, { "epoch": 1.02, "learning_rate": 3.2638877514719636e-05, "loss": 3.9702, "step": 1060352 }, { "epoch": 1.02, "learning_rate": 3.2630491567209115e-05, "loss": 3.9806, "step": 1060864 }, { "epoch": 1.02, "learning_rate": 3.262210561969859e-05, "loss": 3.9734, "step": 1061376 }, { "epoch": 1.02, "learning_rate": 3.2613736050991805e-05, "loss": 3.9672, "step": 1061888 }, { "epoch": 1.02, "learning_rate": 3.2605366482285014e-05, "loss": 3.9693, "step": 1062400 }, { "epoch": 1.02, "learning_rate": 3.2596980534774494e-05, "loss": 3.986, "step": 1062912 }, { "epoch": 1.02, "learning_rate": 3.2588594587263974e-05, "loss": 3.9798, "step": 1063424 }, { "epoch": 1.02, "learning_rate": 3.2580208639753453e-05, "loss": 3.969, "step": 1063936 }, { "epoch": 1.02, "learning_rate": 3.257182269224294e-05, "loss": 3.9631, "step": 1064448 }, { "epoch": 1.02, "learning_rate": 3.2563436744732413e-05, "loss": 3.9774, "step": 1064960 }, { "epoch": 1.02, "learning_rate": 3.255505079722189e-05, "loss": 3.9768, "step": 1065472 }, { "epoch": 1.02, "learning_rate": 3.254666484971137e-05, "loss": 3.9628, "step": 1065984 }, { "epoch": 1.02, "learning_rate": 3.253829528100459e-05, "loss": 3.9849, "step": 1066496 }, { "epoch": 1.02, "learning_rate": 3.252990933349406e-05, "loss": 3.9667, "step": 1067008 }, { "epoch": 1.02, "learning_rate": 3.252152338598354e-05, "loss": 3.9777, "step": 1067520 }, { "epoch": 1.02, "learning_rate": 3.251313743847302e-05, "loss": 3.9741, "step": 1068032 }, { "epoch": 1.03, "eval_loss": 4.080361843109131, "eval_runtime": 348.2572, "eval_samples_per_second": 1095.716, "eval_steps_per_second": 34.242, "step": 1068480 }, { "epoch": 0.0, "learning_rate": 3.250476786976624e-05, "loss": 4.0035, "step": 1068544 }, { "epoch": 0.0, "learning_rate": 3.249638192225571e-05, "loss": 3.9654, "step": 1069056 }, { "epoch": 0.0, "learning_rate": 3.248799597474519e-05, "loss": 3.9717, "step": 1069568 }, { "epoch": 0.0, "learning_rate": 3.247961002723468e-05, "loss": 3.982, "step": 1070080 }, { "epoch": 0.0, "learning_rate": 3.247122407972416e-05, "loss": 3.9742, "step": 1070592 }, { "epoch": 0.0, "learning_rate": 3.246283813221364e-05, "loss": 3.9732, "step": 1071104 }, { "epoch": 0.0, "learning_rate": 3.245445218470312e-05, "loss": 3.9709, "step": 1071616 }, { "epoch": 0.0, "learning_rate": 3.24460662371926e-05, "loss": 3.9669, "step": 1072128 }, { "epoch": 0.0, "learning_rate": 3.243768028968208e-05, "loss": 3.968, "step": 1072640 }, { "epoch": 0.0, "learning_rate": 3.242929434217156e-05, "loss": 3.9767, "step": 1073152 }, { "epoch": 0.0, "learning_rate": 3.242090839466104e-05, "loss": 3.9702, "step": 1073664 }, { "epoch": 0.0, "learning_rate": 3.241252244715052e-05, "loss": 3.9754, "step": 1074176 }, { "epoch": 0.0, "learning_rate": 3.240415287844373e-05, "loss": 3.98, "step": 1074688 }, { "epoch": 0.0, "learning_rate": 3.239576693093321e-05, "loss": 3.9586, "step": 1075200 }, { "epoch": 0.0, "learning_rate": 3.238738098342269e-05, "loss": 3.9681, "step": 1075712 }, { "epoch": 0.0, "learning_rate": 3.237899503591217e-05, "loss": 3.9557, "step": 1076224 }, { "epoch": 0.0, "learning_rate": 3.2370609088401647e-05, "loss": 3.9612, "step": 1076736 }, { "epoch": 0.0, "learning_rate": 3.2362223140891127e-05, "loss": 3.9688, "step": 1077248 }, { "epoch": 0.0, "learning_rate": 3.2353837193380606e-05, "loss": 3.9597, "step": 1077760 }, { "epoch": 0.0, "learning_rate": 3.2345451245870086e-05, "loss": 3.9749, "step": 1078272 }, { "epoch": 0.0, "learning_rate": 3.2337065298359566e-05, "loss": 3.9848, "step": 1078784 }, { "epoch": 0.0, "learning_rate": 3.2328679350849046e-05, "loss": 3.9656, "step": 1079296 }, { "epoch": 0.0, "learning_rate": 3.2320293403338526e-05, "loss": 3.9744, "step": 1079808 }, { "epoch": 0.0, "learning_rate": 3.2311907455828006e-05, "loss": 3.976, "step": 1080320 }, { "epoch": 0.0, "learning_rate": 3.2303537887121215e-05, "loss": 3.959, "step": 1080832 }, { "epoch": 0.0, "learning_rate": 3.2295151939610695e-05, "loss": 3.9752, "step": 1081344 }, { "epoch": 0.0, "learning_rate": 3.2286765992100175e-05, "loss": 3.9623, "step": 1081856 }, { "epoch": 0.0, "learning_rate": 3.2278380044589655e-05, "loss": 3.9635, "step": 1082368 }, { "epoch": 0.0, "learning_rate": 3.2269994097079135e-05, "loss": 3.9633, "step": 1082880 }, { "epoch": 0.0, "learning_rate": 3.2261608149568615e-05, "loss": 3.9564, "step": 1083392 }, { "epoch": 0.01, "learning_rate": 3.2253222202058095e-05, "loss": 3.9633, "step": 1083904 }, { "epoch": 0.01, "learning_rate": 3.2244836254547575e-05, "loss": 3.9709, "step": 1084416 }, { "epoch": 0.01, "learning_rate": 3.2236450307037055e-05, "loss": 3.9774, "step": 1084928 }, { "epoch": 0.01, "learning_rate": 3.2228097117134e-05, "loss": 3.9687, "step": 1085440 }, { "epoch": 0.01, "learning_rate": 3.221972754842721e-05, "loss": 3.961, "step": 1085952 }, { "epoch": 0.01, "learning_rate": 3.221134160091669e-05, "loss": 3.9666, "step": 1086464 }, { "epoch": 0.01, "learning_rate": 3.220295565340617e-05, "loss": 3.9843, "step": 1086976 }, { "epoch": 0.01, "learning_rate": 3.219456970589565e-05, "loss": 3.9594, "step": 1087488 }, { "epoch": 0.01, "learning_rate": 3.218618375838513e-05, "loss": 3.9662, "step": 1088000 }, { "epoch": 0.01, "learning_rate": 3.217779781087461e-05, "loss": 3.9656, "step": 1088512 }, { "epoch": 0.01, "learning_rate": 3.216941186336409e-05, "loss": 3.9606, "step": 1089024 }, { "epoch": 0.01, "learning_rate": 3.216102591585357e-05, "loss": 3.9685, "step": 1089536 }, { "epoch": 0.01, "learning_rate": 3.215263996834305e-05, "loss": 3.9715, "step": 1090048 }, { "epoch": 0.01, "learning_rate": 3.214425402083253e-05, "loss": 3.9779, "step": 1090560 }, { "epoch": 0.01, "learning_rate": 3.213586807332201e-05, "loss": 3.9693, "step": 1091072 }, { "epoch": 0.01, "learning_rate": 3.212748212581149e-05, "loss": 3.9676, "step": 1091584 }, { "epoch": 0.01, "learning_rate": 3.2119112557104705e-05, "loss": 3.9648, "step": 1092096 }, { "epoch": 0.01, "learning_rate": 3.2110726609594184e-05, "loss": 3.9725, "step": 1092608 }, { "epoch": 0.01, "learning_rate": 3.2102340662083664e-05, "loss": 3.9458, "step": 1093120 }, { "epoch": 0.01, "learning_rate": 3.209395471457314e-05, "loss": 3.9702, "step": 1093632 }, { "epoch": 0.01, "learning_rate": 3.208556876706262e-05, "loss": 3.9711, "step": 1094144 }, { "epoch": 0.01, "learning_rate": 3.2077199198355833e-05, "loss": 3.972, "step": 1094656 }, { "epoch": 0.01, "learning_rate": 3.206882962964904e-05, "loss": 3.9639, "step": 1095168 }, { "epoch": 0.01, "learning_rate": 3.206044368213852e-05, "loss": 3.9606, "step": 1095680 }, { "epoch": 0.01, "learning_rate": 3.2052057734628e-05, "loss": 3.965, "step": 1096192 }, { "epoch": 0.01, "learning_rate": 3.204367178711748e-05, "loss": 3.9557, "step": 1096704 }, { "epoch": 0.01, "learning_rate": 3.203528583960696e-05, "loss": 3.9783, "step": 1097216 }, { "epoch": 0.01, "learning_rate": 3.202689989209644e-05, "loss": 3.963, "step": 1097728 }, { "epoch": 0.01, "learning_rate": 3.201851394458592e-05, "loss": 3.9818, "step": 1098240 }, { "epoch": 0.01, "learning_rate": 3.20101279970754e-05, "loss": 3.9681, "step": 1098752 }, { "epoch": 0.01, "learning_rate": 3.200177480717235e-05, "loss": 3.9503, "step": 1099264 }, { "epoch": 0.01, "learning_rate": 3.199338885966183e-05, "loss": 3.9796, "step": 1099776 }, { "epoch": 0.01, "learning_rate": 3.198500291215131e-05, "loss": 3.9568, "step": 1100288 }, { "epoch": 0.01, "learning_rate": 3.197661696464079e-05, "loss": 3.9562, "step": 1100800 }, { "epoch": 0.01, "learning_rate": 3.196823101713026e-05, "loss": 3.967, "step": 1101312 }, { "epoch": 0.01, "learning_rate": 3.195984506961974e-05, "loss": 3.9735, "step": 1101824 }, { "epoch": 0.01, "learning_rate": 3.195145912210922e-05, "loss": 3.954, "step": 1102336 }, { "epoch": 0.01, "learning_rate": 3.19430731745987e-05, "loss": 3.9578, "step": 1102848 }, { "epoch": 0.01, "learning_rate": 3.193468722708819e-05, "loss": 3.957, "step": 1103360 }, { "epoch": 0.01, "learning_rate": 3.1926317658381396e-05, "loss": 3.9524, "step": 1103872 }, { "epoch": 0.01, "learning_rate": 3.191794808967461e-05, "loss": 3.9763, "step": 1104384 }, { "epoch": 0.01, "learning_rate": 3.1909562142164085e-05, "loss": 3.9682, "step": 1104896 }, { "epoch": 0.01, "learning_rate": 3.1901176194653565e-05, "loss": 3.9626, "step": 1105408 }, { "epoch": 0.01, "learning_rate": 3.1892790247143045e-05, "loss": 3.9614, "step": 1105920 }, { "epoch": 0.01, "learning_rate": 3.1884404299632525e-05, "loss": 3.9733, "step": 1106432 }, { "epoch": 0.01, "learning_rate": 3.1876034730925734e-05, "loss": 3.9639, "step": 1106944 }, { "epoch": 0.01, "learning_rate": 3.1867648783415214e-05, "loss": 3.9692, "step": 1107456 }, { "epoch": 0.01, "learning_rate": 3.1859262835904694e-05, "loss": 3.9623, "step": 1107968 }, { "epoch": 0.01, "learning_rate": 3.1850876888394174e-05, "loss": 3.9649, "step": 1108480 }, { "epoch": 0.01, "learning_rate": 3.1842490940883654e-05, "loss": 3.9681, "step": 1108992 }, { "epoch": 0.01, "learning_rate": 3.183412137217687e-05, "loss": 3.9649, "step": 1109504 }, { "epoch": 0.01, "learning_rate": 3.182573542466635e-05, "loss": 3.9644, "step": 1110016 }, { "epoch": 0.01, "learning_rate": 3.181734947715583e-05, "loss": 3.9715, "step": 1110528 }, { "epoch": 0.01, "learning_rate": 3.180896352964531e-05, "loss": 3.9687, "step": 1111040 }, { "epoch": 0.01, "learning_rate": 3.180059396093852e-05, "loss": 3.9508, "step": 1111552 }, { "epoch": 0.01, "learning_rate": 3.1792208013428e-05, "loss": 3.9633, "step": 1112064 }, { "epoch": 0.01, "learning_rate": 3.178382206591748e-05, "loss": 3.9724, "step": 1112576 }, { "epoch": 0.01, "learning_rate": 3.177543611840696e-05, "loss": 3.9595, "step": 1113088 }, { "epoch": 0.01, "learning_rate": 3.176705017089644e-05, "loss": 3.9614, "step": 1113600 }, { "epoch": 0.01, "learning_rate": 3.175868060218965e-05, "loss": 3.9581, "step": 1114112 }, { "epoch": 0.02, "learning_rate": 3.175029465467913e-05, "loss": 3.9625, "step": 1114624 }, { "epoch": 0.02, "learning_rate": 3.174190870716861e-05, "loss": 3.9612, "step": 1115136 }, { "epoch": 0.02, "learning_rate": 3.1733522759658094e-05, "loss": 3.9608, "step": 1115648 }, { "epoch": 0.02, "learning_rate": 3.1725136812147574e-05, "loss": 3.9668, "step": 1116160 }, { "epoch": 0.02, "learning_rate": 3.1716750864637054e-05, "loss": 3.9612, "step": 1116672 }, { "epoch": 0.02, "learning_rate": 3.170838129593026e-05, "loss": 3.977, "step": 1117184 }, { "epoch": 0.02, "learning_rate": 3.169999534841974e-05, "loss": 3.9394, "step": 1117696 }, { "epoch": 0.02, "learning_rate": 3.169160940090922e-05, "loss": 3.9618, "step": 1118208 }, { "epoch": 0.02, "learning_rate": 3.16832234533987e-05, "loss": 3.9552, "step": 1118720 }, { "epoch": 0.02, "learning_rate": 3.167485388469191e-05, "loss": 3.9692, "step": 1119232 }, { "epoch": 0.02, "learning_rate": 3.166646793718139e-05, "loss": 3.9701, "step": 1119744 }, { "epoch": 0.02, "learning_rate": 3.165808198967087e-05, "loss": 3.9605, "step": 1120256 }, { "epoch": 0.02, "learning_rate": 3.164969604216035e-05, "loss": 3.9574, "step": 1120768 }, { "epoch": 0.02, "learning_rate": 3.164132647345356e-05, "loss": 3.9582, "step": 1121280 }, { "epoch": 0.02, "learning_rate": 3.163294052594304e-05, "loss": 3.9583, "step": 1121792 }, { "epoch": 0.02, "learning_rate": 3.162455457843253e-05, "loss": 3.9539, "step": 1122304 }, { "epoch": 0.02, "learning_rate": 3.161616863092201e-05, "loss": 3.9554, "step": 1122816 }, { "epoch": 0.02, "learning_rate": 3.160778268341149e-05, "loss": 3.9616, "step": 1123328 }, { "epoch": 0.02, "learning_rate": 3.15994131147047e-05, "loss": 3.9617, "step": 1123840 }, { "epoch": 0.02, "learning_rate": 3.1591043545997906e-05, "loss": 3.9507, "step": 1124352 }, { "epoch": 0.02, "learning_rate": 3.1582657598487386e-05, "loss": 3.9576, "step": 1124864 }, { "epoch": 0.02, "learning_rate": 3.1574271650976866e-05, "loss": 3.9465, "step": 1125376 }, { "epoch": 0.02, "learning_rate": 3.1565885703466346e-05, "loss": 3.9673, "step": 1125888 }, { "epoch": 0.02, "learning_rate": 3.1557499755955826e-05, "loss": 3.9545, "step": 1126400 }, { "epoch": 0.02, "learning_rate": 3.1549113808445306e-05, "loss": 3.9572, "step": 1126912 }, { "epoch": 0.02, "learning_rate": 3.1540727860934786e-05, "loss": 3.9607, "step": 1127424 }, { "epoch": 0.02, "learning_rate": 3.1532341913424266e-05, "loss": 3.9624, "step": 1127936 }, { "epoch": 0.02, "learning_rate": 3.152397234471748e-05, "loss": 3.9589, "step": 1128448 }, { "epoch": 0.02, "learning_rate": 3.151558639720696e-05, "loss": 3.956, "step": 1128960 }, { "epoch": 0.02, "learning_rate": 3.150720044969644e-05, "loss": 3.9618, "step": 1129472 }, { "epoch": 0.02, "learning_rate": 3.149881450218592e-05, "loss": 3.9535, "step": 1129984 }, { "epoch": 0.02, "learning_rate": 3.1490428554675395e-05, "loss": 3.9519, "step": 1130496 }, { "epoch": 0.02, "learning_rate": 3.148205898596861e-05, "loss": 3.9631, "step": 1131008 }, { "epoch": 0.02, "learning_rate": 3.147367303845809e-05, "loss": 3.962, "step": 1131520 }, { "epoch": 0.02, "learning_rate": 3.1465287090947564e-05, "loss": 3.9616, "step": 1132032 }, { "epoch": 0.02, "learning_rate": 3.1456901143437043e-05, "loss": 3.9534, "step": 1132544 }, { "epoch": 0.02, "learning_rate": 3.1448515195926523e-05, "loss": 3.9569, "step": 1133056 }, { "epoch": 0.02, "learning_rate": 3.1440129248416003e-05, "loss": 3.9552, "step": 1133568 }, { "epoch": 0.02, "learning_rate": 3.143175967970922e-05, "loss": 3.953, "step": 1134080 }, { "epoch": 0.02, "learning_rate": 3.14233737321987e-05, "loss": 3.949, "step": 1134592 }, { "epoch": 0.02, "learning_rate": 3.141498778468818e-05, "loss": 3.9683, "step": 1135104 }, { "epoch": 0.02, "learning_rate": 3.140660183717766e-05, "loss": 3.9707, "step": 1135616 }, { "epoch": 0.02, "learning_rate": 3.139821588966714e-05, "loss": 3.9544, "step": 1136128 }, { "epoch": 0.02, "learning_rate": 3.138984632096035e-05, "loss": 3.9559, "step": 1136640 }, { "epoch": 0.02, "learning_rate": 3.138146037344983e-05, "loss": 3.962, "step": 1137152 }, { "epoch": 0.02, "learning_rate": 3.137307442593931e-05, "loss": 3.9604, "step": 1137664 }, { "epoch": 0.02, "learning_rate": 3.136468847842879e-05, "loss": 3.9559, "step": 1138176 }, { "epoch": 0.02, "learning_rate": 3.135630253091827e-05, "loss": 3.9608, "step": 1138688 }, { "epoch": 0.02, "learning_rate": 3.134791658340775e-05, "loss": 3.972, "step": 1139200 }, { "epoch": 0.02, "learning_rate": 3.133953063589723e-05, "loss": 3.9641, "step": 1139712 }, { "epoch": 0.02, "learning_rate": 3.133114468838671e-05, "loss": 3.9563, "step": 1140224 }, { "epoch": 0.02, "learning_rate": 3.132277511967992e-05, "loss": 3.9488, "step": 1140736 }, { "epoch": 0.02, "learning_rate": 3.131440555097313e-05, "loss": 3.9631, "step": 1141248 }, { "epoch": 0.02, "learning_rate": 3.130601960346261e-05, "loss": 3.964, "step": 1141760 }, { "epoch": 0.02, "learning_rate": 3.129763365595209e-05, "loss": 3.9523, "step": 1142272 }, { "epoch": 0.02, "learning_rate": 3.128924770844157e-05, "loss": 3.9727, "step": 1142784 }, { "epoch": 0.02, "learning_rate": 3.128086176093105e-05, "loss": 3.9555, "step": 1143296 }, { "epoch": 0.02, "learning_rate": 3.127247581342053e-05, "loss": 3.9637, "step": 1143808 }, { "epoch": 0.02, "learning_rate": 3.126408986591001e-05, "loss": 3.9581, "step": 1144320 }, { "epoch": 0.03, "eval_loss": 4.072638988494873, "eval_runtime": 295.1398, "eval_samples_per_second": 1292.916, "eval_steps_per_second": 40.405, "step": 1144800 }, { "epoch": 1.0, "learning_rate": 3.125570391839949e-05, "loss": 3.9585, "step": 1144832 }, { "epoch": 1.0, "learning_rate": 3.124731797088897e-05, "loss": 3.9547, "step": 1145344 }, { "epoch": 1.0, "learning_rate": 3.123894840218218e-05, "loss": 3.9588, "step": 1145856 }, { "epoch": 1.0, "learning_rate": 3.123056245467166e-05, "loss": 3.968, "step": 1146368 }, { "epoch": 1.0, "learning_rate": 3.122217650716114e-05, "loss": 3.963, "step": 1146880 }, { "epoch": 1.0, "learning_rate": 3.121380693845436e-05, "loss": 3.9623, "step": 1147392 }, { "epoch": 1.0, "learning_rate": 3.120542099094384e-05, "loss": 3.9539, "step": 1147904 }, { "epoch": 1.0, "learning_rate": 3.119703504343332e-05, "loss": 3.9558, "step": 1148416 }, { "epoch": 1.0, "learning_rate": 3.11886490959228e-05, "loss": 3.9554, "step": 1148928 }, { "epoch": 1.0, "learning_rate": 3.118026314841228e-05, "loss": 3.9655, "step": 1149440 }, { "epoch": 1.0, "learning_rate": 3.117187720090176e-05, "loss": 3.9572, "step": 1149952 }, { "epoch": 1.0, "learning_rate": 3.116349125339123e-05, "loss": 3.9595, "step": 1150464 }, { "epoch": 1.0, "learning_rate": 3.1155121684684446e-05, "loss": 3.9679, "step": 1150976 }, { "epoch": 1.0, "learning_rate": 3.1146735737173926e-05, "loss": 3.9478, "step": 1151488 }, { "epoch": 1.0, "learning_rate": 3.11383497896634e-05, "loss": 3.9559, "step": 1152000 }, { "epoch": 1.0, "learning_rate": 3.112996384215288e-05, "loss": 3.9401, "step": 1152512 }, { "epoch": 1.0, "learning_rate": 3.112157789464236e-05, "loss": 3.9492, "step": 1153024 }, { "epoch": 1.0, "learning_rate": 3.111319194713184e-05, "loss": 3.9562, "step": 1153536 }, { "epoch": 1.0, "learning_rate": 3.1104805999621326e-05, "loss": 3.9483, "step": 1154048 }, { "epoch": 1.0, "learning_rate": 3.1096420052110806e-05, "loss": 3.9584, "step": 1154560 }, { "epoch": 1.0, "learning_rate": 3.1088050483404015e-05, "loss": 3.9736, "step": 1155072 }, { "epoch": 1.0, "learning_rate": 3.1079680914697224e-05, "loss": 3.9538, "step": 1155584 }, { "epoch": 1.0, "learning_rate": 3.1071294967186704e-05, "loss": 3.9608, "step": 1156096 }, { "epoch": 1.0, "learning_rate": 3.1062909019676184e-05, "loss": 3.9634, "step": 1156608 }, { "epoch": 1.0, "learning_rate": 3.1054523072165664e-05, "loss": 3.9537, "step": 1157120 }, { "epoch": 1.0, "learning_rate": 3.1046137124655144e-05, "loss": 3.9565, "step": 1157632 }, { "epoch": 1.0, "learning_rate": 3.103776755594835e-05, "loss": 3.9455, "step": 1158144 }, { "epoch": 1.0, "learning_rate": 3.102938160843783e-05, "loss": 3.9553, "step": 1158656 }, { "epoch": 1.0, "learning_rate": 3.102099566092731e-05, "loss": 3.9542, "step": 1159168 }, { "epoch": 1.0, "learning_rate": 3.101260971341679e-05, "loss": 3.9451, "step": 1159680 }, { "epoch": 1.01, "learning_rate": 3.100422376590627e-05, "loss": 3.956, "step": 1160192 }, { "epoch": 1.01, "learning_rate": 3.099583781839576e-05, "loss": 3.9482, "step": 1160704 }, { "epoch": 1.01, "learning_rate": 3.098745187088524e-05, "loss": 3.9625, "step": 1161216 }, { "epoch": 1.01, "learning_rate": 3.097908230217845e-05, "loss": 3.9631, "step": 1161728 }, { "epoch": 1.01, "learning_rate": 3.097069635466793e-05, "loss": 3.9467, "step": 1162240 }, { "epoch": 1.01, "learning_rate": 3.096232678596114e-05, "loss": 3.9537, "step": 1162752 }, { "epoch": 1.01, "learning_rate": 3.095394083845062e-05, "loss": 3.9707, "step": 1163264 }, { "epoch": 1.01, "learning_rate": 3.09455548909401e-05, "loss": 3.9455, "step": 1163776 }, { "epoch": 1.01, "learning_rate": 3.093718532223331e-05, "loss": 3.9534, "step": 1164288 }, { "epoch": 1.01, "learning_rate": 3.092879937472279e-05, "loss": 3.9542, "step": 1164800 }, { "epoch": 1.01, "learning_rate": 3.0920413427212267e-05, "loss": 3.9503, "step": 1165312 }, { "epoch": 1.01, "learning_rate": 3.0912027479701747e-05, "loss": 3.9511, "step": 1165824 }, { "epoch": 1.01, "learning_rate": 3.0903641532191227e-05, "loss": 3.967, "step": 1166336 }, { "epoch": 1.01, "learning_rate": 3.089525558468071e-05, "loss": 3.9605, "step": 1166848 }, { "epoch": 1.01, "learning_rate": 3.088686963717019e-05, "loss": 3.9553, "step": 1167360 }, { "epoch": 1.01, "learning_rate": 3.08785000684634e-05, "loss": 3.9592, "step": 1167872 }, { "epoch": 1.01, "learning_rate": 3.087011412095288e-05, "loss": 3.9485, "step": 1168384 }, { "epoch": 1.01, "learning_rate": 3.086172817344236e-05, "loss": 3.9624, "step": 1168896 }, { "epoch": 1.01, "learning_rate": 3.085334222593184e-05, "loss": 3.9324, "step": 1169408 }, { "epoch": 1.01, "learning_rate": 3.084495627842132e-05, "loss": 3.9562, "step": 1169920 }, { "epoch": 1.01, "learning_rate": 3.08365703309108e-05, "loss": 3.9602, "step": 1170432 }, { "epoch": 1.01, "learning_rate": 3.082818438340028e-05, "loss": 3.9612, "step": 1170944 }, { "epoch": 1.01, "learning_rate": 3.081979843588976e-05, "loss": 3.9532, "step": 1171456 }, { "epoch": 1.01, "learning_rate": 3.0811412488379235e-05, "loss": 3.9443, "step": 1171968 }, { "epoch": 1.01, "learning_rate": 3.0803026540868715e-05, "loss": 3.9535, "step": 1172480 }, { "epoch": 1.01, "learning_rate": 3.0794640593358195e-05, "loss": 3.942, "step": 1172992 }, { "epoch": 1.01, "learning_rate": 3.078625464584768e-05, "loss": 3.9695, "step": 1173504 }, { "epoch": 1.01, "learning_rate": 3.077788507714089e-05, "loss": 3.9486, "step": 1174016 }, { "epoch": 1.01, "learning_rate": 3.076949912963037e-05, "loss": 3.9699, "step": 1174528 }, { "epoch": 1.01, "learning_rate": 3.076112956092359e-05, "loss": 3.9529, "step": 1175040 }, { "epoch": 1.01, "learning_rate": 3.075274361341306e-05, "loss": 3.9437, "step": 1175552 }, { "epoch": 1.01, "learning_rate": 3.074435766590254e-05, "loss": 3.9621, "step": 1176064 }, { "epoch": 1.01, "learning_rate": 3.073597171839202e-05, "loss": 3.943, "step": 1176576 }, { "epoch": 1.01, "learning_rate": 3.0727602149685236e-05, "loss": 3.9483, "step": 1177088 }, { "epoch": 1.01, "learning_rate": 3.071921620217471e-05, "loss": 3.9484, "step": 1177600 }, { "epoch": 1.01, "learning_rate": 3.071083025466419e-05, "loss": 3.9621, "step": 1178112 }, { "epoch": 1.01, "learning_rate": 3.070244430715367e-05, "loss": 3.9426, "step": 1178624 }, { "epoch": 1.01, "learning_rate": 3.069405835964315e-05, "loss": 3.9465, "step": 1179136 }, { "epoch": 1.01, "learning_rate": 3.06857051697401e-05, "loss": 3.9418, "step": 1179648 }, { "epoch": 1.01, "learning_rate": 3.067731922222958e-05, "loss": 3.9407, "step": 1180160 }, { "epoch": 1.01, "learning_rate": 3.066893327471906e-05, "loss": 3.9646, "step": 1180672 }, { "epoch": 1.01, "learning_rate": 3.0660547327208534e-05, "loss": 3.9592, "step": 1181184 }, { "epoch": 1.01, "learning_rate": 3.0652161379698014e-05, "loss": 3.9495, "step": 1181696 }, { "epoch": 1.01, "learning_rate": 3.0643775432187494e-05, "loss": 3.9511, "step": 1182208 }, { "epoch": 1.01, "learning_rate": 3.0635389484676973e-05, "loss": 3.9586, "step": 1182720 }, { "epoch": 1.01, "learning_rate": 3.0627003537166453e-05, "loss": 3.9535, "step": 1183232 }, { "epoch": 1.01, "learning_rate": 3.0618617589655933e-05, "loss": 3.9535, "step": 1183744 }, { "epoch": 1.01, "learning_rate": 3.061024802094914e-05, "loss": 3.9522, "step": 1184256 }, { "epoch": 1.01, "learning_rate": 3.060186207343862e-05, "loss": 3.9557, "step": 1184768 }, { "epoch": 1.01, "learning_rate": 3.05934761259281e-05, "loss": 3.9566, "step": 1185280 }, { "epoch": 1.01, "learning_rate": 3.058509017841759e-05, "loss": 3.9502, "step": 1185792 }, { "epoch": 1.01, "learning_rate": 3.057670423090707e-05, "loss": 3.9514, "step": 1186304 }, { "epoch": 1.01, "learning_rate": 3.056831828339655e-05, "loss": 3.9621, "step": 1186816 }, { "epoch": 1.01, "learning_rate": 3.055993233588603e-05, "loss": 3.9541, "step": 1187328 }, { "epoch": 1.01, "learning_rate": 3.055156276717924e-05, "loss": 3.9374, "step": 1187840 }, { "epoch": 1.01, "learning_rate": 3.054317681966872e-05, "loss": 3.9532, "step": 1188352 }, { "epoch": 1.01, "learning_rate": 3.05347908721582e-05, "loss": 3.9547, "step": 1188864 }, { "epoch": 1.01, "learning_rate": 3.052642130345141e-05, "loss": 3.9506, "step": 1189376 }, { "epoch": 1.01, "learning_rate": 3.051803535594089e-05, "loss": 3.9509, "step": 1189888 }, { "epoch": 1.01, "learning_rate": 3.0509649408430367e-05, "loss": 3.9468, "step": 1190400 }, { "epoch": 1.02, "learning_rate": 3.050126346091985e-05, "loss": 3.9523, "step": 1190912 }, { "epoch": 1.02, "learning_rate": 3.049287751340933e-05, "loss": 3.9484, "step": 1191424 }, { "epoch": 1.02, "learning_rate": 3.048449156589881e-05, "loss": 3.9491, "step": 1191936 }, { "epoch": 1.02, "learning_rate": 3.047610561838829e-05, "loss": 3.9535, "step": 1192448 }, { "epoch": 1.02, "learning_rate": 3.046771967087777e-05, "loss": 3.9493, "step": 1192960 }, { "epoch": 1.02, "learning_rate": 3.045935010217098e-05, "loss": 3.9655, "step": 1193472 }, { "epoch": 1.02, "learning_rate": 3.045096415466046e-05, "loss": 3.9357, "step": 1193984 }, { "epoch": 1.02, "learning_rate": 3.0442578207149943e-05, "loss": 3.9431, "step": 1194496 }, { "epoch": 1.02, "learning_rate": 3.0434192259639423e-05, "loss": 3.9504, "step": 1195008 }, { "epoch": 1.02, "learning_rate": 3.042582269093263e-05, "loss": 3.9516, "step": 1195520 }, { "epoch": 1.02, "learning_rate": 3.041743674342211e-05, "loss": 3.9593, "step": 1196032 }, { "epoch": 1.02, "learning_rate": 3.040905079591159e-05, "loss": 3.9511, "step": 1196544 }, { "epoch": 1.02, "learning_rate": 3.040066484840107e-05, "loss": 3.9434, "step": 1197056 }, { "epoch": 1.02, "learning_rate": 3.0392278900890548e-05, "loss": 3.949, "step": 1197568 }, { "epoch": 1.02, "learning_rate": 3.0383909332183764e-05, "loss": 3.9484, "step": 1198080 }, { "epoch": 1.02, "learning_rate": 3.0375523384673244e-05, "loss": 3.9404, "step": 1198592 }, { "epoch": 1.02, "learning_rate": 3.0367153815966453e-05, "loss": 3.942, "step": 1199104 }, { "epoch": 1.02, "learning_rate": 3.0358767868455933e-05, "loss": 3.9514, "step": 1199616 }, { "epoch": 1.02, "learning_rate": 3.0350381920945413e-05, "loss": 3.953, "step": 1200128 }, { "epoch": 1.02, "learning_rate": 3.0341995973434896e-05, "loss": 3.9384, "step": 1200640 }, { "epoch": 1.02, "learning_rate": 3.033361002592437e-05, "loss": 3.9433, "step": 1201152 }, { "epoch": 1.02, "learning_rate": 3.032522407841385e-05, "loss": 3.9359, "step": 1201664 }, { "epoch": 1.02, "learning_rate": 3.031683813090333e-05, "loss": 3.9538, "step": 1202176 }, { "epoch": 1.02, "learning_rate": 3.030845218339281e-05, "loss": 3.9447, "step": 1202688 }, { "epoch": 1.02, "learning_rate": 3.030006623588229e-05, "loss": 3.9455, "step": 1203200 }, { "epoch": 1.02, "learning_rate": 3.0291680288371773e-05, "loss": 3.9489, "step": 1203712 }, { "epoch": 1.02, "learning_rate": 3.0283294340861253e-05, "loss": 3.9509, "step": 1204224 }, { "epoch": 1.02, "learning_rate": 3.0274908393350732e-05, "loss": 3.9485, "step": 1204736 }, { "epoch": 1.02, "learning_rate": 3.0266522445840212e-05, "loss": 3.9467, "step": 1205248 }, { "epoch": 1.02, "learning_rate": 3.025815287713342e-05, "loss": 3.9517, "step": 1205760 }, { "epoch": 1.02, "learning_rate": 3.02497669296229e-05, "loss": 3.9464, "step": 1206272 }, { "epoch": 1.02, "learning_rate": 3.024138098211238e-05, "loss": 3.94, "step": 1206784 }, { "epoch": 1.02, "learning_rate": 3.023299503460186e-05, "loss": 3.9506, "step": 1207296 }, { "epoch": 1.02, "learning_rate": 3.0224625465895074e-05, "loss": 3.9466, "step": 1207808 }, { "epoch": 1.02, "learning_rate": 3.0216239518384554e-05, "loss": 3.9552, "step": 1208320 }, { "epoch": 1.02, "learning_rate": 3.0207853570874034e-05, "loss": 3.9398, "step": 1208832 }, { "epoch": 1.02, "learning_rate": 3.0199467623363514e-05, "loss": 3.9473, "step": 1209344 }, { "epoch": 1.02, "learning_rate": 3.0191081675852994e-05, "loss": 3.9417, "step": 1209856 }, { "epoch": 1.02, "learning_rate": 3.0182728485949935e-05, "loss": 3.9459, "step": 1210368 }, { "epoch": 1.02, "learning_rate": 3.0174342538439415e-05, "loss": 3.9343, "step": 1210880 }, { "epoch": 1.02, "learning_rate": 3.0165972969732624e-05, "loss": 3.9554, "step": 1211392 }, { "epoch": 1.02, "learning_rate": 3.0157587022222104e-05, "loss": 3.9603, "step": 1211904 }, { "epoch": 1.02, "learning_rate": 3.0149201074711588e-05, "loss": 3.9447, "step": 1212416 }, { "epoch": 1.02, "learning_rate": 3.0140815127201068e-05, "loss": 3.9407, "step": 1212928 }, { "epoch": 1.02, "learning_rate": 3.0132429179690548e-05, "loss": 3.9532, "step": 1213440 }, { "epoch": 1.02, "learning_rate": 3.0124059610983757e-05, "loss": 3.9515, "step": 1213952 }, { "epoch": 1.02, "learning_rate": 3.0115673663473237e-05, "loss": 3.9443, "step": 1214464 }, { "epoch": 1.02, "learning_rate": 3.0107287715962717e-05, "loss": 3.9482, "step": 1214976 }, { "epoch": 1.02, "learning_rate": 3.0098901768452197e-05, "loss": 3.9587, "step": 1215488 }, { "epoch": 1.02, "learning_rate": 3.0090515820941677e-05, "loss": 3.9522, "step": 1216000 }, { "epoch": 1.02, "learning_rate": 3.008212987343116e-05, "loss": 3.9477, "step": 1216512 }, { "epoch": 1.02, "learning_rate": 3.007374392592064e-05, "loss": 3.941, "step": 1217024 }, { "epoch": 1.02, "learning_rate": 3.006535797841012e-05, "loss": 3.9529, "step": 1217536 }, { "epoch": 1.02, "learning_rate": 3.00569720308996e-05, "loss": 3.9513, "step": 1218048 }, { "epoch": 1.02, "learning_rate": 3.004858608338908e-05, "loss": 3.9387, "step": 1218560 }, { "epoch": 1.02, "learning_rate": 3.0040200135878553e-05, "loss": 3.9638, "step": 1219072 }, { "epoch": 1.02, "learning_rate": 3.0031814188368036e-05, "loss": 3.944, "step": 1219584 }, { "epoch": 1.02, "learning_rate": 3.0023444619661252e-05, "loss": 3.9513, "step": 1220096 }, { "epoch": 1.02, "learning_rate": 3.001507505095446e-05, "loss": 3.952, "step": 1220608 }, { "epoch": 1.03, "learning_rate": 3.000668910344394e-05, "loss": 3.9422, "step": 1221120 }, { "epoch": 1.03, "eval_loss": 4.067412853240967, "eval_runtime": 293.0255, "eval_samples_per_second": 1302.245, "eval_steps_per_second": 40.696, "step": 1221120 }, { "epoch": 2.0, "learning_rate": 2.999830315593342e-05, "loss": 3.9455, "step": 1221632 }, { "epoch": 2.0, "learning_rate": 2.99899172084229e-05, "loss": 3.9451, "step": 1222144 }, { "epoch": 2.0, "learning_rate": 2.998153126091238e-05, "loss": 3.9599, "step": 1222656 }, { "epoch": 2.0, "learning_rate": 2.9973145313401858e-05, "loss": 3.9493, "step": 1223168 }, { "epoch": 2.0, "learning_rate": 2.9964759365891338e-05, "loss": 3.9513, "step": 1223680 }, { "epoch": 2.0, "learning_rate": 2.9956373418380817e-05, "loss": 3.9424, "step": 1224192 }, { "epoch": 2.0, "learning_rate": 2.9948003849674027e-05, "loss": 3.9449, "step": 1224704 }, { "epoch": 2.0, "learning_rate": 2.9939617902163507e-05, "loss": 3.9436, "step": 1225216 }, { "epoch": 2.0, "learning_rate": 2.993123195465299e-05, "loss": 3.9544, "step": 1225728 }, { "epoch": 2.0, "learning_rate": 2.9922862385946206e-05, "loss": 3.942, "step": 1226240 }, { "epoch": 2.0, "learning_rate": 2.9914492817239415e-05, "loss": 3.9543, "step": 1226752 }, { "epoch": 2.0, "learning_rate": 2.9906123248532624e-05, "loss": 3.9576, "step": 1227264 }, { "epoch": 2.0, "learning_rate": 2.9897737301022104e-05, "loss": 3.938, "step": 1227776 }, { "epoch": 2.0, "learning_rate": 2.9889351353511584e-05, "loss": 3.9436, "step": 1228288 }, { "epoch": 2.0, "learning_rate": 2.9880965406001067e-05, "loss": 3.9332, "step": 1228800 }, { "epoch": 2.0, "learning_rate": 2.9872579458490547e-05, "loss": 3.9374, "step": 1229312 }, { "epoch": 2.0, "learning_rate": 2.9864193510980027e-05, "loss": 3.946, "step": 1229824 }, { "epoch": 2.0, "learning_rate": 2.98558075634695e-05, "loss": 3.9381, "step": 1230336 }, { "epoch": 2.0, "learning_rate": 2.984742161595898e-05, "loss": 3.9439, "step": 1230848 }, { "epoch": 2.0, "learning_rate": 2.983903566844846e-05, "loss": 3.9661, "step": 1231360 }, { "epoch": 2.0, "learning_rate": 2.9830649720937944e-05, "loss": 3.9424, "step": 1231872 }, { "epoch": 2.0, "learning_rate": 2.9822263773427424e-05, "loss": 3.9504, "step": 1232384 }, { "epoch": 2.0, "learning_rate": 2.9813894204720633e-05, "loss": 3.9482, "step": 1232896 }, { "epoch": 2.0, "learning_rate": 2.9805508257210113e-05, "loss": 3.9438, "step": 1233408 }, { "epoch": 2.0, "learning_rate": 2.9797122309699593e-05, "loss": 3.9457, "step": 1233920 }, { "epoch": 2.0, "learning_rate": 2.9788736362189072e-05, "loss": 3.9353, "step": 1234432 }, { "epoch": 2.0, "learning_rate": 2.9780350414678552e-05, "loss": 3.9427, "step": 1234944 }, { "epoch": 2.0, "learning_rate": 2.9771964467168036e-05, "loss": 3.9464, "step": 1235456 }, { "epoch": 2.0, "learning_rate": 2.9763578519657516e-05, "loss": 3.9306, "step": 1235968 }, { "epoch": 2.01, "learning_rate": 2.9755192572146996e-05, "loss": 3.9434, "step": 1236480 }, { "epoch": 2.01, "learning_rate": 2.9746839382243934e-05, "loss": 3.9407, "step": 1236992 }, { "epoch": 2.01, "learning_rate": 2.9738453434733414e-05, "loss": 3.9509, "step": 1237504 }, { "epoch": 2.01, "learning_rate": 2.9730067487222897e-05, "loss": 3.9477, "step": 1238016 }, { "epoch": 2.01, "learning_rate": 2.9721681539712377e-05, "loss": 3.9374, "step": 1238528 }, { "epoch": 2.01, "learning_rate": 2.9713311971005586e-05, "loss": 3.9452, "step": 1239040 }, { "epoch": 2.01, "learning_rate": 2.9704942402298795e-05, "loss": 3.9604, "step": 1239552 }, { "epoch": 2.01, "learning_rate": 2.9696556454788275e-05, "loss": 3.9348, "step": 1240064 }, { "epoch": 2.01, "learning_rate": 2.968817050727776e-05, "loss": 3.9425, "step": 1240576 }, { "epoch": 2.01, "learning_rate": 2.967978455976724e-05, "loss": 3.9433, "step": 1241088 }, { "epoch": 2.01, "learning_rate": 2.967139861225672e-05, "loss": 3.935, "step": 1241600 }, { "epoch": 2.01, "learning_rate": 2.96630126647462e-05, "loss": 3.943, "step": 1242112 }, { "epoch": 2.01, "learning_rate": 2.965462671723568e-05, "loss": 3.9542, "step": 1242624 }, { "epoch": 2.01, "learning_rate": 2.964624076972516e-05, "loss": 3.952, "step": 1243136 }, { "epoch": 2.01, "learning_rate": 2.963785482221464e-05, "loss": 3.9389, "step": 1243648 }, { "epoch": 2.01, "learning_rate": 2.962946887470412e-05, "loss": 3.9491, "step": 1244160 }, { "epoch": 2.01, "learning_rate": 2.962109930599733e-05, "loss": 3.9405, "step": 1244672 }, { "epoch": 2.01, "learning_rate": 2.961271335848681e-05, "loss": 3.9506, "step": 1245184 }, { "epoch": 2.01, "learning_rate": 2.960432741097629e-05, "loss": 3.9243, "step": 1245696 }, { "epoch": 2.01, "learning_rate": 2.959594146346577e-05, "loss": 3.9432, "step": 1246208 }, { "epoch": 2.01, "learning_rate": 2.958755551595525e-05, "loss": 3.9518, "step": 1246720 }, { "epoch": 2.01, "learning_rate": 2.957918594724846e-05, "loss": 3.9473, "step": 1247232 }, { "epoch": 2.01, "learning_rate": 2.9570799999737943e-05, "loss": 3.9446, "step": 1247744 }, { "epoch": 2.01, "learning_rate": 2.9562414052227423e-05, "loss": 3.9349, "step": 1248256 }, { "epoch": 2.01, "learning_rate": 2.9554028104716903e-05, "loss": 3.9446, "step": 1248768 }, { "epoch": 2.01, "learning_rate": 2.9545642157206383e-05, "loss": 3.9314, "step": 1249280 }, { "epoch": 2.01, "learning_rate": 2.9537272588499592e-05, "loss": 3.957, "step": 1249792 }, { "epoch": 2.01, "learning_rate": 2.9528886640989072e-05, "loss": 3.9379, "step": 1250304 }, { "epoch": 2.01, "learning_rate": 2.9520500693478552e-05, "loss": 3.9555, "step": 1250816 }, { "epoch": 2.01, "learning_rate": 2.9512114745968032e-05, "loss": 3.9422, "step": 1251328 }, { "epoch": 2.01, "learning_rate": 2.9503728798457515e-05, "loss": 3.9365, "step": 1251840 }, { "epoch": 2.01, "learning_rate": 2.949534285094699e-05, "loss": 3.9449, "step": 1252352 }, { "epoch": 2.01, "learning_rate": 2.9486973282240204e-05, "loss": 3.9368, "step": 1252864 }, { "epoch": 2.01, "learning_rate": 2.9478587334729684e-05, "loss": 3.9395, "step": 1253376 }, { "epoch": 2.01, "learning_rate": 2.9470217766022897e-05, "loss": 3.9377, "step": 1253888 }, { "epoch": 2.01, "learning_rate": 2.9461831818512377e-05, "loss": 3.9508, "step": 1254400 }, { "epoch": 2.01, "learning_rate": 2.9453445871001857e-05, "loss": 3.9357, "step": 1254912 }, { "epoch": 2.01, "learning_rate": 2.9445059923491337e-05, "loss": 3.9344, "step": 1255424 }, { "epoch": 2.01, "learning_rate": 2.943667397598081e-05, "loss": 3.93, "step": 1255936 }, { "epoch": 2.01, "learning_rate": 2.942828802847029e-05, "loss": 3.9315, "step": 1256448 }, { "epoch": 2.01, "learning_rate": 2.941990208095977e-05, "loss": 3.9538, "step": 1256960 }, { "epoch": 2.01, "learning_rate": 2.9411516133449253e-05, "loss": 3.9488, "step": 1257472 }, { "epoch": 2.01, "learning_rate": 2.9403130185938733e-05, "loss": 3.9394, "step": 1257984 }, { "epoch": 2.01, "learning_rate": 2.9394744238428213e-05, "loss": 3.9416, "step": 1258496 }, { "epoch": 2.01, "learning_rate": 2.9386358290917693e-05, "loss": 3.9458, "step": 1259008 }, { "epoch": 2.01, "learning_rate": 2.9377988722210902e-05, "loss": 3.9474, "step": 1259520 }, { "epoch": 2.01, "learning_rate": 2.9369619153504115e-05, "loss": 3.9412, "step": 1260032 }, { "epoch": 2.01, "learning_rate": 2.9361233205993594e-05, "loss": 3.9451, "step": 1260544 }, { "epoch": 2.01, "learning_rate": 2.9352847258483074e-05, "loss": 3.9423, "step": 1261056 }, { "epoch": 2.01, "learning_rate": 2.9344461310972554e-05, "loss": 3.9484, "step": 1261568 }, { "epoch": 2.01, "learning_rate": 2.9336075363462034e-05, "loss": 3.9396, "step": 1262080 }, { "epoch": 2.01, "learning_rate": 2.9327689415951514e-05, "loss": 3.9443, "step": 1262592 }, { "epoch": 2.01, "learning_rate": 2.9319303468440994e-05, "loss": 3.9526, "step": 1263104 }, { "epoch": 2.01, "learning_rate": 2.9310917520930474e-05, "loss": 3.9454, "step": 1263616 }, { "epoch": 2.01, "learning_rate": 2.9302531573419954e-05, "loss": 3.9265, "step": 1264128 }, { "epoch": 2.01, "learning_rate": 2.9294162004713167e-05, "loss": 3.9409, "step": 1264640 }, { "epoch": 2.01, "learning_rate": 2.9285792436006376e-05, "loss": 3.9442, "step": 1265152 }, { "epoch": 2.01, "learning_rate": 2.9277406488495856e-05, "loss": 3.945, "step": 1265664 }, { "epoch": 2.01, "learning_rate": 2.9269020540985336e-05, "loss": 3.9402, "step": 1266176 }, { "epoch": 2.01, "learning_rate": 2.9260634593474816e-05, "loss": 3.935, "step": 1266688 }, { "epoch": 2.02, "learning_rate": 2.92522486459643e-05, "loss": 3.9448, "step": 1267200 }, { "epoch": 2.02, "learning_rate": 2.924386269845378e-05, "loss": 3.9335, "step": 1267712 }, { "epoch": 2.02, "learning_rate": 2.923547675094326e-05, "loss": 3.9424, "step": 1268224 }, { "epoch": 2.02, "learning_rate": 2.922709080343274e-05, "loss": 3.9409, "step": 1268736 }, { "epoch": 2.02, "learning_rate": 2.9218721234725948e-05, "loss": 3.9368, "step": 1269248 }, { "epoch": 2.02, "learning_rate": 2.9210335287215428e-05, "loss": 3.9587, "step": 1269760 }, { "epoch": 2.02, "learning_rate": 2.9201949339704908e-05, "loss": 3.9293, "step": 1270272 }, { "epoch": 2.02, "learning_rate": 2.919356339219439e-05, "loss": 3.9274, "step": 1270784 }, { "epoch": 2.02, "learning_rate": 2.918517744468387e-05, "loss": 3.9417, "step": 1271296 }, { "epoch": 2.02, "learning_rate": 2.9176791497173344e-05, "loss": 3.9437, "step": 1271808 }, { "epoch": 2.02, "learning_rate": 2.9168405549662824e-05, "loss": 3.9483, "step": 1272320 }, { "epoch": 2.02, "learning_rate": 2.9160019602152304e-05, "loss": 3.9391, "step": 1272832 }, { "epoch": 2.02, "learning_rate": 2.9151633654641784e-05, "loss": 3.9335, "step": 1273344 }, { "epoch": 2.02, "learning_rate": 2.9143247707131268e-05, "loss": 3.9355, "step": 1273856 }, { "epoch": 2.02, "learning_rate": 2.9134861759620747e-05, "loss": 3.9456, "step": 1274368 }, { "epoch": 2.02, "learning_rate": 2.9126508569717692e-05, "loss": 3.9297, "step": 1274880 }, { "epoch": 2.02, "learning_rate": 2.9118122622207172e-05, "loss": 3.933, "step": 1275392 }, { "epoch": 2.02, "learning_rate": 2.9109736674696646e-05, "loss": 3.9445, "step": 1275904 }, { "epoch": 2.02, "learning_rate": 2.910135072718613e-05, "loss": 3.9394, "step": 1276416 }, { "epoch": 2.02, "learning_rate": 2.909296477967561e-05, "loss": 3.9303, "step": 1276928 }, { "epoch": 2.02, "learning_rate": 2.908457883216509e-05, "loss": 3.9309, "step": 1277440 }, { "epoch": 2.02, "learning_rate": 2.907619288465457e-05, "loss": 3.9296, "step": 1277952 }, { "epoch": 2.02, "learning_rate": 2.906780693714405e-05, "loss": 3.9458, "step": 1278464 }, { "epoch": 2.02, "learning_rate": 2.9059437368437258e-05, "loss": 3.9323, "step": 1278976 }, { "epoch": 2.02, "learning_rate": 2.9051051420926738e-05, "loss": 3.9384, "step": 1279488 }, { "epoch": 2.02, "learning_rate": 2.904268185221995e-05, "loss": 3.939, "step": 1280000 }, { "epoch": 2.02, "learning_rate": 2.903429590470943e-05, "loss": 3.9429, "step": 1280512 }, { "epoch": 2.02, "learning_rate": 2.9025926336002646e-05, "loss": 3.9345, "step": 1281024 }, { "epoch": 2.02, "learning_rate": 2.901754038849212e-05, "loss": 3.9387, "step": 1281536 }, { "epoch": 2.02, "learning_rate": 2.90091544409816e-05, "loss": 3.9405, "step": 1282048 }, { "epoch": 2.02, "learning_rate": 2.9000768493471083e-05, "loss": 3.94, "step": 1282560 }, { "epoch": 2.02, "learning_rate": 2.8992382545960563e-05, "loss": 3.9257, "step": 1283072 }, { "epoch": 2.02, "learning_rate": 2.8983996598450043e-05, "loss": 3.9419, "step": 1283584 }, { "epoch": 2.02, "learning_rate": 2.8975610650939523e-05, "loss": 3.939, "step": 1284096 }, { "epoch": 2.02, "learning_rate": 2.8967224703429002e-05, "loss": 3.9438, "step": 1284608 }, { "epoch": 2.02, "learning_rate": 2.895885513472221e-05, "loss": 3.9289, "step": 1285120 }, { "epoch": 2.02, "learning_rate": 2.895046918721169e-05, "loss": 3.9426, "step": 1285632 }, { "epoch": 2.02, "learning_rate": 2.8942083239701175e-05, "loss": 3.9329, "step": 1286144 }, { "epoch": 2.02, "learning_rate": 2.8933697292190655e-05, "loss": 3.937, "step": 1286656 }, { "epoch": 2.02, "learning_rate": 2.8925311344680135e-05, "loss": 3.9201, "step": 1287168 }, { "epoch": 2.02, "learning_rate": 2.8916925397169615e-05, "loss": 3.9497, "step": 1287680 }, { "epoch": 2.02, "learning_rate": 2.8908555828462824e-05, "loss": 3.9507, "step": 1288192 }, { "epoch": 2.02, "learning_rate": 2.8900169880952304e-05, "loss": 3.9356, "step": 1288704 }, { "epoch": 2.02, "learning_rate": 2.8891783933441784e-05, "loss": 3.9273, "step": 1289216 }, { "epoch": 2.02, "learning_rate": 2.8883397985931264e-05, "loss": 3.9507, "step": 1289728 }, { "epoch": 2.02, "learning_rate": 2.8875028417224476e-05, "loss": 3.9389, "step": 1290240 }, { "epoch": 2.02, "learning_rate": 2.8866642469713956e-05, "loss": 3.9388, "step": 1290752 }, { "epoch": 2.02, "learning_rate": 2.8858256522203436e-05, "loss": 3.9374, "step": 1291264 }, { "epoch": 2.02, "learning_rate": 2.8849870574692916e-05, "loss": 3.9481, "step": 1291776 }, { "epoch": 2.02, "learning_rate": 2.8841484627182396e-05, "loss": 3.9387, "step": 1292288 }, { "epoch": 2.02, "learning_rate": 2.883311505847561e-05, "loss": 3.94, "step": 1292800 }, { "epoch": 2.02, "learning_rate": 2.882472911096509e-05, "loss": 3.9285, "step": 1293312 }, { "epoch": 2.02, "learning_rate": 2.881634316345457e-05, "loss": 3.9434, "step": 1293824 }, { "epoch": 2.02, "learning_rate": 2.880795721594405e-05, "loss": 3.9404, "step": 1294336 }, { "epoch": 2.02, "learning_rate": 2.8799571268433528e-05, "loss": 3.9311, "step": 1294848 }, { "epoch": 2.02, "learning_rate": 2.8791185320923008e-05, "loss": 3.9536, "step": 1295360 }, { "epoch": 2.02, "learning_rate": 2.8782799373412485e-05, "loss": 3.9351, "step": 1295872 }, { "epoch": 2.02, "learning_rate": 2.8774413425901965e-05, "loss": 3.9433, "step": 1296384 }, { "epoch": 2.02, "learning_rate": 2.876606023599891e-05, "loss": 3.9421, "step": 1296896 }, { "epoch": 2.02, "learning_rate": 2.875769066729212e-05, "loss": 3.9348, "step": 1297408 }, { "epoch": 2.03, "eval_loss": 4.062602519989014, "eval_runtime": 306.3018, "eval_samples_per_second": 1245.801, "eval_steps_per_second": 38.932, "step": 1297440 }, { "epoch": 0.0, "learning_rate": 2.87493047197816e-05, "loss": 3.9316, "step": 1297920 }, { "epoch": 0.0, "learning_rate": 2.874091877227108e-05, "loss": 3.9384, "step": 1298432 }, { "epoch": 0.0, "learning_rate": 2.8732532824760562e-05, "loss": 3.9486, "step": 1298944 }, { "epoch": 0.0, "learning_rate": 2.8724146877250042e-05, "loss": 3.9415, "step": 1299456 }, { "epoch": 0.0, "learning_rate": 2.8715760929739522e-05, "loss": 3.9468, "step": 1299968 }, { "epoch": 0.0, "learning_rate": 2.8707374982229002e-05, "loss": 3.9311, "step": 1300480 }, { "epoch": 0.0, "learning_rate": 2.8698989034718482e-05, "loss": 3.9328, "step": 1300992 }, { "epoch": 0.0, "learning_rate": 2.8690603087207955e-05, "loss": 3.9338, "step": 1301504 }, { "epoch": 0.0, "learning_rate": 2.868221713969744e-05, "loss": 3.9485, "step": 1302016 }, { "epoch": 0.0, "learning_rate": 2.867383119218692e-05, "loss": 3.933, "step": 1302528 }, { "epoch": 0.0, "learning_rate": 2.86654452446764e-05, "loss": 3.9429, "step": 1303040 }, { "epoch": 0.0, "learning_rate": 2.865705929716588e-05, "loss": 3.9461, "step": 1303552 }, { "epoch": 0.0, "learning_rate": 2.8648689728459087e-05, "loss": 3.9293, "step": 1304064 }, { "epoch": 0.0, "learning_rate": 2.8640303780948567e-05, "loss": 3.9324, "step": 1304576 }, { "epoch": 0.0, "learning_rate": 2.8631917833438047e-05, "loss": 3.9231, "step": 1305088 }, { "epoch": 0.0, "learning_rate": 2.862353188592753e-05, "loss": 3.9311, "step": 1305600 }, { "epoch": 0.0, "learning_rate": 2.861514593841701e-05, "loss": 3.9313, "step": 1306112 }, { "epoch": 0.0, "learning_rate": 2.860675999090649e-05, "loss": 3.9317, "step": 1306624 }, { "epoch": 0.0, "learning_rate": 2.859837404339597e-05, "loss": 3.9323, "step": 1307136 }, { "epoch": 0.0, "learning_rate": 2.858998809588545e-05, "loss": 3.9583, "step": 1307648 }, { "epoch": 0.0, "learning_rate": 2.858160214837493e-05, "loss": 3.9319, "step": 1308160 }, { "epoch": 0.0, "learning_rate": 2.857321620086441e-05, "loss": 3.9374, "step": 1308672 }, { "epoch": 0.0, "learning_rate": 2.856483025335389e-05, "loss": 3.9448, "step": 1309184 }, { "epoch": 0.0, "learning_rate": 2.8556444305843367e-05, "loss": 3.9375, "step": 1309696 }, { "epoch": 0.0, "learning_rate": 2.8548074737136583e-05, "loss": 3.9314, "step": 1310208 }, { "epoch": 0.0, "learning_rate": 2.8539705168429792e-05, "loss": 3.9258, "step": 1310720 }, { "epoch": 0.0, "learning_rate": 2.8531319220919272e-05, "loss": 3.9336, "step": 1311232 }, { "epoch": 0.0, "learning_rate": 2.8522933273408752e-05, "loss": 3.9337, "step": 1311744 }, { "epoch": 0.0, "learning_rate": 2.8514563704701964e-05, "loss": 3.9207, "step": 1312256 }, { "epoch": 0.01, "learning_rate": 2.8506177757191444e-05, "loss": 3.9379, "step": 1312768 }, { "epoch": 0.01, "learning_rate": 2.8497791809680924e-05, "loss": 3.9287, "step": 1313280 }, { "epoch": 0.01, "learning_rate": 2.8489405862170404e-05, "loss": 3.9417, "step": 1313792 }, { "epoch": 0.01, "learning_rate": 2.8481019914659884e-05, "loss": 3.9407, "step": 1314304 }, { "epoch": 0.01, "learning_rate": 2.8472633967149364e-05, "loss": 3.9248, "step": 1314816 }, { "epoch": 0.01, "learning_rate": 2.8464264398442577e-05, "loss": 3.94, "step": 1315328 }, { "epoch": 0.01, "learning_rate": 2.8455878450932057e-05, "loss": 3.9487, "step": 1315840 }, { "epoch": 0.01, "learning_rate": 2.8447492503421537e-05, "loss": 3.9222, "step": 1316352 }, { "epoch": 0.01, "learning_rate": 2.8439106555911016e-05, "loss": 3.9374, "step": 1316864 }, { "epoch": 0.01, "learning_rate": 2.843072060840049e-05, "loss": 3.9319, "step": 1317376 }, { "epoch": 0.01, "learning_rate": 2.842233466088997e-05, "loss": 3.9264, "step": 1317888 }, { "epoch": 0.01, "learning_rate": 2.8413948713379453e-05, "loss": 3.9347, "step": 1318400 }, { "epoch": 0.01, "learning_rate": 2.8405562765868933e-05, "loss": 3.9459, "step": 1318912 }, { "epoch": 0.01, "learning_rate": 2.8397176818358413e-05, "loss": 3.9416, "step": 1319424 }, { "epoch": 0.01, "learning_rate": 2.8388790870847893e-05, "loss": 3.9326, "step": 1319936 }, { "epoch": 0.01, "learning_rate": 2.8380404923337373e-05, "loss": 3.9444, "step": 1320448 }, { "epoch": 0.01, "learning_rate": 2.8372018975826853e-05, "loss": 3.9289, "step": 1320960 }, { "epoch": 0.01, "learning_rate": 2.8363649407120062e-05, "loss": 3.9383, "step": 1321472 }, { "epoch": 0.01, "learning_rate": 2.8355263459609542e-05, "loss": 3.9172, "step": 1321984 }, { "epoch": 0.01, "learning_rate": 2.8346877512099025e-05, "loss": 3.9285, "step": 1322496 }, { "epoch": 0.01, "learning_rate": 2.8338491564588505e-05, "loss": 3.9444, "step": 1323008 }, { "epoch": 0.01, "learning_rate": 2.8330121995881714e-05, "loss": 3.9408, "step": 1323520 }, { "epoch": 0.01, "learning_rate": 2.8321736048371194e-05, "loss": 3.9309, "step": 1324032 }, { "epoch": 0.01, "learning_rate": 2.8313350100860674e-05, "loss": 3.9254, "step": 1324544 }, { "epoch": 0.01, "learning_rate": 2.8304964153350154e-05, "loss": 3.9382, "step": 1325056 }, { "epoch": 0.01, "learning_rate": 2.8296578205839634e-05, "loss": 3.9198, "step": 1325568 }, { "epoch": 0.01, "learning_rate": 2.8288208637132846e-05, "loss": 3.9466, "step": 1326080 }, { "epoch": 0.01, "learning_rate": 2.8279822689622326e-05, "loss": 3.9302, "step": 1326592 }, { "epoch": 0.01, "learning_rate": 2.8271436742111806e-05, "loss": 3.9471, "step": 1327104 }, { "epoch": 0.01, "learning_rate": 2.8263050794601286e-05, "loss": 3.935, "step": 1327616 }, { "epoch": 0.01, "learning_rate": 2.8254664847090766e-05, "loss": 3.9286, "step": 1328128 }, { "epoch": 0.01, "learning_rate": 2.8246311657187708e-05, "loss": 3.9317, "step": 1328640 }, { "epoch": 0.01, "learning_rate": 2.8237925709677188e-05, "loss": 3.9349, "step": 1329152 }, { "epoch": 0.01, "learning_rate": 2.8229539762166668e-05, "loss": 3.9251, "step": 1329664 }, { "epoch": 0.01, "learning_rate": 2.8221153814656148e-05, "loss": 3.9259, "step": 1330176 }, { "epoch": 0.01, "learning_rate": 2.8212767867145628e-05, "loss": 3.9424, "step": 1330688 }, { "epoch": 0.01, "learning_rate": 2.8204381919635108e-05, "loss": 3.9289, "step": 1331200 }, { "epoch": 0.01, "learning_rate": 2.8195995972124588e-05, "loss": 3.9208, "step": 1331712 }, { "epoch": 0.01, "learning_rate": 2.818761002461407e-05, "loss": 3.9214, "step": 1332224 }, { "epoch": 0.01, "learning_rate": 2.817924045590728e-05, "loss": 3.9222, "step": 1332736 }, { "epoch": 0.01, "learning_rate": 2.817085450839676e-05, "loss": 3.9432, "step": 1333248 }, { "epoch": 0.01, "learning_rate": 2.816246856088624e-05, "loss": 3.9412, "step": 1333760 }, { "epoch": 0.01, "learning_rate": 2.815408261337572e-05, "loss": 3.9302, "step": 1334272 }, { "epoch": 0.01, "learning_rate": 2.81456966658652e-05, "loss": 3.9332, "step": 1334784 }, { "epoch": 0.01, "learning_rate": 2.8137310718354676e-05, "loss": 3.9361, "step": 1335296 }, { "epoch": 0.01, "learning_rate": 2.812895752845162e-05, "loss": 3.9363, "step": 1335808 }, { "epoch": 0.01, "learning_rate": 2.812058795974483e-05, "loss": 3.9304, "step": 1336320 }, { "epoch": 0.01, "learning_rate": 2.811220201223431e-05, "loss": 3.939, "step": 1336832 }, { "epoch": 0.01, "learning_rate": 2.8103816064723794e-05, "loss": 3.934, "step": 1337344 }, { "epoch": 0.01, "learning_rate": 2.8095430117213274e-05, "loss": 3.942, "step": 1337856 }, { "epoch": 0.01, "learning_rate": 2.8087044169702754e-05, "loss": 3.9312, "step": 1338368 }, { "epoch": 0.01, "learning_rate": 2.8078658222192234e-05, "loss": 3.9325, "step": 1338880 }, { "epoch": 0.01, "learning_rate": 2.8070272274681714e-05, "loss": 3.9393, "step": 1339392 }, { "epoch": 0.01, "learning_rate": 2.8061886327171194e-05, "loss": 3.9375, "step": 1339904 }, { "epoch": 0.01, "learning_rate": 2.8053500379660674e-05, "loss": 3.9218, "step": 1340416 }, { "epoch": 0.01, "learning_rate": 2.804511443215015e-05, "loss": 3.933, "step": 1340928 }, { "epoch": 0.01, "learning_rate": 2.803672848463963e-05, "loss": 3.9315, "step": 1341440 }, { "epoch": 0.01, "learning_rate": 2.802834253712911e-05, "loss": 3.9383, "step": 1341952 }, { "epoch": 0.01, "learning_rate": 2.801995658961859e-05, "loss": 3.9319, "step": 1342464 }, { "epoch": 0.01, "learning_rate": 2.801157064210807e-05, "loss": 3.9239, "step": 1342976 }, { "epoch": 0.02, "learning_rate": 2.800320107340128e-05, "loss": 3.9328, "step": 1343488 }, { "epoch": 0.02, "learning_rate": 2.7994815125890762e-05, "loss": 3.9252, "step": 1344000 }, { "epoch": 0.02, "learning_rate": 2.7986429178380242e-05, "loss": 3.937, "step": 1344512 }, { "epoch": 0.02, "learning_rate": 2.7978043230869722e-05, "loss": 3.9251, "step": 1345024 }, { "epoch": 0.02, "learning_rate": 2.7969657283359202e-05, "loss": 3.9311, "step": 1345536 }, { "epoch": 0.02, "learning_rate": 2.7961271335848682e-05, "loss": 3.9429, "step": 1346048 }, { "epoch": 0.02, "learning_rate": 2.7952885388338162e-05, "loss": 3.9305, "step": 1346560 }, { "epoch": 0.02, "learning_rate": 2.7944499440827642e-05, "loss": 3.9138, "step": 1347072 }, { "epoch": 0.02, "learning_rate": 2.7936113493317122e-05, "loss": 3.9313, "step": 1347584 }, { "epoch": 0.02, "learning_rate": 2.7927743924610335e-05, "loss": 3.9353, "step": 1348096 }, { "epoch": 0.02, "learning_rate": 2.7919357977099815e-05, "loss": 3.9389, "step": 1348608 }, { "epoch": 0.02, "learning_rate": 2.7910972029589295e-05, "loss": 3.9293, "step": 1349120 }, { "epoch": 0.02, "learning_rate": 2.7902586082078774e-05, "loss": 3.9263, "step": 1349632 }, { "epoch": 0.02, "learning_rate": 2.7894232892175716e-05, "loss": 3.9232, "step": 1350144 }, { "epoch": 0.02, "learning_rate": 2.7885846944665196e-05, "loss": 3.9373, "step": 1350656 }, { "epoch": 0.02, "learning_rate": 2.7877460997154676e-05, "loss": 3.9167, "step": 1351168 }, { "epoch": 0.02, "learning_rate": 2.7869075049644156e-05, "loss": 3.9257, "step": 1351680 }, { "epoch": 0.02, "learning_rate": 2.7860689102133636e-05, "loss": 3.9324, "step": 1352192 }, { "epoch": 0.02, "learning_rate": 2.7852319533426845e-05, "loss": 3.9351, "step": 1352704 }, { "epoch": 0.02, "learning_rate": 2.7843933585916325e-05, "loss": 3.914, "step": 1353216 }, { "epoch": 0.02, "learning_rate": 2.783554763840581e-05, "loss": 3.9287, "step": 1353728 }, { "epoch": 0.02, "learning_rate": 2.7827161690895288e-05, "loss": 3.9171, "step": 1354240 }, { "epoch": 0.02, "learning_rate": 2.7818792122188497e-05, "loss": 3.9357, "step": 1354752 }, { "epoch": 0.02, "learning_rate": 2.7810406174677977e-05, "loss": 3.9262, "step": 1355264 }, { "epoch": 0.02, "learning_rate": 2.7802020227167457e-05, "loss": 3.9198, "step": 1355776 }, { "epoch": 0.02, "learning_rate": 2.7793634279656937e-05, "loss": 3.9368, "step": 1356288 }, { "epoch": 0.02, "learning_rate": 2.7785248332146417e-05, "loss": 3.933, "step": 1356800 }, { "epoch": 0.02, "learning_rate": 2.777687876343963e-05, "loss": 3.9262, "step": 1357312 }, { "epoch": 0.02, "learning_rate": 2.776849281592911e-05, "loss": 3.9307, "step": 1357824 }, { "epoch": 0.02, "learning_rate": 2.776010686841859e-05, "loss": 3.9276, "step": 1358336 }, { "epoch": 0.02, "learning_rate": 2.775172092090807e-05, "loss": 3.9327, "step": 1358848 }, { "epoch": 0.02, "learning_rate": 2.774333497339755e-05, "loss": 3.9128, "step": 1359360 }, { "epoch": 0.02, "learning_rate": 2.773494902588703e-05, "loss": 3.9387, "step": 1359872 }, { "epoch": 0.02, "learning_rate": 2.772656307837651e-05, "loss": 3.925, "step": 1360384 }, { "epoch": 0.02, "learning_rate": 2.7718177130865986e-05, "loss": 3.9334, "step": 1360896 }, { "epoch": 0.02, "learning_rate": 2.7709807562159202e-05, "loss": 3.9222, "step": 1361408 }, { "epoch": 0.02, "learning_rate": 2.7701421614648682e-05, "loss": 3.9284, "step": 1361920 }, { "epoch": 0.02, "learning_rate": 2.7693035667138162e-05, "loss": 3.9241, "step": 1362432 }, { "epoch": 0.02, "learning_rate": 2.768466609843137e-05, "loss": 3.9286, "step": 1362944 }, { "epoch": 0.02, "learning_rate": 2.767628015092085e-05, "loss": 3.9102, "step": 1363456 }, { "epoch": 0.02, "learning_rate": 2.7667894203410334e-05, "loss": 3.9421, "step": 1363968 }, { "epoch": 0.02, "learning_rate": 2.7659508255899807e-05, "loss": 3.936, "step": 1364480 }, { "epoch": 0.02, "learning_rate": 2.7651122308389287e-05, "loss": 3.9283, "step": 1364992 }, { "epoch": 0.02, "learning_rate": 2.7642736360878767e-05, "loss": 3.9207, "step": 1365504 }, { "epoch": 0.02, "learning_rate": 2.7634350413368247e-05, "loss": 3.936, "step": 1366016 }, { "epoch": 0.02, "learning_rate": 2.762598084466146e-05, "loss": 3.9346, "step": 1366528 }, { "epoch": 0.02, "learning_rate": 2.761759489715094e-05, "loss": 3.9264, "step": 1367040 }, { "epoch": 0.02, "learning_rate": 2.760920894964042e-05, "loss": 3.9245, "step": 1367552 }, { "epoch": 0.02, "learning_rate": 2.76008230021299e-05, "loss": 3.9374, "step": 1368064 }, { "epoch": 0.02, "learning_rate": 2.759243705461938e-05, "loss": 3.9293, "step": 1368576 }, { "epoch": 0.02, "learning_rate": 2.7584083864716325e-05, "loss": 3.9375, "step": 1369088 }, { "epoch": 0.02, "learning_rate": 2.7575697917205805e-05, "loss": 3.9189, "step": 1369600 }, { "epoch": 0.02, "learning_rate": 2.756731196969528e-05, "loss": 3.9327, "step": 1370112 }, { "epoch": 0.02, "learning_rate": 2.755892602218476e-05, "loss": 3.9313, "step": 1370624 }, { "epoch": 0.02, "learning_rate": 2.755054007467424e-05, "loss": 3.9232, "step": 1371136 }, { "epoch": 0.02, "learning_rate": 2.7542170505967457e-05, "loss": 3.9433, "step": 1371648 }, { "epoch": 0.02, "learning_rate": 2.7533784558456933e-05, "loss": 3.9254, "step": 1372160 }, { "epoch": 0.02, "learning_rate": 2.7525398610946413e-05, "loss": 3.9316, "step": 1372672 }, { "epoch": 0.02, "learning_rate": 2.7517012663435893e-05, "loss": 3.9295, "step": 1373184 }, { "epoch": 0.02, "learning_rate": 2.7508626715925373e-05, "loss": 3.9277, "step": 1373696 }, { "epoch": 0.03, "eval_loss": 4.058403491973877, "eval_runtime": 338.5715, "eval_samples_per_second": 1127.062, "eval_steps_per_second": 35.222, "step": 1373760 }, { "epoch": 1.0, "learning_rate": 2.7500240768414853e-05, "loss": 3.925, "step": 1374208 }, { "epoch": 1.0, "learning_rate": 2.7491854820904333e-05, "loss": 3.931, "step": 1374720 }, { "epoch": 1.0, "learning_rate": 2.7483468873393813e-05, "loss": 3.936, "step": 1375232 }, { "epoch": 1.0, "learning_rate": 2.7475099304687026e-05, "loss": 3.9334, "step": 1375744 }, { "epoch": 1.0, "learning_rate": 2.7466713357176506e-05, "loss": 3.9399, "step": 1376256 }, { "epoch": 1.0, "learning_rate": 2.7458327409665986e-05, "loss": 3.9186, "step": 1376768 }, { "epoch": 1.0, "learning_rate": 2.7449941462155466e-05, "loss": 3.9234, "step": 1377280 }, { "epoch": 1.0, "learning_rate": 2.7441571893448675e-05, "loss": 3.9246, "step": 1377792 }, { "epoch": 1.0, "learning_rate": 2.7433185945938155e-05, "loss": 3.9376, "step": 1378304 }, { "epoch": 1.0, "learning_rate": 2.7424799998427635e-05, "loss": 3.9277, "step": 1378816 }, { "epoch": 1.0, "learning_rate": 2.7416414050917118e-05, "loss": 3.9344, "step": 1379328 }, { "epoch": 1.0, "learning_rate": 2.7408028103406598e-05, "loss": 3.9362, "step": 1379840 }, { "epoch": 1.0, "learning_rate": 2.7399674913503536e-05, "loss": 3.9193, "step": 1380352 }, { "epoch": 1.0, "learning_rate": 2.7391288965993016e-05, "loss": 3.9248, "step": 1380864 }, { "epoch": 1.0, "learning_rate": 2.7382903018482496e-05, "loss": 3.9119, "step": 1381376 }, { "epoch": 1.0, "learning_rate": 2.737451707097198e-05, "loss": 3.9223, "step": 1381888 }, { "epoch": 1.0, "learning_rate": 2.736613112346146e-05, "loss": 3.9262, "step": 1382400 }, { "epoch": 1.0, "learning_rate": 2.735774517595094e-05, "loss": 3.9218, "step": 1382912 }, { "epoch": 1.0, "learning_rate": 2.734935922844042e-05, "loss": 3.9225, "step": 1383424 }, { "epoch": 1.0, "learning_rate": 2.73409732809299e-05, "loss": 3.9453, "step": 1383936 }, { "epoch": 1.0, "learning_rate": 2.7332603712223108e-05, "loss": 3.9261, "step": 1384448 }, { "epoch": 1.0, "learning_rate": 2.7324217764712588e-05, "loss": 3.9282, "step": 1384960 }, { "epoch": 1.0, "learning_rate": 2.731583181720207e-05, "loss": 3.936, "step": 1385472 }, { "epoch": 1.0, "learning_rate": 2.730746224849528e-05, "loss": 3.9305, "step": 1385984 }, { "epoch": 1.0, "learning_rate": 2.729907630098476e-05, "loss": 3.9224, "step": 1386496 }, { "epoch": 1.0, "learning_rate": 2.729069035347424e-05, "loss": 3.9157, "step": 1387008 }, { "epoch": 1.0, "learning_rate": 2.728230440596372e-05, "loss": 3.9277, "step": 1387520 }, { "epoch": 1.0, "learning_rate": 2.72739184584532e-05, "loss": 3.9207, "step": 1388032 }, { "epoch": 1.0, "learning_rate": 2.726553251094268e-05, "loss": 3.9153, "step": 1388544 }, { "epoch": 1.01, "learning_rate": 2.7257146563432164e-05, "loss": 3.9281, "step": 1389056 }, { "epoch": 1.01, "learning_rate": 2.7248760615921644e-05, "loss": 3.9213, "step": 1389568 }, { "epoch": 1.01, "learning_rate": 2.7240391047214853e-05, "loss": 3.9346, "step": 1390080 }, { "epoch": 1.01, "learning_rate": 2.7232005099704333e-05, "loss": 3.9304, "step": 1390592 }, { "epoch": 1.01, "learning_rate": 2.7223619152193813e-05, "loss": 3.9169, "step": 1391104 }, { "epoch": 1.01, "learning_rate": 2.7215249583487025e-05, "loss": 3.9297, "step": 1391616 }, { "epoch": 1.01, "learning_rate": 2.7206863635976505e-05, "loss": 3.944, "step": 1392128 }, { "epoch": 1.01, "learning_rate": 2.7198477688465985e-05, "loss": 3.9106, "step": 1392640 }, { "epoch": 1.01, "learning_rate": 2.7190091740955465e-05, "loss": 3.9298, "step": 1393152 }, { "epoch": 1.01, "learning_rate": 2.7181705793444938e-05, "loss": 3.9196, "step": 1393664 }, { "epoch": 1.01, "learning_rate": 2.7173319845934418e-05, "loss": 3.9215, "step": 1394176 }, { "epoch": 1.01, "learning_rate": 2.71649338984239e-05, "loss": 3.9227, "step": 1394688 }, { "epoch": 1.01, "learning_rate": 2.7156564329717117e-05, "loss": 3.9369, "step": 1395200 }, { "epoch": 1.01, "learning_rate": 2.714817838220659e-05, "loss": 3.9294, "step": 1395712 }, { "epoch": 1.01, "learning_rate": 2.713979243469607e-05, "loss": 3.9234, "step": 1396224 }, { "epoch": 1.01, "learning_rate": 2.713140648718555e-05, "loss": 3.9299, "step": 1396736 }, { "epoch": 1.01, "learning_rate": 2.712302053967503e-05, "loss": 3.9185, "step": 1397248 }, { "epoch": 1.01, "learning_rate": 2.711463459216451e-05, "loss": 3.9342, "step": 1397760 }, { "epoch": 1.01, "learning_rate": 2.710624864465399e-05, "loss": 3.9112, "step": 1398272 }, { "epoch": 1.01, "learning_rate": 2.7097862697143474e-05, "loss": 3.9178, "step": 1398784 }, { "epoch": 1.01, "learning_rate": 2.7089476749632954e-05, "loss": 3.9322, "step": 1399296 }, { "epoch": 1.01, "learning_rate": 2.7081090802122434e-05, "loss": 3.9294, "step": 1399808 }, { "epoch": 1.01, "learning_rate": 2.7072721233415643e-05, "loss": 3.9215, "step": 1400320 }, { "epoch": 1.01, "learning_rate": 2.7064335285905123e-05, "loss": 3.9209, "step": 1400832 }, { "epoch": 1.01, "learning_rate": 2.7055949338394603e-05, "loss": 3.9282, "step": 1401344 }, { "epoch": 1.01, "learning_rate": 2.7047563390884083e-05, "loss": 3.9114, "step": 1401856 }, { "epoch": 1.01, "learning_rate": 2.7039177443373566e-05, "loss": 3.9334, "step": 1402368 }, { "epoch": 1.01, "learning_rate": 2.7030807874666775e-05, "loss": 3.9241, "step": 1402880 }, { "epoch": 1.01, "learning_rate": 2.7022421927156255e-05, "loss": 3.9349, "step": 1403392 }, { "epoch": 1.01, "learning_rate": 2.7014035979645735e-05, "loss": 3.9308, "step": 1403904 }, { "epoch": 1.01, "learning_rate": 2.7005650032135215e-05, "loss": 3.917, "step": 1404416 }, { "epoch": 1.01, "learning_rate": 2.6997264084624695e-05, "loss": 3.9213, "step": 1404928 }, { "epoch": 1.01, "learning_rate": 2.6988878137114175e-05, "loss": 3.9271, "step": 1405440 }, { "epoch": 1.01, "learning_rate": 2.6980508568407387e-05, "loss": 3.9138, "step": 1405952 }, { "epoch": 1.01, "learning_rate": 2.6972138999700596e-05, "loss": 3.918, "step": 1406464 }, { "epoch": 1.01, "learning_rate": 2.6963753052190076e-05, "loss": 3.9317, "step": 1406976 }, { "epoch": 1.01, "learning_rate": 2.6955367104679556e-05, "loss": 3.9228, "step": 1407488 }, { "epoch": 1.01, "learning_rate": 2.6946981157169036e-05, "loss": 3.9096, "step": 1408000 }, { "epoch": 1.01, "learning_rate": 2.693859520965852e-05, "loss": 3.9134, "step": 1408512 }, { "epoch": 1.01, "learning_rate": 2.6930209262148e-05, "loss": 3.9122, "step": 1409024 }, { "epoch": 1.01, "learning_rate": 2.692182331463748e-05, "loss": 3.9352, "step": 1409536 }, { "epoch": 1.01, "learning_rate": 2.6913437367126953e-05, "loss": 3.9309, "step": 1410048 }, { "epoch": 1.01, "learning_rate": 2.690506779842017e-05, "loss": 3.9204, "step": 1410560 }, { "epoch": 1.01, "learning_rate": 2.689668185090965e-05, "loss": 3.9261, "step": 1411072 }, { "epoch": 1.01, "learning_rate": 2.6888295903399125e-05, "loss": 3.923, "step": 1411584 }, { "epoch": 1.01, "learning_rate": 2.6879909955888605e-05, "loss": 3.93, "step": 1412096 }, { "epoch": 1.01, "learning_rate": 2.687154038718182e-05, "loss": 3.9176, "step": 1412608 }, { "epoch": 1.01, "learning_rate": 2.68631544396713e-05, "loss": 3.9301, "step": 1413120 }, { "epoch": 1.01, "learning_rate": 2.6854768492160774e-05, "loss": 3.9256, "step": 1413632 }, { "epoch": 1.01, "learning_rate": 2.6846382544650257e-05, "loss": 3.9286, "step": 1414144 }, { "epoch": 1.01, "learning_rate": 2.6837996597139737e-05, "loss": 3.919, "step": 1414656 }, { "epoch": 1.01, "learning_rate": 2.6829627028432953e-05, "loss": 3.9251, "step": 1415168 }, { "epoch": 1.01, "learning_rate": 2.6821241080922426e-05, "loss": 3.9286, "step": 1415680 }, { "epoch": 1.01, "learning_rate": 2.6812855133411906e-05, "loss": 3.9283, "step": 1416192 }, { "epoch": 1.01, "learning_rate": 2.6804469185901386e-05, "loss": 3.915, "step": 1416704 }, { "epoch": 1.01, "learning_rate": 2.6796083238390866e-05, "loss": 3.9218, "step": 1417216 }, { "epoch": 1.01, "learning_rate": 2.678769729088035e-05, "loss": 3.9209, "step": 1417728 }, { "epoch": 1.01, "learning_rate": 2.677931134336983e-05, "loss": 3.9261, "step": 1418240 }, { "epoch": 1.01, "learning_rate": 2.677092539585931e-05, "loss": 3.9263, "step": 1418752 }, { "epoch": 1.01, "learning_rate": 2.676253944834879e-05, "loss": 3.9122, "step": 1419264 }, { "epoch": 1.02, "learning_rate": 2.675415350083827e-05, "loss": 3.9231, "step": 1419776 }, { "epoch": 1.02, "learning_rate": 2.674576755332775e-05, "loss": 3.919, "step": 1420288 }, { "epoch": 1.02, "learning_rate": 2.673739798462096e-05, "loss": 3.928, "step": 1420800 }, { "epoch": 1.02, "learning_rate": 2.6729012037110442e-05, "loss": 3.9106, "step": 1421312 }, { "epoch": 1.02, "learning_rate": 2.6720626089599922e-05, "loss": 3.9218, "step": 1421824 }, { "epoch": 1.02, "learning_rate": 2.6712240142089402e-05, "loss": 3.9349, "step": 1422336 }, { "epoch": 1.02, "learning_rate": 2.670387057338261e-05, "loss": 3.9218, "step": 1422848 }, { "epoch": 1.02, "learning_rate": 2.669548462587209e-05, "loss": 3.9053, "step": 1423360 }, { "epoch": 1.02, "learning_rate": 2.668709867836157e-05, "loss": 3.9212, "step": 1423872 }, { "epoch": 1.02, "learning_rate": 2.667871273085105e-05, "loss": 3.9274, "step": 1424384 }, { "epoch": 1.02, "learning_rate": 2.6670326783340534e-05, "loss": 3.9282, "step": 1424896 }, { "epoch": 1.02, "learning_rate": 2.6661940835830014e-05, "loss": 3.9227, "step": 1425408 }, { "epoch": 1.02, "learning_rate": 2.6653554888319487e-05, "loss": 3.9132, "step": 1425920 }, { "epoch": 1.02, "learning_rate": 2.6645185319612703e-05, "loss": 3.9146, "step": 1426432 }, { "epoch": 1.02, "learning_rate": 2.6636799372102183e-05, "loss": 3.9255, "step": 1426944 }, { "epoch": 1.02, "learning_rate": 2.6628413424591663e-05, "loss": 3.9074, "step": 1427456 }, { "epoch": 1.02, "learning_rate": 2.662002747708114e-05, "loss": 3.9189, "step": 1427968 }, { "epoch": 1.02, "learning_rate": 2.661164152957062e-05, "loss": 3.9218, "step": 1428480 }, { "epoch": 1.02, "learning_rate": 2.66032555820601e-05, "loss": 3.9246, "step": 1428992 }, { "epoch": 1.02, "learning_rate": 2.6594886013353315e-05, "loss": 3.9038, "step": 1429504 }, { "epoch": 1.02, "learning_rate": 2.658650006584279e-05, "loss": 3.9201, "step": 1430016 }, { "epoch": 1.02, "learning_rate": 2.6578114118332272e-05, "loss": 3.9076, "step": 1430528 }, { "epoch": 1.02, "learning_rate": 2.6569728170821752e-05, "loss": 3.9213, "step": 1431040 }, { "epoch": 1.02, "learning_rate": 2.656135860211496e-05, "loss": 3.9192, "step": 1431552 }, { "epoch": 1.02, "learning_rate": 2.655297265460444e-05, "loss": 3.9113, "step": 1432064 }, { "epoch": 1.02, "learning_rate": 2.654458670709392e-05, "loss": 3.9268, "step": 1432576 }, { "epoch": 1.02, "learning_rate": 2.65362007595834e-05, "loss": 3.9251, "step": 1433088 }, { "epoch": 1.02, "learning_rate": 2.6527831190876613e-05, "loss": 3.913, "step": 1433600 }, { "epoch": 1.02, "learning_rate": 2.651946162216983e-05, "loss": 3.9198, "step": 1434112 }, { "epoch": 1.02, "learning_rate": 2.651107567465931e-05, "loss": 3.9195, "step": 1434624 }, { "epoch": 1.02, "learning_rate": 2.650268972714879e-05, "loss": 3.9214, "step": 1435136 }, { "epoch": 1.02, "learning_rate": 2.6494303779638262e-05, "loss": 3.9077, "step": 1435648 }, { "epoch": 1.02, "learning_rate": 2.6485917832127742e-05, "loss": 3.9245, "step": 1436160 }, { "epoch": 1.02, "learning_rate": 2.6477531884617222e-05, "loss": 3.9164, "step": 1436672 }, { "epoch": 1.02, "learning_rate": 2.6469145937106705e-05, "loss": 3.9232, "step": 1437184 }, { "epoch": 1.02, "learning_rate": 2.6460759989596185e-05, "loss": 3.918, "step": 1437696 }, { "epoch": 1.02, "learning_rate": 2.6452374042085665e-05, "loss": 3.9227, "step": 1438208 }, { "epoch": 1.02, "learning_rate": 2.6443988094575145e-05, "loss": 3.9087, "step": 1438720 }, { "epoch": 1.02, "learning_rate": 2.6435618525868354e-05, "loss": 3.9178, "step": 1439232 }, { "epoch": 1.02, "learning_rate": 2.6427232578357834e-05, "loss": 3.9028, "step": 1439744 }, { "epoch": 1.02, "learning_rate": 2.6418846630847314e-05, "loss": 3.9338, "step": 1440256 }, { "epoch": 1.02, "learning_rate": 2.6410460683336798e-05, "loss": 3.9243, "step": 1440768 }, { "epoch": 1.02, "learning_rate": 2.6402074735826278e-05, "loss": 3.9225, "step": 1441280 }, { "epoch": 1.02, "learning_rate": 2.6393688788315758e-05, "loss": 3.9104, "step": 1441792 }, { "epoch": 1.02, "learning_rate": 2.6385302840805238e-05, "loss": 3.926, "step": 1442304 }, { "epoch": 1.02, "learning_rate": 2.6376933272098447e-05, "loss": 3.9284, "step": 1442816 }, { "epoch": 1.02, "learning_rate": 2.6368547324587927e-05, "loss": 3.9162, "step": 1443328 }, { "epoch": 1.02, "learning_rate": 2.6360161377077407e-05, "loss": 3.918, "step": 1443840 }, { "epoch": 1.02, "learning_rate": 2.635177542956689e-05, "loss": 3.927, "step": 1444352 }, { "epoch": 1.02, "learning_rate": 2.634338948205637e-05, "loss": 3.9184, "step": 1444864 }, { "epoch": 1.02, "learning_rate": 2.6335036292153308e-05, "loss": 3.9293, "step": 1445376 }, { "epoch": 1.02, "learning_rate": 2.6326650344642788e-05, "loss": 3.9112, "step": 1445888 }, { "epoch": 1.02, "learning_rate": 2.6318264397132268e-05, "loss": 3.9225, "step": 1446400 }, { "epoch": 1.02, "learning_rate": 2.630987844962175e-05, "loss": 3.9213, "step": 1446912 }, { "epoch": 1.02, "learning_rate": 2.630149250211123e-05, "loss": 3.9113, "step": 1447424 }, { "epoch": 1.02, "learning_rate": 2.629310655460071e-05, "loss": 3.9345, "step": 1447936 }, { "epoch": 1.02, "learning_rate": 2.628472060709019e-05, "loss": 3.9154, "step": 1448448 }, { "epoch": 1.02, "learning_rate": 2.627633465957967e-05, "loss": 3.9215, "step": 1448960 }, { "epoch": 1.02, "learning_rate": 2.6267948712069144e-05, "loss": 3.9224, "step": 1449472 }, { "epoch": 1.02, "learning_rate": 2.6259562764558628e-05, "loss": 3.9161, "step": 1449984 }, { "epoch": 1.03, "eval_loss": 4.054060459136963, "eval_runtime": 290.0998, "eval_samples_per_second": 1315.378, "eval_steps_per_second": 41.107, "step": 1450080 }, { "epoch": 2.0, "learning_rate": 2.6251176817048108e-05, "loss": 3.9202, "step": 1450496 }, { "epoch": 2.0, "learning_rate": 2.6242790869537588e-05, "loss": 3.9192, "step": 1451008 }, { "epoch": 2.0, "learning_rate": 2.6234404922027068e-05, "loss": 3.9278, "step": 1451520 }, { "epoch": 2.0, "learning_rate": 2.6226018974516548e-05, "loss": 3.9252, "step": 1452032 }, { "epoch": 2.0, "learning_rate": 2.6217633027006027e-05, "loss": 3.9295, "step": 1452544 }, { "epoch": 2.0, "learning_rate": 2.6209263458299237e-05, "loss": 3.9145, "step": 1453056 }, { "epoch": 2.0, "learning_rate": 2.620087751078872e-05, "loss": 3.9174, "step": 1453568 }, { "epoch": 2.0, "learning_rate": 2.61924915632782e-05, "loss": 3.9082, "step": 1454080 }, { "epoch": 2.0, "learning_rate": 2.618410561576768e-05, "loss": 3.9336, "step": 1454592 }, { "epoch": 2.0, "learning_rate": 2.617573604706089e-05, "loss": 3.9164, "step": 1455104 }, { "epoch": 2.0, "learning_rate": 2.616735009955037e-05, "loss": 3.9262, "step": 1455616 }, { "epoch": 2.0, "learning_rate": 2.615898053084358e-05, "loss": 3.9261, "step": 1456128 }, { "epoch": 2.0, "learning_rate": 2.6150610962136797e-05, "loss": 3.9158, "step": 1456640 }, { "epoch": 2.0, "learning_rate": 2.614222501462627e-05, "loss": 3.9084, "step": 1457152 }, { "epoch": 2.0, "learning_rate": 2.613383906711575e-05, "loss": 3.9097, "step": 1457664 }, { "epoch": 2.0, "learning_rate": 2.612545311960523e-05, "loss": 3.9083, "step": 1458176 }, { "epoch": 2.0, "learning_rate": 2.611706717209471e-05, "loss": 3.9189, "step": 1458688 }, { "epoch": 2.0, "learning_rate": 2.610868122458419e-05, "loss": 3.9123, "step": 1459200 }, { "epoch": 2.0, "learning_rate": 2.6100295277073674e-05, "loss": 3.9134, "step": 1459712 }, { "epoch": 2.0, "learning_rate": 2.6091925708366883e-05, "loss": 3.9362, "step": 1460224 }, { "epoch": 2.0, "learning_rate": 2.6083539760856363e-05, "loss": 3.9194, "step": 1460736 }, { "epoch": 2.0, "learning_rate": 2.6075153813345843e-05, "loss": 3.9175, "step": 1461248 }, { "epoch": 2.0, "learning_rate": 2.6066767865835323e-05, "loss": 3.9259, "step": 1461760 }, { "epoch": 2.0, "learning_rate": 2.6058381918324802e-05, "loss": 3.9236, "step": 1462272 }, { "epoch": 2.0, "learning_rate": 2.6050012349618015e-05, "loss": 3.9129, "step": 1462784 }, { "epoch": 2.0, "learning_rate": 2.6041626402107495e-05, "loss": 3.9057, "step": 1463296 }, { "epoch": 2.0, "learning_rate": 2.6033240454596975e-05, "loss": 3.9223, "step": 1463808 }, { "epoch": 2.0, "learning_rate": 2.6024854507086455e-05, "loss": 3.9065, "step": 1464320 }, { "epoch": 2.0, "learning_rate": 2.6016468559575935e-05, "loss": 3.9099, "step": 1464832 }, { "epoch": 2.01, "learning_rate": 2.6008082612065415e-05, "loss": 3.9145, "step": 1465344 }, { "epoch": 2.01, "learning_rate": 2.5999696664554895e-05, "loss": 3.9104, "step": 1465856 }, { "epoch": 2.01, "learning_rate": 2.5991327095848107e-05, "loss": 3.9243, "step": 1466368 }, { "epoch": 2.01, "learning_rate": 2.5982941148337587e-05, "loss": 3.9202, "step": 1466880 }, { "epoch": 2.01, "learning_rate": 2.5974555200827067e-05, "loss": 3.909, "step": 1467392 }, { "epoch": 2.01, "learning_rate": 2.5966185632120276e-05, "loss": 3.9223, "step": 1467904 }, { "epoch": 2.01, "learning_rate": 2.5957799684609756e-05, "loss": 3.9297, "step": 1468416 }, { "epoch": 2.01, "learning_rate": 2.5949413737099236e-05, "loss": 3.907, "step": 1468928 }, { "epoch": 2.01, "learning_rate": 2.5941027789588716e-05, "loss": 3.9202, "step": 1469440 }, { "epoch": 2.01, "learning_rate": 2.59326418420782e-05, "loss": 3.908, "step": 1469952 }, { "epoch": 2.01, "learning_rate": 2.592425589456768e-05, "loss": 3.9198, "step": 1470464 }, { "epoch": 2.01, "learning_rate": 2.591586994705716e-05, "loss": 3.9092, "step": 1470976 }, { "epoch": 2.01, "learning_rate": 2.5907483999546633e-05, "loss": 3.9311, "step": 1471488 }, { "epoch": 2.01, "learning_rate": 2.5899098052036112e-05, "loss": 3.9184, "step": 1472000 }, { "epoch": 2.01, "learning_rate": 2.589072848332933e-05, "loss": 3.9159, "step": 1472512 }, { "epoch": 2.01, "learning_rate": 2.5882342535818808e-05, "loss": 3.9217, "step": 1473024 }, { "epoch": 2.01, "learning_rate": 2.5873956588308285e-05, "loss": 3.9108, "step": 1473536 }, { "epoch": 2.01, "learning_rate": 2.5865570640797765e-05, "loss": 3.9219, "step": 1474048 }, { "epoch": 2.01, "learning_rate": 2.5857184693287245e-05, "loss": 3.9069, "step": 1474560 }, { "epoch": 2.01, "learning_rate": 2.5848798745776725e-05, "loss": 3.9087, "step": 1475072 }, { "epoch": 2.01, "learning_rate": 2.5840412798266205e-05, "loss": 3.9262, "step": 1475584 }, { "epoch": 2.01, "learning_rate": 2.5832043229559417e-05, "loss": 3.9159, "step": 1476096 }, { "epoch": 2.01, "learning_rate": 2.5823657282048897e-05, "loss": 3.9207, "step": 1476608 }, { "epoch": 2.01, "learning_rate": 2.5815271334538377e-05, "loss": 3.9095, "step": 1477120 }, { "epoch": 2.01, "learning_rate": 2.5806885387027857e-05, "loss": 3.9173, "step": 1477632 }, { "epoch": 2.01, "learning_rate": 2.5798499439517337e-05, "loss": 3.9048, "step": 1478144 }, { "epoch": 2.01, "learning_rate": 2.5790113492006817e-05, "loss": 3.9228, "step": 1478656 }, { "epoch": 2.01, "learning_rate": 2.5781727544496297e-05, "loss": 3.9164, "step": 1479168 }, { "epoch": 2.01, "learning_rate": 2.5773341596985777e-05, "loss": 3.9279, "step": 1479680 }, { "epoch": 2.01, "learning_rate": 2.576498840708272e-05, "loss": 3.9219, "step": 1480192 }, { "epoch": 2.01, "learning_rate": 2.57566024595722e-05, "loss": 3.9131, "step": 1480704 }, { "epoch": 2.01, "learning_rate": 2.574821651206168e-05, "loss": 3.9081, "step": 1481216 }, { "epoch": 2.01, "learning_rate": 2.573983056455116e-05, "loss": 3.9198, "step": 1481728 }, { "epoch": 2.01, "learning_rate": 2.573146099584437e-05, "loss": 3.9072, "step": 1482240 }, { "epoch": 2.01, "learning_rate": 2.572307504833385e-05, "loss": 3.9101, "step": 1482752 }, { "epoch": 2.01, "learning_rate": 2.571468910082333e-05, "loss": 3.9192, "step": 1483264 }, { "epoch": 2.01, "learning_rate": 2.570630315331281e-05, "loss": 3.9183, "step": 1483776 }, { "epoch": 2.01, "learning_rate": 2.569791720580229e-05, "loss": 3.9, "step": 1484288 }, { "epoch": 2.01, "learning_rate": 2.568953125829177e-05, "loss": 3.9027, "step": 1484800 }, { "epoch": 2.01, "learning_rate": 2.568114531078125e-05, "loss": 3.9016, "step": 1485312 }, { "epoch": 2.01, "learning_rate": 2.567275936327073e-05, "loss": 3.9294, "step": 1485824 }, { "epoch": 2.01, "learning_rate": 2.5664373415760214e-05, "loss": 3.9199, "step": 1486336 }, { "epoch": 2.01, "learning_rate": 2.5656003847053423e-05, "loss": 3.9147, "step": 1486848 }, { "epoch": 2.01, "learning_rate": 2.5647617899542903e-05, "loss": 3.9172, "step": 1487360 }, { "epoch": 2.01, "learning_rate": 2.5639231952032383e-05, "loss": 3.9131, "step": 1487872 }, { "epoch": 2.01, "learning_rate": 2.5630846004521863e-05, "loss": 3.9277, "step": 1488384 }, { "epoch": 2.01, "learning_rate": 2.5622476435815075e-05, "loss": 3.9032, "step": 1488896 }, { "epoch": 2.01, "learning_rate": 2.5614090488304555e-05, "loss": 3.9276, "step": 1489408 }, { "epoch": 2.01, "learning_rate": 2.5605704540794035e-05, "loss": 3.9147, "step": 1489920 }, { "epoch": 2.01, "learning_rate": 2.5597318593283515e-05, "loss": 3.9193, "step": 1490432 }, { "epoch": 2.01, "learning_rate": 2.5588932645772995e-05, "loss": 3.9172, "step": 1490944 }, { "epoch": 2.01, "learning_rate": 2.558054669826247e-05, "loss": 3.9123, "step": 1491456 }, { "epoch": 2.01, "learning_rate": 2.557216075075195e-05, "loss": 3.9236, "step": 1491968 }, { "epoch": 2.01, "learning_rate": 2.556377480324143e-05, "loss": 3.9181, "step": 1492480 }, { "epoch": 2.01, "learning_rate": 2.555538885573091e-05, "loss": 3.9067, "step": 1492992 }, { "epoch": 2.01, "learning_rate": 2.554701928702412e-05, "loss": 3.9163, "step": 1493504 }, { "epoch": 2.01, "learning_rate": 2.55386333395136e-05, "loss": 3.9078, "step": 1494016 }, { "epoch": 2.01, "learning_rate": 2.553024739200308e-05, "loss": 3.9226, "step": 1494528 }, { "epoch": 2.01, "learning_rate": 2.552186144449256e-05, "loss": 3.9155, "step": 1495040 }, { "epoch": 2.01, "learning_rate": 2.5513491875785773e-05, "loss": 3.9045, "step": 1495552 }, { "epoch": 2.02, "learning_rate": 2.5505105928275253e-05, "loss": 3.9189, "step": 1496064 }, { "epoch": 2.02, "learning_rate": 2.5496719980764733e-05, "loss": 3.9086, "step": 1496576 }, { "epoch": 2.02, "learning_rate": 2.5488334033254213e-05, "loss": 3.9182, "step": 1497088 }, { "epoch": 2.02, "learning_rate": 2.5479948085743693e-05, "loss": 3.9048, "step": 1497600 }, { "epoch": 2.02, "learning_rate": 2.5471562138233173e-05, "loss": 3.9168, "step": 1498112 }, { "epoch": 2.02, "learning_rate": 2.5463192569526385e-05, "loss": 3.9253, "step": 1498624 }, { "epoch": 2.02, "learning_rate": 2.5454806622015865e-05, "loss": 3.91, "step": 1499136 }, { "epoch": 2.02, "learning_rate": 2.5446420674505345e-05, "loss": 3.9011, "step": 1499648 }, { "epoch": 2.02, "learning_rate": 2.5438034726994825e-05, "loss": 3.914, "step": 1500160 }, { "epoch": 2.02, "learning_rate": 2.5429648779484305e-05, "loss": 3.9103, "step": 1500672 }, { "epoch": 2.02, "learning_rate": 2.5421262831973785e-05, "loss": 3.9254, "step": 1501184 }, { "epoch": 2.02, "learning_rate": 2.5412876884463265e-05, "loss": 3.9137, "step": 1501696 }, { "epoch": 2.02, "learning_rate": 2.5404490936952745e-05, "loss": 3.9088, "step": 1502208 }, { "epoch": 2.02, "learning_rate": 2.5396137747049687e-05, "loss": 3.9072, "step": 1502720 }, { "epoch": 2.02, "learning_rate": 2.5387751799539167e-05, "loss": 3.9185, "step": 1503232 }, { "epoch": 2.02, "learning_rate": 2.5379365852028647e-05, "loss": 3.8964, "step": 1503744 }, { "epoch": 2.02, "learning_rate": 2.5370979904518126e-05, "loss": 3.911, "step": 1504256 }, { "epoch": 2.02, "learning_rate": 2.5362593957007606e-05, "loss": 3.9132, "step": 1504768 }, { "epoch": 2.02, "learning_rate": 2.5354208009497086e-05, "loss": 3.9188, "step": 1505280 }, { "epoch": 2.02, "learning_rate": 2.53458384407903e-05, "loss": 3.8936, "step": 1505792 }, { "epoch": 2.02, "learning_rate": 2.533745249327978e-05, "loss": 3.9129, "step": 1506304 }, { "epoch": 2.02, "learning_rate": 2.532906654576926e-05, "loss": 3.9066, "step": 1506816 }, { "epoch": 2.02, "learning_rate": 2.532068059825874e-05, "loss": 3.9073, "step": 1507328 }, { "epoch": 2.02, "learning_rate": 2.531229465074822e-05, "loss": 3.9151, "step": 1507840 }, { "epoch": 2.02, "learning_rate": 2.53039087032377e-05, "loss": 3.9021, "step": 1508352 }, { "epoch": 2.02, "learning_rate": 2.529553913453091e-05, "loss": 3.9202, "step": 1508864 }, { "epoch": 2.02, "learning_rate": 2.528715318702039e-05, "loss": 3.9144, "step": 1509376 }, { "epoch": 2.02, "learning_rate": 2.527876723950987e-05, "loss": 3.9072, "step": 1509888 }, { "epoch": 2.02, "learning_rate": 2.527038129199935e-05, "loss": 3.9117, "step": 1510400 }, { "epoch": 2.02, "learning_rate": 2.526199534448883e-05, "loss": 3.9093, "step": 1510912 }, { "epoch": 2.02, "learning_rate": 2.5253609396978308e-05, "loss": 3.9156, "step": 1511424 }, { "epoch": 2.02, "learning_rate": 2.5245223449467787e-05, "loss": 3.8944, "step": 1511936 }, { "epoch": 2.02, "learning_rate": 2.5236837501957267e-05, "loss": 3.9204, "step": 1512448 }, { "epoch": 2.02, "learning_rate": 2.5228467933250477e-05, "loss": 3.9056, "step": 1512960 }, { "epoch": 2.02, "learning_rate": 2.5220098364543692e-05, "loss": 3.914, "step": 1513472 }, { "epoch": 2.02, "learning_rate": 2.5211712417033172e-05, "loss": 3.9088, "step": 1513984 }, { "epoch": 2.02, "learning_rate": 2.5203326469522652e-05, "loss": 3.918, "step": 1514496 }, { "epoch": 2.02, "learning_rate": 2.519494052201213e-05, "loss": 3.9063, "step": 1515008 }, { "epoch": 2.02, "learning_rate": 2.518655457450161e-05, "loss": 3.9046, "step": 1515520 }, { "epoch": 2.02, "learning_rate": 2.517816862699109e-05, "loss": 3.8975, "step": 1516032 }, { "epoch": 2.02, "learning_rate": 2.5169815437088034e-05, "loss": 3.9222, "step": 1516544 }, { "epoch": 2.02, "learning_rate": 2.5161429489577514e-05, "loss": 3.9156, "step": 1517056 }, { "epoch": 2.02, "learning_rate": 2.5153043542066994e-05, "loss": 3.9153, "step": 1517568 }, { "epoch": 2.02, "learning_rate": 2.5144657594556477e-05, "loss": 3.9038, "step": 1518080 }, { "epoch": 2.02, "learning_rate": 2.513627164704595e-05, "loss": 3.918, "step": 1518592 }, { "epoch": 2.02, "learning_rate": 2.512788569953543e-05, "loss": 3.9192, "step": 1519104 }, { "epoch": 2.02, "learning_rate": 2.511949975202491e-05, "loss": 3.9082, "step": 1519616 }, { "epoch": 2.02, "learning_rate": 2.511111380451439e-05, "loss": 3.9105, "step": 1520128 }, { "epoch": 2.02, "learning_rate": 2.5102744235807603e-05, "loss": 3.9174, "step": 1520640 }, { "epoch": 2.02, "learning_rate": 2.5094358288297083e-05, "loss": 3.9174, "step": 1521152 }, { "epoch": 2.02, "learning_rate": 2.5085972340786562e-05, "loss": 3.9195, "step": 1521664 }, { "epoch": 2.02, "learning_rate": 2.5077586393276042e-05, "loss": 3.9033, "step": 1522176 }, { "epoch": 2.02, "learning_rate": 2.506921682456925e-05, "loss": 3.9138, "step": 1522688 }, { "epoch": 2.02, "learning_rate": 2.506083087705873e-05, "loss": 3.9098, "step": 1523200 }, { "epoch": 2.02, "learning_rate": 2.5052444929548215e-05, "loss": 3.9085, "step": 1523712 }, { "epoch": 2.02, "learning_rate": 2.5044058982037695e-05, "loss": 3.9206, "step": 1524224 }, { "epoch": 2.02, "learning_rate": 2.5035689413330904e-05, "loss": 3.91, "step": 1524736 }, { "epoch": 2.02, "learning_rate": 2.5027303465820384e-05, "loss": 3.9147, "step": 1525248 }, { "epoch": 2.02, "learning_rate": 2.5018917518309864e-05, "loss": 3.9111, "step": 1525760 }, { "epoch": 2.02, "learning_rate": 2.5010531570799344e-05, "loss": 3.9137, "step": 1526272 }, { "epoch": 2.03, "eval_loss": 4.05128288269043, "eval_runtime": 290.7411, "eval_samples_per_second": 1312.477, "eval_steps_per_second": 41.016, "step": 1526400 }, { "epoch": 0.0, "learning_rate": 2.5002145623288824e-05, "loss": 3.9054, "step": 1526784 }, { "epoch": 0.0, "learning_rate": 2.4993759675778307e-05, "loss": 3.9153, "step": 1527296 }, { "epoch": 0.0, "learning_rate": 2.4985373728267787e-05, "loss": 3.9177, "step": 1527808 }, { "epoch": 0.0, "learning_rate": 2.4976987780757267e-05, "loss": 3.9152, "step": 1528320 }, { "epoch": 0.0, "learning_rate": 2.4968601833246747e-05, "loss": 3.9239, "step": 1528832 }, { "epoch": 0.0, "learning_rate": 2.4960215885736223e-05, "loss": 3.9061, "step": 1529344 }, { "epoch": 0.0, "learning_rate": 2.4951829938225703e-05, "loss": 3.9082, "step": 1529856 }, { "epoch": 0.0, "learning_rate": 2.4943443990715183e-05, "loss": 3.9029, "step": 1530368 }, { "epoch": 0.0, "learning_rate": 2.4935058043204663e-05, "loss": 3.9215, "step": 1530880 }, { "epoch": 0.0, "learning_rate": 2.4926672095694147e-05, "loss": 3.9144, "step": 1531392 }, { "epoch": 0.0, "learning_rate": 2.4918286148183627e-05, "loss": 3.9152, "step": 1531904 }, { "epoch": 0.0, "learning_rate": 2.4909900200673107e-05, "loss": 3.9128, "step": 1532416 }, { "epoch": 0.0, "learning_rate": 2.4901530631966316e-05, "loss": 3.91, "step": 1532928 }, { "epoch": 0.0, "learning_rate": 2.4893144684455796e-05, "loss": 3.9014, "step": 1533440 }, { "epoch": 0.0, "learning_rate": 2.4884758736945276e-05, "loss": 3.9076, "step": 1533952 }, { "epoch": 0.0, "learning_rate": 2.4876372789434756e-05, "loss": 3.8965, "step": 1534464 }, { "epoch": 0.0, "learning_rate": 2.4867986841924236e-05, "loss": 3.9114, "step": 1534976 }, { "epoch": 0.0, "learning_rate": 2.4859600894413715e-05, "loss": 3.9048, "step": 1535488 }, { "epoch": 0.0, "learning_rate": 2.4851214946903195e-05, "loss": 3.903, "step": 1536000 }, { "epoch": 0.0, "learning_rate": 2.4842828999392675e-05, "loss": 3.9336, "step": 1536512 }, { "epoch": 0.0, "learning_rate": 2.4834459430685884e-05, "loss": 3.9068, "step": 1537024 }, { "epoch": 0.0, "learning_rate": 2.4826073483175364e-05, "loss": 3.9133, "step": 1537536 }, { "epoch": 0.0, "learning_rate": 2.4817687535664848e-05, "loss": 3.9167, "step": 1538048 }, { "epoch": 0.0, "learning_rate": 2.4809301588154328e-05, "loss": 3.9137, "step": 1538560 }, { "epoch": 0.0, "learning_rate": 2.4800915640643808e-05, "loss": 3.9077, "step": 1539072 }, { "epoch": 0.0, "learning_rate": 2.4792546071937017e-05, "loss": 3.8983, "step": 1539584 }, { "epoch": 0.0, "learning_rate": 2.4784160124426497e-05, "loss": 3.9161, "step": 1540096 }, { "epoch": 0.0, "learning_rate": 2.4775774176915977e-05, "loss": 3.8949, "step": 1540608 }, { "epoch": 0.0, "learning_rate": 2.4767388229405457e-05, "loss": 3.9036, "step": 1541120 }, { "epoch": 0.0, "learning_rate": 2.4759002281894937e-05, "loss": 3.9044, "step": 1541632 }, { "epoch": 0.01, "learning_rate": 2.475063271318815e-05, "loss": 3.904, "step": 1542144 }, { "epoch": 0.01, "learning_rate": 2.474224676567763e-05, "loss": 3.9172, "step": 1542656 }, { "epoch": 0.01, "learning_rate": 2.473386081816711e-05, "loss": 3.9108, "step": 1543168 }, { "epoch": 0.01, "learning_rate": 2.4725474870656586e-05, "loss": 3.9061, "step": 1543680 }, { "epoch": 0.01, "learning_rate": 2.47171053019498e-05, "loss": 3.9144, "step": 1544192 }, { "epoch": 0.01, "learning_rate": 2.470871935443928e-05, "loss": 3.9183, "step": 1544704 }, { "epoch": 0.01, "learning_rate": 2.470033340692876e-05, "loss": 3.9019, "step": 1545216 }, { "epoch": 0.01, "learning_rate": 2.4691947459418238e-05, "loss": 3.9134, "step": 1545728 }, { "epoch": 0.01, "learning_rate": 2.4683561511907718e-05, "loss": 3.9018, "step": 1546240 }, { "epoch": 0.01, "learning_rate": 2.4675175564397198e-05, "loss": 3.9125, "step": 1546752 }, { "epoch": 0.01, "learning_rate": 2.4666789616886678e-05, "loss": 3.8979, "step": 1547264 }, { "epoch": 0.01, "learning_rate": 2.4658403669376158e-05, "loss": 3.9227, "step": 1547776 }, { "epoch": 0.01, "learning_rate": 2.465003410066937e-05, "loss": 3.911, "step": 1548288 }, { "epoch": 0.01, "learning_rate": 2.464164815315885e-05, "loss": 3.9063, "step": 1548800 }, { "epoch": 0.01, "learning_rate": 2.463326220564833e-05, "loss": 3.9146, "step": 1549312 }, { "epoch": 0.01, "learning_rate": 2.462487625813781e-05, "loss": 3.9051, "step": 1549824 }, { "epoch": 0.01, "learning_rate": 2.461650668943102e-05, "loss": 3.9128, "step": 1550336 }, { "epoch": 0.01, "learning_rate": 2.4608120741920503e-05, "loss": 3.899, "step": 1550848 }, { "epoch": 0.01, "learning_rate": 2.4599734794409983e-05, "loss": 3.8998, "step": 1551360 }, { "epoch": 0.01, "learning_rate": 2.4591348846899462e-05, "loss": 3.9201, "step": 1551872 }, { "epoch": 0.01, "learning_rate": 2.4582962899388942e-05, "loss": 3.91, "step": 1552384 }, { "epoch": 0.01, "learning_rate": 2.457459333068215e-05, "loss": 3.9103, "step": 1552896 }, { "epoch": 0.01, "learning_rate": 2.456620738317163e-05, "loss": 3.9049, "step": 1553408 }, { "epoch": 0.01, "learning_rate": 2.455782143566111e-05, "loss": 3.9077, "step": 1553920 }, { "epoch": 0.01, "learning_rate": 2.454943548815059e-05, "loss": 3.9004, "step": 1554432 }, { "epoch": 0.01, "learning_rate": 2.4541065919443804e-05, "loss": 3.9115, "step": 1554944 }, { "epoch": 0.01, "learning_rate": 2.4532679971933284e-05, "loss": 3.9086, "step": 1555456 }, { "epoch": 0.01, "learning_rate": 2.4524294024422764e-05, "loss": 3.9221, "step": 1555968 }, { "epoch": 0.01, "learning_rate": 2.451590807691224e-05, "loss": 3.9143, "step": 1556480 }, { "epoch": 0.01, "learning_rate": 2.4507538508205456e-05, "loss": 3.9027, "step": 1556992 }, { "epoch": 0.01, "learning_rate": 2.4499152560694936e-05, "loss": 3.9049, "step": 1557504 }, { "epoch": 0.01, "learning_rate": 2.4490766613184413e-05, "loss": 3.9096, "step": 1558016 }, { "epoch": 0.01, "learning_rate": 2.4482380665673893e-05, "loss": 3.8971, "step": 1558528 }, { "epoch": 0.01, "learning_rate": 2.4473994718163373e-05, "loss": 3.9061, "step": 1559040 }, { "epoch": 0.01, "learning_rate": 2.4465608770652853e-05, "loss": 3.9094, "step": 1559552 }, { "epoch": 0.01, "learning_rate": 2.4457239201946065e-05, "loss": 3.9126, "step": 1560064 }, { "epoch": 0.01, "learning_rate": 2.4448853254435545e-05, "loss": 3.8921, "step": 1560576 }, { "epoch": 0.01, "learning_rate": 2.4440467306925025e-05, "loss": 3.8976, "step": 1561088 }, { "epoch": 0.01, "learning_rate": 2.4432081359414505e-05, "loss": 3.8954, "step": 1561600 }, { "epoch": 0.01, "learning_rate": 2.4423695411903985e-05, "loss": 3.9168, "step": 1562112 }, { "epoch": 0.01, "learning_rate": 2.4415309464393465e-05, "loss": 3.9116, "step": 1562624 }, { "epoch": 0.01, "learning_rate": 2.4406923516882945e-05, "loss": 3.9094, "step": 1563136 }, { "epoch": 0.01, "learning_rate": 2.4398553948176157e-05, "loss": 3.9086, "step": 1563648 }, { "epoch": 0.01, "learning_rate": 2.4390168000665637e-05, "loss": 3.9049, "step": 1564160 }, { "epoch": 0.01, "learning_rate": 2.4381782053155117e-05, "loss": 3.9223, "step": 1564672 }, { "epoch": 0.01, "learning_rate": 2.4373396105644594e-05, "loss": 3.8958, "step": 1565184 }, { "epoch": 0.01, "learning_rate": 2.4365010158134074e-05, "loss": 3.9157, "step": 1565696 }, { "epoch": 0.01, "learning_rate": 2.4356640589427286e-05, "loss": 3.9105, "step": 1566208 }, { "epoch": 0.01, "learning_rate": 2.43482710207205e-05, "loss": 3.9102, "step": 1566720 }, { "epoch": 0.01, "learning_rate": 2.433988507320998e-05, "loss": 3.9097, "step": 1567232 }, { "epoch": 0.01, "learning_rate": 2.433149912569946e-05, "loss": 3.9072, "step": 1567744 }, { "epoch": 0.01, "learning_rate": 2.432311317818894e-05, "loss": 3.9126, "step": 1568256 }, { "epoch": 0.01, "learning_rate": 2.431472723067842e-05, "loss": 3.9139, "step": 1568768 }, { "epoch": 0.01, "learning_rate": 2.4306341283167895e-05, "loss": 3.8957, "step": 1569280 }, { "epoch": 0.01, "learning_rate": 2.429795533565738e-05, "loss": 3.9095, "step": 1569792 }, { "epoch": 0.01, "learning_rate": 2.428956938814686e-05, "loss": 3.9005, "step": 1570304 }, { "epoch": 0.01, "learning_rate": 2.428118344063634e-05, "loss": 3.914, "step": 1570816 }, { "epoch": 0.01, "learning_rate": 2.4272813871929547e-05, "loss": 3.9084, "step": 1571328 }, { "epoch": 0.01, "learning_rate": 2.4264427924419027e-05, "loss": 3.897, "step": 1571840 }, { "epoch": 0.02, "learning_rate": 2.4256041976908507e-05, "loss": 3.9088, "step": 1572352 }, { "epoch": 0.02, "learning_rate": 2.4247656029397987e-05, "loss": 3.9037, "step": 1572864 }, { "epoch": 0.02, "learning_rate": 2.423927008188747e-05, "loss": 3.9104, "step": 1573376 }, { "epoch": 0.02, "learning_rate": 2.423090051318068e-05, "loss": 3.8931, "step": 1573888 }, { "epoch": 0.02, "learning_rate": 2.422251456567016e-05, "loss": 3.9096, "step": 1574400 }, { "epoch": 0.02, "learning_rate": 2.421412861815964e-05, "loss": 3.9225, "step": 1574912 }, { "epoch": 0.02, "learning_rate": 2.420574267064912e-05, "loss": 3.9016, "step": 1575424 }, { "epoch": 0.02, "learning_rate": 2.41973567231386e-05, "loss": 3.8869, "step": 1575936 }, { "epoch": 0.02, "learning_rate": 2.418897077562808e-05, "loss": 3.9075, "step": 1576448 }, { "epoch": 0.02, "learning_rate": 2.418058482811756e-05, "loss": 3.9069, "step": 1576960 }, { "epoch": 0.02, "learning_rate": 2.417219888060704e-05, "loss": 3.9139, "step": 1577472 }, { "epoch": 0.02, "learning_rate": 2.416382931190025e-05, "loss": 3.9076, "step": 1577984 }, { "epoch": 0.02, "learning_rate": 2.415545974319346e-05, "loss": 3.9009, "step": 1578496 }, { "epoch": 0.02, "learning_rate": 2.414707379568294e-05, "loss": 3.8999, "step": 1579008 }, { "epoch": 0.02, "learning_rate": 2.4138687848172424e-05, "loss": 3.911, "step": 1579520 }, { "epoch": 0.02, "learning_rate": 2.41303019006619e-05, "loss": 3.8899, "step": 1580032 }, { "epoch": 0.02, "learning_rate": 2.412191595315138e-05, "loss": 3.9025, "step": 1580544 }, { "epoch": 0.02, "learning_rate": 2.4113546384444593e-05, "loss": 3.9051, "step": 1581056 }, { "epoch": 0.02, "learning_rate": 2.4105160436934073e-05, "loss": 3.9119, "step": 1581568 }, { "epoch": 0.02, "learning_rate": 2.409677448942355e-05, "loss": 3.8873, "step": 1582080 }, { "epoch": 0.02, "learning_rate": 2.4088388541913033e-05, "loss": 3.9053, "step": 1582592 }, { "epoch": 0.02, "learning_rate": 2.4080002594402513e-05, "loss": 3.8982, "step": 1583104 }, { "epoch": 0.02, "learning_rate": 2.4071616646891993e-05, "loss": 3.9034, "step": 1583616 }, { "epoch": 0.02, "learning_rate": 2.4063230699381473e-05, "loss": 3.9053, "step": 1584128 }, { "epoch": 0.02, "learning_rate": 2.4054844751870953e-05, "loss": 3.8973, "step": 1584640 }, { "epoch": 0.02, "learning_rate": 2.4046475183164162e-05, "loss": 3.9078, "step": 1585152 }, { "epoch": 0.02, "learning_rate": 2.4038089235653642e-05, "loss": 3.9104, "step": 1585664 }, { "epoch": 0.02, "learning_rate": 2.4029719666946855e-05, "loss": 3.8984, "step": 1586176 }, { "epoch": 0.02, "learning_rate": 2.4021333719436335e-05, "loss": 3.9075, "step": 1586688 }, { "epoch": 0.02, "learning_rate": 2.4012947771925814e-05, "loss": 3.899, "step": 1587200 }, { "epoch": 0.02, "learning_rate": 2.4004561824415294e-05, "loss": 3.9086, "step": 1587712 }, { "epoch": 0.02, "learning_rate": 2.3996175876904774e-05, "loss": 3.8899, "step": 1588224 }, { "epoch": 0.02, "learning_rate": 2.3987789929394254e-05, "loss": 3.9151, "step": 1588736 }, { "epoch": 0.02, "learning_rate": 2.3979403981883734e-05, "loss": 3.8931, "step": 1589248 }, { "epoch": 0.02, "learning_rate": 2.3971018034373214e-05, "loss": 3.9066, "step": 1589760 }, { "epoch": 0.02, "learning_rate": 2.3962632086862694e-05, "loss": 3.897, "step": 1590272 }, { "epoch": 0.02, "learning_rate": 2.3954262518155903e-05, "loss": 3.9122, "step": 1590784 }, { "epoch": 0.02, "learning_rate": 2.3945876570645383e-05, "loss": 3.902, "step": 1591296 }, { "epoch": 0.02, "learning_rate": 2.3937507001938596e-05, "loss": 3.8999, "step": 1591808 }, { "epoch": 0.02, "learning_rate": 2.392912105442808e-05, "loss": 3.8884, "step": 1592320 }, { "epoch": 0.02, "learning_rate": 2.3920735106917556e-05, "loss": 3.9188, "step": 1592832 }, { "epoch": 0.02, "learning_rate": 2.3912349159407036e-05, "loss": 3.9038, "step": 1593344 }, { "epoch": 0.02, "learning_rate": 2.3903963211896516e-05, "loss": 3.9074, "step": 1593856 }, { "epoch": 0.02, "learning_rate": 2.3895593643189725e-05, "loss": 3.896, "step": 1594368 }, { "epoch": 0.02, "learning_rate": 2.3887207695679205e-05, "loss": 3.9104, "step": 1594880 }, { "epoch": 0.02, "learning_rate": 2.3878821748168688e-05, "loss": 3.9144, "step": 1595392 }, { "epoch": 0.02, "learning_rate": 2.3870435800658168e-05, "loss": 3.8987, "step": 1595904 }, { "epoch": 0.02, "learning_rate": 2.3862049853147648e-05, "loss": 3.9003, "step": 1596416 }, { "epoch": 0.02, "learning_rate": 2.3853663905637128e-05, "loss": 3.9087, "step": 1596928 }, { "epoch": 0.02, "learning_rate": 2.3845277958126608e-05, "loss": 3.9106, "step": 1597440 }, { "epoch": 0.02, "learning_rate": 2.3836892010616084e-05, "loss": 3.9131, "step": 1597952 }, { "epoch": 0.02, "learning_rate": 2.3828522441909297e-05, "loss": 3.8943, "step": 1598464 }, { "epoch": 0.02, "learning_rate": 2.382013649439878e-05, "loss": 3.9063, "step": 1598976 }, { "epoch": 0.02, "learning_rate": 2.381175054688826e-05, "loss": 3.9023, "step": 1599488 }, { "epoch": 0.02, "learning_rate": 2.3803364599377737e-05, "loss": 3.9051, "step": 1600000 }, { "epoch": 0.02, "learning_rate": 2.379499503067095e-05, "loss": 3.9117, "step": 1600512 }, { "epoch": 0.02, "learning_rate": 2.378660908316043e-05, "loss": 3.9, "step": 1601024 }, { "epoch": 0.02, "learning_rate": 2.377823951445364e-05, "loss": 3.9118, "step": 1601536 }, { "epoch": 0.02, "learning_rate": 2.376985356694312e-05, "loss": 3.899, "step": 1602048 }, { "epoch": 0.02, "learning_rate": 2.37614676194326e-05, "loss": 3.9114, "step": 1602560 }, { "epoch": 0.03, "eval_loss": 4.047024726867676, "eval_runtime": 295.9784, "eval_samples_per_second": 1289.253, "eval_steps_per_second": 40.29, "step": 1602720 }, { "epoch": 1.0, "learning_rate": 2.375308167192208e-05, "loss": 3.8997, "step": 1603072 }, { "epoch": 1.0, "learning_rate": 2.3744695724411558e-05, "loss": 3.9105, "step": 1603584 }, { "epoch": 1.0, "learning_rate": 2.3736309776901038e-05, "loss": 3.9103, "step": 1604096 }, { "epoch": 1.0, "learning_rate": 2.3727923829390518e-05, "loss": 3.9064, "step": 1604608 }, { "epoch": 1.0, "learning_rate": 2.3719537881879998e-05, "loss": 3.9149, "step": 1605120 }, { "epoch": 1.0, "learning_rate": 2.371116831317321e-05, "loss": 3.9006, "step": 1605632 }, { "epoch": 1.0, "learning_rate": 2.370278236566269e-05, "loss": 3.8986, "step": 1606144 }, { "epoch": 1.0, "learning_rate": 2.369439641815217e-05, "loss": 3.896, "step": 1606656 }, { "epoch": 1.0, "learning_rate": 2.368602684944538e-05, "loss": 3.9125, "step": 1607168 }, { "epoch": 1.0, "learning_rate": 2.367764090193486e-05, "loss": 3.912, "step": 1607680 }, { "epoch": 1.0, "learning_rate": 2.3669254954424343e-05, "loss": 3.9042, "step": 1608192 }, { "epoch": 1.0, "learning_rate": 2.3660869006913823e-05, "loss": 3.9075, "step": 1608704 }, { "epoch": 1.0, "learning_rate": 2.3652499438207032e-05, "loss": 3.901, "step": 1609216 }, { "epoch": 1.0, "learning_rate": 2.3644113490696512e-05, "loss": 3.896, "step": 1609728 }, { "epoch": 1.0, "learning_rate": 2.3635727543185992e-05, "loss": 3.8988, "step": 1610240 }, { "epoch": 1.0, "learning_rate": 2.362734159567547e-05, "loss": 3.8895, "step": 1610752 }, { "epoch": 1.0, "learning_rate": 2.361895564816495e-05, "loss": 3.9019, "step": 1611264 }, { "epoch": 1.0, "learning_rate": 2.3610569700654435e-05, "loss": 3.8953, "step": 1611776 }, { "epoch": 1.0, "learning_rate": 2.3602183753143915e-05, "loss": 3.8964, "step": 1612288 }, { "epoch": 1.0, "learning_rate": 2.359379780563339e-05, "loss": 3.9315, "step": 1612800 }, { "epoch": 1.0, "learning_rate": 2.358541185812287e-05, "loss": 3.8981, "step": 1613312 }, { "epoch": 1.0, "learning_rate": 2.357702591061235e-05, "loss": 3.9054, "step": 1613824 }, { "epoch": 1.0, "learning_rate": 2.356863996310183e-05, "loss": 3.9079, "step": 1614336 }, { "epoch": 1.0, "learning_rate": 2.356025401559131e-05, "loss": 3.9064, "step": 1614848 }, { "epoch": 1.0, "learning_rate": 2.3551884446884524e-05, "loss": 3.8979, "step": 1615360 }, { "epoch": 1.0, "learning_rate": 2.3543498499374004e-05, "loss": 3.8945, "step": 1615872 }, { "epoch": 1.0, "learning_rate": 2.3535112551863484e-05, "loss": 3.9065, "step": 1616384 }, { "epoch": 1.0, "learning_rate": 2.3526726604352964e-05, "loss": 3.8877, "step": 1616896 }, { "epoch": 1.0, "learning_rate": 2.3518340656842444e-05, "loss": 3.8986, "step": 1617408 }, { "epoch": 1.0, "learning_rate": 2.3509971088135656e-05, "loss": 3.8944, "step": 1617920 }, { "epoch": 1.01, "learning_rate": 2.3501585140625136e-05, "loss": 3.9004, "step": 1618432 }, { "epoch": 1.01, "learning_rate": 2.3493199193114616e-05, "loss": 3.9071, "step": 1618944 }, { "epoch": 1.01, "learning_rate": 2.3484813245604096e-05, "loss": 3.9054, "step": 1619456 }, { "epoch": 1.01, "learning_rate": 2.3476427298093573e-05, "loss": 3.9006, "step": 1619968 }, { "epoch": 1.01, "learning_rate": 2.3468057729386785e-05, "loss": 3.9067, "step": 1620480 }, { "epoch": 1.01, "learning_rate": 2.3459671781876265e-05, "loss": 3.9075, "step": 1620992 }, { "epoch": 1.01, "learning_rate": 2.3451285834365745e-05, "loss": 3.8942, "step": 1621504 }, { "epoch": 1.01, "learning_rate": 2.3442899886855225e-05, "loss": 3.9078, "step": 1622016 }, { "epoch": 1.01, "learning_rate": 2.3434513939344705e-05, "loss": 3.8907, "step": 1622528 }, { "epoch": 1.01, "learning_rate": 2.3426127991834185e-05, "loss": 3.9089, "step": 1623040 }, { "epoch": 1.01, "learning_rate": 2.3417774801931126e-05, "loss": 3.8863, "step": 1623552 }, { "epoch": 1.01, "learning_rate": 2.3409388854420606e-05, "loss": 3.9188, "step": 1624064 }, { "epoch": 1.01, "learning_rate": 2.340100290691009e-05, "loss": 3.9034, "step": 1624576 }, { "epoch": 1.01, "learning_rate": 2.339261695939957e-05, "loss": 3.9014, "step": 1625088 }, { "epoch": 1.01, "learning_rate": 2.3384231011889046e-05, "loss": 3.9063, "step": 1625600 }, { "epoch": 1.01, "learning_rate": 2.3375845064378526e-05, "loss": 3.9026, "step": 1626112 }, { "epoch": 1.01, "learning_rate": 2.3367459116868006e-05, "loss": 3.9037, "step": 1626624 }, { "epoch": 1.01, "learning_rate": 2.3359073169357486e-05, "loss": 3.8907, "step": 1627136 }, { "epoch": 1.01, "learning_rate": 2.3350687221846966e-05, "loss": 3.8866, "step": 1627648 }, { "epoch": 1.01, "learning_rate": 2.334230127433645e-05, "loss": 3.9177, "step": 1628160 }, { "epoch": 1.01, "learning_rate": 2.3333915326825926e-05, "loss": 3.9004, "step": 1628672 }, { "epoch": 1.01, "learning_rate": 2.332554575811914e-05, "loss": 3.9086, "step": 1629184 }, { "epoch": 1.01, "learning_rate": 2.331715981060862e-05, "loss": 3.896, "step": 1629696 }, { "epoch": 1.01, "learning_rate": 2.33087738630981e-05, "loss": 3.9002, "step": 1630208 }, { "epoch": 1.01, "learning_rate": 2.3300387915587575e-05, "loss": 3.8925, "step": 1630720 }, { "epoch": 1.01, "learning_rate": 2.3292001968077058e-05, "loss": 3.9044, "step": 1631232 }, { "epoch": 1.01, "learning_rate": 2.328363239937027e-05, "loss": 3.8976, "step": 1631744 }, { "epoch": 1.01, "learning_rate": 2.3275246451859747e-05, "loss": 3.9138, "step": 1632256 }, { "epoch": 1.01, "learning_rate": 2.326687688315296e-05, "loss": 3.9098, "step": 1632768 }, { "epoch": 1.01, "learning_rate": 2.325849093564244e-05, "loss": 3.8945, "step": 1633280 }, { "epoch": 1.01, "learning_rate": 2.325010498813192e-05, "loss": 3.8975, "step": 1633792 }, { "epoch": 1.01, "learning_rate": 2.32417190406214e-05, "loss": 3.9064, "step": 1634304 }, { "epoch": 1.01, "learning_rate": 2.323333309311088e-05, "loss": 3.8894, "step": 1634816 }, { "epoch": 1.01, "learning_rate": 2.322494714560036e-05, "loss": 3.8964, "step": 1635328 }, { "epoch": 1.01, "learning_rate": 2.321656119808984e-05, "loss": 3.9017, "step": 1635840 }, { "epoch": 1.01, "learning_rate": 2.320817525057932e-05, "loss": 3.9042, "step": 1636352 }, { "epoch": 1.01, "learning_rate": 2.319980568187253e-05, "loss": 3.8847, "step": 1636864 }, { "epoch": 1.01, "learning_rate": 2.3191419734362012e-05, "loss": 3.8925, "step": 1637376 }, { "epoch": 1.01, "learning_rate": 2.3183033786851492e-05, "loss": 3.8859, "step": 1637888 }, { "epoch": 1.01, "learning_rate": 2.3174647839340972e-05, "loss": 3.9093, "step": 1638400 }, { "epoch": 1.01, "learning_rate": 2.3166261891830452e-05, "loss": 3.9041, "step": 1638912 }, { "epoch": 1.01, "learning_rate": 2.315787594431993e-05, "loss": 3.9008, "step": 1639424 }, { "epoch": 1.01, "learning_rate": 2.314948999680941e-05, "loss": 3.9069, "step": 1639936 }, { "epoch": 1.01, "learning_rate": 2.3141104049298888e-05, "loss": 3.8946, "step": 1640448 }, { "epoch": 1.01, "learning_rate": 2.3132734480592104e-05, "loss": 3.9158, "step": 1640960 }, { "epoch": 1.01, "learning_rate": 2.312434853308158e-05, "loss": 3.8893, "step": 1641472 }, { "epoch": 1.01, "learning_rate": 2.311596258557106e-05, "loss": 3.9085, "step": 1641984 }, { "epoch": 1.01, "learning_rate": 2.310757663806054e-05, "loss": 3.9036, "step": 1642496 }, { "epoch": 1.01, "learning_rate": 2.309919069055002e-05, "loss": 3.9025, "step": 1643008 }, { "epoch": 1.01, "learning_rate": 2.309082112184323e-05, "loss": 3.9056, "step": 1643520 }, { "epoch": 1.01, "learning_rate": 2.3082451553136446e-05, "loss": 3.9001, "step": 1644032 }, { "epoch": 1.01, "learning_rate": 2.3074065605625926e-05, "loss": 3.9031, "step": 1644544 }, { "epoch": 1.01, "learning_rate": 2.3065679658115402e-05, "loss": 3.9068, "step": 1645056 }, { "epoch": 1.01, "learning_rate": 2.3057293710604882e-05, "loss": 3.8885, "step": 1645568 }, { "epoch": 1.01, "learning_rate": 2.3048907763094362e-05, "loss": 3.9058, "step": 1646080 }, { "epoch": 1.01, "learning_rate": 2.3040521815583842e-05, "loss": 3.895, "step": 1646592 }, { "epoch": 1.01, "learning_rate": 2.3032152246877054e-05, "loss": 3.9072, "step": 1647104 }, { "epoch": 1.01, "learning_rate": 2.3023766299366534e-05, "loss": 3.8955, "step": 1647616 }, { "epoch": 1.01, "learning_rate": 2.3015380351856014e-05, "loss": 3.8912, "step": 1648128 }, { "epoch": 1.02, "learning_rate": 2.3006994404345494e-05, "loss": 3.9012, "step": 1648640 }, { "epoch": 1.02, "learning_rate": 2.2998608456834974e-05, "loss": 3.9003, "step": 1649152 }, { "epoch": 1.02, "learning_rate": 2.2990222509324454e-05, "loss": 3.9021, "step": 1649664 }, { "epoch": 1.02, "learning_rate": 2.2981836561813934e-05, "loss": 3.8871, "step": 1650176 }, { "epoch": 1.02, "learning_rate": 2.2973450614303414e-05, "loss": 3.9064, "step": 1650688 }, { "epoch": 1.02, "learning_rate": 2.2965081045596627e-05, "loss": 3.9134, "step": 1651200 }, { "epoch": 1.02, "learning_rate": 2.2956711476889836e-05, "loss": 3.8997, "step": 1651712 }, { "epoch": 1.02, "learning_rate": 2.2948325529379316e-05, "loss": 3.8801, "step": 1652224 }, { "epoch": 1.02, "learning_rate": 2.2939939581868796e-05, "loss": 3.8997, "step": 1652736 }, { "epoch": 1.02, "learning_rate": 2.2931553634358276e-05, "loss": 3.9008, "step": 1653248 }, { "epoch": 1.02, "learning_rate": 2.292316768684776e-05, "loss": 3.9041, "step": 1653760 }, { "epoch": 1.02, "learning_rate": 2.2914781739337235e-05, "loss": 3.9034, "step": 1654272 }, { "epoch": 1.02, "learning_rate": 2.2906412170630448e-05, "loss": 3.8969, "step": 1654784 }, { "epoch": 1.02, "learning_rate": 2.2898026223119928e-05, "loss": 3.8936, "step": 1655296 }, { "epoch": 1.02, "learning_rate": 2.2889656654413137e-05, "loss": 3.9042, "step": 1655808 }, { "epoch": 1.02, "learning_rate": 2.288127070690262e-05, "loss": 3.883, "step": 1656320 }, { "epoch": 1.02, "learning_rate": 2.28728847593921e-05, "loss": 3.8983, "step": 1656832 }, { "epoch": 1.02, "learning_rate": 2.286449881188158e-05, "loss": 3.8948, "step": 1657344 }, { "epoch": 1.02, "learning_rate": 2.2856112864371057e-05, "loss": 3.9059, "step": 1657856 }, { "epoch": 1.02, "learning_rate": 2.2847726916860537e-05, "loss": 3.8834, "step": 1658368 }, { "epoch": 1.02, "learning_rate": 2.2839340969350017e-05, "loss": 3.8941, "step": 1658880 }, { "epoch": 1.02, "learning_rate": 2.2830955021839497e-05, "loss": 3.895, "step": 1659392 }, { "epoch": 1.02, "learning_rate": 2.2822569074328977e-05, "loss": 3.8957, "step": 1659904 }, { "epoch": 1.02, "learning_rate": 2.281418312681846e-05, "loss": 3.9003, "step": 1660416 }, { "epoch": 1.02, "learning_rate": 2.280579717930794e-05, "loss": 3.8889, "step": 1660928 }, { "epoch": 1.02, "learning_rate": 2.279742761060115e-05, "loss": 3.9045, "step": 1661440 }, { "epoch": 1.02, "learning_rate": 2.278904166309063e-05, "loss": 3.9019, "step": 1661952 }, { "epoch": 1.02, "learning_rate": 2.2780672094383838e-05, "loss": 3.8916, "step": 1662464 }, { "epoch": 1.02, "learning_rate": 2.277228614687332e-05, "loss": 3.9033, "step": 1662976 }, { "epoch": 1.02, "learning_rate": 2.27639001993628e-05, "loss": 3.8911, "step": 1663488 }, { "epoch": 1.02, "learning_rate": 2.275551425185228e-05, "loss": 3.9041, "step": 1664000 }, { "epoch": 1.02, "learning_rate": 2.274712830434176e-05, "loss": 3.8897, "step": 1664512 }, { "epoch": 1.02, "learning_rate": 2.2738742356831238e-05, "loss": 3.9024, "step": 1665024 }, { "epoch": 1.02, "learning_rate": 2.2730356409320718e-05, "loss": 3.8875, "step": 1665536 }, { "epoch": 1.02, "learning_rate": 2.2721970461810198e-05, "loss": 3.9007, "step": 1666048 }, { "epoch": 1.02, "learning_rate": 2.271358451429968e-05, "loss": 3.8923, "step": 1666560 }, { "epoch": 1.02, "learning_rate": 2.270519856678916e-05, "loss": 3.9033, "step": 1667072 }, { "epoch": 1.02, "learning_rate": 2.269681261927864e-05, "loss": 3.8925, "step": 1667584 }, { "epoch": 1.02, "learning_rate": 2.268844305057185e-05, "loss": 3.899, "step": 1668096 }, { "epoch": 1.02, "learning_rate": 2.268005710306133e-05, "loss": 3.8782, "step": 1668608 }, { "epoch": 1.02, "learning_rate": 2.267167115555081e-05, "loss": 3.912, "step": 1669120 }, { "epoch": 1.02, "learning_rate": 2.266328520804029e-05, "loss": 3.8939, "step": 1669632 }, { "epoch": 1.02, "learning_rate": 2.265489926052977e-05, "loss": 3.9031, "step": 1670144 }, { "epoch": 1.02, "learning_rate": 2.264654607062671e-05, "loss": 3.8896, "step": 1670656 }, { "epoch": 1.02, "learning_rate": 2.263816012311619e-05, "loss": 3.9046, "step": 1671168 }, { "epoch": 1.02, "learning_rate": 2.262977417560567e-05, "loss": 3.9054, "step": 1671680 }, { "epoch": 1.02, "learning_rate": 2.262138822809515e-05, "loss": 3.8927, "step": 1672192 }, { "epoch": 1.02, "learning_rate": 2.261300228058463e-05, "loss": 3.8971, "step": 1672704 }, { "epoch": 1.02, "learning_rate": 2.2604616333074115e-05, "loss": 3.9033, "step": 1673216 }, { "epoch": 1.02, "learning_rate": 2.2596230385563595e-05, "loss": 3.9021, "step": 1673728 }, { "epoch": 1.02, "learning_rate": 2.2587860816856804e-05, "loss": 3.9138, "step": 1674240 }, { "epoch": 1.02, "learning_rate": 2.2579474869346284e-05, "loss": 3.8828, "step": 1674752 }, { "epoch": 1.02, "learning_rate": 2.2571088921835764e-05, "loss": 3.9046, "step": 1675264 }, { "epoch": 1.02, "learning_rate": 2.2562702974325244e-05, "loss": 3.8926, "step": 1675776 }, { "epoch": 1.02, "learning_rate": 2.2554317026814724e-05, "loss": 3.9017, "step": 1676288 }, { "epoch": 1.02, "learning_rate": 2.2545931079304204e-05, "loss": 3.9006, "step": 1676800 }, { "epoch": 1.02, "learning_rate": 2.2537561510597416e-05, "loss": 3.8913, "step": 1677312 }, { "epoch": 1.02, "learning_rate": 2.2529175563086893e-05, "loss": 3.9074, "step": 1677824 }, { "epoch": 1.02, "learning_rate": 2.2520789615576373e-05, "loss": 3.8974, "step": 1678336 }, { "epoch": 1.02, "learning_rate": 2.2512403668065853e-05, "loss": 3.9006, "step": 1678848 }, { "epoch": 1.03, "eval_loss": 4.045112609863281, "eval_runtime": 295.5114, "eval_samples_per_second": 1291.29, "eval_steps_per_second": 40.354, "step": 1679040 }, { "epoch": 2.0, "learning_rate": 2.2504017720555336e-05, "loss": 3.8939, "step": 1679360 }, { "epoch": 2.0, "learning_rate": 2.2495631773044816e-05, "loss": 3.8975, "step": 1679872 }, { "epoch": 2.0, "learning_rate": 2.2487245825534296e-05, "loss": 3.904, "step": 1680384 }, { "epoch": 2.0, "learning_rate": 2.2478859878023776e-05, "loss": 3.9026, "step": 1680896 }, { "epoch": 2.0, "learning_rate": 2.2470473930513252e-05, "loss": 3.9073, "step": 1681408 }, { "epoch": 2.0, "learning_rate": 2.2462087983002732e-05, "loss": 3.8979, "step": 1681920 }, { "epoch": 2.0, "learning_rate": 2.2453718414295945e-05, "loss": 3.8888, "step": 1682432 }, { "epoch": 2.0, "learning_rate": 2.2445332466785425e-05, "loss": 3.8934, "step": 1682944 }, { "epoch": 2.0, "learning_rate": 2.2436946519274905e-05, "loss": 3.9008, "step": 1683456 }, { "epoch": 2.0, "learning_rate": 2.2428560571764385e-05, "loss": 3.906, "step": 1683968 }, { "epoch": 2.0, "learning_rate": 2.2420174624253865e-05, "loss": 3.8985, "step": 1684480 }, { "epoch": 2.0, "learning_rate": 2.2411805055547074e-05, "loss": 3.9023, "step": 1684992 }, { "epoch": 2.0, "learning_rate": 2.240343548684029e-05, "loss": 3.8895, "step": 1685504 }, { "epoch": 2.0, "learning_rate": 2.239504953932977e-05, "loss": 3.8929, "step": 1686016 }, { "epoch": 2.0, "learning_rate": 2.238666359181925e-05, "loss": 3.8948, "step": 1686528 }, { "epoch": 2.0, "learning_rate": 2.2378277644308726e-05, "loss": 3.8826, "step": 1687040 }, { "epoch": 2.0, "learning_rate": 2.2369891696798206e-05, "loss": 3.8989, "step": 1687552 }, { "epoch": 2.0, "learning_rate": 2.2361505749287686e-05, "loss": 3.8858, "step": 1688064 }, { "epoch": 2.0, "learning_rate": 2.2353119801777166e-05, "loss": 3.8892, "step": 1688576 }, { "epoch": 2.0, "learning_rate": 2.2344733854266646e-05, "loss": 3.9262, "step": 1689088 }, { "epoch": 2.0, "learning_rate": 2.233634790675613e-05, "loss": 3.8937, "step": 1689600 }, { "epoch": 2.0, "learning_rate": 2.232797833804934e-05, "loss": 3.8972, "step": 1690112 }, { "epoch": 2.0, "learning_rate": 2.2319592390538818e-05, "loss": 3.901, "step": 1690624 }, { "epoch": 2.0, "learning_rate": 2.2311206443028298e-05, "loss": 3.9053, "step": 1691136 }, { "epoch": 2.0, "learning_rate": 2.2302820495517778e-05, "loss": 3.8827, "step": 1691648 }, { "epoch": 2.0, "learning_rate": 2.229445092681099e-05, "loss": 3.8921, "step": 1692160 }, { "epoch": 2.0, "learning_rate": 2.228606497930047e-05, "loss": 3.896, "step": 1692672 }, { "epoch": 2.0, "learning_rate": 2.227769541059368e-05, "loss": 3.8888, "step": 1693184 }, { "epoch": 2.0, "learning_rate": 2.226930946308316e-05, "loss": 3.8911, "step": 1693696 }, { "epoch": 2.0, "learning_rate": 2.226092351557264e-05, "loss": 3.8864, "step": 1694208 }, { "epoch": 2.01, "learning_rate": 2.225253756806212e-05, "loss": 3.8952, "step": 1694720 }, { "epoch": 2.01, "learning_rate": 2.22441516205516e-05, "loss": 3.9016, "step": 1695232 }, { "epoch": 2.01, "learning_rate": 2.223576567304108e-05, "loss": 3.897, "step": 1695744 }, { "epoch": 2.01, "learning_rate": 2.222737972553056e-05, "loss": 3.8941, "step": 1696256 }, { "epoch": 2.01, "learning_rate": 2.2219010156823772e-05, "loss": 3.8988, "step": 1696768 }, { "epoch": 2.01, "learning_rate": 2.2210624209313252e-05, "loss": 3.9015, "step": 1697280 }, { "epoch": 2.01, "learning_rate": 2.220223826180273e-05, "loss": 3.8875, "step": 1697792 }, { "epoch": 2.01, "learning_rate": 2.219385231429221e-05, "loss": 3.9061, "step": 1698304 }, { "epoch": 2.01, "learning_rate": 2.2185466366781692e-05, "loss": 3.8838, "step": 1698816 }, { "epoch": 2.01, "learning_rate": 2.2177080419271172e-05, "loss": 3.9013, "step": 1699328 }, { "epoch": 2.01, "learning_rate": 2.216869447176065e-05, "loss": 3.8797, "step": 1699840 }, { "epoch": 2.01, "learning_rate": 2.216032490305386e-05, "loss": 3.912, "step": 1700352 }, { "epoch": 2.01, "learning_rate": 2.2151955334347073e-05, "loss": 3.8957, "step": 1700864 }, { "epoch": 2.01, "learning_rate": 2.2143569386836553e-05, "loss": 3.8993, "step": 1701376 }, { "epoch": 2.01, "learning_rate": 2.2135183439326033e-05, "loss": 3.8981, "step": 1701888 }, { "epoch": 2.01, "learning_rate": 2.2126797491815513e-05, "loss": 3.8963, "step": 1702400 }, { "epoch": 2.01, "learning_rate": 2.2118411544304993e-05, "loss": 3.9013, "step": 1702912 }, { "epoch": 2.01, "learning_rate": 2.2110025596794473e-05, "loss": 3.8865, "step": 1703424 }, { "epoch": 2.01, "learning_rate": 2.2101639649283953e-05, "loss": 3.8754, "step": 1703936 }, { "epoch": 2.01, "learning_rate": 2.2093270080577162e-05, "loss": 3.9135, "step": 1704448 }, { "epoch": 2.01, "learning_rate": 2.2084884133066645e-05, "loss": 3.8929, "step": 1704960 }, { "epoch": 2.01, "learning_rate": 2.2076498185556125e-05, "loss": 3.9046, "step": 1705472 }, { "epoch": 2.01, "learning_rate": 2.2068112238045605e-05, "loss": 3.8881, "step": 1705984 }, { "epoch": 2.01, "learning_rate": 2.2059726290535082e-05, "loss": 3.8921, "step": 1706496 }, { "epoch": 2.01, "learning_rate": 2.2051340343024562e-05, "loss": 3.8848, "step": 1707008 }, { "epoch": 2.01, "learning_rate": 2.2042954395514042e-05, "loss": 3.9001, "step": 1707520 }, { "epoch": 2.01, "learning_rate": 2.2034568448003522e-05, "loss": 3.8971, "step": 1708032 }, { "epoch": 2.01, "learning_rate": 2.2026198879296734e-05, "loss": 3.9024, "step": 1708544 }, { "epoch": 2.01, "learning_rate": 2.2017812931786214e-05, "loss": 3.9045, "step": 1709056 }, { "epoch": 2.01, "learning_rate": 2.2009426984275694e-05, "loss": 3.8862, "step": 1709568 }, { "epoch": 2.01, "learning_rate": 2.2001041036765174e-05, "loss": 3.8889, "step": 1710080 }, { "epoch": 2.01, "learning_rate": 2.1992655089254654e-05, "loss": 3.9056, "step": 1710592 }, { "epoch": 2.01, "learning_rate": 2.1984269141744134e-05, "loss": 3.8811, "step": 1711104 }, { "epoch": 2.01, "learning_rate": 2.1975899573037347e-05, "loss": 3.891, "step": 1711616 }, { "epoch": 2.01, "learning_rate": 2.1967513625526826e-05, "loss": 3.8965, "step": 1712128 }, { "epoch": 2.01, "learning_rate": 2.1959127678016306e-05, "loss": 3.904, "step": 1712640 }, { "epoch": 2.01, "learning_rate": 2.1950741730505786e-05, "loss": 3.8776, "step": 1713152 }, { "epoch": 2.01, "learning_rate": 2.1942355782995263e-05, "loss": 3.8846, "step": 1713664 }, { "epoch": 2.01, "learning_rate": 2.1933969835484743e-05, "loss": 3.8862, "step": 1714176 }, { "epoch": 2.01, "learning_rate": 2.1925583887974223e-05, "loss": 3.8928, "step": 1714688 }, { "epoch": 2.01, "learning_rate": 2.191721431926744e-05, "loss": 3.9017, "step": 1715200 }, { "epoch": 2.01, "learning_rate": 2.1908828371756915e-05, "loss": 3.8959, "step": 1715712 }, { "epoch": 2.01, "learning_rate": 2.1900442424246395e-05, "loss": 3.8999, "step": 1716224 }, { "epoch": 2.01, "learning_rate": 2.1892056476735875e-05, "loss": 3.8876, "step": 1716736 }, { "epoch": 2.01, "learning_rate": 2.1883670529225355e-05, "loss": 3.912, "step": 1717248 }, { "epoch": 2.01, "learning_rate": 2.1875284581714835e-05, "loss": 3.8836, "step": 1717760 }, { "epoch": 2.01, "learning_rate": 2.1866915013008048e-05, "loss": 3.9005, "step": 1718272 }, { "epoch": 2.01, "learning_rate": 2.1858529065497528e-05, "loss": 3.8972, "step": 1718784 }, { "epoch": 2.01, "learning_rate": 2.1850143117987008e-05, "loss": 3.8954, "step": 1719296 }, { "epoch": 2.01, "learning_rate": 2.1841757170476487e-05, "loss": 3.9006, "step": 1719808 }, { "epoch": 2.01, "learning_rate": 2.1833371222965967e-05, "loss": 3.8956, "step": 1720320 }, { "epoch": 2.01, "learning_rate": 2.1824985275455444e-05, "loss": 3.8916, "step": 1720832 }, { "epoch": 2.01, "learning_rate": 2.1816599327944924e-05, "loss": 3.9028, "step": 1721344 }, { "epoch": 2.01, "learning_rate": 2.180822975923814e-05, "loss": 3.8854, "step": 1721856 }, { "epoch": 2.01, "learning_rate": 2.179984381172762e-05, "loss": 3.8964, "step": 1722368 }, { "epoch": 2.01, "learning_rate": 2.1791457864217096e-05, "loss": 3.8917, "step": 1722880 }, { "epoch": 2.01, "learning_rate": 2.1783071916706576e-05, "loss": 3.9028, "step": 1723392 }, { "epoch": 2.01, "learning_rate": 2.177470234799979e-05, "loss": 3.8907, "step": 1723904 }, { "epoch": 2.01, "learning_rate": 2.176631640048927e-05, "loss": 3.8861, "step": 1724416 }, { "epoch": 2.02, "learning_rate": 2.175793045297875e-05, "loss": 3.8934, "step": 1724928 }, { "epoch": 2.02, "learning_rate": 2.174954450546823e-05, "loss": 3.8956, "step": 1725440 }, { "epoch": 2.02, "learning_rate": 2.174117493676144e-05, "loss": 3.8971, "step": 1725952 }, { "epoch": 2.02, "learning_rate": 2.1732788989250918e-05, "loss": 3.8821, "step": 1726464 }, { "epoch": 2.02, "learning_rate": 2.1724403041740398e-05, "loss": 3.8998, "step": 1726976 }, { "epoch": 2.02, "learning_rate": 2.171603347303361e-05, "loss": 3.9051, "step": 1727488 }, { "epoch": 2.02, "learning_rate": 2.1707647525523093e-05, "loss": 3.8946, "step": 1728000 }, { "epoch": 2.02, "learning_rate": 2.169926157801257e-05, "loss": 3.8736, "step": 1728512 }, { "epoch": 2.02, "learning_rate": 2.169087563050205e-05, "loss": 3.8928, "step": 1729024 }, { "epoch": 2.02, "learning_rate": 2.1682506061795263e-05, "loss": 3.8892, "step": 1729536 }, { "epoch": 2.02, "learning_rate": 2.1674120114284742e-05, "loss": 3.9016, "step": 1730048 }, { "epoch": 2.02, "learning_rate": 2.1665734166774222e-05, "loss": 3.8992, "step": 1730560 }, { "epoch": 2.02, "learning_rate": 2.1657348219263702e-05, "loss": 3.8881, "step": 1731072 }, { "epoch": 2.02, "learning_rate": 2.1648962271753182e-05, "loss": 3.8879, "step": 1731584 }, { "epoch": 2.02, "learning_rate": 2.1640576324242662e-05, "loss": 3.8993, "step": 1732096 }, { "epoch": 2.02, "learning_rate": 2.1632190376732142e-05, "loss": 3.8782, "step": 1732608 }, { "epoch": 2.02, "learning_rate": 2.1623804429221622e-05, "loss": 3.8935, "step": 1733120 }, { "epoch": 2.02, "learning_rate": 2.161543486051483e-05, "loss": 3.8845, "step": 1733632 }, { "epoch": 2.02, "learning_rate": 2.1607048913004315e-05, "loss": 3.9024, "step": 1734144 }, { "epoch": 2.02, "learning_rate": 2.1598662965493795e-05, "loss": 3.8773, "step": 1734656 }, { "epoch": 2.02, "learning_rate": 2.1590277017983275e-05, "loss": 3.8868, "step": 1735168 }, { "epoch": 2.02, "learning_rate": 2.158189107047275e-05, "loss": 3.8849, "step": 1735680 }, { "epoch": 2.02, "learning_rate": 2.157350512296223e-05, "loss": 3.8956, "step": 1736192 }, { "epoch": 2.02, "learning_rate": 2.156511917545171e-05, "loss": 3.8879, "step": 1736704 }, { "epoch": 2.02, "learning_rate": 2.155673322794119e-05, "loss": 3.8859, "step": 1737216 }, { "epoch": 2.02, "learning_rate": 2.1548363659234403e-05, "loss": 3.8928, "step": 1737728 }, { "epoch": 2.02, "learning_rate": 2.1539977711723883e-05, "loss": 3.8964, "step": 1738240 }, { "epoch": 2.02, "learning_rate": 2.1531591764213363e-05, "loss": 3.8847, "step": 1738752 }, { "epoch": 2.02, "learning_rate": 2.1523205816702843e-05, "loss": 3.9017, "step": 1739264 }, { "epoch": 2.02, "learning_rate": 2.1514819869192323e-05, "loss": 3.8853, "step": 1739776 }, { "epoch": 2.02, "learning_rate": 2.1506433921681803e-05, "loss": 3.8944, "step": 1740288 }, { "epoch": 2.02, "learning_rate": 2.149804797417128e-05, "loss": 3.8856, "step": 1740800 }, { "epoch": 2.02, "learning_rate": 2.1489678405464496e-05, "loss": 3.8933, "step": 1741312 }, { "epoch": 2.02, "learning_rate": 2.1481292457953976e-05, "loss": 3.8824, "step": 1741824 }, { "epoch": 2.02, "learning_rate": 2.1472906510443456e-05, "loss": 3.8925, "step": 1742336 }, { "epoch": 2.02, "learning_rate": 2.1464520562932932e-05, "loss": 3.894, "step": 1742848 }, { "epoch": 2.02, "learning_rate": 2.1456134615422412e-05, "loss": 3.8912, "step": 1743360 }, { "epoch": 2.02, "learning_rate": 2.1447748667911892e-05, "loss": 3.8847, "step": 1743872 }, { "epoch": 2.02, "learning_rate": 2.1439379099205105e-05, "loss": 3.8941, "step": 1744384 }, { "epoch": 2.02, "learning_rate": 2.1430993151694585e-05, "loss": 3.8745, "step": 1744896 }, { "epoch": 2.02, "learning_rate": 2.1422607204184064e-05, "loss": 3.9046, "step": 1745408 }, { "epoch": 2.02, "learning_rate": 2.1414221256673544e-05, "loss": 3.8904, "step": 1745920 }, { "epoch": 2.02, "learning_rate": 2.1405835309163024e-05, "loss": 3.8964, "step": 1746432 }, { "epoch": 2.02, "learning_rate": 2.1397449361652504e-05, "loss": 3.8854, "step": 1746944 }, { "epoch": 2.02, "learning_rate": 2.1389063414141984e-05, "loss": 3.9043, "step": 1747456 }, { "epoch": 2.02, "learning_rate": 2.1380677466631464e-05, "loss": 3.8921, "step": 1747968 }, { "epoch": 2.02, "learning_rate": 2.1372307897924677e-05, "loss": 3.8904, "step": 1748480 }, { "epoch": 2.02, "learning_rate": 2.1363921950414157e-05, "loss": 3.8908, "step": 1748992 }, { "epoch": 2.02, "learning_rate": 2.1355536002903637e-05, "loss": 3.895, "step": 1749504 }, { "epoch": 2.02, "learning_rate": 2.1347150055393113e-05, "loss": 3.8937, "step": 1750016 }, { "epoch": 2.02, "learning_rate": 2.1338780486686326e-05, "loss": 3.9064, "step": 1750528 }, { "epoch": 2.02, "learning_rate": 2.133039453917581e-05, "loss": 3.8792, "step": 1751040 }, { "epoch": 2.02, "learning_rate": 2.1322024970469018e-05, "loss": 3.8968, "step": 1751552 }, { "epoch": 2.02, "learning_rate": 2.1313639022958498e-05, "loss": 3.8885, "step": 1752064 }, { "epoch": 2.02, "learning_rate": 2.1305253075447978e-05, "loss": 3.8972, "step": 1752576 }, { "epoch": 2.02, "learning_rate": 2.1296867127937458e-05, "loss": 3.8913, "step": 1753088 }, { "epoch": 2.02, "learning_rate": 2.1288481180426938e-05, "loss": 3.8863, "step": 1753600 }, { "epoch": 2.02, "learning_rate": 2.1280095232916418e-05, "loss": 3.8995, "step": 1754112 }, { "epoch": 2.02, "learning_rate": 2.1271709285405898e-05, "loss": 3.8911, "step": 1754624 }, { "epoch": 2.02, "learning_rate": 2.1263323337895378e-05, "loss": 3.8935, "step": 1755136 }, { "epoch": 2.03, "eval_loss": 4.04240083694458, "eval_runtime": 294.3229, "eval_samples_per_second": 1296.505, "eval_steps_per_second": 40.517, "step": 1755360 }, { "epoch": 0.0, "learning_rate": 2.1254937390384858e-05, "loss": 3.8905, "step": 1755648 }, { "epoch": 0.0, "learning_rate": 2.1246551442874338e-05, "loss": 3.8893, "step": 1756160 }, { "epoch": 0.0, "learning_rate": 2.1238165495363818e-05, "loss": 3.8982, "step": 1756672 }, { "epoch": 0.0, "learning_rate": 2.1229779547853294e-05, "loss": 3.8979, "step": 1757184 }, { "epoch": 0.0, "learning_rate": 2.1221393600342778e-05, "loss": 3.9031, "step": 1757696 }, { "epoch": 0.0, "learning_rate": 2.1213007652832258e-05, "loss": 3.8888, "step": 1758208 }, { "epoch": 0.0, "learning_rate": 2.1204621705321738e-05, "loss": 3.8837, "step": 1758720 }, { "epoch": 0.0, "learning_rate": 2.1196235757811217e-05, "loss": 3.8829, "step": 1759232 }, { "epoch": 0.0, "learning_rate": 2.1187849810300697e-05, "loss": 3.8976, "step": 1759744 }, { "epoch": 0.0, "learning_rate": 2.1179463862790174e-05, "loss": 3.9023, "step": 1760256 }, { "epoch": 0.0, "learning_rate": 2.1171077915279654e-05, "loss": 3.887, "step": 1760768 }, { "epoch": 0.0, "learning_rate": 2.1162691967769134e-05, "loss": 3.8968, "step": 1761280 }, { "epoch": 0.0, "learning_rate": 2.115432239906235e-05, "loss": 3.8866, "step": 1761792 }, { "epoch": 0.0, "learning_rate": 2.1145936451551826e-05, "loss": 3.8867, "step": 1762304 }, { "epoch": 0.0, "learning_rate": 2.1137550504041306e-05, "loss": 3.886, "step": 1762816 }, { "epoch": 0.0, "learning_rate": 2.1129164556530786e-05, "loss": 3.8812, "step": 1763328 }, { "epoch": 0.0, "learning_rate": 2.1120778609020266e-05, "loss": 3.8876, "step": 1763840 }, { "epoch": 0.0, "learning_rate": 2.1112392661509746e-05, "loss": 3.8819, "step": 1764352 }, { "epoch": 0.0, "learning_rate": 2.1104006713999226e-05, "loss": 3.8817, "step": 1764864 }, { "epoch": 0.0, "learning_rate": 2.109562076648871e-05, "loss": 3.9164, "step": 1765376 }, { "epoch": 0.0, "learning_rate": 2.1087234818978186e-05, "loss": 3.8909, "step": 1765888 }, { "epoch": 0.0, "learning_rate": 2.1078848871467666e-05, "loss": 3.8894, "step": 1766400 }, { "epoch": 0.0, "learning_rate": 2.1070462923957146e-05, "loss": 3.8931, "step": 1766912 }, { "epoch": 0.0, "learning_rate": 2.1062076976446626e-05, "loss": 3.8974, "step": 1767424 }, { "epoch": 0.0, "learning_rate": 2.1053707407739835e-05, "loss": 3.8778, "step": 1767936 }, { "epoch": 0.0, "learning_rate": 2.104533783903305e-05, "loss": 3.8861, "step": 1768448 }, { "epoch": 0.0, "learning_rate": 2.103695189152253e-05, "loss": 3.8904, "step": 1768960 }, { "epoch": 0.0, "learning_rate": 2.1028565944012007e-05, "loss": 3.8843, "step": 1769472 }, { "epoch": 0.0, "learning_rate": 2.1020179996501487e-05, "loss": 3.8819, "step": 1769984 }, { "epoch": 0.0, "learning_rate": 2.1011794048990967e-05, "loss": 3.8823, "step": 1770496 }, { "epoch": 0.01, "learning_rate": 2.1003408101480447e-05, "loss": 3.8891, "step": 1771008 }, { "epoch": 0.01, "learning_rate": 2.099503853277366e-05, "loss": 3.8947, "step": 1771520 }, { "epoch": 0.01, "learning_rate": 2.098665258526314e-05, "loss": 3.8926, "step": 1772032 }, { "epoch": 0.01, "learning_rate": 2.097826663775262e-05, "loss": 3.885, "step": 1772544 }, { "epoch": 0.01, "learning_rate": 2.096989706904583e-05, "loss": 3.8931, "step": 1773056 }, { "epoch": 0.01, "learning_rate": 2.096151112153531e-05, "loss": 3.8938, "step": 1773568 }, { "epoch": 0.01, "learning_rate": 2.095312517402479e-05, "loss": 3.8874, "step": 1774080 }, { "epoch": 0.01, "learning_rate": 2.0944739226514272e-05, "loss": 3.8949, "step": 1774592 }, { "epoch": 0.01, "learning_rate": 2.0936353279003752e-05, "loss": 3.8803, "step": 1775104 }, { "epoch": 0.01, "learning_rate": 2.0927967331493232e-05, "loss": 3.8929, "step": 1775616 }, { "epoch": 0.01, "learning_rate": 2.0919581383982712e-05, "loss": 3.8775, "step": 1776128 }, { "epoch": 0.01, "learning_rate": 2.091119543647219e-05, "loss": 3.9039, "step": 1776640 }, { "epoch": 0.01, "learning_rate": 2.090280948896167e-05, "loss": 3.8918, "step": 1777152 }, { "epoch": 0.01, "learning_rate": 2.089442354145115e-05, "loss": 3.8906, "step": 1777664 }, { "epoch": 0.01, "learning_rate": 2.0886037593940628e-05, "loss": 3.8959, "step": 1778176 }, { "epoch": 0.01, "learning_rate": 2.087765164643011e-05, "loss": 3.8872, "step": 1778688 }, { "epoch": 0.01, "learning_rate": 2.086926569891959e-05, "loss": 3.8955, "step": 1779200 }, { "epoch": 0.01, "learning_rate": 2.08608961302128e-05, "loss": 3.8834, "step": 1779712 }, { "epoch": 0.01, "learning_rate": 2.085251018270228e-05, "loss": 3.8663, "step": 1780224 }, { "epoch": 0.01, "learning_rate": 2.0844140613995493e-05, "loss": 3.9073, "step": 1780736 }, { "epoch": 0.01, "learning_rate": 2.0835754666484973e-05, "loss": 3.8854, "step": 1781248 }, { "epoch": 0.01, "learning_rate": 2.0827385097778186e-05, "loss": 3.9007, "step": 1781760 }, { "epoch": 0.01, "learning_rate": 2.0818999150267662e-05, "loss": 3.8844, "step": 1782272 }, { "epoch": 0.01, "learning_rate": 2.0810613202757142e-05, "loss": 3.8872, "step": 1782784 }, { "epoch": 0.01, "learning_rate": 2.0802227255246622e-05, "loss": 3.8751, "step": 1783296 }, { "epoch": 0.01, "learning_rate": 2.0793841307736102e-05, "loss": 3.8942, "step": 1783808 }, { "epoch": 0.01, "learning_rate": 2.0785471739029314e-05, "loss": 3.8893, "step": 1784320 }, { "epoch": 0.01, "learning_rate": 2.0777085791518794e-05, "loss": 3.8944, "step": 1784832 }, { "epoch": 0.01, "learning_rate": 2.0768699844008274e-05, "loss": 3.9032, "step": 1785344 }, { "epoch": 0.01, "learning_rate": 2.0760313896497754e-05, "loss": 3.8812, "step": 1785856 }, { "epoch": 0.01, "learning_rate": 2.0751927948987234e-05, "loss": 3.8832, "step": 1786368 }, { "epoch": 0.01, "learning_rate": 2.0743542001476714e-05, "loss": 3.9008, "step": 1786880 }, { "epoch": 0.01, "learning_rate": 2.0735156053966194e-05, "loss": 3.8777, "step": 1787392 }, { "epoch": 0.01, "learning_rate": 2.0726770106455674e-05, "loss": 3.8808, "step": 1787904 }, { "epoch": 0.01, "learning_rate": 2.0718384158945154e-05, "loss": 3.8908, "step": 1788416 }, { "epoch": 0.01, "learning_rate": 2.0710030969042096e-05, "loss": 3.8959, "step": 1788928 }, { "epoch": 0.01, "learning_rate": 2.0701645021531576e-05, "loss": 3.876, "step": 1789440 }, { "epoch": 0.01, "learning_rate": 2.0693259074021056e-05, "loss": 3.8796, "step": 1789952 }, { "epoch": 0.01, "learning_rate": 2.0684873126510536e-05, "loss": 3.874, "step": 1790464 }, { "epoch": 0.01, "learning_rate": 2.0676487179000016e-05, "loss": 3.8886, "step": 1790976 }, { "epoch": 0.01, "learning_rate": 2.0668101231489496e-05, "loss": 3.8954, "step": 1791488 }, { "epoch": 0.01, "learning_rate": 2.0659715283978975e-05, "loss": 3.891, "step": 1792000 }, { "epoch": 0.01, "learning_rate": 2.0651329336468455e-05, "loss": 3.8867, "step": 1792512 }, { "epoch": 0.01, "learning_rate": 2.0642943388957935e-05, "loss": 3.8868, "step": 1793024 }, { "epoch": 0.01, "learning_rate": 2.0634557441447415e-05, "loss": 3.9049, "step": 1793536 }, { "epoch": 0.01, "learning_rate": 2.0626171493936895e-05, "loss": 3.876, "step": 1794048 }, { "epoch": 0.01, "learning_rate": 2.0617785546426375e-05, "loss": 3.8985, "step": 1794560 }, { "epoch": 0.01, "learning_rate": 2.0609415977719588e-05, "loss": 3.8887, "step": 1795072 }, { "epoch": 0.01, "learning_rate": 2.0601046409012797e-05, "loss": 3.8832, "step": 1795584 }, { "epoch": 0.01, "learning_rate": 2.0592660461502277e-05, "loss": 3.8985, "step": 1796096 }, { "epoch": 0.01, "learning_rate": 2.0584274513991757e-05, "loss": 3.8905, "step": 1796608 }, { "epoch": 0.01, "learning_rate": 2.0575888566481237e-05, "loss": 3.8864, "step": 1797120 }, { "epoch": 0.01, "learning_rate": 2.056750261897072e-05, "loss": 3.8957, "step": 1797632 }, { "epoch": 0.01, "learning_rate": 2.055913305026393e-05, "loss": 3.8788, "step": 1798144 }, { "epoch": 0.01, "learning_rate": 2.055074710275341e-05, "loss": 3.8873, "step": 1798656 }, { "epoch": 0.01, "learning_rate": 2.054236115524289e-05, "loss": 3.8848, "step": 1799168 }, { "epoch": 0.01, "learning_rate": 2.053397520773237e-05, "loss": 3.8974, "step": 1799680 }, { "epoch": 0.01, "learning_rate": 2.052558926022185e-05, "loss": 3.8824, "step": 1800192 }, { "epoch": 0.01, "learning_rate": 2.051720331271133e-05, "loss": 3.8843, "step": 1800704 }, { "epoch": 0.02, "learning_rate": 2.050881736520081e-05, "loss": 3.8808, "step": 1801216 }, { "epoch": 0.02, "learning_rate": 2.050043141769029e-05, "loss": 3.8926, "step": 1801728 }, { "epoch": 0.02, "learning_rate": 2.0492061848983498e-05, "loss": 3.8909, "step": 1802240 }, { "epoch": 0.02, "learning_rate": 2.0483675901472978e-05, "loss": 3.8736, "step": 1802752 }, { "epoch": 0.02, "learning_rate": 2.0475289953962458e-05, "loss": 3.8956, "step": 1803264 }, { "epoch": 0.02, "learning_rate": 2.046692038525567e-05, "loss": 3.8975, "step": 1803776 }, { "epoch": 0.02, "learning_rate": 2.045853443774515e-05, "loss": 3.8891, "step": 1804288 }, { "epoch": 0.02, "learning_rate": 2.045014849023463e-05, "loss": 3.8696, "step": 1804800 }, { "epoch": 0.02, "learning_rate": 2.044176254272411e-05, "loss": 3.8869, "step": 1805312 }, { "epoch": 0.02, "learning_rate": 2.043339297401732e-05, "loss": 3.8819, "step": 1805824 }, { "epoch": 0.02, "learning_rate": 2.0425007026506803e-05, "loss": 3.8986, "step": 1806336 }, { "epoch": 0.02, "learning_rate": 2.0416621078996283e-05, "loss": 3.8938, "step": 1806848 }, { "epoch": 0.02, "learning_rate": 2.0408235131485763e-05, "loss": 3.8828, "step": 1807360 }, { "epoch": 0.02, "learning_rate": 2.0399849183975243e-05, "loss": 3.882, "step": 1807872 }, { "epoch": 0.02, "learning_rate": 2.0391463236464722e-05, "loss": 3.885, "step": 1808384 }, { "epoch": 0.02, "learning_rate": 2.03830772889542e-05, "loss": 3.8757, "step": 1808896 }, { "epoch": 0.02, "learning_rate": 2.037470772024741e-05, "loss": 3.8852, "step": 1809408 }, { "epoch": 0.02, "learning_rate": 2.0366321772736895e-05, "loss": 3.8786, "step": 1809920 }, { "epoch": 0.02, "learning_rate": 2.0357935825226375e-05, "loss": 3.8984, "step": 1810432 }, { "epoch": 0.02, "learning_rate": 2.034954987771585e-05, "loss": 3.8706, "step": 1810944 }, { "epoch": 0.02, "learning_rate": 2.034116393020533e-05, "loss": 3.8806, "step": 1811456 }, { "epoch": 0.02, "learning_rate": 2.033277798269481e-05, "loss": 3.8772, "step": 1811968 }, { "epoch": 0.02, "learning_rate": 2.0324408413988024e-05, "loss": 3.89, "step": 1812480 }, { "epoch": 0.02, "learning_rate": 2.0316022466477504e-05, "loss": 3.8783, "step": 1812992 }, { "epoch": 0.02, "learning_rate": 2.0307636518966984e-05, "loss": 3.8819, "step": 1813504 }, { "epoch": 0.02, "learning_rate": 2.0299250571456464e-05, "loss": 3.8904, "step": 1814016 }, { "epoch": 0.02, "learning_rate": 2.0290881002749673e-05, "loss": 3.8919, "step": 1814528 }, { "epoch": 0.02, "learning_rate": 2.0282495055239153e-05, "loss": 3.8754, "step": 1815040 }, { "epoch": 0.02, "learning_rate": 2.0274125486532365e-05, "loss": 3.8925, "step": 1815552 }, { "epoch": 0.02, "learning_rate": 2.026573953902185e-05, "loss": 3.882, "step": 1816064 }, { "epoch": 0.02, "learning_rate": 2.0257353591511325e-05, "loss": 3.8875, "step": 1816576 }, { "epoch": 0.02, "learning_rate": 2.0248967644000805e-05, "loss": 3.8825, "step": 1817088 }, { "epoch": 0.02, "learning_rate": 2.0240598075294018e-05, "loss": 3.8862, "step": 1817600 }, { "epoch": 0.02, "learning_rate": 2.0232212127783498e-05, "loss": 3.8783, "step": 1818112 }, { "epoch": 0.02, "learning_rate": 2.0223826180272974e-05, "loss": 3.8886, "step": 1818624 }, { "epoch": 0.02, "learning_rate": 2.0215440232762457e-05, "loss": 3.8874, "step": 1819136 }, { "epoch": 0.02, "learning_rate": 2.0207054285251937e-05, "loss": 3.8851, "step": 1819648 }, { "epoch": 0.02, "learning_rate": 2.0198668337741417e-05, "loss": 3.8805, "step": 1820160 }, { "epoch": 0.02, "learning_rate": 2.0190298769034626e-05, "loss": 3.885, "step": 1820672 }, { "epoch": 0.02, "learning_rate": 2.0181912821524106e-05, "loss": 3.8691, "step": 1821184 }, { "epoch": 0.02, "learning_rate": 2.0173526874013586e-05, "loss": 3.9023, "step": 1821696 }, { "epoch": 0.02, "learning_rate": 2.0165140926503066e-05, "loss": 3.8816, "step": 1822208 }, { "epoch": 0.02, "learning_rate": 2.015675497899255e-05, "loss": 3.89, "step": 1822720 }, { "epoch": 0.02, "learning_rate": 2.014836903148203e-05, "loss": 3.8763, "step": 1823232 }, { "epoch": 0.02, "learning_rate": 2.0139983083971506e-05, "loss": 3.8949, "step": 1823744 }, { "epoch": 0.02, "learning_rate": 2.0131597136460986e-05, "loss": 3.8894, "step": 1824256 }, { "epoch": 0.02, "learning_rate": 2.0123211188950466e-05, "loss": 3.8845, "step": 1824768 }, { "epoch": 0.02, "learning_rate": 2.0114825241439946e-05, "loss": 3.8878, "step": 1825280 }, { "epoch": 0.02, "learning_rate": 2.0106439293929426e-05, "loss": 3.8852, "step": 1825792 }, { "epoch": 0.02, "learning_rate": 2.0098053346418906e-05, "loss": 3.8884, "step": 1826304 }, { "epoch": 0.02, "learning_rate": 2.008968377771212e-05, "loss": 3.9038, "step": 1826816 }, { "epoch": 0.02, "learning_rate": 2.00812978302016e-05, "loss": 3.8683, "step": 1827328 }, { "epoch": 0.02, "learning_rate": 2.007291188269108e-05, "loss": 3.8946, "step": 1827840 }, { "epoch": 0.02, "learning_rate": 2.0064525935180558e-05, "loss": 3.8825, "step": 1828352 }, { "epoch": 0.02, "learning_rate": 2.0056156366473767e-05, "loss": 3.891, "step": 1828864 }, { "epoch": 0.02, "learning_rate": 2.004777041896325e-05, "loss": 3.8836, "step": 1829376 }, { "epoch": 0.02, "learning_rate": 2.003938447145273e-05, "loss": 3.8863, "step": 1829888 }, { "epoch": 0.02, "learning_rate": 2.003099852394221e-05, "loss": 3.8919, "step": 1830400 }, { "epoch": 0.02, "learning_rate": 2.002262895523542e-05, "loss": 3.8865, "step": 1830912 }, { "epoch": 0.02, "learning_rate": 2.001425938652863e-05, "loss": 3.8884, "step": 1831424 }, { "epoch": 0.03, "eval_loss": 4.040306568145752, "eval_runtime": 316.4996, "eval_samples_per_second": 1205.66, "eval_steps_per_second": 37.678, "step": 1831680 }, { "epoch": 1.0, "learning_rate": 2.0005873439018112e-05, "loss": 3.8858, "step": 1831936 }, { "epoch": 1.0, "learning_rate": 1.9997487491507592e-05, "loss": 3.8843, "step": 1832448 }, { "epoch": 1.0, "learning_rate": 1.9989101543997072e-05, "loss": 3.8915, "step": 1832960 }, { "epoch": 1.0, "learning_rate": 1.9980715596486552e-05, "loss": 3.888, "step": 1833472 }, { "epoch": 1.0, "learning_rate": 1.9972329648976032e-05, "loss": 3.8983, "step": 1833984 }, { "epoch": 1.0, "learning_rate": 1.996396008026924e-05, "loss": 3.8816, "step": 1834496 }, { "epoch": 1.0, "learning_rate": 1.995557413275872e-05, "loss": 3.8786, "step": 1835008 }, { "epoch": 1.0, "learning_rate": 1.9947188185248204e-05, "loss": 3.8809, "step": 1835520 }, { "epoch": 1.0, "learning_rate": 1.9938802237737684e-05, "loss": 3.889, "step": 1836032 }, { "epoch": 1.0, "learning_rate": 1.993041629022716e-05, "loss": 3.8972, "step": 1836544 }, { "epoch": 1.0, "learning_rate": 1.992203034271664e-05, "loss": 3.8819, "step": 1837056 }, { "epoch": 1.0, "learning_rate": 1.991364439520612e-05, "loss": 3.8887, "step": 1837568 }, { "epoch": 1.0, "learning_rate": 1.9905274826499333e-05, "loss": 3.8863, "step": 1838080 }, { "epoch": 1.0, "learning_rate": 1.9896888878988813e-05, "loss": 3.8771, "step": 1838592 }, { "epoch": 1.0, "learning_rate": 1.9888502931478293e-05, "loss": 3.8832, "step": 1839104 }, { "epoch": 1.0, "learning_rate": 1.9880116983967773e-05, "loss": 3.871, "step": 1839616 }, { "epoch": 1.0, "learning_rate": 1.9871731036457253e-05, "loss": 3.8815, "step": 1840128 }, { "epoch": 1.0, "learning_rate": 1.9863361467750462e-05, "loss": 3.8758, "step": 1840640 }, { "epoch": 1.0, "learning_rate": 1.9854991899043675e-05, "loss": 3.8796, "step": 1841152 }, { "epoch": 1.0, "learning_rate": 1.9846605951533158e-05, "loss": 3.9055, "step": 1841664 }, { "epoch": 1.0, "learning_rate": 1.9838220004022635e-05, "loss": 3.8889, "step": 1842176 }, { "epoch": 1.0, "learning_rate": 1.9829834056512115e-05, "loss": 3.8849, "step": 1842688 }, { "epoch": 1.0, "learning_rate": 1.9821448109001595e-05, "loss": 3.8878, "step": 1843200 }, { "epoch": 1.0, "learning_rate": 1.9813062161491074e-05, "loss": 3.8934, "step": 1843712 }, { "epoch": 1.0, "learning_rate": 1.9804676213980554e-05, "loss": 3.869, "step": 1844224 }, { "epoch": 1.0, "learning_rate": 1.9796290266470034e-05, "loss": 3.8842, "step": 1844736 }, { "epoch": 1.0, "learning_rate": 1.9787904318959514e-05, "loss": 3.8866, "step": 1845248 }, { "epoch": 1.0, "learning_rate": 1.9779518371448994e-05, "loss": 3.8763, "step": 1845760 }, { "epoch": 1.0, "learning_rate": 1.9771132423938474e-05, "loss": 3.8725, "step": 1846272 }, { "epoch": 1.0, "learning_rate": 1.9762746476427954e-05, "loss": 3.8763, "step": 1846784 }, { "epoch": 1.01, "learning_rate": 1.9754376907721163e-05, "loss": 3.8824, "step": 1847296 }, { "epoch": 1.01, "learning_rate": 1.9746007339014376e-05, "loss": 3.8938, "step": 1847808 }, { "epoch": 1.01, "learning_rate": 1.973762139150386e-05, "loss": 3.8849, "step": 1848320 }, { "epoch": 1.01, "learning_rate": 1.972923544399334e-05, "loss": 3.8827, "step": 1848832 }, { "epoch": 1.01, "learning_rate": 1.9720865875286548e-05, "loss": 3.8859, "step": 1849344 }, { "epoch": 1.01, "learning_rate": 1.9712479927776028e-05, "loss": 3.8874, "step": 1849856 }, { "epoch": 1.01, "learning_rate": 1.9704093980265508e-05, "loss": 3.8826, "step": 1850368 }, { "epoch": 1.01, "learning_rate": 1.9695708032754988e-05, "loss": 3.8855, "step": 1850880 }, { "epoch": 1.01, "learning_rate": 1.9687322085244468e-05, "loss": 3.8727, "step": 1851392 }, { "epoch": 1.01, "learning_rate": 1.9678936137733948e-05, "loss": 3.8855, "step": 1851904 }, { "epoch": 1.01, "learning_rate": 1.9670550190223428e-05, "loss": 3.8743, "step": 1852416 }, { "epoch": 1.01, "learning_rate": 1.9662164242712908e-05, "loss": 3.8951, "step": 1852928 }, { "epoch": 1.01, "learning_rate": 1.9653778295202388e-05, "loss": 3.8876, "step": 1853440 }, { "epoch": 1.01, "learning_rate": 1.9645392347691868e-05, "loss": 3.8847, "step": 1853952 }, { "epoch": 1.01, "learning_rate": 1.9637006400181344e-05, "loss": 3.8908, "step": 1854464 }, { "epoch": 1.01, "learning_rate": 1.962863683147456e-05, "loss": 3.8816, "step": 1854976 }, { "epoch": 1.01, "learning_rate": 1.962025088396404e-05, "loss": 3.8919, "step": 1855488 }, { "epoch": 1.01, "learning_rate": 1.961186493645352e-05, "loss": 3.8786, "step": 1856000 }, { "epoch": 1.01, "learning_rate": 1.9603478988942997e-05, "loss": 3.8559, "step": 1856512 }, { "epoch": 1.01, "learning_rate": 1.9595093041432477e-05, "loss": 3.8985, "step": 1857024 }, { "epoch": 1.01, "learning_rate": 1.9586707093921957e-05, "loss": 3.8798, "step": 1857536 }, { "epoch": 1.01, "learning_rate": 1.9578321146411437e-05, "loss": 3.8974, "step": 1858048 }, { "epoch": 1.01, "learning_rate": 1.956993519890092e-05, "loss": 3.8804, "step": 1858560 }, { "epoch": 1.01, "learning_rate": 1.95615492513904e-05, "loss": 3.8787, "step": 1859072 }, { "epoch": 1.01, "learning_rate": 1.9553163303879876e-05, "loss": 3.871, "step": 1859584 }, { "epoch": 1.01, "learning_rate": 1.954479373517309e-05, "loss": 3.885, "step": 1860096 }, { "epoch": 1.01, "learning_rate": 1.953640778766257e-05, "loss": 3.8858, "step": 1860608 }, { "epoch": 1.01, "learning_rate": 1.952803821895578e-05, "loss": 3.888, "step": 1861120 }, { "epoch": 1.01, "learning_rate": 1.951965227144526e-05, "loss": 3.8968, "step": 1861632 }, { "epoch": 1.01, "learning_rate": 1.951126632393474e-05, "loss": 3.8769, "step": 1862144 }, { "epoch": 1.01, "learning_rate": 1.950288037642422e-05, "loss": 3.8747, "step": 1862656 }, { "epoch": 1.01, "learning_rate": 1.94944944289137e-05, "loss": 3.8947, "step": 1863168 }, { "epoch": 1.01, "learning_rate": 1.9486108481403178e-05, "loss": 3.8719, "step": 1863680 }, { "epoch": 1.01, "learning_rate": 1.9477722533892658e-05, "loss": 3.8762, "step": 1864192 }, { "epoch": 1.01, "learning_rate": 1.9469336586382138e-05, "loss": 3.8825, "step": 1864704 }, { "epoch": 1.01, "learning_rate": 1.946095063887162e-05, "loss": 3.8923, "step": 1865216 }, { "epoch": 1.01, "learning_rate": 1.945258107016483e-05, "loss": 3.8696, "step": 1865728 }, { "epoch": 1.01, "learning_rate": 1.944419512265431e-05, "loss": 3.8766, "step": 1866240 }, { "epoch": 1.01, "learning_rate": 1.943580917514379e-05, "loss": 3.8677, "step": 1866752 }, { "epoch": 1.01, "learning_rate": 1.942742322763327e-05, "loss": 3.8798, "step": 1867264 }, { "epoch": 1.01, "learning_rate": 1.941903728012275e-05, "loss": 3.8911, "step": 1867776 }, { "epoch": 1.01, "learning_rate": 1.941065133261223e-05, "loss": 3.8812, "step": 1868288 }, { "epoch": 1.01, "learning_rate": 1.9402281763905442e-05, "loss": 3.8844, "step": 1868800 }, { "epoch": 1.01, "learning_rate": 1.9393895816394922e-05, "loss": 3.8805, "step": 1869312 }, { "epoch": 1.01, "learning_rate": 1.9385509868884402e-05, "loss": 3.9012, "step": 1869824 }, { "epoch": 1.01, "learning_rate": 1.9377123921373882e-05, "loss": 3.874, "step": 1870336 }, { "epoch": 1.01, "learning_rate": 1.936873797386336e-05, "loss": 3.891, "step": 1870848 }, { "epoch": 1.01, "learning_rate": 1.936035202635284e-05, "loss": 3.8851, "step": 1871360 }, { "epoch": 1.01, "learning_rate": 1.9351982457646055e-05, "loss": 3.8797, "step": 1871872 }, { "epoch": 1.01, "learning_rate": 1.934359651013553e-05, "loss": 3.8877, "step": 1872384 }, { "epoch": 1.01, "learning_rate": 1.933521056262501e-05, "loss": 3.886, "step": 1872896 }, { "epoch": 1.01, "learning_rate": 1.932682461511449e-05, "loss": 3.8832, "step": 1873408 }, { "epoch": 1.01, "learning_rate": 1.931843866760397e-05, "loss": 3.8872, "step": 1873920 }, { "epoch": 1.01, "learning_rate": 1.931005272009345e-05, "loss": 3.8764, "step": 1874432 }, { "epoch": 1.01, "learning_rate": 1.930166677258293e-05, "loss": 3.8797, "step": 1874944 }, { "epoch": 1.01, "learning_rate": 1.9293280825072414e-05, "loss": 3.8811, "step": 1875456 }, { "epoch": 1.01, "learning_rate": 1.9284911256365623e-05, "loss": 3.8894, "step": 1875968 }, { "epoch": 1.01, "learning_rate": 1.9276525308855103e-05, "loss": 3.8761, "step": 1876480 }, { "epoch": 1.01, "learning_rate": 1.9268139361344583e-05, "loss": 3.8785, "step": 1876992 }, { "epoch": 1.02, "learning_rate": 1.9259753413834063e-05, "loss": 3.8762, "step": 1877504 }, { "epoch": 1.02, "learning_rate": 1.9251383845127276e-05, "loss": 3.8894, "step": 1878016 }, { "epoch": 1.02, "learning_rate": 1.9243014276420485e-05, "loss": 3.8852, "step": 1878528 }, { "epoch": 1.02, "learning_rate": 1.9234628328909965e-05, "loss": 3.8707, "step": 1879040 }, { "epoch": 1.02, "learning_rate": 1.9226242381399445e-05, "loss": 3.8894, "step": 1879552 }, { "epoch": 1.02, "learning_rate": 1.9217872812692654e-05, "loss": 3.8905, "step": 1880064 }, { "epoch": 1.02, "learning_rate": 1.9209486865182137e-05, "loss": 3.8826, "step": 1880576 }, { "epoch": 1.02, "learning_rate": 1.9201100917671617e-05, "loss": 3.864, "step": 1881088 }, { "epoch": 1.02, "learning_rate": 1.9192714970161097e-05, "loss": 3.88, "step": 1881600 }, { "epoch": 1.02, "learning_rate": 1.9184345401454306e-05, "loss": 3.8759, "step": 1882112 }, { "epoch": 1.02, "learning_rate": 1.9175959453943786e-05, "loss": 3.8932, "step": 1882624 }, { "epoch": 1.02, "learning_rate": 1.9167573506433266e-05, "loss": 3.8848, "step": 1883136 }, { "epoch": 1.02, "learning_rate": 1.9159187558922746e-05, "loss": 3.8842, "step": 1883648 }, { "epoch": 1.02, "learning_rate": 1.915080161141223e-05, "loss": 3.8771, "step": 1884160 }, { "epoch": 1.02, "learning_rate": 1.914241566390171e-05, "loss": 3.8767, "step": 1884672 }, { "epoch": 1.02, "learning_rate": 1.9134029716391186e-05, "loss": 3.8737, "step": 1885184 }, { "epoch": 1.02, "learning_rate": 1.9125643768880666e-05, "loss": 3.8785, "step": 1885696 }, { "epoch": 1.02, "learning_rate": 1.9117257821370146e-05, "loss": 3.8735, "step": 1886208 }, { "epoch": 1.02, "learning_rate": 1.9108871873859626e-05, "loss": 3.8919, "step": 1886720 }, { "epoch": 1.02, "learning_rate": 1.910050230515284e-05, "loss": 3.8692, "step": 1887232 }, { "epoch": 1.02, "learning_rate": 1.9092116357642318e-05, "loss": 3.8715, "step": 1887744 }, { "epoch": 1.02, "learning_rate": 1.9083730410131798e-05, "loss": 3.8743, "step": 1888256 }, { "epoch": 1.02, "learning_rate": 1.9075344462621278e-05, "loss": 3.8787, "step": 1888768 }, { "epoch": 1.02, "learning_rate": 1.9066958515110758e-05, "loss": 3.8789, "step": 1889280 }, { "epoch": 1.02, "learning_rate": 1.90586053252077e-05, "loss": 3.8743, "step": 1889792 }, { "epoch": 1.02, "learning_rate": 1.9050219377697183e-05, "loss": 3.8821, "step": 1890304 }, { "epoch": 1.02, "learning_rate": 1.904183343018666e-05, "loss": 3.8898, "step": 1890816 }, { "epoch": 1.02, "learning_rate": 1.903344748267614e-05, "loss": 3.8688, "step": 1891328 }, { "epoch": 1.02, "learning_rate": 1.902506153516562e-05, "loss": 3.8834, "step": 1891840 }, { "epoch": 1.02, "learning_rate": 1.9016691966458832e-05, "loss": 3.8761, "step": 1892352 }, { "epoch": 1.02, "learning_rate": 1.900830601894831e-05, "loss": 3.8833, "step": 1892864 }, { "epoch": 1.02, "learning_rate": 1.8999920071437792e-05, "loss": 3.8779, "step": 1893376 }, { "epoch": 1.02, "learning_rate": 1.8991534123927272e-05, "loss": 3.8762, "step": 1893888 }, { "epoch": 1.02, "learning_rate": 1.8983148176416752e-05, "loss": 3.8744, "step": 1894400 }, { "epoch": 1.02, "learning_rate": 1.8974762228906232e-05, "loss": 3.8828, "step": 1894912 }, { "epoch": 1.02, "learning_rate": 1.8966376281395712e-05, "loss": 3.8839, "step": 1895424 }, { "epoch": 1.02, "learning_rate": 1.895799033388519e-05, "loss": 3.8792, "step": 1895936 }, { "epoch": 1.02, "learning_rate": 1.894960438637467e-05, "loss": 3.8763, "step": 1896448 }, { "epoch": 1.02, "learning_rate": 1.894121843886415e-05, "loss": 3.8808, "step": 1896960 }, { "epoch": 1.02, "learning_rate": 1.8932848870157364e-05, "loss": 3.8663, "step": 1897472 }, { "epoch": 1.02, "learning_rate": 1.892446292264684e-05, "loss": 3.8936, "step": 1897984 }, { "epoch": 1.02, "learning_rate": 1.891607697513632e-05, "loss": 3.8737, "step": 1898496 }, { "epoch": 1.02, "learning_rate": 1.89076910276258e-05, "loss": 3.8881, "step": 1899008 }, { "epoch": 1.02, "learning_rate": 1.889930508011528e-05, "loss": 3.8706, "step": 1899520 }, { "epoch": 1.02, "learning_rate": 1.889091913260476e-05, "loss": 3.8906, "step": 1900032 }, { "epoch": 1.02, "learning_rate": 1.888253318509424e-05, "loss": 3.8845, "step": 1900544 }, { "epoch": 1.02, "learning_rate": 1.8874163616387453e-05, "loss": 3.8775, "step": 1901056 }, { "epoch": 1.02, "learning_rate": 1.8865777668876933e-05, "loss": 3.88, "step": 1901568 }, { "epoch": 1.02, "learning_rate": 1.8857391721366413e-05, "loss": 3.8809, "step": 1902080 }, { "epoch": 1.02, "learning_rate": 1.8849005773855893e-05, "loss": 3.8827, "step": 1902592 }, { "epoch": 1.02, "learning_rate": 1.884061982634537e-05, "loss": 3.8967, "step": 1903104 }, { "epoch": 1.02, "learning_rate": 1.8832233878834853e-05, "loss": 3.865, "step": 1903616 }, { "epoch": 1.02, "learning_rate": 1.8823864310128065e-05, "loss": 3.8918, "step": 1904128 }, { "epoch": 1.02, "learning_rate": 1.8815478362617545e-05, "loss": 3.874, "step": 1904640 }, { "epoch": 1.02, "learning_rate": 1.8807092415107022e-05, "loss": 3.8845, "step": 1905152 }, { "epoch": 1.02, "learning_rate": 1.8798706467596502e-05, "loss": 3.8806, "step": 1905664 }, { "epoch": 1.02, "learning_rate": 1.879032052008598e-05, "loss": 3.8779, "step": 1906176 }, { "epoch": 1.02, "learning_rate": 1.8781950951379194e-05, "loss": 3.8839, "step": 1906688 }, { "epoch": 1.02, "learning_rate": 1.8773565003868674e-05, "loss": 3.8844, "step": 1907200 }, { "epoch": 1.02, "learning_rate": 1.8765179056358154e-05, "loss": 3.8812, "step": 1907712 }, { "epoch": 1.03, "eval_loss": 4.038342475891113, "eval_runtime": 314.4494, "eval_samples_per_second": 1213.521, "eval_steps_per_second": 37.923, "step": 1908000 }, { "epoch": 0.0, "learning_rate": 1.8756793108847634e-05, "loss": 3.8748, "step": 1908224 }, { "epoch": 0.0, "learning_rate": 1.8748407161337114e-05, "loss": 3.8796, "step": 1908736 }, { "epoch": 0.0, "learning_rate": 1.8740021213826594e-05, "loss": 3.8869, "step": 1909248 }, { "epoch": 0.0, "learning_rate": 1.8731635266316074e-05, "loss": 3.8825, "step": 1909760 }, { "epoch": 0.0, "learning_rate": 1.8723249318805554e-05, "loss": 3.8922, "step": 1910272 }, { "epoch": 0.0, "learning_rate": 1.8714863371295034e-05, "loss": 3.8782, "step": 1910784 }, { "epoch": 0.0, "learning_rate": 1.8706477423784514e-05, "loss": 3.8761, "step": 1911296 }, { "epoch": 0.0, "learning_rate": 1.8698091476273994e-05, "loss": 3.8776, "step": 1911808 }, { "epoch": 0.0, "learning_rate": 1.8689705528763474e-05, "loss": 3.8829, "step": 1912320 }, { "epoch": 0.0, "learning_rate": 1.8681319581252954e-05, "loss": 3.8907, "step": 1912832 }, { "epoch": 0.0, "learning_rate": 1.8672933633742434e-05, "loss": 3.8789, "step": 1913344 }, { "epoch": 0.0, "learning_rate": 1.866454768623191e-05, "loss": 3.8806, "step": 1913856 }, { "epoch": 0.0, "learning_rate": 1.8656178117525126e-05, "loss": 3.8841, "step": 1914368 }, { "epoch": 0.0, "learning_rate": 1.8647792170014606e-05, "loss": 3.8701, "step": 1914880 }, { "epoch": 0.0, "learning_rate": 1.8639406222504083e-05, "loss": 3.8775, "step": 1915392 }, { "epoch": 0.0, "learning_rate": 1.8631020274993563e-05, "loss": 3.8682, "step": 1915904 }, { "epoch": 0.0, "learning_rate": 1.8622634327483042e-05, "loss": 3.8738, "step": 1916416 }, { "epoch": 0.0, "learning_rate": 1.8614248379972522e-05, "loss": 3.8703, "step": 1916928 }, { "epoch": 0.0, "learning_rate": 1.8605862432462002e-05, "loss": 3.8754, "step": 1917440 }, { "epoch": 0.0, "learning_rate": 1.8597492863755215e-05, "loss": 3.8948, "step": 1917952 }, { "epoch": 0.0, "learning_rate": 1.8589106916244695e-05, "loss": 3.8856, "step": 1918464 }, { "epoch": 0.0, "learning_rate": 1.8580720968734175e-05, "loss": 3.8796, "step": 1918976 }, { "epoch": 0.0, "learning_rate": 1.8572335021223655e-05, "loss": 3.8798, "step": 1919488 }, { "epoch": 0.0, "learning_rate": 1.8563949073713135e-05, "loss": 3.8882, "step": 1920000 }, { "epoch": 0.0, "learning_rate": 1.8555563126202615e-05, "loss": 3.8648, "step": 1920512 }, { "epoch": 0.0, "learning_rate": 1.8547177178692095e-05, "loss": 3.8795, "step": 1921024 }, { "epoch": 0.0, "learning_rate": 1.8538791231181575e-05, "loss": 3.8798, "step": 1921536 }, { "epoch": 0.0, "learning_rate": 1.8530405283671055e-05, "loss": 3.8656, "step": 1922048 }, { "epoch": 0.0, "learning_rate": 1.8522019336160534e-05, "loss": 3.8749, "step": 1922560 }, { "epoch": 0.0, "learning_rate": 1.8513633388650014e-05, "loss": 3.8672, "step": 1923072 }, { "epoch": 0.01, "learning_rate": 1.8505263819943224e-05, "loss": 3.8769, "step": 1923584 }, { "epoch": 0.01, "learning_rate": 1.8496877872432707e-05, "loss": 3.8823, "step": 1924096 }, { "epoch": 0.01, "learning_rate": 1.8488491924922187e-05, "loss": 3.879, "step": 1924608 }, { "epoch": 0.01, "learning_rate": 1.8480105977411667e-05, "loss": 3.8843, "step": 1925120 }, { "epoch": 0.01, "learning_rate": 1.8471736408704876e-05, "loss": 3.8754, "step": 1925632 }, { "epoch": 0.01, "learning_rate": 1.8463350461194356e-05, "loss": 3.8815, "step": 1926144 }, { "epoch": 0.01, "learning_rate": 1.845498089248757e-05, "loss": 3.8839, "step": 1926656 }, { "epoch": 0.01, "learning_rate": 1.8446594944977048e-05, "loss": 3.8763, "step": 1927168 }, { "epoch": 0.01, "learning_rate": 1.8438208997466528e-05, "loss": 3.8673, "step": 1927680 }, { "epoch": 0.01, "learning_rate": 1.8429823049956008e-05, "loss": 3.8801, "step": 1928192 }, { "epoch": 0.01, "learning_rate": 1.8421437102445488e-05, "loss": 3.8698, "step": 1928704 }, { "epoch": 0.01, "learning_rate": 1.8413051154934968e-05, "loss": 3.8914, "step": 1929216 }, { "epoch": 0.01, "learning_rate": 1.8404665207424445e-05, "loss": 3.8822, "step": 1929728 }, { "epoch": 0.01, "learning_rate": 1.8396279259913925e-05, "loss": 3.8762, "step": 1930240 }, { "epoch": 0.01, "learning_rate": 1.8387893312403408e-05, "loss": 3.8854, "step": 1930752 }, { "epoch": 0.01, "learning_rate": 1.8379507364892888e-05, "loss": 3.8766, "step": 1931264 }, { "epoch": 0.01, "learning_rate": 1.8371121417382368e-05, "loss": 3.8836, "step": 1931776 }, { "epoch": 0.01, "learning_rate": 1.8362735469871848e-05, "loss": 3.8792, "step": 1932288 }, { "epoch": 0.01, "learning_rate": 1.835438227996879e-05, "loss": 3.8472, "step": 1932800 }, { "epoch": 0.01, "learning_rate": 1.834599633245827e-05, "loss": 3.8928, "step": 1933312 }, { "epoch": 0.01, "learning_rate": 1.833761038494775e-05, "loss": 3.8777, "step": 1933824 }, { "epoch": 0.01, "learning_rate": 1.8329240816240962e-05, "loss": 3.8851, "step": 1934336 }, { "epoch": 0.01, "learning_rate": 1.8320854868730442e-05, "loss": 3.8755, "step": 1934848 }, { "epoch": 0.01, "learning_rate": 1.831246892121992e-05, "loss": 3.8761, "step": 1935360 }, { "epoch": 0.01, "learning_rate": 1.83040829737094e-05, "loss": 3.8664, "step": 1935872 }, { "epoch": 0.01, "learning_rate": 1.8295697026198878e-05, "loss": 3.8799, "step": 1936384 }, { "epoch": 0.01, "learning_rate": 1.828731107868836e-05, "loss": 3.879, "step": 1936896 }, { "epoch": 0.01, "learning_rate": 1.827892513117784e-05, "loss": 3.8794, "step": 1937408 }, { "epoch": 0.01, "learning_rate": 1.827055556247105e-05, "loss": 3.8962, "step": 1937920 }, { "epoch": 0.01, "learning_rate": 1.826216961496053e-05, "loss": 3.8736, "step": 1938432 }, { "epoch": 0.01, "learning_rate": 1.825378366745001e-05, "loss": 3.8645, "step": 1938944 }, { "epoch": 0.01, "learning_rate": 1.824539771993949e-05, "loss": 3.891, "step": 1939456 }, { "epoch": 0.01, "learning_rate": 1.823701177242897e-05, "loss": 3.8666, "step": 1939968 }, { "epoch": 0.01, "learning_rate": 1.8228625824918454e-05, "loss": 3.8638, "step": 1940480 }, { "epoch": 0.01, "learning_rate": 1.822023987740793e-05, "loss": 3.8836, "step": 1940992 }, { "epoch": 0.01, "learning_rate": 1.821185392989741e-05, "loss": 3.8821, "step": 1941504 }, { "epoch": 0.01, "learning_rate": 1.820346798238689e-05, "loss": 3.8685, "step": 1942016 }, { "epoch": 0.01, "learning_rate": 1.819508203487637e-05, "loss": 3.8678, "step": 1942528 }, { "epoch": 0.01, "learning_rate": 1.818669608736585e-05, "loss": 3.8625, "step": 1943040 }, { "epoch": 0.01, "learning_rate": 1.817831013985533e-05, "loss": 3.8731, "step": 1943552 }, { "epoch": 0.01, "learning_rate": 1.8169940571148543e-05, "loss": 3.8884, "step": 1944064 }, { "epoch": 0.01, "learning_rate": 1.8161571002441752e-05, "loss": 3.877, "step": 1944576 }, { "epoch": 0.01, "learning_rate": 1.8153185054931232e-05, "loss": 3.8809, "step": 1945088 }, { "epoch": 0.01, "learning_rate": 1.814479910742071e-05, "loss": 3.8718, "step": 1945600 }, { "epoch": 0.01, "learning_rate": 1.813641315991019e-05, "loss": 3.8953, "step": 1946112 }, { "epoch": 0.01, "learning_rate": 1.8128043591203404e-05, "loss": 3.8687, "step": 1946624 }, { "epoch": 0.01, "learning_rate": 1.8119657643692884e-05, "loss": 3.8861, "step": 1947136 }, { "epoch": 0.01, "learning_rate": 1.8111271696182364e-05, "loss": 3.8768, "step": 1947648 }, { "epoch": 0.01, "learning_rate": 1.8102885748671844e-05, "loss": 3.8769, "step": 1948160 }, { "epoch": 0.01, "learning_rate": 1.8094499801161324e-05, "loss": 3.8812, "step": 1948672 }, { "epoch": 0.01, "learning_rate": 1.8086113853650804e-05, "loss": 3.8846, "step": 1949184 }, { "epoch": 0.01, "learning_rate": 1.807772790614028e-05, "loss": 3.873, "step": 1949696 }, { "epoch": 0.01, "learning_rate": 1.8069341958629764e-05, "loss": 3.8835, "step": 1950208 }, { "epoch": 0.01, "learning_rate": 1.8060956011119244e-05, "loss": 3.8734, "step": 1950720 }, { "epoch": 0.01, "learning_rate": 1.8052586442412456e-05, "loss": 3.874, "step": 1951232 }, { "epoch": 0.01, "learning_rate": 1.8044216873705665e-05, "loss": 3.8764, "step": 1951744 }, { "epoch": 0.01, "learning_rate": 1.8035830926195145e-05, "loss": 3.8837, "step": 1952256 }, { "epoch": 0.01, "learning_rate": 1.8027444978684625e-05, "loss": 3.8723, "step": 1952768 }, { "epoch": 0.01, "learning_rate": 1.8019075409977838e-05, "loss": 3.8758, "step": 1953280 }, { "epoch": 0.02, "learning_rate": 1.8010689462467318e-05, "loss": 3.8735, "step": 1953792 }, { "epoch": 0.02, "learning_rate": 1.8002303514956798e-05, "loss": 3.8777, "step": 1954304 }, { "epoch": 0.02, "learning_rate": 1.7993917567446278e-05, "loss": 3.8784, "step": 1954816 }, { "epoch": 0.02, "learning_rate": 1.7985531619935754e-05, "loss": 3.8649, "step": 1955328 }, { "epoch": 0.02, "learning_rate": 1.7977145672425234e-05, "loss": 3.884, "step": 1955840 }, { "epoch": 0.02, "learning_rate": 1.7968759724914717e-05, "loss": 3.8817, "step": 1956352 }, { "epoch": 0.02, "learning_rate": 1.7960373777404197e-05, "loss": 3.8827, "step": 1956864 }, { "epoch": 0.02, "learning_rate": 1.7951987829893677e-05, "loss": 3.859, "step": 1957376 }, { "epoch": 0.02, "learning_rate": 1.7943618261186886e-05, "loss": 3.8721, "step": 1957888 }, { "epoch": 0.02, "learning_rate": 1.7935232313676366e-05, "loss": 3.87, "step": 1958400 }, { "epoch": 0.02, "learning_rate": 1.7926846366165846e-05, "loss": 3.8876, "step": 1958912 }, { "epoch": 0.02, "learning_rate": 1.7918460418655326e-05, "loss": 3.8794, "step": 1959424 }, { "epoch": 0.02, "learning_rate": 1.791009084994854e-05, "loss": 3.8805, "step": 1959936 }, { "epoch": 0.02, "learning_rate": 1.790170490243802e-05, "loss": 3.8748, "step": 1960448 }, { "epoch": 0.02, "learning_rate": 1.78933189549275e-05, "loss": 3.8707, "step": 1960960 }, { "epoch": 0.02, "learning_rate": 1.788493300741698e-05, "loss": 3.8663, "step": 1961472 }, { "epoch": 0.02, "learning_rate": 1.787654705990646e-05, "loss": 3.8761, "step": 1961984 }, { "epoch": 0.02, "learning_rate": 1.786817749119967e-05, "loss": 3.8696, "step": 1962496 }, { "epoch": 0.02, "learning_rate": 1.785979154368915e-05, "loss": 3.8813, "step": 1963008 }, { "epoch": 0.02, "learning_rate": 1.785140559617863e-05, "loss": 3.8681, "step": 1963520 }, { "epoch": 0.02, "learning_rate": 1.784301964866811e-05, "loss": 3.8643, "step": 1964032 }, { "epoch": 0.02, "learning_rate": 1.7834633701157588e-05, "loss": 3.8673, "step": 1964544 }, { "epoch": 0.02, "learning_rate": 1.7826247753647068e-05, "loss": 3.8749, "step": 1965056 }, { "epoch": 0.02, "learning_rate": 1.7817861806136547e-05, "loss": 3.872, "step": 1965568 }, { "epoch": 0.02, "learning_rate": 1.7809475858626027e-05, "loss": 3.8683, "step": 1966080 }, { "epoch": 0.02, "learning_rate": 1.780110628991924e-05, "loss": 3.8818, "step": 1966592 }, { "epoch": 0.02, "learning_rate": 1.779272034240872e-05, "loss": 3.8831, "step": 1967104 }, { "epoch": 0.02, "learning_rate": 1.77843343948982e-05, "loss": 3.8648, "step": 1967616 }, { "epoch": 0.02, "learning_rate": 1.777596482619141e-05, "loss": 3.8774, "step": 1968128 }, { "epoch": 0.02, "learning_rate": 1.776757887868089e-05, "loss": 3.875, "step": 1968640 }, { "epoch": 0.02, "learning_rate": 1.7759192931170372e-05, "loss": 3.874, "step": 1969152 }, { "epoch": 0.02, "learning_rate": 1.7750806983659852e-05, "loss": 3.8747, "step": 1969664 }, { "epoch": 0.02, "learning_rate": 1.7742421036149332e-05, "loss": 3.872, "step": 1970176 }, { "epoch": 0.02, "learning_rate": 1.7734035088638812e-05, "loss": 3.8735, "step": 1970688 }, { "epoch": 0.02, "learning_rate": 1.7725649141128292e-05, "loss": 3.8729, "step": 1971200 }, { "epoch": 0.02, "learning_rate": 1.771726319361777e-05, "loss": 3.8782, "step": 1971712 }, { "epoch": 0.02, "learning_rate": 1.770887724610725e-05, "loss": 3.8744, "step": 1972224 }, { "epoch": 0.02, "learning_rate": 1.7700507677400464e-05, "loss": 3.8677, "step": 1972736 }, { "epoch": 0.02, "learning_rate": 1.7692138108693674e-05, "loss": 3.8757, "step": 1973248 }, { "epoch": 0.02, "learning_rate": 1.7683752161183154e-05, "loss": 3.8584, "step": 1973760 }, { "epoch": 0.02, "learning_rate": 1.7675366213672633e-05, "loss": 3.8882, "step": 1974272 }, { "epoch": 0.02, "learning_rate": 1.7666980266162113e-05, "loss": 3.8673, "step": 1974784 }, { "epoch": 0.02, "learning_rate": 1.7658594318651593e-05, "loss": 3.8861, "step": 1975296 }, { "epoch": 0.02, "learning_rate": 1.7650208371141073e-05, "loss": 3.8653, "step": 1975808 }, { "epoch": 0.02, "learning_rate": 1.7641822423630553e-05, "loss": 3.884, "step": 1976320 }, { "epoch": 0.02, "learning_rate": 1.7633436476120033e-05, "loss": 3.8806, "step": 1976832 }, { "epoch": 0.02, "learning_rate": 1.7625050528609513e-05, "loss": 3.8708, "step": 1977344 }, { "epoch": 0.02, "learning_rate": 1.7616664581098993e-05, "loss": 3.8775, "step": 1977856 }, { "epoch": 0.02, "learning_rate": 1.7608278633588473e-05, "loss": 3.8725, "step": 1978368 }, { "epoch": 0.02, "learning_rate": 1.7599909064881686e-05, "loss": 3.8838, "step": 1978880 }, { "epoch": 0.02, "learning_rate": 1.7591523117371166e-05, "loss": 3.8869, "step": 1979392 }, { "epoch": 0.02, "learning_rate": 1.7583153548664375e-05, "loss": 3.8597, "step": 1979904 }, { "epoch": 0.02, "learning_rate": 1.7574767601153855e-05, "loss": 3.8791, "step": 1980416 }, { "epoch": 0.02, "learning_rate": 1.7566381653643335e-05, "loss": 3.8722, "step": 1980928 }, { "epoch": 0.02, "learning_rate": 1.7557995706132815e-05, "loss": 3.8808, "step": 1981440 }, { "epoch": 0.02, "learning_rate": 1.7549609758622294e-05, "loss": 3.874, "step": 1981952 }, { "epoch": 0.02, "learning_rate": 1.7541223811111774e-05, "loss": 3.8773, "step": 1982464 }, { "epoch": 0.02, "learning_rate": 1.7532837863601254e-05, "loss": 3.8741, "step": 1982976 }, { "epoch": 0.02, "learning_rate": 1.7524451916090734e-05, "loss": 3.8764, "step": 1983488 }, { "epoch": 0.02, "learning_rate": 1.7516065968580214e-05, "loss": 3.8775, "step": 1984000 }, { "epoch": 0.03, "eval_loss": 4.036375999450684, "eval_runtime": 298.0051, "eval_samples_per_second": 1280.485, "eval_steps_per_second": 40.016, "step": 1984320 }, { "epoch": 1.0, "learning_rate": 1.7507680021069694e-05, "loss": 3.8707, "step": 1984512 }, { "epoch": 1.0, "learning_rate": 1.7499294073559174e-05, "loss": 3.8734, "step": 1985024 }, { "epoch": 1.0, "learning_rate": 1.749090812604865e-05, "loss": 3.8797, "step": 1985536 }, { "epoch": 1.0, "learning_rate": 1.7482554936145596e-05, "loss": 3.8789, "step": 1986048 }, { "epoch": 1.0, "learning_rate": 1.7474168988635076e-05, "loss": 3.8848, "step": 1986560 }, { "epoch": 1.0, "learning_rate": 1.7465783041124556e-05, "loss": 3.8739, "step": 1987072 }, { "epoch": 1.0, "learning_rate": 1.7457397093614036e-05, "loss": 3.8715, "step": 1987584 }, { "epoch": 1.0, "learning_rate": 1.7449011146103516e-05, "loss": 3.8711, "step": 1988096 }, { "epoch": 1.0, "learning_rate": 1.7440625198592996e-05, "loss": 3.8726, "step": 1988608 }, { "epoch": 1.0, "learning_rate": 1.743223925108248e-05, "loss": 3.887, "step": 1989120 }, { "epoch": 1.0, "learning_rate": 1.7423853303571955e-05, "loss": 3.8723, "step": 1989632 }, { "epoch": 1.0, "learning_rate": 1.7415483734865168e-05, "loss": 3.873, "step": 1990144 }, { "epoch": 1.0, "learning_rate": 1.7407114166158377e-05, "loss": 3.8823, "step": 1990656 }, { "epoch": 1.0, "learning_rate": 1.7398728218647857e-05, "loss": 3.8641, "step": 1991168 }, { "epoch": 1.0, "learning_rate": 1.739034227113734e-05, "loss": 3.8729, "step": 1991680 }, { "epoch": 1.0, "learning_rate": 1.738195632362682e-05, "loss": 3.8618, "step": 1992192 }, { "epoch": 1.0, "learning_rate": 1.73735703761163e-05, "loss": 3.8674, "step": 1992704 }, { "epoch": 1.0, "learning_rate": 1.7365184428605777e-05, "loss": 3.8704, "step": 1993216 }, { "epoch": 1.0, "learning_rate": 1.7356798481095257e-05, "loss": 3.8653, "step": 1993728 }, { "epoch": 1.0, "learning_rate": 1.734842891238847e-05, "loss": 3.8877, "step": 1994240 }, { "epoch": 1.0, "learning_rate": 1.734004296487795e-05, "loss": 3.8843, "step": 1994752 }, { "epoch": 1.0, "learning_rate": 1.733165701736743e-05, "loss": 3.8744, "step": 1995264 }, { "epoch": 1.0, "learning_rate": 1.732327106985691e-05, "loss": 3.8742, "step": 1995776 }, { "epoch": 1.0, "learning_rate": 1.731490150115012e-05, "loss": 3.8796, "step": 1996288 }, { "epoch": 1.0, "learning_rate": 1.7306515553639598e-05, "loss": 3.8649, "step": 1996800 }, { "epoch": 1.0, "learning_rate": 1.7298129606129078e-05, "loss": 3.8728, "step": 1997312 }, { "epoch": 1.0, "learning_rate": 1.7289743658618558e-05, "loss": 3.8733, "step": 1997824 }, { "epoch": 1.0, "learning_rate": 1.728135771110804e-05, "loss": 3.8601, "step": 1998336 }, { "epoch": 1.0, "learning_rate": 1.727298814240125e-05, "loss": 3.8676, "step": 1998848 }, { "epoch": 1.0, "learning_rate": 1.726460219489073e-05, "loss": 3.8643, "step": 1999360 }, { "epoch": 1.01, "learning_rate": 1.725621624738021e-05, "loss": 3.8758, "step": 1999872 }, { "epoch": 1.01, "learning_rate": 1.724783029986969e-05, "loss": 3.8747, "step": 2000384 }, { "epoch": 1.01, "learning_rate": 1.723944435235917e-05, "loss": 3.8735, "step": 2000896 }, { "epoch": 1.01, "learning_rate": 1.723105840484865e-05, "loss": 3.8798, "step": 2001408 }, { "epoch": 1.01, "learning_rate": 1.7222688836141863e-05, "loss": 3.8679, "step": 2001920 }, { "epoch": 1.01, "learning_rate": 1.7214302888631343e-05, "loss": 3.8793, "step": 2002432 }, { "epoch": 1.01, "learning_rate": 1.7205916941120823e-05, "loss": 3.8817, "step": 2002944 }, { "epoch": 1.01, "learning_rate": 1.7197530993610303e-05, "loss": 3.8671, "step": 2003456 }, { "epoch": 1.01, "learning_rate": 1.718914504609978e-05, "loss": 3.8708, "step": 2003968 }, { "epoch": 1.01, "learning_rate": 1.7180775477392995e-05, "loss": 3.8697, "step": 2004480 }, { "epoch": 1.01, "learning_rate": 1.7172389529882475e-05, "loss": 3.8656, "step": 2004992 }, { "epoch": 1.01, "learning_rate": 1.7164003582371955e-05, "loss": 3.8847, "step": 2005504 }, { "epoch": 1.01, "learning_rate": 1.715561763486143e-05, "loss": 3.8766, "step": 2006016 }, { "epoch": 1.01, "learning_rate": 1.7147248066154644e-05, "loss": 3.8724, "step": 2006528 }, { "epoch": 1.01, "learning_rate": 1.7138862118644124e-05, "loss": 3.8776, "step": 2007040 }, { "epoch": 1.01, "learning_rate": 1.7130476171133604e-05, "loss": 3.8727, "step": 2007552 }, { "epoch": 1.01, "learning_rate": 1.7122090223623084e-05, "loss": 3.877, "step": 2008064 }, { "epoch": 1.01, "learning_rate": 1.7113704276112564e-05, "loss": 3.8754, "step": 2008576 }, { "epoch": 1.01, "learning_rate": 1.7105318328602044e-05, "loss": 3.8455, "step": 2009088 }, { "epoch": 1.01, "learning_rate": 1.7096948759895253e-05, "loss": 3.8858, "step": 2009600 }, { "epoch": 1.01, "learning_rate": 1.7088562812384733e-05, "loss": 3.8689, "step": 2010112 }, { "epoch": 1.01, "learning_rate": 1.7080176864874213e-05, "loss": 3.8817, "step": 2010624 }, { "epoch": 1.01, "learning_rate": 1.7071790917363696e-05, "loss": 3.8748, "step": 2011136 }, { "epoch": 1.01, "learning_rate": 1.7063404969853176e-05, "loss": 3.8677, "step": 2011648 }, { "epoch": 1.01, "learning_rate": 1.7055019022342656e-05, "loss": 3.8634, "step": 2012160 }, { "epoch": 1.01, "learning_rate": 1.7046633074832136e-05, "loss": 3.8771, "step": 2012672 }, { "epoch": 1.01, "learning_rate": 1.7038263506125345e-05, "loss": 3.8759, "step": 2013184 }, { "epoch": 1.01, "learning_rate": 1.7029877558614825e-05, "loss": 3.8729, "step": 2013696 }, { "epoch": 1.01, "learning_rate": 1.7021491611104305e-05, "loss": 3.8906, "step": 2014208 }, { "epoch": 1.01, "learning_rate": 1.701310566359379e-05, "loss": 3.8761, "step": 2014720 }, { "epoch": 1.01, "learning_rate": 1.7004719716083265e-05, "loss": 3.8527, "step": 2015232 }, { "epoch": 1.01, "learning_rate": 1.6996350147376477e-05, "loss": 3.8856, "step": 2015744 }, { "epoch": 1.01, "learning_rate": 1.6987964199865957e-05, "loss": 3.8631, "step": 2016256 }, { "epoch": 1.01, "learning_rate": 1.6979578252355434e-05, "loss": 3.8633, "step": 2016768 }, { "epoch": 1.01, "learning_rate": 1.6971192304844914e-05, "loss": 3.8776, "step": 2017280 }, { "epoch": 1.01, "learning_rate": 1.6962806357334397e-05, "loss": 3.8767, "step": 2017792 }, { "epoch": 1.01, "learning_rate": 1.6954420409823877e-05, "loss": 3.8621, "step": 2018304 }, { "epoch": 1.01, "learning_rate": 1.6946050841117086e-05, "loss": 3.8643, "step": 2018816 }, { "epoch": 1.01, "learning_rate": 1.6937664893606566e-05, "loss": 3.8576, "step": 2019328 }, { "epoch": 1.01, "learning_rate": 1.6929278946096046e-05, "loss": 3.868, "step": 2019840 }, { "epoch": 1.01, "learning_rate": 1.6920892998585526e-05, "loss": 3.8803, "step": 2020352 }, { "epoch": 1.01, "learning_rate": 1.691252342987874e-05, "loss": 3.8728, "step": 2020864 }, { "epoch": 1.01, "learning_rate": 1.690413748236822e-05, "loss": 3.8744, "step": 2021376 }, { "epoch": 1.01, "learning_rate": 1.68957515348577e-05, "loss": 3.867, "step": 2021888 }, { "epoch": 1.01, "learning_rate": 1.6887381966150908e-05, "loss": 3.8872, "step": 2022400 }, { "epoch": 1.01, "learning_rate": 1.6878996018640388e-05, "loss": 3.8673, "step": 2022912 }, { "epoch": 1.01, "learning_rate": 1.6870610071129868e-05, "loss": 3.8797, "step": 2023424 }, { "epoch": 1.01, "learning_rate": 1.686222412361935e-05, "loss": 3.867, "step": 2023936 }, { "epoch": 1.01, "learning_rate": 1.685383817610883e-05, "loss": 3.8746, "step": 2024448 }, { "epoch": 1.01, "learning_rate": 1.684545222859831e-05, "loss": 3.8775, "step": 2024960 }, { "epoch": 1.01, "learning_rate": 1.683706628108779e-05, "loss": 3.8784, "step": 2025472 }, { "epoch": 1.01, "learning_rate": 1.6828680333577267e-05, "loss": 3.8688, "step": 2025984 }, { "epoch": 1.01, "learning_rate": 1.6820294386066747e-05, "loss": 3.8826, "step": 2026496 }, { "epoch": 1.01, "learning_rate": 1.6811908438556227e-05, "loss": 3.8601, "step": 2027008 }, { "epoch": 1.01, "learning_rate": 1.680352249104571e-05, "loss": 3.8703, "step": 2027520 }, { "epoch": 1.01, "learning_rate": 1.679513654353519e-05, "loss": 3.873, "step": 2028032 }, { "epoch": 1.01, "learning_rate": 1.67867669748284e-05, "loss": 3.8788, "step": 2028544 }, { "epoch": 1.01, "learning_rate": 1.677838102731788e-05, "loss": 3.865, "step": 2029056 }, { "epoch": 1.01, "learning_rate": 1.677001145861109e-05, "loss": 3.8683, "step": 2029568 }, { "epoch": 1.01, "learning_rate": 1.6761641889904305e-05, "loss": 3.8659, "step": 2030080 }, { "epoch": 1.02, "learning_rate": 1.6753255942393785e-05, "loss": 3.8709, "step": 2030592 }, { "epoch": 1.02, "learning_rate": 1.6744869994883265e-05, "loss": 3.8748, "step": 2031104 }, { "epoch": 1.02, "learning_rate": 1.673648404737274e-05, "loss": 3.8604, "step": 2031616 }, { "epoch": 1.02, "learning_rate": 1.672809809986222e-05, "loss": 3.8756, "step": 2032128 }, { "epoch": 1.02, "learning_rate": 1.67197121523517e-05, "loss": 3.879, "step": 2032640 }, { "epoch": 1.02, "learning_rate": 1.671132620484118e-05, "loss": 3.8807, "step": 2033152 }, { "epoch": 1.02, "learning_rate": 1.670294025733066e-05, "loss": 3.8522, "step": 2033664 }, { "epoch": 1.02, "learning_rate": 1.6694554309820144e-05, "loss": 3.8685, "step": 2034176 }, { "epoch": 1.02, "learning_rate": 1.668616836230962e-05, "loss": 3.8658, "step": 2034688 }, { "epoch": 1.02, "learning_rate": 1.66777824147991e-05, "loss": 3.8797, "step": 2035200 }, { "epoch": 1.02, "learning_rate": 1.666939646728858e-05, "loss": 3.8783, "step": 2035712 }, { "epoch": 1.02, "learning_rate": 1.666101051977806e-05, "loss": 3.872, "step": 2036224 }, { "epoch": 1.02, "learning_rate": 1.6652640951071273e-05, "loss": 3.8677, "step": 2036736 }, { "epoch": 1.02, "learning_rate": 1.6644271382364486e-05, "loss": 3.8715, "step": 2037248 }, { "epoch": 1.02, "learning_rate": 1.6635885434853966e-05, "loss": 3.8612, "step": 2037760 }, { "epoch": 1.02, "learning_rate": 1.6627499487343446e-05, "loss": 3.8703, "step": 2038272 }, { "epoch": 1.02, "learning_rate": 1.6619113539832922e-05, "loss": 3.8646, "step": 2038784 }, { "epoch": 1.02, "learning_rate": 1.6610727592322402e-05, "loss": 3.8746, "step": 2039296 }, { "epoch": 1.02, "learning_rate": 1.6602358023615615e-05, "loss": 3.8638, "step": 2039808 }, { "epoch": 1.02, "learning_rate": 1.6593972076105095e-05, "loss": 3.862, "step": 2040320 }, { "epoch": 1.02, "learning_rate": 1.6585586128594575e-05, "loss": 3.8594, "step": 2040832 }, { "epoch": 1.02, "learning_rate": 1.6577200181084054e-05, "loss": 3.8669, "step": 2041344 }, { "epoch": 1.02, "learning_rate": 1.6568814233573534e-05, "loss": 3.8729, "step": 2041856 }, { "epoch": 1.02, "learning_rate": 1.6560428286063014e-05, "loss": 3.8643, "step": 2042368 }, { "epoch": 1.02, "learning_rate": 1.6552042338552494e-05, "loss": 3.8731, "step": 2042880 }, { "epoch": 1.02, "learning_rate": 1.6543672769845707e-05, "loss": 3.8741, "step": 2043392 }, { "epoch": 1.02, "learning_rate": 1.653530320113892e-05, "loss": 3.8635, "step": 2043904 }, { "epoch": 1.02, "learning_rate": 1.6526917253628396e-05, "loss": 3.8744, "step": 2044416 }, { "epoch": 1.02, "learning_rate": 1.6518531306117876e-05, "loss": 3.8682, "step": 2044928 }, { "epoch": 1.02, "learning_rate": 1.6510145358607356e-05, "loss": 3.8722, "step": 2045440 }, { "epoch": 1.02, "learning_rate": 1.6501759411096836e-05, "loss": 3.8684, "step": 2045952 }, { "epoch": 1.02, "learning_rate": 1.649337346358632e-05, "loss": 3.8655, "step": 2046464 }, { "epoch": 1.02, "learning_rate": 1.64849875160758e-05, "loss": 3.8707, "step": 2046976 }, { "epoch": 1.02, "learning_rate": 1.6476617947369008e-05, "loss": 3.8642, "step": 2047488 }, { "epoch": 1.02, "learning_rate": 1.6468231999858488e-05, "loss": 3.875, "step": 2048000 }, { "epoch": 1.02, "learning_rate": 1.6459846052347968e-05, "loss": 3.873, "step": 2048512 }, { "epoch": 1.02, "learning_rate": 1.6451460104837448e-05, "loss": 3.8613, "step": 2049024 }, { "epoch": 1.02, "learning_rate": 1.644309053613066e-05, "loss": 3.8672, "step": 2049536 }, { "epoch": 1.02, "learning_rate": 1.643470458862014e-05, "loss": 3.8573, "step": 2050048 }, { "epoch": 1.02, "learning_rate": 1.642631864110962e-05, "loss": 3.8814, "step": 2050560 }, { "epoch": 1.02, "learning_rate": 1.64179326935991e-05, "loss": 3.8628, "step": 2051072 }, { "epoch": 1.02, "learning_rate": 1.6409546746088577e-05, "loss": 3.8783, "step": 2051584 }, { "epoch": 1.02, "learning_rate": 1.640117717738179e-05, "loss": 3.8641, "step": 2052096 }, { "epoch": 1.02, "learning_rate": 1.639279122987127e-05, "loss": 3.8788, "step": 2052608 }, { "epoch": 1.02, "learning_rate": 1.638440528236075e-05, "loss": 3.8756, "step": 2053120 }, { "epoch": 1.02, "learning_rate": 1.637601933485023e-05, "loss": 3.865, "step": 2053632 }, { "epoch": 1.02, "learning_rate": 1.636763338733971e-05, "loss": 3.875, "step": 2054144 }, { "epoch": 1.02, "learning_rate": 1.635924743982919e-05, "loss": 3.8634, "step": 2054656 }, { "epoch": 1.02, "learning_rate": 1.635086149231867e-05, "loss": 3.8811, "step": 2055168 }, { "epoch": 1.02, "learning_rate": 1.634247554480815e-05, "loss": 3.8772, "step": 2055680 }, { "epoch": 1.02, "learning_rate": 1.633410597610136e-05, "loss": 3.8634, "step": 2056192 }, { "epoch": 1.02, "learning_rate": 1.6325736407394574e-05, "loss": 3.87, "step": 2056704 }, { "epoch": 1.02, "learning_rate": 1.631735045988405e-05, "loss": 3.8699, "step": 2057216 }, { "epoch": 1.02, "learning_rate": 1.630896451237353e-05, "loss": 3.8794, "step": 2057728 }, { "epoch": 1.02, "learning_rate": 1.630057856486301e-05, "loss": 3.8648, "step": 2058240 }, { "epoch": 1.02, "learning_rate": 1.629219261735249e-05, "loss": 3.8755, "step": 2058752 }, { "epoch": 1.02, "learning_rate": 1.6283806669841974e-05, "loss": 3.8645, "step": 2059264 }, { "epoch": 1.02, "learning_rate": 1.6275420722331454e-05, "loss": 3.8771, "step": 2059776 }, { "epoch": 1.02, "learning_rate": 1.626703477482093e-05, "loss": 3.8699, "step": 2060288 }, { "epoch": 1.03, "eval_loss": 4.035151481628418, "eval_runtime": 294.7345, "eval_samples_per_second": 1294.694, "eval_steps_per_second": 40.46, "step": 2060640 }, { "epoch": 0.0, "learning_rate": 1.625864882731041e-05, "loss": 3.8656, "step": 2060800 }, { "epoch": 0.0, "learning_rate": 1.625026287979989e-05, "loss": 3.8669, "step": 2061312 }, { "epoch": 0.0, "learning_rate": 1.624187693228937e-05, "loss": 3.8732, "step": 2061824 }, { "epoch": 0.0, "learning_rate": 1.623349098477885e-05, "loss": 3.876, "step": 2062336 }, { "epoch": 0.0, "learning_rate": 1.622510503726833e-05, "loss": 3.8832, "step": 2062848 }, { "epoch": 0.0, "learning_rate": 1.6216719089757813e-05, "loss": 3.8687, "step": 2063360 }, { "epoch": 0.0, "learning_rate": 1.620833314224729e-05, "loss": 3.8663, "step": 2063872 }, { "epoch": 0.0, "learning_rate": 1.619994719473677e-05, "loss": 3.8671, "step": 2064384 }, { "epoch": 0.0, "learning_rate": 1.619156124722625e-05, "loss": 3.871, "step": 2064896 }, { "epoch": 0.0, "learning_rate": 1.618317529971573e-05, "loss": 3.8765, "step": 2065408 }, { "epoch": 0.0, "learning_rate": 1.617478935220521e-05, "loss": 3.8677, "step": 2065920 }, { "epoch": 0.0, "learning_rate": 1.616640340469469e-05, "loss": 3.8689, "step": 2066432 }, { "epoch": 0.0, "learning_rate": 1.6158033835987902e-05, "loss": 3.8799, "step": 2066944 }, { "epoch": 0.0, "learning_rate": 1.6149647888477382e-05, "loss": 3.862, "step": 2067456 }, { "epoch": 0.0, "learning_rate": 1.6141261940966862e-05, "loss": 3.8647, "step": 2067968 }, { "epoch": 0.0, "learning_rate": 1.6132875993456342e-05, "loss": 3.8579, "step": 2068480 }, { "epoch": 0.0, "learning_rate": 1.612449004594582e-05, "loss": 3.8596, "step": 2068992 }, { "epoch": 0.0, "learning_rate": 1.61161040984353e-05, "loss": 3.8663, "step": 2069504 }, { "epoch": 0.0, "learning_rate": 1.6107734529728515e-05, "loss": 3.8659, "step": 2070016 }, { "epoch": 0.0, "learning_rate": 1.6099348582217995e-05, "loss": 3.8788, "step": 2070528 }, { "epoch": 0.0, "learning_rate": 1.609096263470747e-05, "loss": 3.8785, "step": 2071040 }, { "epoch": 0.0, "learning_rate": 1.608257668719695e-05, "loss": 3.8695, "step": 2071552 }, { "epoch": 0.0, "learning_rate": 1.607419073968643e-05, "loss": 3.8711, "step": 2072064 }, { "epoch": 0.0, "learning_rate": 1.606580479217591e-05, "loss": 3.8759, "step": 2072576 }, { "epoch": 0.0, "learning_rate": 1.605741884466539e-05, "loss": 3.8555, "step": 2073088 }, { "epoch": 0.0, "learning_rate": 1.6049049275958603e-05, "loss": 3.872, "step": 2073600 }, { "epoch": 0.0, "learning_rate": 1.6040663328448083e-05, "loss": 3.867, "step": 2074112 }, { "epoch": 0.0, "learning_rate": 1.6032277380937563e-05, "loss": 3.8559, "step": 2074624 }, { "epoch": 0.0, "learning_rate": 1.6023891433427043e-05, "loss": 3.8638, "step": 2075136 }, { "epoch": 0.0, "learning_rate": 1.6015505485916523e-05, "loss": 3.8639, "step": 2075648 }, { "epoch": 0.01, "learning_rate": 1.6007119538406e-05, "loss": 3.8668, "step": 2076160 }, { "epoch": 0.01, "learning_rate": 1.5998733590895483e-05, "loss": 3.8683, "step": 2076672 }, { "epoch": 0.01, "learning_rate": 1.5990347643384963e-05, "loss": 3.8748, "step": 2077184 }, { "epoch": 0.01, "learning_rate": 1.5981961695874443e-05, "loss": 3.8689, "step": 2077696 }, { "epoch": 0.01, "learning_rate": 1.5973575748363923e-05, "loss": 3.8609, "step": 2078208 }, { "epoch": 0.01, "learning_rate": 1.5965222558460865e-05, "loss": 3.8753, "step": 2078720 }, { "epoch": 0.01, "learning_rate": 1.5956836610950345e-05, "loss": 3.8785, "step": 2079232 }, { "epoch": 0.01, "learning_rate": 1.5948450663439825e-05, "loss": 3.8616, "step": 2079744 }, { "epoch": 0.01, "learning_rate": 1.5940064715929304e-05, "loss": 3.8663, "step": 2080256 }, { "epoch": 0.01, "learning_rate": 1.5931678768418784e-05, "loss": 3.8639, "step": 2080768 }, { "epoch": 0.01, "learning_rate": 1.5923292820908264e-05, "loss": 3.8582, "step": 2081280 }, { "epoch": 0.01, "learning_rate": 1.5914906873397744e-05, "loss": 3.8791, "step": 2081792 }, { "epoch": 0.01, "learning_rate": 1.5906520925887224e-05, "loss": 3.8713, "step": 2082304 }, { "epoch": 0.01, "learning_rate": 1.5898134978376704e-05, "loss": 3.8751, "step": 2082816 }, { "epoch": 0.01, "learning_rate": 1.5889749030866184e-05, "loss": 3.8676, "step": 2083328 }, { "epoch": 0.01, "learning_rate": 1.5881363083355664e-05, "loss": 3.8693, "step": 2083840 }, { "epoch": 0.01, "learning_rate": 1.5872977135845144e-05, "loss": 3.871, "step": 2084352 }, { "epoch": 0.01, "learning_rate": 1.5864591188334624e-05, "loss": 3.87, "step": 2084864 }, { "epoch": 0.01, "learning_rate": 1.5856237998431566e-05, "loss": 3.8423, "step": 2085376 }, { "epoch": 0.01, "learning_rate": 1.5847852050921046e-05, "loss": 3.8801, "step": 2085888 }, { "epoch": 0.01, "learning_rate": 1.583946610341053e-05, "loss": 3.864, "step": 2086400 }, { "epoch": 0.01, "learning_rate": 1.5831080155900006e-05, "loss": 3.8807, "step": 2086912 }, { "epoch": 0.01, "learning_rate": 1.5822694208389486e-05, "loss": 3.8683, "step": 2087424 }, { "epoch": 0.01, "learning_rate": 1.5814308260878965e-05, "loss": 3.8633, "step": 2087936 }, { "epoch": 0.01, "learning_rate": 1.5805922313368445e-05, "loss": 3.8581, "step": 2088448 }, { "epoch": 0.01, "learning_rate": 1.5797536365857925e-05, "loss": 3.8692, "step": 2088960 }, { "epoch": 0.01, "learning_rate": 1.578918317595487e-05, "loss": 3.8772, "step": 2089472 }, { "epoch": 0.01, "learning_rate": 1.578079722844435e-05, "loss": 3.8636, "step": 2089984 }, { "epoch": 0.01, "learning_rate": 1.577241128093383e-05, "loss": 3.8854, "step": 2090496 }, { "epoch": 0.01, "learning_rate": 1.5764025333423307e-05, "loss": 3.8689, "step": 2091008 }, { "epoch": 0.01, "learning_rate": 1.575565576471652e-05, "loss": 3.8491, "step": 2091520 }, { "epoch": 0.01, "learning_rate": 1.5747269817206e-05, "loss": 3.8807, "step": 2092032 }, { "epoch": 0.01, "learning_rate": 1.573888386969548e-05, "loss": 3.8613, "step": 2092544 }, { "epoch": 0.01, "learning_rate": 1.573049792218496e-05, "loss": 3.8595, "step": 2093056 }, { "epoch": 0.01, "learning_rate": 1.5722128353478172e-05, "loss": 3.8709, "step": 2093568 }, { "epoch": 0.01, "learning_rate": 1.571374240596765e-05, "loss": 3.8726, "step": 2094080 }, { "epoch": 0.01, "learning_rate": 1.5705356458457128e-05, "loss": 3.8546, "step": 2094592 }, { "epoch": 0.01, "learning_rate": 1.5696970510946608e-05, "loss": 3.8609, "step": 2095104 }, { "epoch": 0.01, "learning_rate": 1.568858456343609e-05, "loss": 3.8531, "step": 2095616 }, { "epoch": 0.01, "learning_rate": 1.568019861592557e-05, "loss": 3.8667, "step": 2096128 }, { "epoch": 0.01, "learning_rate": 1.567182904721878e-05, "loss": 3.8717, "step": 2096640 }, { "epoch": 0.01, "learning_rate": 1.566344309970826e-05, "loss": 3.8676, "step": 2097152 }, { "epoch": 0.01, "learning_rate": 1.565505715219774e-05, "loss": 3.8729, "step": 2097664 }, { "epoch": 0.01, "learning_rate": 1.564667120468722e-05, "loss": 3.8603, "step": 2098176 }, { "epoch": 0.01, "learning_rate": 1.56382852571767e-05, "loss": 3.8801, "step": 2098688 }, { "epoch": 0.01, "learning_rate": 1.5629899309666184e-05, "loss": 3.8684, "step": 2099200 }, { "epoch": 0.01, "learning_rate": 1.562151336215566e-05, "loss": 3.877, "step": 2099712 }, { "epoch": 0.01, "learning_rate": 1.561312741464514e-05, "loss": 3.8628, "step": 2100224 }, { "epoch": 0.01, "learning_rate": 1.5604757845938353e-05, "loss": 3.8699, "step": 2100736 }, { "epoch": 0.01, "learning_rate": 1.5596371898427833e-05, "loss": 3.8705, "step": 2101248 }, { "epoch": 0.01, "learning_rate": 1.558798595091731e-05, "loss": 3.8729, "step": 2101760 }, { "epoch": 0.01, "learning_rate": 1.5579600003406793e-05, "loss": 3.867, "step": 2102272 }, { "epoch": 0.01, "learning_rate": 1.5571214055896273e-05, "loss": 3.8776, "step": 2102784 }, { "epoch": 0.01, "learning_rate": 1.5562828108385753e-05, "loss": 3.8567, "step": 2103296 }, { "epoch": 0.01, "learning_rate": 1.5554442160875233e-05, "loss": 3.8635, "step": 2103808 }, { "epoch": 0.01, "learning_rate": 1.5546056213364712e-05, "loss": 3.8666, "step": 2104320 }, { "epoch": 0.01, "learning_rate": 1.553768664465792e-05, "loss": 3.8754, "step": 2104832 }, { "epoch": 0.01, "learning_rate": 1.55293006971474e-05, "loss": 3.86, "step": 2105344 }, { "epoch": 0.01, "learning_rate": 1.5520931128440614e-05, "loss": 3.8658, "step": 2105856 }, { "epoch": 0.01, "learning_rate": 1.5512545180930094e-05, "loss": 3.8662, "step": 2106368 }, { "epoch": 0.02, "learning_rate": 1.5504159233419574e-05, "loss": 3.8658, "step": 2106880 }, { "epoch": 0.02, "learning_rate": 1.5495773285909054e-05, "loss": 3.8704, "step": 2107392 }, { "epoch": 0.02, "learning_rate": 1.5487387338398534e-05, "loss": 3.8577, "step": 2107904 }, { "epoch": 0.02, "learning_rate": 1.5479001390888014e-05, "loss": 3.8698, "step": 2108416 }, { "epoch": 0.02, "learning_rate": 1.5470615443377494e-05, "loss": 3.876, "step": 2108928 }, { "epoch": 0.02, "learning_rate": 1.5462229495866974e-05, "loss": 3.8739, "step": 2109440 }, { "epoch": 0.02, "learning_rate": 1.5453843548356454e-05, "loss": 3.8488, "step": 2109952 }, { "epoch": 0.02, "learning_rate": 1.5445473979649663e-05, "loss": 3.8613, "step": 2110464 }, { "epoch": 0.02, "learning_rate": 1.5437088032139143e-05, "loss": 3.8597, "step": 2110976 }, { "epoch": 0.02, "learning_rate": 1.5428702084628623e-05, "loss": 3.8748, "step": 2111488 }, { "epoch": 0.02, "learning_rate": 1.5420316137118103e-05, "loss": 3.8751, "step": 2112000 }, { "epoch": 0.02, "learning_rate": 1.5411946568411315e-05, "loss": 3.8658, "step": 2112512 }, { "epoch": 0.02, "learning_rate": 1.5403560620900795e-05, "loss": 3.8625, "step": 2113024 }, { "epoch": 0.02, "learning_rate": 1.5395174673390275e-05, "loss": 3.8658, "step": 2113536 }, { "epoch": 0.02, "learning_rate": 1.5386788725879755e-05, "loss": 3.8567, "step": 2114048 }, { "epoch": 0.02, "learning_rate": 1.5378419157172967e-05, "loss": 3.867, "step": 2114560 }, { "epoch": 0.02, "learning_rate": 1.537004958846618e-05, "loss": 3.8633, "step": 2115072 }, { "epoch": 0.02, "learning_rate": 1.536166364095566e-05, "loss": 3.8686, "step": 2115584 }, { "epoch": 0.02, "learning_rate": 1.5353277693445136e-05, "loss": 3.8621, "step": 2116096 }, { "epoch": 0.02, "learning_rate": 1.5344891745934616e-05, "loss": 3.8534, "step": 2116608 }, { "epoch": 0.02, "learning_rate": 1.533652217722783e-05, "loss": 3.8562, "step": 2117120 }, { "epoch": 0.02, "learning_rate": 1.532813622971731e-05, "loss": 3.8606, "step": 2117632 }, { "epoch": 0.02, "learning_rate": 1.531975028220679e-05, "loss": 3.8684, "step": 2118144 }, { "epoch": 0.02, "learning_rate": 1.531136433469627e-05, "loss": 3.8575, "step": 2118656 }, { "epoch": 0.02, "learning_rate": 1.530297838718575e-05, "loss": 3.8704, "step": 2119168 }, { "epoch": 0.02, "learning_rate": 1.529460881847896e-05, "loss": 3.8658, "step": 2119680 }, { "epoch": 0.02, "learning_rate": 1.5286222870968438e-05, "loss": 3.8649, "step": 2120192 }, { "epoch": 0.02, "learning_rate": 1.5277853302261654e-05, "loss": 3.87, "step": 2120704 }, { "epoch": 0.02, "learning_rate": 1.5269467354751134e-05, "loss": 3.8623, "step": 2121216 }, { "epoch": 0.02, "learning_rate": 1.526108140724061e-05, "loss": 3.8695, "step": 2121728 }, { "epoch": 0.02, "learning_rate": 1.525269545973009e-05, "loss": 3.8609, "step": 2122240 }, { "epoch": 0.02, "learning_rate": 1.524430951221957e-05, "loss": 3.8589, "step": 2122752 }, { "epoch": 0.02, "learning_rate": 1.5235923564709052e-05, "loss": 3.8666, "step": 2123264 }, { "epoch": 0.02, "learning_rate": 1.522755399600226e-05, "loss": 3.8628, "step": 2123776 }, { "epoch": 0.02, "learning_rate": 1.521916804849174e-05, "loss": 3.8684, "step": 2124288 }, { "epoch": 0.02, "learning_rate": 1.5210782100981222e-05, "loss": 3.8652, "step": 2124800 }, { "epoch": 0.02, "learning_rate": 1.5202396153470702e-05, "loss": 3.8587, "step": 2125312 }, { "epoch": 0.02, "learning_rate": 1.5194010205960182e-05, "loss": 3.8608, "step": 2125824 }, { "epoch": 0.02, "learning_rate": 1.5185624258449662e-05, "loss": 3.8551, "step": 2126336 }, { "epoch": 0.02, "learning_rate": 1.5177238310939142e-05, "loss": 3.8743, "step": 2126848 }, { "epoch": 0.02, "learning_rate": 1.516885236342862e-05, "loss": 3.8637, "step": 2127360 }, { "epoch": 0.02, "learning_rate": 1.51604664159181e-05, "loss": 3.8748, "step": 2127872 }, { "epoch": 0.02, "learning_rate": 1.515208046840758e-05, "loss": 3.8583, "step": 2128384 }, { "epoch": 0.02, "learning_rate": 1.5143710899700791e-05, "loss": 3.8711, "step": 2128896 }, { "epoch": 0.02, "learning_rate": 1.5135324952190271e-05, "loss": 3.8706, "step": 2129408 }, { "epoch": 0.02, "learning_rate": 1.5126939004679753e-05, "loss": 3.8629, "step": 2129920 }, { "epoch": 0.02, "learning_rate": 1.5118553057169233e-05, "loss": 3.8647, "step": 2130432 }, { "epoch": 0.02, "learning_rate": 1.5110167109658713e-05, "loss": 3.8624, "step": 2130944 }, { "epoch": 0.02, "learning_rate": 1.5101781162148193e-05, "loss": 3.8765, "step": 2131456 }, { "epoch": 0.02, "learning_rate": 1.5093395214637673e-05, "loss": 3.8742, "step": 2131968 }, { "epoch": 0.02, "learning_rate": 1.5085025645930883e-05, "loss": 3.861, "step": 2132480 }, { "epoch": 0.02, "learning_rate": 1.5076656077224094e-05, "loss": 3.8603, "step": 2132992 }, { "epoch": 0.02, "learning_rate": 1.5068270129713574e-05, "loss": 3.8678, "step": 2133504 }, { "epoch": 0.02, "learning_rate": 1.5059884182203054e-05, "loss": 3.8729, "step": 2134016 }, { "epoch": 0.02, "learning_rate": 1.5051498234692534e-05, "loss": 3.8594, "step": 2134528 }, { "epoch": 0.02, "learning_rate": 1.5043112287182016e-05, "loss": 3.8741, "step": 2135040 }, { "epoch": 0.02, "learning_rate": 1.5034726339671496e-05, "loss": 3.8619, "step": 2135552 }, { "epoch": 0.02, "learning_rate": 1.5026340392160972e-05, "loss": 3.8728, "step": 2136064 }, { "epoch": 0.02, "learning_rate": 1.5017954444650454e-05, "loss": 3.8649, "step": 2136576 }, { "epoch": 0.03, "eval_loss": 4.03360652923584, "eval_runtime": 298.8683, "eval_samples_per_second": 1276.786, "eval_steps_per_second": 39.901, "step": 2136960 }, { "epoch": 1.0, "learning_rate": 1.5009584875943666e-05, "loss": 3.8654, "step": 2137088 }, { "epoch": 1.0, "learning_rate": 1.5001198928433146e-05, "loss": 3.8605, "step": 2137600 }, { "epoch": 1.0, "learning_rate": 1.4992812980922625e-05, "loss": 3.8677, "step": 2138112 }, { "epoch": 1.0, "learning_rate": 1.4984427033412105e-05, "loss": 3.8736, "step": 2138624 }, { "epoch": 1.0, "learning_rate": 1.4976041085901585e-05, "loss": 3.8759, "step": 2139136 }, { "epoch": 1.0, "learning_rate": 1.4967671517194795e-05, "loss": 3.867, "step": 2139648 }, { "epoch": 1.0, "learning_rate": 1.4959285569684275e-05, "loss": 3.863, "step": 2140160 }, { "epoch": 1.0, "learning_rate": 1.4950899622173755e-05, "loss": 3.8648, "step": 2140672 }, { "epoch": 1.0, "learning_rate": 1.4942513674663237e-05, "loss": 3.8646, "step": 2141184 }, { "epoch": 1.0, "learning_rate": 1.4934127727152717e-05, "loss": 3.8705, "step": 2141696 }, { "epoch": 1.0, "learning_rate": 1.4925741779642197e-05, "loss": 3.8663, "step": 2142208 }, { "epoch": 1.0, "learning_rate": 1.4917372210935408e-05, "loss": 3.8649, "step": 2142720 }, { "epoch": 1.0, "learning_rate": 1.490900264222862e-05, "loss": 3.8769, "step": 2143232 }, { "epoch": 1.0, "learning_rate": 1.4900616694718098e-05, "loss": 3.8538, "step": 2143744 }, { "epoch": 1.0, "learning_rate": 1.4892230747207578e-05, "loss": 3.8601, "step": 2144256 }, { "epoch": 1.0, "learning_rate": 1.4883844799697058e-05, "loss": 3.8534, "step": 2144768 }, { "epoch": 1.0, "learning_rate": 1.4875458852186538e-05, "loss": 3.8545, "step": 2145280 }, { "epoch": 1.0, "learning_rate": 1.4867072904676018e-05, "loss": 3.8619, "step": 2145792 }, { "epoch": 1.0, "learning_rate": 1.48586869571655e-05, "loss": 3.8591, "step": 2146304 }, { "epoch": 1.0, "learning_rate": 1.4850301009654976e-05, "loss": 3.8752, "step": 2146816 }, { "epoch": 1.0, "learning_rate": 1.4841915062144456e-05, "loss": 3.8769, "step": 2147328 }, { "epoch": 1.0, "learning_rate": 1.4833529114633938e-05, "loss": 3.866, "step": 2147840 }, { "epoch": 1.0, "learning_rate": 1.4825143167123418e-05, "loss": 3.8662, "step": 2148352 }, { "epoch": 1.0, "learning_rate": 1.4816757219612898e-05, "loss": 3.8724, "step": 2148864 }, { "epoch": 1.0, "learning_rate": 1.4808371272102378e-05, "loss": 3.8521, "step": 2149376 }, { "epoch": 1.0, "learning_rate": 1.4800001703395589e-05, "loss": 3.8713, "step": 2149888 }, { "epoch": 1.0, "learning_rate": 1.4791615755885069e-05, "loss": 3.858, "step": 2150400 }, { "epoch": 1.0, "learning_rate": 1.4783229808374549e-05, "loss": 3.8539, "step": 2150912 }, { "epoch": 1.0, "learning_rate": 1.477484386086403e-05, "loss": 3.8608, "step": 2151424 }, { "epoch": 1.0, "learning_rate": 1.476645791335351e-05, "loss": 3.8558, "step": 2151936 }, { "epoch": 1.01, "learning_rate": 1.4758071965842987e-05, "loss": 3.8634, "step": 2152448 }, { "epoch": 1.01, "learning_rate": 1.4749702397136201e-05, "loss": 3.8615, "step": 2152960 }, { "epoch": 1.01, "learning_rate": 1.4741316449625681e-05, "loss": 3.8749, "step": 2153472 }, { "epoch": 1.01, "learning_rate": 1.4732930502115157e-05, "loss": 3.8636, "step": 2153984 }, { "epoch": 1.01, "learning_rate": 1.4724560933408372e-05, "loss": 3.86, "step": 2154496 }, { "epoch": 1.01, "learning_rate": 1.471619136470158e-05, "loss": 3.8706, "step": 2155008 }, { "epoch": 1.01, "learning_rate": 1.4707805417191062e-05, "loss": 3.8771, "step": 2155520 }, { "epoch": 1.01, "learning_rate": 1.4699419469680542e-05, "loss": 3.8576, "step": 2156032 }, { "epoch": 1.01, "learning_rate": 1.4691033522170022e-05, "loss": 3.8579, "step": 2156544 }, { "epoch": 1.01, "learning_rate": 1.4682647574659502e-05, "loss": 3.8617, "step": 2157056 }, { "epoch": 1.01, "learning_rate": 1.4674261627148982e-05, "loss": 3.8576, "step": 2157568 }, { "epoch": 1.01, "learning_rate": 1.466587567963846e-05, "loss": 3.8693, "step": 2158080 }, { "epoch": 1.01, "learning_rate": 1.465748973212794e-05, "loss": 3.8644, "step": 2158592 }, { "epoch": 1.01, "learning_rate": 1.464910378461742e-05, "loss": 3.872, "step": 2159104 }, { "epoch": 1.01, "learning_rate": 1.4640717837106902e-05, "loss": 3.8657, "step": 2159616 }, { "epoch": 1.01, "learning_rate": 1.4632331889596382e-05, "loss": 3.8652, "step": 2160128 }, { "epoch": 1.01, "learning_rate": 1.4623945942085862e-05, "loss": 3.8666, "step": 2160640 }, { "epoch": 1.01, "learning_rate": 1.461555999457534e-05, "loss": 3.8637, "step": 2161152 }, { "epoch": 1.01, "learning_rate": 1.460717404706482e-05, "loss": 3.8395, "step": 2161664 }, { "epoch": 1.01, "learning_rate": 1.45987880995543e-05, "loss": 3.8728, "step": 2162176 }, { "epoch": 1.01, "learning_rate": 1.4590418530847513e-05, "loss": 3.8615, "step": 2162688 }, { "epoch": 1.01, "learning_rate": 1.458203258333699e-05, "loss": 3.8733, "step": 2163200 }, { "epoch": 1.01, "learning_rate": 1.4573663014630203e-05, "loss": 3.8611, "step": 2163712 }, { "epoch": 1.01, "learning_rate": 1.4565277067119685e-05, "loss": 3.8636, "step": 2164224 }, { "epoch": 1.01, "learning_rate": 1.4556891119609165e-05, "loss": 3.8507, "step": 2164736 }, { "epoch": 1.01, "learning_rate": 1.4548505172098641e-05, "loss": 3.8606, "step": 2165248 }, { "epoch": 1.01, "learning_rate": 1.4540119224588123e-05, "loss": 3.8777, "step": 2165760 }, { "epoch": 1.01, "learning_rate": 1.4531733277077603e-05, "loss": 3.8604, "step": 2166272 }, { "epoch": 1.01, "learning_rate": 1.4523347329567083e-05, "loss": 3.8795, "step": 2166784 }, { "epoch": 1.01, "learning_rate": 1.4514961382056563e-05, "loss": 3.8663, "step": 2167296 }, { "epoch": 1.01, "learning_rate": 1.4506591813349774e-05, "loss": 3.8439, "step": 2167808 }, { "epoch": 1.01, "learning_rate": 1.4498205865839254e-05, "loss": 3.8806, "step": 2168320 }, { "epoch": 1.01, "learning_rate": 1.4489819918328734e-05, "loss": 3.8542, "step": 2168832 }, { "epoch": 1.01, "learning_rate": 1.4481433970818215e-05, "loss": 3.8547, "step": 2169344 }, { "epoch": 1.01, "learning_rate": 1.4473048023307695e-05, "loss": 3.8689, "step": 2169856 }, { "epoch": 1.01, "learning_rate": 1.4464678454600904e-05, "loss": 3.8676, "step": 2170368 }, { "epoch": 1.01, "learning_rate": 1.4456292507090386e-05, "loss": 3.854, "step": 2170880 }, { "epoch": 1.01, "learning_rate": 1.4447906559579866e-05, "loss": 3.8559, "step": 2171392 }, { "epoch": 1.01, "learning_rate": 1.4439520612069343e-05, "loss": 3.8519, "step": 2171904 }, { "epoch": 1.01, "learning_rate": 1.4431134664558824e-05, "loss": 3.8551, "step": 2172416 }, { "epoch": 1.01, "learning_rate": 1.4422748717048304e-05, "loss": 3.8734, "step": 2172928 }, { "epoch": 1.01, "learning_rate": 1.4414362769537784e-05, "loss": 3.866, "step": 2173440 }, { "epoch": 1.01, "learning_rate": 1.4405993200830995e-05, "loss": 3.8636, "step": 2173952 }, { "epoch": 1.01, "learning_rate": 1.4397607253320475e-05, "loss": 3.8556, "step": 2174464 }, { "epoch": 1.01, "learning_rate": 1.4389221305809955e-05, "loss": 3.8755, "step": 2174976 }, { "epoch": 1.01, "learning_rate": 1.4380851737103167e-05, "loss": 3.8622, "step": 2175488 }, { "epoch": 1.01, "learning_rate": 1.4372465789592646e-05, "loss": 3.8705, "step": 2176000 }, { "epoch": 1.01, "learning_rate": 1.4364079842082126e-05, "loss": 3.8586, "step": 2176512 }, { "epoch": 1.01, "learning_rate": 1.4355693894571605e-05, "loss": 3.8643, "step": 2177024 }, { "epoch": 1.01, "learning_rate": 1.4347307947061087e-05, "loss": 3.8694, "step": 2177536 }, { "epoch": 1.01, "learning_rate": 1.4338938378354296e-05, "loss": 3.8662, "step": 2178048 }, { "epoch": 1.01, "learning_rate": 1.4330552430843778e-05, "loss": 3.8657, "step": 2178560 }, { "epoch": 1.01, "learning_rate": 1.4322166483333258e-05, "loss": 3.8711, "step": 2179072 }, { "epoch": 1.01, "learning_rate": 1.4313780535822738e-05, "loss": 3.8553, "step": 2179584 }, { "epoch": 1.01, "learning_rate": 1.4305394588312218e-05, "loss": 3.8585, "step": 2180096 }, { "epoch": 1.01, "learning_rate": 1.4297008640801698e-05, "loss": 3.8641, "step": 2180608 }, { "epoch": 1.01, "learning_rate": 1.4288622693291176e-05, "loss": 3.869, "step": 2181120 }, { "epoch": 1.01, "learning_rate": 1.4280236745780656e-05, "loss": 3.8573, "step": 2181632 }, { "epoch": 1.01, "learning_rate": 1.427186717707387e-05, "loss": 3.8639, "step": 2182144 }, { "epoch": 1.01, "learning_rate": 1.426348122956335e-05, "loss": 3.8593, "step": 2182656 }, { "epoch": 1.02, "learning_rate": 1.4255095282052827e-05, "loss": 3.8597, "step": 2183168 }, { "epoch": 1.02, "learning_rate": 1.4246709334542308e-05, "loss": 3.8664, "step": 2183680 }, { "epoch": 1.02, "learning_rate": 1.4238323387031788e-05, "loss": 3.8564, "step": 2184192 }, { "epoch": 1.02, "learning_rate": 1.4229937439521268e-05, "loss": 3.8664, "step": 2184704 }, { "epoch": 1.02, "learning_rate": 1.4221567870814479e-05, "loss": 3.8707, "step": 2185216 }, { "epoch": 1.02, "learning_rate": 1.4213181923303959e-05, "loss": 3.8761, "step": 2185728 }, { "epoch": 1.02, "learning_rate": 1.4204812354597171e-05, "loss": 3.84, "step": 2186240 }, { "epoch": 1.02, "learning_rate": 1.419642640708665e-05, "loss": 3.8601, "step": 2186752 }, { "epoch": 1.02, "learning_rate": 1.418804045957613e-05, "loss": 3.855, "step": 2187264 }, { "epoch": 1.02, "learning_rate": 1.417965451206561e-05, "loss": 3.8713, "step": 2187776 }, { "epoch": 1.02, "learning_rate": 1.417126856455509e-05, "loss": 3.8704, "step": 2188288 }, { "epoch": 1.02, "learning_rate": 1.4162882617044571e-05, "loss": 3.8605, "step": 2188800 }, { "epoch": 1.02, "learning_rate": 1.4154496669534051e-05, "loss": 3.8586, "step": 2189312 }, { "epoch": 1.02, "learning_rate": 1.4146110722023531e-05, "loss": 3.8598, "step": 2189824 }, { "epoch": 1.02, "learning_rate": 1.413772477451301e-05, "loss": 3.856, "step": 2190336 }, { "epoch": 1.02, "learning_rate": 1.412933882700249e-05, "loss": 3.8586, "step": 2190848 }, { "epoch": 1.02, "learning_rate": 1.4120969258295702e-05, "loss": 3.8594, "step": 2191360 }, { "epoch": 1.02, "learning_rate": 1.411258331078518e-05, "loss": 3.8637, "step": 2191872 }, { "epoch": 1.02, "learning_rate": 1.410419736327466e-05, "loss": 3.8577, "step": 2192384 }, { "epoch": 1.02, "learning_rate": 1.409581141576414e-05, "loss": 3.8522, "step": 2192896 }, { "epoch": 1.02, "learning_rate": 1.408742546825362e-05, "loss": 3.8528, "step": 2193408 }, { "epoch": 1.02, "learning_rate": 1.4079039520743102e-05, "loss": 3.8519, "step": 2193920 }, { "epoch": 1.02, "learning_rate": 1.407066995203631e-05, "loss": 3.8659, "step": 2194432 }, { "epoch": 1.02, "learning_rate": 1.406228400452579e-05, "loss": 3.8514, "step": 2194944 }, { "epoch": 1.02, "learning_rate": 1.4053898057015272e-05, "loss": 3.8658, "step": 2195456 }, { "epoch": 1.02, "learning_rate": 1.4045512109504752e-05, "loss": 3.862, "step": 2195968 }, { "epoch": 1.02, "learning_rate": 1.4037126161994232e-05, "loss": 3.8616, "step": 2196480 }, { "epoch": 1.02, "learning_rate": 1.4028756593287443e-05, "loss": 3.862, "step": 2196992 }, { "epoch": 1.02, "learning_rate": 1.4020370645776923e-05, "loss": 3.8601, "step": 2197504 }, { "epoch": 1.02, "learning_rate": 1.4011984698266403e-05, "loss": 3.8653, "step": 2198016 }, { "epoch": 1.02, "learning_rate": 1.4003598750755883e-05, "loss": 3.8571, "step": 2198528 }, { "epoch": 1.02, "learning_rate": 1.3995212803245361e-05, "loss": 3.8542, "step": 2199040 }, { "epoch": 1.02, "learning_rate": 1.3986826855734841e-05, "loss": 3.8625, "step": 2199552 }, { "epoch": 1.02, "learning_rate": 1.3978440908224321e-05, "loss": 3.8589, "step": 2200064 }, { "epoch": 1.02, "learning_rate": 1.3970054960713803e-05, "loss": 3.8646, "step": 2200576 }, { "epoch": 1.02, "learning_rate": 1.3961685392007012e-05, "loss": 3.858, "step": 2201088 }, { "epoch": 1.02, "learning_rate": 1.3953299444496493e-05, "loss": 3.856, "step": 2201600 }, { "epoch": 1.02, "learning_rate": 1.3944929875789706e-05, "loss": 3.8583, "step": 2202112 }, { "epoch": 1.02, "learning_rate": 1.3936560307082917e-05, "loss": 3.8539, "step": 2202624 }, { "epoch": 1.02, "learning_rate": 1.3928174359572397e-05, "loss": 3.8623, "step": 2203136 }, { "epoch": 1.02, "learning_rate": 1.3919788412061877e-05, "loss": 3.8615, "step": 2203648 }, { "epoch": 1.02, "learning_rate": 1.3911402464551357e-05, "loss": 3.8724, "step": 2204160 }, { "epoch": 1.02, "learning_rate": 1.3903016517040835e-05, "loss": 3.8554, "step": 2204672 }, { "epoch": 1.02, "learning_rate": 1.3894630569530315e-05, "loss": 3.8624, "step": 2205184 }, { "epoch": 1.02, "learning_rate": 1.3886244622019795e-05, "loss": 3.8683, "step": 2205696 }, { "epoch": 1.02, "learning_rate": 1.3877858674509275e-05, "loss": 3.8638, "step": 2206208 }, { "epoch": 1.02, "learning_rate": 1.3869472726998756e-05, "loss": 3.8579, "step": 2206720 }, { "epoch": 1.02, "learning_rate": 1.3861086779488236e-05, "loss": 3.8581, "step": 2207232 }, { "epoch": 1.02, "learning_rate": 1.3852717210781445e-05, "loss": 3.8735, "step": 2207744 }, { "epoch": 1.02, "learning_rate": 1.3844331263270927e-05, "loss": 3.8695, "step": 2208256 }, { "epoch": 1.02, "learning_rate": 1.3835945315760407e-05, "loss": 3.8595, "step": 2208768 }, { "epoch": 1.02, "learning_rate": 1.3827559368249887e-05, "loss": 3.8552, "step": 2209280 }, { "epoch": 1.02, "learning_rate": 1.3819173420739365e-05, "loss": 3.8647, "step": 2209792 }, { "epoch": 1.02, "learning_rate": 1.3810803852032578e-05, "loss": 3.8693, "step": 2210304 }, { "epoch": 1.02, "learning_rate": 1.3802417904522058e-05, "loss": 3.8526, "step": 2210816 }, { "epoch": 1.02, "learning_rate": 1.3794031957011538e-05, "loss": 3.8762, "step": 2211328 }, { "epoch": 1.02, "learning_rate": 1.3785646009501016e-05, "loss": 3.8546, "step": 2211840 }, { "epoch": 1.02, "learning_rate": 1.3777260061990496e-05, "loss": 3.8671, "step": 2212352 }, { "epoch": 1.02, "learning_rate": 1.3768874114479976e-05, "loss": 3.8632, "step": 2212864 }, { "epoch": 1.03, "eval_loss": 4.032455921173096, "eval_runtime": 295.2432, "eval_samples_per_second": 1292.463, "eval_steps_per_second": 40.39, "step": 2213280 }, { "epoch": 0.0, "learning_rate": 1.376050454577319e-05, "loss": 3.8868, "step": 2213376 }, { "epoch": 0.0, "learning_rate": 1.3752118598262667e-05, "loss": 3.8577, "step": 2213888 }, { "epoch": 0.0, "learning_rate": 1.3743732650752148e-05, "loss": 3.8608, "step": 2214400 }, { "epoch": 0.0, "learning_rate": 1.3735346703241628e-05, "loss": 3.872, "step": 2214912 }, { "epoch": 0.0, "learning_rate": 1.3726960755731108e-05, "loss": 3.865, "step": 2215424 }, { "epoch": 0.0, "learning_rate": 1.3718574808220588e-05, "loss": 3.8661, "step": 2215936 }, { "epoch": 0.0, "learning_rate": 1.3710188860710068e-05, "loss": 3.8581, "step": 2216448 }, { "epoch": 0.0, "learning_rate": 1.3701802913199546e-05, "loss": 3.8565, "step": 2216960 }, { "epoch": 0.0, "learning_rate": 1.3693416965689026e-05, "loss": 3.8607, "step": 2217472 }, { "epoch": 0.0, "learning_rate": 1.3685031018178506e-05, "loss": 3.8695, "step": 2217984 }, { "epoch": 0.0, "learning_rate": 1.3676645070667988e-05, "loss": 3.8596, "step": 2218496 }, { "epoch": 0.0, "learning_rate": 1.3668259123157468e-05, "loss": 3.8658, "step": 2219008 }, { "epoch": 0.0, "learning_rate": 1.3659889554450679e-05, "loss": 3.8704, "step": 2219520 }, { "epoch": 0.0, "learning_rate": 1.3651503606940159e-05, "loss": 3.8488, "step": 2220032 }, { "epoch": 0.0, "learning_rate": 1.3643117659429638e-05, "loss": 3.8615, "step": 2220544 }, { "epoch": 0.0, "learning_rate": 1.3634731711919118e-05, "loss": 3.8473, "step": 2221056 }, { "epoch": 0.0, "learning_rate": 1.362636214321233e-05, "loss": 3.8485, "step": 2221568 }, { "epoch": 0.0, "learning_rate": 1.361797619570181e-05, "loss": 3.8632, "step": 2222080 }, { "epoch": 0.0, "learning_rate": 1.3609590248191289e-05, "loss": 3.8509, "step": 2222592 }, { "epoch": 0.0, "learning_rate": 1.3601204300680769e-05, "loss": 3.8676, "step": 2223104 }, { "epoch": 0.0, "learning_rate": 1.359281835317025e-05, "loss": 3.8716, "step": 2223616 }, { "epoch": 0.0, "learning_rate": 1.3584432405659727e-05, "loss": 3.8607, "step": 2224128 }, { "epoch": 0.0, "learning_rate": 1.3576046458149207e-05, "loss": 3.8644, "step": 2224640 }, { "epoch": 0.0, "learning_rate": 1.3567660510638689e-05, "loss": 3.8665, "step": 2225152 }, { "epoch": 0.0, "learning_rate": 1.3559290941931901e-05, "loss": 3.8495, "step": 2225664 }, { "epoch": 0.0, "learning_rate": 1.355090499442138e-05, "loss": 3.8643, "step": 2226176 }, { "epoch": 0.0, "learning_rate": 1.354251904691086e-05, "loss": 3.8562, "step": 2226688 }, { "epoch": 0.0, "learning_rate": 1.353413309940034e-05, "loss": 3.8524, "step": 2227200 }, { "epoch": 0.0, "learning_rate": 1.3525763530693552e-05, "loss": 3.8589, "step": 2227712 }, { "epoch": 0.0, "learning_rate": 1.351737758318303e-05, "loss": 3.8499, "step": 2228224 }, { "epoch": 0.01, "learning_rate": 1.350899163567251e-05, "loss": 3.8581, "step": 2228736 }, { "epoch": 0.01, "learning_rate": 1.350060568816199e-05, "loss": 3.8592, "step": 2229248 }, { "epoch": 0.01, "learning_rate": 1.3492219740651472e-05, "loss": 3.869, "step": 2229760 }, { "epoch": 0.01, "learning_rate": 1.3483850171944681e-05, "loss": 3.8579, "step": 2230272 }, { "epoch": 0.01, "learning_rate": 1.3475464224434161e-05, "loss": 3.8546, "step": 2230784 }, { "epoch": 0.01, "learning_rate": 1.3467094655727375e-05, "loss": 3.8602, "step": 2231296 }, { "epoch": 0.01, "learning_rate": 1.3458708708216852e-05, "loss": 3.873, "step": 2231808 }, { "epoch": 0.01, "learning_rate": 1.3450322760706333e-05, "loss": 3.855, "step": 2232320 }, { "epoch": 0.01, "learning_rate": 1.3441936813195813e-05, "loss": 3.8533, "step": 2232832 }, { "epoch": 0.01, "learning_rate": 1.3433550865685293e-05, "loss": 3.857, "step": 2233344 }, { "epoch": 0.01, "learning_rate": 1.3425164918174773e-05, "loss": 3.8592, "step": 2233856 }, { "epoch": 0.01, "learning_rate": 1.3416778970664253e-05, "loss": 3.8609, "step": 2234368 }, { "epoch": 0.01, "learning_rate": 1.3408409401957464e-05, "loss": 3.8652, "step": 2234880 }, { "epoch": 0.01, "learning_rate": 1.3400023454446944e-05, "loss": 3.8655, "step": 2235392 }, { "epoch": 0.01, "learning_rate": 1.3391637506936426e-05, "loss": 3.8616, "step": 2235904 }, { "epoch": 0.01, "learning_rate": 1.3383251559425906e-05, "loss": 3.8595, "step": 2236416 }, { "epoch": 0.01, "learning_rate": 1.3374865611915382e-05, "loss": 3.8615, "step": 2236928 }, { "epoch": 0.01, "learning_rate": 1.3366479664404862e-05, "loss": 3.8602, "step": 2237440 }, { "epoch": 0.01, "learning_rate": 1.3358093716894344e-05, "loss": 3.8413, "step": 2237952 }, { "epoch": 0.01, "learning_rate": 1.3349724148187556e-05, "loss": 3.8666, "step": 2238464 }, { "epoch": 0.01, "learning_rate": 1.3341338200677034e-05, "loss": 3.86, "step": 2238976 }, { "epoch": 0.01, "learning_rate": 1.3332952253166514e-05, "loss": 3.8697, "step": 2239488 }, { "epoch": 0.01, "learning_rate": 1.3324566305655994e-05, "loss": 3.8551, "step": 2240000 }, { "epoch": 0.01, "learning_rate": 1.3316180358145474e-05, "loss": 3.8582, "step": 2240512 }, { "epoch": 0.01, "learning_rate": 1.3307794410634954e-05, "loss": 3.8527, "step": 2241024 }, { "epoch": 0.01, "learning_rate": 1.3299408463124436e-05, "loss": 3.8512, "step": 2241536 }, { "epoch": 0.01, "learning_rate": 1.3291022515613912e-05, "loss": 3.8729, "step": 2242048 }, { "epoch": 0.01, "learning_rate": 1.3282636568103392e-05, "loss": 3.8568, "step": 2242560 }, { "epoch": 0.01, "learning_rate": 1.3274266999396607e-05, "loss": 3.8808, "step": 2243072 }, { "epoch": 0.01, "learning_rate": 1.3265881051886087e-05, "loss": 3.8581, "step": 2243584 }, { "epoch": 0.01, "learning_rate": 1.3257495104375565e-05, "loss": 3.8433, "step": 2244096 }, { "epoch": 0.01, "learning_rate": 1.3249109156865045e-05, "loss": 3.8744, "step": 2244608 }, { "epoch": 0.01, "learning_rate": 1.3240723209354525e-05, "loss": 3.8535, "step": 2245120 }, { "epoch": 0.01, "learning_rate": 1.3232337261844005e-05, "loss": 3.8474, "step": 2245632 }, { "epoch": 0.01, "learning_rate": 1.3223967693137215e-05, "loss": 3.8582, "step": 2246144 }, { "epoch": 0.01, "learning_rate": 1.3215581745626695e-05, "loss": 3.867, "step": 2246656 }, { "epoch": 0.01, "learning_rate": 1.3207195798116175e-05, "loss": 3.849, "step": 2247168 }, { "epoch": 0.01, "learning_rate": 1.3198809850605657e-05, "loss": 3.8539, "step": 2247680 }, { "epoch": 0.01, "learning_rate": 1.3190423903095137e-05, "loss": 3.8491, "step": 2248192 }, { "epoch": 0.01, "learning_rate": 1.3182037955584617e-05, "loss": 3.8481, "step": 2248704 }, { "epoch": 0.01, "learning_rate": 1.3173652008074095e-05, "loss": 3.8702, "step": 2249216 }, { "epoch": 0.01, "learning_rate": 1.3165266060563575e-05, "loss": 3.8602, "step": 2249728 }, { "epoch": 0.01, "learning_rate": 1.3156896491856788e-05, "loss": 3.8589, "step": 2250240 }, { "epoch": 0.01, "learning_rate": 1.3148510544346268e-05, "loss": 3.8522, "step": 2250752 }, { "epoch": 0.01, "learning_rate": 1.3140124596835746e-05, "loss": 3.8708, "step": 2251264 }, { "epoch": 0.01, "learning_rate": 1.3131738649325226e-05, "loss": 3.8601, "step": 2251776 }, { "epoch": 0.01, "learning_rate": 1.3123369080618438e-05, "loss": 3.8687, "step": 2252288 }, { "epoch": 0.01, "learning_rate": 1.311498313310792e-05, "loss": 3.8541, "step": 2252800 }, { "epoch": 0.01, "learning_rate": 1.3106597185597397e-05, "loss": 3.8614, "step": 2253312 }, { "epoch": 0.01, "learning_rate": 1.3098211238086876e-05, "loss": 3.8668, "step": 2253824 }, { "epoch": 0.01, "learning_rate": 1.3089825290576358e-05, "loss": 3.8598, "step": 2254336 }, { "epoch": 0.01, "learning_rate": 1.3081439343065838e-05, "loss": 3.8612, "step": 2254848 }, { "epoch": 0.01, "learning_rate": 1.3073053395555318e-05, "loss": 3.868, "step": 2255360 }, { "epoch": 0.01, "learning_rate": 1.3064667448044798e-05, "loss": 3.8574, "step": 2255872 }, { "epoch": 0.01, "learning_rate": 1.3056314258141741e-05, "loss": 3.8515, "step": 2256384 }, { "epoch": 0.01, "learning_rate": 1.304792831063122e-05, "loss": 3.8576, "step": 2256896 }, { "epoch": 0.01, "learning_rate": 1.30395423631207e-05, "loss": 3.8642, "step": 2257408 }, { "epoch": 0.01, "learning_rate": 1.303115641561018e-05, "loss": 3.8556, "step": 2257920 }, { "epoch": 0.01, "learning_rate": 1.302277046809966e-05, "loss": 3.8559, "step": 2258432 }, { "epoch": 0.01, "learning_rate": 1.301438452058914e-05, "loss": 3.8555, "step": 2258944 }, { "epoch": 0.02, "learning_rate": 1.3005998573078621e-05, "loss": 3.858, "step": 2259456 }, { "epoch": 0.02, "learning_rate": 1.299762900437183e-05, "loss": 3.8603, "step": 2259968 }, { "epoch": 0.02, "learning_rate": 1.2989243056861312e-05, "loss": 3.854, "step": 2260480 }, { "epoch": 0.02, "learning_rate": 1.2980857109350792e-05, "loss": 3.8626, "step": 2260992 }, { "epoch": 0.02, "learning_rate": 1.2972471161840272e-05, "loss": 3.8643, "step": 2261504 }, { "epoch": 0.02, "learning_rate": 1.2964101593133482e-05, "loss": 3.8704, "step": 2262016 }, { "epoch": 0.02, "learning_rate": 1.2955715645622962e-05, "loss": 3.8372, "step": 2262528 }, { "epoch": 0.02, "learning_rate": 1.2947329698112442e-05, "loss": 3.8544, "step": 2263040 }, { "epoch": 0.02, "learning_rate": 1.2938943750601922e-05, "loss": 3.8514, "step": 2263552 }, { "epoch": 0.02, "learning_rate": 1.29305578030914e-05, "loss": 3.8657, "step": 2264064 }, { "epoch": 0.02, "learning_rate": 1.292217185558088e-05, "loss": 3.8685, "step": 2264576 }, { "epoch": 0.02, "learning_rate": 1.291378590807036e-05, "loss": 3.8559, "step": 2265088 }, { "epoch": 0.02, "learning_rate": 1.2905399960559842e-05, "loss": 3.8547, "step": 2265600 }, { "epoch": 0.02, "learning_rate": 1.2897030391853051e-05, "loss": 3.8577, "step": 2266112 }, { "epoch": 0.02, "learning_rate": 1.2888660823146265e-05, "loss": 3.8543, "step": 2266624 }, { "epoch": 0.02, "learning_rate": 1.2880274875635745e-05, "loss": 3.8524, "step": 2267136 }, { "epoch": 0.02, "learning_rate": 1.2871905306928955e-05, "loss": 3.8557, "step": 2267648 }, { "epoch": 0.02, "learning_rate": 1.2863519359418436e-05, "loss": 3.8598, "step": 2268160 }, { "epoch": 0.02, "learning_rate": 1.2855133411907916e-05, "loss": 3.8535, "step": 2268672 }, { "epoch": 0.02, "learning_rate": 1.2846747464397396e-05, "loss": 3.8497, "step": 2269184 }, { "epoch": 0.02, "learning_rate": 1.2838361516886874e-05, "loss": 3.8509, "step": 2269696 }, { "epoch": 0.02, "learning_rate": 1.2829975569376354e-05, "loss": 3.8435, "step": 2270208 }, { "epoch": 0.02, "learning_rate": 1.2821589621865834e-05, "loss": 3.8602, "step": 2270720 }, { "epoch": 0.02, "learning_rate": 1.2813203674355314e-05, "loss": 3.8547, "step": 2271232 }, { "epoch": 0.02, "learning_rate": 1.2804834105648525e-05, "loss": 3.8558, "step": 2271744 }, { "epoch": 0.02, "learning_rate": 1.2796448158138005e-05, "loss": 3.8617, "step": 2272256 }, { "epoch": 0.02, "learning_rate": 1.2788062210627485e-05, "loss": 3.8581, "step": 2272768 }, { "epoch": 0.02, "learning_rate": 1.2779692641920696e-05, "loss": 3.8555, "step": 2273280 }, { "epoch": 0.02, "learning_rate": 1.2771306694410176e-05, "loss": 3.8541, "step": 2273792 }, { "epoch": 0.02, "learning_rate": 1.2762920746899656e-05, "loss": 3.8638, "step": 2274304 }, { "epoch": 0.02, "learning_rate": 1.2754534799389137e-05, "loss": 3.8533, "step": 2274816 }, { "epoch": 0.02, "learning_rate": 1.2746148851878617e-05, "loss": 3.8484, "step": 2275328 }, { "epoch": 0.02, "learning_rate": 1.2737762904368097e-05, "loss": 3.8604, "step": 2275840 }, { "epoch": 0.02, "learning_rate": 1.2729376956857577e-05, "loss": 3.8562, "step": 2276352 }, { "epoch": 0.02, "learning_rate": 1.2720991009347055e-05, "loss": 3.8562, "step": 2276864 }, { "epoch": 0.02, "learning_rate": 1.2712621440640268e-05, "loss": 3.8522, "step": 2277376 }, { "epoch": 0.02, "learning_rate": 1.2704235493129748e-05, "loss": 3.8581, "step": 2277888 }, { "epoch": 0.02, "learning_rate": 1.2695849545619226e-05, "loss": 3.8534, "step": 2278400 }, { "epoch": 0.02, "learning_rate": 1.2687463598108706e-05, "loss": 3.8511, "step": 2278912 }, { "epoch": 0.02, "learning_rate": 1.2679077650598186e-05, "loss": 3.8498, "step": 2279424 }, { "epoch": 0.02, "learning_rate": 1.2670691703087668e-05, "loss": 3.8647, "step": 2279936 }, { "epoch": 0.02, "learning_rate": 1.2662305755577148e-05, "loss": 3.8689, "step": 2280448 }, { "epoch": 0.02, "learning_rate": 1.2653919808066628e-05, "loss": 3.8475, "step": 2280960 }, { "epoch": 0.02, "learning_rate": 1.2645533860556108e-05, "loss": 3.8544, "step": 2281472 }, { "epoch": 0.02, "learning_rate": 1.2637147913045586e-05, "loss": 3.8676, "step": 2281984 }, { "epoch": 0.02, "learning_rate": 1.2628778344338798e-05, "loss": 3.859, "step": 2282496 }, { "epoch": 0.02, "learning_rate": 1.2620408775632009e-05, "loss": 3.8505, "step": 2283008 }, { "epoch": 0.02, "learning_rate": 1.2612022828121489e-05, "loss": 3.8535, "step": 2283520 }, { "epoch": 0.02, "learning_rate": 1.2603636880610969e-05, "loss": 3.8732, "step": 2284032 }, { "epoch": 0.02, "learning_rate": 1.259525093310045e-05, "loss": 3.8649, "step": 2284544 }, { "epoch": 0.02, "learning_rate": 1.258686498558993e-05, "loss": 3.855, "step": 2285056 }, { "epoch": 0.02, "learning_rate": 1.2578479038079407e-05, "loss": 3.8478, "step": 2285568 }, { "epoch": 0.02, "learning_rate": 1.2570093090568889e-05, "loss": 3.8618, "step": 2286080 }, { "epoch": 0.02, "learning_rate": 1.2561707143058369e-05, "loss": 3.8626, "step": 2286592 }, { "epoch": 0.02, "learning_rate": 1.2553321195547849e-05, "loss": 3.8505, "step": 2287104 }, { "epoch": 0.02, "learning_rate": 1.2544935248037329e-05, "loss": 3.8709, "step": 2287616 }, { "epoch": 0.02, "learning_rate": 1.253656567933054e-05, "loss": 3.8565, "step": 2288128 }, { "epoch": 0.02, "learning_rate": 1.252817973182002e-05, "loss": 3.8608, "step": 2288640 }, { "epoch": 0.02, "learning_rate": 1.25197937843095e-05, "loss": 3.8588, "step": 2289152 }, { "epoch": 0.03, "eval_loss": 4.030513763427734, "eval_runtime": 295.3582, "eval_samples_per_second": 1291.96, "eval_steps_per_second": 40.375, "step": 2289600 }, { "epoch": 1.0, "learning_rate": 1.251140783679898e-05, "loss": 3.8607, "step": 2289664 }, { "epoch": 1.0, "learning_rate": 1.2503021889288461e-05, "loss": 3.8505, "step": 2290176 }, { "epoch": 1.0, "learning_rate": 1.249465232058167e-05, "loss": 3.8594, "step": 2290688 }, { "epoch": 1.0, "learning_rate": 1.2486266373071152e-05, "loss": 3.8692, "step": 2291200 }, { "epoch": 1.0, "learning_rate": 1.2477880425560632e-05, "loss": 3.8625, "step": 2291712 }, { "epoch": 1.0, "learning_rate": 1.246949447805011e-05, "loss": 3.8619, "step": 2292224 }, { "epoch": 1.0, "learning_rate": 1.246110853053959e-05, "loss": 3.8572, "step": 2292736 }, { "epoch": 1.0, "learning_rate": 1.2452722583029072e-05, "loss": 3.8533, "step": 2293248 }, { "epoch": 1.0, "learning_rate": 1.244435301432228e-05, "loss": 3.8564, "step": 2293760 }, { "epoch": 1.0, "learning_rate": 1.2435983445615493e-05, "loss": 3.8636, "step": 2294272 }, { "epoch": 1.0, "learning_rate": 1.2427597498104973e-05, "loss": 3.8578, "step": 2294784 }, { "epoch": 1.0, "learning_rate": 1.2419211550594453e-05, "loss": 3.8641, "step": 2295296 }, { "epoch": 1.0, "learning_rate": 1.2410841981887664e-05, "loss": 3.8661, "step": 2295808 }, { "epoch": 1.0, "learning_rate": 1.2402456034377144e-05, "loss": 3.8458, "step": 2296320 }, { "epoch": 1.0, "learning_rate": 1.2394070086866624e-05, "loss": 3.8554, "step": 2296832 }, { "epoch": 1.0, "learning_rate": 1.2385684139356105e-05, "loss": 3.8435, "step": 2297344 }, { "epoch": 1.0, "learning_rate": 1.2377298191845584e-05, "loss": 3.8476, "step": 2297856 }, { "epoch": 1.0, "learning_rate": 1.2368912244335064e-05, "loss": 3.8551, "step": 2298368 }, { "epoch": 1.0, "learning_rate": 1.2360526296824544e-05, "loss": 3.8471, "step": 2298880 }, { "epoch": 1.0, "learning_rate": 1.2352140349314023e-05, "loss": 3.8619, "step": 2299392 }, { "epoch": 1.0, "learning_rate": 1.2343754401803503e-05, "loss": 3.8719, "step": 2299904 }, { "epoch": 1.0, "learning_rate": 1.2335368454292983e-05, "loss": 3.8523, "step": 2300416 }, { "epoch": 1.0, "learning_rate": 1.2326998885586196e-05, "loss": 3.8647, "step": 2300928 }, { "epoch": 1.0, "learning_rate": 1.2318612938075674e-05, "loss": 3.8636, "step": 2301440 }, { "epoch": 1.0, "learning_rate": 1.2310226990565154e-05, "loss": 3.848, "step": 2301952 }, { "epoch": 1.0, "learning_rate": 1.2301841043054636e-05, "loss": 3.8622, "step": 2302464 }, { "epoch": 1.0, "learning_rate": 1.2293455095544114e-05, "loss": 3.849, "step": 2302976 }, { "epoch": 1.0, "learning_rate": 1.2285069148033594e-05, "loss": 3.8512, "step": 2303488 }, { "epoch": 1.0, "learning_rate": 1.2276683200523074e-05, "loss": 3.8516, "step": 2304000 }, { "epoch": 1.0, "learning_rate": 1.2268313631816286e-05, "loss": 3.8451, "step": 2304512 }, { "epoch": 1.01, "learning_rate": 1.2259927684305765e-05, "loss": 3.8535, "step": 2305024 }, { "epoch": 1.01, "learning_rate": 1.2251541736795245e-05, "loss": 3.8588, "step": 2305536 }, { "epoch": 1.01, "learning_rate": 1.2243155789284726e-05, "loss": 3.8642, "step": 2306048 }, { "epoch": 1.01, "learning_rate": 1.2234769841774205e-05, "loss": 3.8575, "step": 2306560 }, { "epoch": 1.01, "learning_rate": 1.2226383894263685e-05, "loss": 3.8479, "step": 2307072 }, { "epoch": 1.01, "learning_rate": 1.2218014325556897e-05, "loss": 3.8568, "step": 2307584 }, { "epoch": 1.01, "learning_rate": 1.2209628378046375e-05, "loss": 3.8743, "step": 2308096 }, { "epoch": 1.01, "learning_rate": 1.2201242430535855e-05, "loss": 3.8486, "step": 2308608 }, { "epoch": 1.01, "learning_rate": 1.2192856483025337e-05, "loss": 3.8537, "step": 2309120 }, { "epoch": 1.01, "learning_rate": 1.2184470535514817e-05, "loss": 3.8545, "step": 2309632 }, { "epoch": 1.01, "learning_rate": 1.2176084588004295e-05, "loss": 3.8492, "step": 2310144 }, { "epoch": 1.01, "learning_rate": 1.2167698640493775e-05, "loss": 3.8573, "step": 2310656 }, { "epoch": 1.01, "learning_rate": 1.2159312692983257e-05, "loss": 3.8609, "step": 2311168 }, { "epoch": 1.01, "learning_rate": 1.2150926745472735e-05, "loss": 3.8657, "step": 2311680 }, { "epoch": 1.01, "learning_rate": 1.2142573555569678e-05, "loss": 3.8569, "step": 2312192 }, { "epoch": 1.01, "learning_rate": 1.2134187608059158e-05, "loss": 3.8559, "step": 2312704 }, { "epoch": 1.01, "learning_rate": 1.2125801660548638e-05, "loss": 3.8559, "step": 2313216 }, { "epoch": 1.01, "learning_rate": 1.2117415713038118e-05, "loss": 3.862, "step": 2313728 }, { "epoch": 1.01, "learning_rate": 1.2109029765527598e-05, "loss": 3.8344, "step": 2314240 }, { "epoch": 1.01, "learning_rate": 1.2100643818017078e-05, "loss": 3.8593, "step": 2314752 }, { "epoch": 1.01, "learning_rate": 1.2092257870506556e-05, "loss": 3.8609, "step": 2315264 }, { "epoch": 1.01, "learning_rate": 1.2083871922996038e-05, "loss": 3.8624, "step": 2315776 }, { "epoch": 1.01, "learning_rate": 1.2075485975485518e-05, "loss": 3.8525, "step": 2316288 }, { "epoch": 1.01, "learning_rate": 1.2067116406778729e-05, "loss": 3.8485, "step": 2316800 }, { "epoch": 1.01, "learning_rate": 1.2058730459268209e-05, "loss": 3.8531, "step": 2317312 }, { "epoch": 1.01, "learning_rate": 1.2050344511757689e-05, "loss": 3.8459, "step": 2317824 }, { "epoch": 1.01, "learning_rate": 1.2041958564247169e-05, "loss": 3.8681, "step": 2318336 }, { "epoch": 1.01, "learning_rate": 1.2033572616736649e-05, "loss": 3.8535, "step": 2318848 }, { "epoch": 1.01, "learning_rate": 1.202520304802986e-05, "loss": 3.8714, "step": 2319360 }, { "epoch": 1.01, "learning_rate": 1.201681710051934e-05, "loss": 3.8552, "step": 2319872 }, { "epoch": 1.01, "learning_rate": 1.200843115300882e-05, "loss": 3.8421, "step": 2320384 }, { "epoch": 1.01, "learning_rate": 1.20000452054983e-05, "loss": 3.8709, "step": 2320896 }, { "epoch": 1.01, "learning_rate": 1.1991659257987779e-05, "loss": 3.8461, "step": 2321408 }, { "epoch": 1.01, "learning_rate": 1.1983289689280992e-05, "loss": 3.846, "step": 2321920 }, { "epoch": 1.01, "learning_rate": 1.1974903741770472e-05, "loss": 3.8562, "step": 2322432 }, { "epoch": 1.01, "learning_rate": 1.1966534173063682e-05, "loss": 3.8618, "step": 2322944 }, { "epoch": 1.01, "learning_rate": 1.1958148225553162e-05, "loss": 3.8445, "step": 2323456 }, { "epoch": 1.01, "learning_rate": 1.1949762278042642e-05, "loss": 3.848, "step": 2323968 }, { "epoch": 1.01, "learning_rate": 1.194137633053212e-05, "loss": 3.8466, "step": 2324480 }, { "epoch": 1.01, "learning_rate": 1.1932990383021602e-05, "loss": 3.8439, "step": 2324992 }, { "epoch": 1.01, "learning_rate": 1.1924604435511082e-05, "loss": 3.8662, "step": 2325504 }, { "epoch": 1.01, "learning_rate": 1.1916218488000562e-05, "loss": 3.8587, "step": 2326016 }, { "epoch": 1.01, "learning_rate": 1.190783254049004e-05, "loss": 3.8538, "step": 2326528 }, { "epoch": 1.01, "learning_rate": 1.1899446592979522e-05, "loss": 3.8535, "step": 2327040 }, { "epoch": 1.01, "learning_rate": 1.1891077024272733e-05, "loss": 3.8642, "step": 2327552 }, { "epoch": 1.01, "learning_rate": 1.1882691076762211e-05, "loss": 3.8546, "step": 2328064 }, { "epoch": 1.01, "learning_rate": 1.1874321508055424e-05, "loss": 3.862, "step": 2328576 }, { "epoch": 1.01, "learning_rate": 1.1865935560544903e-05, "loss": 3.8522, "step": 2329088 }, { "epoch": 1.01, "learning_rate": 1.1857549613034383e-05, "loss": 3.8565, "step": 2329600 }, { "epoch": 1.01, "learning_rate": 1.1849163665523863e-05, "loss": 3.8632, "step": 2330112 }, { "epoch": 1.01, "learning_rate": 1.1840777718013343e-05, "loss": 3.8563, "step": 2330624 }, { "epoch": 1.01, "learning_rate": 1.1832391770502823e-05, "loss": 3.8554, "step": 2331136 }, { "epoch": 1.01, "learning_rate": 1.1824005822992303e-05, "loss": 3.8628, "step": 2331648 }, { "epoch": 1.01, "learning_rate": 1.1815619875481783e-05, "loss": 3.8606, "step": 2332160 }, { "epoch": 1.01, "learning_rate": 1.1807233927971263e-05, "loss": 3.8441, "step": 2332672 }, { "epoch": 1.01, "learning_rate": 1.1798864359264476e-05, "loss": 3.8536, "step": 2333184 }, { "epoch": 1.01, "learning_rate": 1.1790478411753954e-05, "loss": 3.8624, "step": 2333696 }, { "epoch": 1.01, "learning_rate": 1.1782092464243434e-05, "loss": 3.8524, "step": 2334208 }, { "epoch": 1.01, "learning_rate": 1.1773706516732914e-05, "loss": 3.8526, "step": 2334720 }, { "epoch": 1.01, "learning_rate": 1.1765336948026126e-05, "loss": 3.8507, "step": 2335232 }, { "epoch": 1.02, "learning_rate": 1.1756951000515605e-05, "loss": 3.8539, "step": 2335744 }, { "epoch": 1.02, "learning_rate": 1.1748565053005085e-05, "loss": 3.853, "step": 2336256 }, { "epoch": 1.02, "learning_rate": 1.1740179105494566e-05, "loss": 3.854, "step": 2336768 }, { "epoch": 1.02, "learning_rate": 1.1731793157984044e-05, "loss": 3.8583, "step": 2337280 }, { "epoch": 1.02, "learning_rate": 1.1723423589277257e-05, "loss": 3.8554, "step": 2337792 }, { "epoch": 1.02, "learning_rate": 1.1715037641766737e-05, "loss": 3.8697, "step": 2338304 }, { "epoch": 1.02, "learning_rate": 1.1706668073059948e-05, "loss": 3.8322, "step": 2338816 }, { "epoch": 1.02, "learning_rate": 1.1698282125549428e-05, "loss": 3.8554, "step": 2339328 }, { "epoch": 1.02, "learning_rate": 1.1689896178038908e-05, "loss": 3.8492, "step": 2339840 }, { "epoch": 1.02, "learning_rate": 1.1681510230528388e-05, "loss": 3.8603, "step": 2340352 }, { "epoch": 1.02, "learning_rate": 1.1673124283017866e-05, "loss": 3.8625, "step": 2340864 }, { "epoch": 1.02, "learning_rate": 1.1664738335507347e-05, "loss": 3.8533, "step": 2341376 }, { "epoch": 1.02, "learning_rate": 1.1656352387996827e-05, "loss": 3.8489, "step": 2341888 }, { "epoch": 1.02, "learning_rate": 1.1647966440486307e-05, "loss": 3.8528, "step": 2342400 }, { "epoch": 1.02, "learning_rate": 1.1639580492975787e-05, "loss": 3.8536, "step": 2342912 }, { "epoch": 1.02, "learning_rate": 1.1631210924268998e-05, "loss": 3.8483, "step": 2343424 }, { "epoch": 1.02, "learning_rate": 1.162284135556221e-05, "loss": 3.8496, "step": 2343936 }, { "epoch": 1.02, "learning_rate": 1.161445540805169e-05, "loss": 3.8536, "step": 2344448 }, { "epoch": 1.02, "learning_rate": 1.1606069460541169e-05, "loss": 3.8576, "step": 2344960 }, { "epoch": 1.02, "learning_rate": 1.1597683513030649e-05, "loss": 3.8436, "step": 2345472 }, { "epoch": 1.02, "learning_rate": 1.158929756552013e-05, "loss": 3.8508, "step": 2345984 }, { "epoch": 1.02, "learning_rate": 1.1580911618009609e-05, "loss": 3.839, "step": 2346496 }, { "epoch": 1.02, "learning_rate": 1.1572525670499089e-05, "loss": 3.8604, "step": 2347008 }, { "epoch": 1.02, "learning_rate": 1.1564139722988569e-05, "loss": 3.8485, "step": 2347520 }, { "epoch": 1.02, "learning_rate": 1.1555753775478049e-05, "loss": 3.8525, "step": 2348032 }, { "epoch": 1.02, "learning_rate": 1.1547367827967529e-05, "loss": 3.8561, "step": 2348544 }, { "epoch": 1.02, "learning_rate": 1.153899825926074e-05, "loss": 3.8563, "step": 2349056 }, { "epoch": 1.02, "learning_rate": 1.1530628690553952e-05, "loss": 3.853, "step": 2349568 }, { "epoch": 1.02, "learning_rate": 1.152224274304343e-05, "loss": 3.8515, "step": 2350080 }, { "epoch": 1.02, "learning_rate": 1.1513856795532912e-05, "loss": 3.8572, "step": 2350592 }, { "epoch": 1.02, "learning_rate": 1.1505470848022392e-05, "loss": 3.8468, "step": 2351104 }, { "epoch": 1.02, "learning_rate": 1.149708490051187e-05, "loss": 3.8448, "step": 2351616 }, { "epoch": 1.02, "learning_rate": 1.148869895300135e-05, "loss": 3.8574, "step": 2352128 }, { "epoch": 1.02, "learning_rate": 1.1480313005490832e-05, "loss": 3.8571, "step": 2352640 }, { "epoch": 1.02, "learning_rate": 1.1471927057980311e-05, "loss": 3.8563, "step": 2353152 }, { "epoch": 1.02, "learning_rate": 1.1463557489273522e-05, "loss": 3.8485, "step": 2353664 }, { "epoch": 1.02, "learning_rate": 1.1455171541763002e-05, "loss": 3.8502, "step": 2354176 }, { "epoch": 1.02, "learning_rate": 1.1446785594252482e-05, "loss": 3.8477, "step": 2354688 }, { "epoch": 1.02, "learning_rate": 1.143839964674196e-05, "loss": 3.8491, "step": 2355200 }, { "epoch": 1.02, "learning_rate": 1.1430013699231442e-05, "loss": 3.8448, "step": 2355712 }, { "epoch": 1.02, "learning_rate": 1.1421644130524653e-05, "loss": 3.8643, "step": 2356224 }, { "epoch": 1.02, "learning_rate": 1.1413258183014133e-05, "loss": 3.8642, "step": 2356736 }, { "epoch": 1.02, "learning_rate": 1.1404872235503613e-05, "loss": 3.8496, "step": 2357248 }, { "epoch": 1.02, "learning_rate": 1.1396486287993093e-05, "loss": 3.8515, "step": 2357760 }, { "epoch": 1.02, "learning_rate": 1.1388100340482573e-05, "loss": 3.8592, "step": 2358272 }, { "epoch": 1.02, "learning_rate": 1.1379714392972051e-05, "loss": 3.8568, "step": 2358784 }, { "epoch": 1.02, "learning_rate": 1.1371328445461533e-05, "loss": 3.8499, "step": 2359296 }, { "epoch": 1.02, "learning_rate": 1.1362958876754743e-05, "loss": 3.8545, "step": 2359808 }, { "epoch": 1.02, "learning_rate": 1.1354572929244223e-05, "loss": 3.8664, "step": 2360320 }, { "epoch": 1.02, "learning_rate": 1.1346186981733703e-05, "loss": 3.8586, "step": 2360832 }, { "epoch": 1.02, "learning_rate": 1.1337801034223183e-05, "loss": 3.8519, "step": 2361344 }, { "epoch": 1.02, "learning_rate": 1.1329431465516396e-05, "loss": 3.8449, "step": 2361856 }, { "epoch": 1.02, "learning_rate": 1.1321045518005876e-05, "loss": 3.857, "step": 2362368 }, { "epoch": 1.02, "learning_rate": 1.1312659570495354e-05, "loss": 3.8601, "step": 2362880 }, { "epoch": 1.02, "learning_rate": 1.1304290001788566e-05, "loss": 3.8456, "step": 2363392 }, { "epoch": 1.02, "learning_rate": 1.1295904054278046e-05, "loss": 3.8681, "step": 2363904 }, { "epoch": 1.02, "learning_rate": 1.1287518106767525e-05, "loss": 3.8502, "step": 2364416 }, { "epoch": 1.02, "learning_rate": 1.1279132159257005e-05, "loss": 3.8573, "step": 2364928 }, { "epoch": 1.02, "learning_rate": 1.1270746211746486e-05, "loss": 3.8516, "step": 2365440 }, { "epoch": 1.03, "eval_loss": 4.029923439025879, "eval_runtime": 293.5256, "eval_samples_per_second": 1300.026, "eval_steps_per_second": 40.627, "step": 2365920 }, { "epoch": 2.0, "learning_rate": 1.1262360264235966e-05, "loss": 3.8554, "step": 2365952 }, { "epoch": 2.0, "learning_rate": 1.1253974316725444e-05, "loss": 3.8496, "step": 2366464 }, { "epoch": 2.0, "learning_rate": 1.1245588369214924e-05, "loss": 3.8556, "step": 2366976 }, { "epoch": 2.0, "learning_rate": 1.1237202421704406e-05, "loss": 3.8642, "step": 2367488 }, { "epoch": 2.0, "learning_rate": 1.1228816474193884e-05, "loss": 3.8604, "step": 2368000 }, { "epoch": 2.0, "learning_rate": 1.1220430526683364e-05, "loss": 3.8591, "step": 2368512 }, { "epoch": 2.0, "learning_rate": 1.1212060957976577e-05, "loss": 3.8498, "step": 2369024 }, { "epoch": 2.0, "learning_rate": 1.1203675010466057e-05, "loss": 3.8511, "step": 2369536 }, { "epoch": 2.0, "learning_rate": 1.1195289062955535e-05, "loss": 3.8537, "step": 2370048 }, { "epoch": 2.0, "learning_rate": 1.1186903115445017e-05, "loss": 3.8635, "step": 2370560 }, { "epoch": 2.0, "learning_rate": 1.1178517167934497e-05, "loss": 3.8545, "step": 2371072 }, { "epoch": 2.0, "learning_rate": 1.1170147599227707e-05, "loss": 3.8584, "step": 2371584 }, { "epoch": 2.0, "learning_rate": 1.1161778030520918e-05, "loss": 3.8648, "step": 2372096 }, { "epoch": 2.0, "learning_rate": 1.115340846181413e-05, "loss": 3.8461, "step": 2372608 }, { "epoch": 2.0, "learning_rate": 1.114502251430361e-05, "loss": 3.8509, "step": 2373120 }, { "epoch": 2.0, "learning_rate": 1.1136636566793089e-05, "loss": 3.8382, "step": 2373632 }, { "epoch": 2.0, "learning_rate": 1.1128250619282569e-05, "loss": 3.8448, "step": 2374144 }, { "epoch": 2.0, "learning_rate": 1.111986467177205e-05, "loss": 3.8542, "step": 2374656 }, { "epoch": 2.0, "learning_rate": 1.111147872426153e-05, "loss": 3.8453, "step": 2375168 }, { "epoch": 2.0, "learning_rate": 1.1103092776751009e-05, "loss": 3.855, "step": 2375680 }, { "epoch": 2.0, "learning_rate": 1.1094706829240489e-05, "loss": 3.8701, "step": 2376192 }, { "epoch": 2.0, "learning_rate": 1.108632088172997e-05, "loss": 3.8503, "step": 2376704 }, { "epoch": 2.0, "learning_rate": 1.1077934934219449e-05, "loss": 3.8562, "step": 2377216 }, { "epoch": 2.0, "learning_rate": 1.1069548986708929e-05, "loss": 3.8591, "step": 2377728 }, { "epoch": 2.0, "learning_rate": 1.1061163039198409e-05, "loss": 3.8496, "step": 2378240 }, { "epoch": 2.0, "learning_rate": 1.1052777091687888e-05, "loss": 3.8531, "step": 2378752 }, { "epoch": 2.0, "learning_rate": 1.1044391144177368e-05, "loss": 3.8426, "step": 2379264 }, { "epoch": 2.0, "learning_rate": 1.1036021575470581e-05, "loss": 3.8542, "step": 2379776 }, { "epoch": 2.0, "learning_rate": 1.1027635627960061e-05, "loss": 3.85, "step": 2380288 }, { "epoch": 2.0, "learning_rate": 1.1019249680449539e-05, "loss": 3.8406, "step": 2380800 }, { "epoch": 2.01, "learning_rate": 1.1010863732939019e-05, "loss": 3.852, "step": 2381312 }, { "epoch": 2.01, "learning_rate": 1.1002494164232232e-05, "loss": 3.8479, "step": 2381824 }, { "epoch": 2.01, "learning_rate": 1.099410821672171e-05, "loss": 3.8597, "step": 2382336 }, { "epoch": 2.01, "learning_rate": 1.098572226921119e-05, "loss": 3.8575, "step": 2382848 }, { "epoch": 2.01, "learning_rate": 1.0977336321700671e-05, "loss": 3.8448, "step": 2383360 }, { "epoch": 2.01, "learning_rate": 1.0968966752993882e-05, "loss": 3.8532, "step": 2383872 }, { "epoch": 2.01, "learning_rate": 1.0960580805483362e-05, "loss": 3.8707, "step": 2384384 }, { "epoch": 2.01, "learning_rate": 1.0952194857972842e-05, "loss": 3.8433, "step": 2384896 }, { "epoch": 2.01, "learning_rate": 1.0943808910462322e-05, "loss": 3.8507, "step": 2385408 }, { "epoch": 2.01, "learning_rate": 1.0935439341755533e-05, "loss": 3.8513, "step": 2385920 }, { "epoch": 2.01, "learning_rate": 1.0927053394245013e-05, "loss": 3.8477, "step": 2386432 }, { "epoch": 2.01, "learning_rate": 1.0918667446734493e-05, "loss": 3.8491, "step": 2386944 }, { "epoch": 2.01, "learning_rate": 1.0910281499223973e-05, "loss": 3.8635, "step": 2387456 }, { "epoch": 2.01, "learning_rate": 1.0901895551713453e-05, "loss": 3.8585, "step": 2387968 }, { "epoch": 2.01, "learning_rate": 1.0893509604202933e-05, "loss": 3.8533, "step": 2388480 }, { "epoch": 2.01, "learning_rate": 1.0885123656692413e-05, "loss": 3.8558, "step": 2388992 }, { "epoch": 2.01, "learning_rate": 1.0876737709181891e-05, "loss": 3.8472, "step": 2389504 }, { "epoch": 2.01, "learning_rate": 1.0868368140475103e-05, "loss": 3.861, "step": 2390016 }, { "epoch": 2.01, "learning_rate": 1.0859998571768316e-05, "loss": 3.8314, "step": 2390528 }, { "epoch": 2.01, "learning_rate": 1.0851612624257796e-05, "loss": 3.855, "step": 2391040 }, { "epoch": 2.01, "learning_rate": 1.0843226676747274e-05, "loss": 3.8587, "step": 2391552 }, { "epoch": 2.01, "learning_rate": 1.0834840729236754e-05, "loss": 3.8602, "step": 2392064 }, { "epoch": 2.01, "learning_rate": 1.0826454781726236e-05, "loss": 3.8502, "step": 2392576 }, { "epoch": 2.01, "learning_rate": 1.0818068834215716e-05, "loss": 3.8434, "step": 2393088 }, { "epoch": 2.01, "learning_rate": 1.0809682886705194e-05, "loss": 3.8512, "step": 2393600 }, { "epoch": 2.01, "learning_rate": 1.0801296939194674e-05, "loss": 3.842, "step": 2394112 }, { "epoch": 2.01, "learning_rate": 1.0792927370487886e-05, "loss": 3.8692, "step": 2394624 }, { "epoch": 2.01, "learning_rate": 1.0784541422977365e-05, "loss": 3.8476, "step": 2395136 }, { "epoch": 2.01, "learning_rate": 1.0776155475466845e-05, "loss": 3.8682, "step": 2395648 }, { "epoch": 2.01, "learning_rate": 1.0767769527956326e-05, "loss": 3.8514, "step": 2396160 }, { "epoch": 2.01, "learning_rate": 1.0759383580445806e-05, "loss": 3.8442, "step": 2396672 }, { "epoch": 2.01, "learning_rate": 1.0750997632935284e-05, "loss": 3.8601, "step": 2397184 }, { "epoch": 2.01, "learning_rate": 1.0742611685424764e-05, "loss": 3.8429, "step": 2397696 }, { "epoch": 2.01, "learning_rate": 1.0734225737914246e-05, "loss": 3.8477, "step": 2398208 }, { "epoch": 2.01, "learning_rate": 1.072587254801119e-05, "loss": 3.8486, "step": 2398720 }, { "epoch": 2.01, "learning_rate": 1.0717486600500668e-05, "loss": 3.8609, "step": 2399232 }, { "epoch": 2.01, "learning_rate": 1.0709100652990148e-05, "loss": 3.8435, "step": 2399744 }, { "epoch": 2.01, "learning_rate": 1.0700714705479628e-05, "loss": 3.8455, "step": 2400256 }, { "epoch": 2.01, "learning_rate": 1.0692328757969107e-05, "loss": 3.842, "step": 2400768 }, { "epoch": 2.01, "learning_rate": 1.0683942810458587e-05, "loss": 3.8414, "step": 2401280 }, { "epoch": 2.01, "learning_rate": 1.067558962055553e-05, "loss": 3.8639, "step": 2401792 }, { "epoch": 2.01, "learning_rate": 1.066720367304501e-05, "loss": 3.8574, "step": 2402304 }, { "epoch": 2.01, "learning_rate": 1.0658817725534489e-05, "loss": 3.848, "step": 2402816 }, { "epoch": 2.01, "learning_rate": 1.065043177802397e-05, "loss": 3.8498, "step": 2403328 }, { "epoch": 2.01, "learning_rate": 1.064204583051345e-05, "loss": 3.8588, "step": 2403840 }, { "epoch": 2.01, "learning_rate": 1.0633659883002929e-05, "loss": 3.853, "step": 2404352 }, { "epoch": 2.01, "learning_rate": 1.0625290314296141e-05, "loss": 3.8567, "step": 2404864 }, { "epoch": 2.01, "learning_rate": 1.0616904366785621e-05, "loss": 3.8521, "step": 2405376 }, { "epoch": 2.01, "learning_rate": 1.0608518419275101e-05, "loss": 3.8537, "step": 2405888 }, { "epoch": 2.01, "learning_rate": 1.060013247176458e-05, "loss": 3.8593, "step": 2406400 }, { "epoch": 2.01, "learning_rate": 1.0591746524254061e-05, "loss": 3.8524, "step": 2406912 }, { "epoch": 2.01, "learning_rate": 1.0583360576743541e-05, "loss": 3.8518, "step": 2407424 }, { "epoch": 2.01, "learning_rate": 1.057497462923302e-05, "loss": 3.8636, "step": 2407936 }, { "epoch": 2.01, "learning_rate": 1.0566588681722501e-05, "loss": 3.8522, "step": 2408448 }, { "epoch": 2.01, "learning_rate": 1.0558202734211981e-05, "loss": 3.8389, "step": 2408960 }, { "epoch": 2.01, "learning_rate": 1.0549816786701461e-05, "loss": 3.8534, "step": 2409472 }, { "epoch": 2.01, "learning_rate": 1.054143083919094e-05, "loss": 3.8545, "step": 2409984 }, { "epoch": 2.01, "learning_rate": 1.053304489168042e-05, "loss": 3.8512, "step": 2410496 }, { "epoch": 2.01, "learning_rate": 1.0524691701777362e-05, "loss": 3.8509, "step": 2411008 }, { "epoch": 2.01, "learning_rate": 1.0516305754266844e-05, "loss": 3.8462, "step": 2411520 }, { "epoch": 2.02, "learning_rate": 1.0507919806756322e-05, "loss": 3.8509, "step": 2412032 }, { "epoch": 2.02, "learning_rate": 1.0499550238049533e-05, "loss": 3.8493, "step": 2412544 }, { "epoch": 2.02, "learning_rate": 1.0491164290539015e-05, "loss": 3.8481, "step": 2413056 }, { "epoch": 2.02, "learning_rate": 1.0482778343028493e-05, "loss": 3.8539, "step": 2413568 }, { "epoch": 2.02, "learning_rate": 1.0474392395517973e-05, "loss": 3.8502, "step": 2414080 }, { "epoch": 2.02, "learning_rate": 1.0466006448007453e-05, "loss": 3.8666, "step": 2414592 }, { "epoch": 2.02, "learning_rate": 1.0457620500496935e-05, "loss": 3.8368, "step": 2415104 }, { "epoch": 2.02, "learning_rate": 1.0449234552986413e-05, "loss": 3.8433, "step": 2415616 }, { "epoch": 2.02, "learning_rate": 1.0440848605475893e-05, "loss": 3.8522, "step": 2416128 }, { "epoch": 2.02, "learning_rate": 1.0432462657965374e-05, "loss": 3.8511, "step": 2416640 }, { "epoch": 2.02, "learning_rate": 1.0424076710454853e-05, "loss": 3.8595, "step": 2417152 }, { "epoch": 2.02, "learning_rate": 1.0415690762944333e-05, "loss": 3.8532, "step": 2417664 }, { "epoch": 2.02, "learning_rate": 1.0407304815433813e-05, "loss": 3.8458, "step": 2418176 }, { "epoch": 2.02, "learning_rate": 1.0398918867923293e-05, "loss": 3.8522, "step": 2418688 }, { "epoch": 2.02, "learning_rate": 1.0390549299216503e-05, "loss": 3.8502, "step": 2419200 }, { "epoch": 2.02, "learning_rate": 1.0382163351705983e-05, "loss": 3.8426, "step": 2419712 }, { "epoch": 2.02, "learning_rate": 1.0373793782999196e-05, "loss": 3.8446, "step": 2420224 }, { "epoch": 2.02, "learning_rate": 1.0365407835488674e-05, "loss": 3.8531, "step": 2420736 }, { "epoch": 2.02, "learning_rate": 1.0357021887978156e-05, "loss": 3.8551, "step": 2421248 }, { "epoch": 2.02, "learning_rate": 1.0348635940467636e-05, "loss": 3.8396, "step": 2421760 }, { "epoch": 2.02, "learning_rate": 1.0340249992957114e-05, "loss": 3.8458, "step": 2422272 }, { "epoch": 2.02, "learning_rate": 1.0331864045446594e-05, "loss": 3.8374, "step": 2422784 }, { "epoch": 2.02, "learning_rate": 1.0323478097936076e-05, "loss": 3.8559, "step": 2423296 }, { "epoch": 2.02, "learning_rate": 1.0315092150425556e-05, "loss": 3.8449, "step": 2423808 }, { "epoch": 2.02, "learning_rate": 1.0306706202915034e-05, "loss": 3.85, "step": 2424320 }, { "epoch": 2.02, "learning_rate": 1.0298320255404514e-05, "loss": 3.8524, "step": 2424832 }, { "epoch": 2.02, "learning_rate": 1.0289934307893995e-05, "loss": 3.854, "step": 2425344 }, { "epoch": 2.02, "learning_rate": 1.0281564739187204e-05, "loss": 3.849, "step": 2425856 }, { "epoch": 2.02, "learning_rate": 1.0273178791676684e-05, "loss": 3.848, "step": 2426368 }, { "epoch": 2.02, "learning_rate": 1.0264792844166166e-05, "loss": 3.8539, "step": 2426880 }, { "epoch": 2.02, "learning_rate": 1.0256406896655646e-05, "loss": 3.8473, "step": 2427392 }, { "epoch": 2.02, "learning_rate": 1.0248020949145124e-05, "loss": 3.8404, "step": 2427904 }, { "epoch": 2.02, "learning_rate": 1.0239651380438337e-05, "loss": 3.8528, "step": 2428416 }, { "epoch": 2.02, "learning_rate": 1.0231265432927817e-05, "loss": 3.8482, "step": 2428928 }, { "epoch": 2.02, "learning_rate": 1.0222879485417295e-05, "loss": 3.8587, "step": 2429440 }, { "epoch": 2.02, "learning_rate": 1.0214493537906777e-05, "loss": 3.843, "step": 2429952 }, { "epoch": 2.02, "learning_rate": 1.0206107590396257e-05, "loss": 3.8499, "step": 2430464 }, { "epoch": 2.02, "learning_rate": 1.0197738021689467e-05, "loss": 3.845, "step": 2430976 }, { "epoch": 2.02, "learning_rate": 1.0189352074178947e-05, "loss": 3.8485, "step": 2431488 }, { "epoch": 2.02, "learning_rate": 1.0180966126668427e-05, "loss": 3.8366, "step": 2432000 }, { "epoch": 2.02, "learning_rate": 1.0172580179157907e-05, "loss": 3.8593, "step": 2432512 }, { "epoch": 2.02, "learning_rate": 1.0164194231647387e-05, "loss": 3.8642, "step": 2433024 }, { "epoch": 2.02, "learning_rate": 1.0155808284136867e-05, "loss": 3.8478, "step": 2433536 }, { "epoch": 2.02, "learning_rate": 1.0147422336626347e-05, "loss": 3.8443, "step": 2434048 }, { "epoch": 2.02, "learning_rate": 1.0139052767919558e-05, "loss": 3.8556, "step": 2434560 }, { "epoch": 2.02, "learning_rate": 1.0130666820409038e-05, "loss": 3.8536, "step": 2435072 }, { "epoch": 2.02, "learning_rate": 1.0122280872898518e-05, "loss": 3.8472, "step": 2435584 }, { "epoch": 2.02, "learning_rate": 1.0113894925387998e-05, "loss": 3.851, "step": 2436096 }, { "epoch": 2.02, "learning_rate": 1.0105508977877478e-05, "loss": 3.8623, "step": 2436608 }, { "epoch": 2.02, "learning_rate": 1.0097123030366958e-05, "loss": 3.8549, "step": 2437120 }, { "epoch": 2.02, "learning_rate": 1.0088737082856438e-05, "loss": 3.8502, "step": 2437632 }, { "epoch": 2.02, "learning_rate": 1.0080351135345918e-05, "loss": 3.8444, "step": 2438144 }, { "epoch": 2.02, "learning_rate": 1.0071981566639128e-05, "loss": 3.8549, "step": 2438656 }, { "epoch": 2.02, "learning_rate": 1.0063595619128608e-05, "loss": 3.8553, "step": 2439168 }, { "epoch": 2.02, "learning_rate": 1.0055209671618088e-05, "loss": 3.8403, "step": 2439680 }, { "epoch": 2.02, "learning_rate": 1.0046823724107568e-05, "loss": 3.8672, "step": 2440192 }, { "epoch": 2.02, "learning_rate": 1.0038454155400779e-05, "loss": 3.849, "step": 2440704 }, { "epoch": 2.02, "learning_rate": 1.003006820789026e-05, "loss": 3.853, "step": 2441216 }, { "epoch": 2.02, "learning_rate": 1.002168226037974e-05, "loss": 3.855, "step": 2441728 }, { "epoch": 2.03, "learning_rate": 1.0013296312869219e-05, "loss": 3.8467, "step": 2442240 }, { "epoch": 2.03, "eval_loss": 4.029435157775879, "eval_runtime": 291.2125, "eval_samples_per_second": 1310.352, "eval_steps_per_second": 40.949, "step": 2442240 }, { "epoch": 0.0, "learning_rate": 1.0004910365358699e-05, "loss": 3.8484, "step": 2442752 }, { "epoch": 0.0, "learning_rate": 9.99652441784818e-06, "loss": 3.8488, "step": 2443264 }, { "epoch": 0.0, "learning_rate": 9.988138470337659e-06, "loss": 3.8624, "step": 2443776 }, { "epoch": 0.0, "learning_rate": 9.979752522827139e-06, "loss": 3.8533, "step": 2444288 }, { "epoch": 0.0, "learning_rate": 9.971366575316619e-06, "loss": 3.8558, "step": 2444800 }, { "epoch": 0.0, "learning_rate": 9.9629806278061e-06, "loss": 3.8455, "step": 2445312 }, { "epoch": 0.0, "learning_rate": 9.954594680295579e-06, "loss": 3.85, "step": 2445824 }, { "epoch": 0.0, "learning_rate": 9.946208732785059e-06, "loss": 3.8485, "step": 2446336 }, { "epoch": 0.0, "learning_rate": 9.937822785274539e-06, "loss": 3.8584, "step": 2446848 }, { "epoch": 0.0, "learning_rate": 9.929436837764018e-06, "loss": 3.8469, "step": 2447360 }, { "epoch": 0.0, "learning_rate": 9.921050890253498e-06, "loss": 3.8596, "step": 2447872 }, { "epoch": 0.0, "learning_rate": 9.912681321546711e-06, "loss": 3.8614, "step": 2448384 }, { "epoch": 0.0, "learning_rate": 9.904295374036191e-06, "loss": 3.8427, "step": 2448896 }, { "epoch": 0.0, "learning_rate": 9.89590942652567e-06, "loss": 3.8467, "step": 2449408 }, { "epoch": 0.0, "learning_rate": 9.887523479015149e-06, "loss": 3.8385, "step": 2449920 }, { "epoch": 0.0, "learning_rate": 9.87913753150463e-06, "loss": 3.8395, "step": 2450432 }, { "epoch": 0.0, "learning_rate": 9.870751583994109e-06, "loss": 3.8492, "step": 2450944 }, { "epoch": 0.0, "learning_rate": 9.862365636483589e-06, "loss": 3.8446, "step": 2451456 }, { "epoch": 0.0, "learning_rate": 9.853979688973069e-06, "loss": 3.8474, "step": 2451968 }, { "epoch": 0.0, "learning_rate": 9.84561012026628e-06, "loss": 3.8703, "step": 2452480 }, { "epoch": 0.0, "learning_rate": 9.83722417275576e-06, "loss": 3.8458, "step": 2452992 }, { "epoch": 0.0, "learning_rate": 9.82883822524524e-06, "loss": 3.855, "step": 2453504 }, { "epoch": 0.0, "learning_rate": 9.820452277734721e-06, "loss": 3.8514, "step": 2454016 }, { "epoch": 0.0, "learning_rate": 9.8120663302242e-06, "loss": 3.8498, "step": 2454528 }, { "epoch": 0.0, "learning_rate": 9.803713140321143e-06, "loss": 3.8498, "step": 2455040 }, { "epoch": 0.0, "learning_rate": 9.795327192810623e-06, "loss": 3.8392, "step": 2455552 }, { "epoch": 0.0, "learning_rate": 9.786941245300103e-06, "loss": 3.8486, "step": 2456064 }, { "epoch": 0.0, "learning_rate": 9.778555297789583e-06, "loss": 3.8505, "step": 2456576 }, { "epoch": 0.0, "learning_rate": 9.770169350279063e-06, "loss": 3.8349, "step": 2457088 }, { "epoch": 0.01, "learning_rate": 9.761783402768543e-06, "loss": 3.8502, "step": 2457600 }, { "epoch": 0.01, "learning_rate": 9.753397455258023e-06, "loss": 3.8474, "step": 2458112 }, { "epoch": 0.01, "learning_rate": 9.745011507747503e-06, "loss": 3.8571, "step": 2458624 }, { "epoch": 0.01, "learning_rate": 9.736625560236983e-06, "loss": 3.8511, "step": 2459136 }, { "epoch": 0.01, "learning_rate": 9.72823961272646e-06, "loss": 3.8427, "step": 2459648 }, { "epoch": 0.01, "learning_rate": 9.719870044019673e-06, "loss": 3.85, "step": 2460160 }, { "epoch": 0.01, "learning_rate": 9.711484096509153e-06, "loss": 3.8646, "step": 2460672 }, { "epoch": 0.01, "learning_rate": 9.703114527802366e-06, "loss": 3.8391, "step": 2461184 }, { "epoch": 0.01, "learning_rate": 9.694728580291844e-06, "loss": 3.8489, "step": 2461696 }, { "epoch": 0.01, "learning_rate": 9.686342632781324e-06, "loss": 3.8499, "step": 2462208 }, { "epoch": 0.01, "learning_rate": 9.677956685270804e-06, "loss": 3.8402, "step": 2462720 }, { "epoch": 0.01, "learning_rate": 9.669570737760286e-06, "loss": 3.8485, "step": 2463232 }, { "epoch": 0.01, "learning_rate": 9.661184790249764e-06, "loss": 3.8619, "step": 2463744 }, { "epoch": 0.01, "learning_rate": 9.652798842739244e-06, "loss": 3.8564, "step": 2464256 }, { "epoch": 0.01, "learning_rate": 9.644412895228724e-06, "loss": 3.8445, "step": 2464768 }, { "epoch": 0.01, "learning_rate": 9.636026947718204e-06, "loss": 3.8551, "step": 2465280 }, { "epoch": 0.01, "learning_rate": 9.627641000207684e-06, "loss": 3.8462, "step": 2465792 }, { "epoch": 0.01, "learning_rate": 9.619255052697164e-06, "loss": 3.8551, "step": 2466304 }, { "epoch": 0.01, "learning_rate": 9.610885483990376e-06, "loss": 3.8286, "step": 2466816 }, { "epoch": 0.01, "learning_rate": 9.602499536479854e-06, "loss": 3.8497, "step": 2467328 }, { "epoch": 0.01, "learning_rate": 9.594129967773067e-06, "loss": 3.8573, "step": 2467840 }, { "epoch": 0.01, "learning_rate": 9.585744020262547e-06, "loss": 3.8533, "step": 2468352 }, { "epoch": 0.01, "learning_rate": 9.577358072752025e-06, "loss": 3.8497, "step": 2468864 }, { "epoch": 0.01, "learning_rate": 9.568972125241505e-06, "loss": 3.841, "step": 2469376 }, { "epoch": 0.01, "learning_rate": 9.560586177730987e-06, "loss": 3.8514, "step": 2469888 }, { "epoch": 0.01, "learning_rate": 9.552216609024197e-06, "loss": 3.8383, "step": 2470400 }, { "epoch": 0.01, "learning_rate": 9.543830661513677e-06, "loss": 3.8636, "step": 2470912 }, { "epoch": 0.01, "learning_rate": 9.535444714003157e-06, "loss": 3.8443, "step": 2471424 }, { "epoch": 0.01, "learning_rate": 9.527058766492637e-06, "loss": 3.862, "step": 2471936 }, { "epoch": 0.01, "learning_rate": 9.518672818982116e-06, "loss": 3.8489, "step": 2472448 }, { "epoch": 0.01, "learning_rate": 9.510303250275328e-06, "loss": 3.8433, "step": 2472960 }, { "epoch": 0.01, "learning_rate": 9.501917302764808e-06, "loss": 3.8514, "step": 2473472 }, { "epoch": 0.01, "learning_rate": 9.493531355254288e-06, "loss": 3.8446, "step": 2473984 }, { "epoch": 0.01, "learning_rate": 9.485145407743768e-06, "loss": 3.8458, "step": 2474496 }, { "epoch": 0.01, "learning_rate": 9.476775839036979e-06, "loss": 3.8433, "step": 2475008 }, { "epoch": 0.01, "learning_rate": 9.468389891526459e-06, "loss": 3.8575, "step": 2475520 }, { "epoch": 0.01, "learning_rate": 9.46000394401594e-06, "loss": 3.8423, "step": 2476032 }, { "epoch": 0.01, "learning_rate": 9.451617996505419e-06, "loss": 3.841, "step": 2476544 }, { "epoch": 0.01, "learning_rate": 9.443232048994898e-06, "loss": 3.8361, "step": 2477056 }, { "epoch": 0.01, "learning_rate": 9.434846101484378e-06, "loss": 3.8376, "step": 2477568 }, { "epoch": 0.01, "learning_rate": 9.426460153973858e-06, "loss": 3.8604, "step": 2478080 }, { "epoch": 0.01, "learning_rate": 9.418074206463338e-06, "loss": 3.8576, "step": 2478592 }, { "epoch": 0.01, "learning_rate": 9.409704637756551e-06, "loss": 3.8466, "step": 2479104 }, { "epoch": 0.01, "learning_rate": 9.40131869024603e-06, "loss": 3.8477, "step": 2479616 }, { "epoch": 0.01, "learning_rate": 9.392932742735509e-06, "loss": 3.8529, "step": 2480128 }, { "epoch": 0.01, "learning_rate": 9.384546795224989e-06, "loss": 3.8542, "step": 2480640 }, { "epoch": 0.01, "learning_rate": 9.37616084771447e-06, "loss": 3.8489, "step": 2481152 }, { "epoch": 0.01, "learning_rate": 9.367774900203949e-06, "loss": 3.8523, "step": 2481664 }, { "epoch": 0.01, "learning_rate": 9.359388952693429e-06, "loss": 3.8499, "step": 2482176 }, { "epoch": 0.01, "learning_rate": 9.351003005182909e-06, "loss": 3.8554, "step": 2482688 }, { "epoch": 0.01, "learning_rate": 9.342617057672389e-06, "loss": 3.8496, "step": 2483200 }, { "epoch": 0.01, "learning_rate": 9.334231110161869e-06, "loss": 3.8494, "step": 2483712 }, { "epoch": 0.01, "learning_rate": 9.325861541455081e-06, "loss": 3.8595, "step": 2484224 }, { "epoch": 0.01, "learning_rate": 9.317475593944561e-06, "loss": 3.8508, "step": 2484736 }, { "epoch": 0.01, "learning_rate": 9.30908964643404e-06, "loss": 3.8341, "step": 2485248 }, { "epoch": 0.01, "learning_rate": 9.300720077727252e-06, "loss": 3.8487, "step": 2485760 }, { "epoch": 0.01, "learning_rate": 9.292334130216732e-06, "loss": 3.8508, "step": 2486272 }, { "epoch": 0.01, "learning_rate": 9.28394818270621e-06, "loss": 3.8515, "step": 2486784 }, { "epoch": 0.01, "learning_rate": 9.27556223519569e-06, "loss": 3.8466, "step": 2487296 }, { "epoch": 0.01, "learning_rate": 9.267176287685172e-06, "loss": 3.8437, "step": 2487808 }, { "epoch": 0.02, "learning_rate": 9.258790340174652e-06, "loss": 3.8528, "step": 2488320 }, { "epoch": 0.02, "learning_rate": 9.25040439266413e-06, "loss": 3.8415, "step": 2488832 }, { "epoch": 0.02, "learning_rate": 9.24201844515361e-06, "loss": 3.8494, "step": 2489344 }, { "epoch": 0.02, "learning_rate": 9.233632497643092e-06, "loss": 3.8482, "step": 2489856 }, { "epoch": 0.02, "learning_rate": 9.225279307740033e-06, "loss": 3.8463, "step": 2490368 }, { "epoch": 0.02, "learning_rate": 9.216893360229513e-06, "loss": 3.8667, "step": 2490880 }, { "epoch": 0.02, "learning_rate": 9.208507412718993e-06, "loss": 3.8349, "step": 2491392 }, { "epoch": 0.02, "learning_rate": 9.200121465208473e-06, "loss": 3.8372, "step": 2491904 }, { "epoch": 0.02, "learning_rate": 9.191735517697953e-06, "loss": 3.8508, "step": 2492416 }, { "epoch": 0.02, "learning_rate": 9.183349570187433e-06, "loss": 3.8507, "step": 2492928 }, { "epoch": 0.02, "learning_rate": 9.174963622676913e-06, "loss": 3.8571, "step": 2493440 }, { "epoch": 0.02, "learning_rate": 9.166577675166391e-06, "loss": 3.8471, "step": 2493952 }, { "epoch": 0.02, "learning_rate": 9.158191727655873e-06, "loss": 3.8409, "step": 2494464 }, { "epoch": 0.02, "learning_rate": 9.149822158949084e-06, "loss": 3.8439, "step": 2494976 }, { "epoch": 0.02, "learning_rate": 9.141436211438564e-06, "loss": 3.852, "step": 2495488 }, { "epoch": 0.02, "learning_rate": 9.133050263928044e-06, "loss": 3.8382, "step": 2496000 }, { "epoch": 0.02, "learning_rate": 9.124680695221254e-06, "loss": 3.8398, "step": 2496512 }, { "epoch": 0.02, "learning_rate": 9.116294747710736e-06, "loss": 3.8519, "step": 2497024 }, { "epoch": 0.02, "learning_rate": 9.107908800200216e-06, "loss": 3.8501, "step": 2497536 }, { "epoch": 0.02, "learning_rate": 9.099522852689694e-06, "loss": 3.8395, "step": 2498048 }, { "epoch": 0.02, "learning_rate": 9.091136905179174e-06, "loss": 3.8387, "step": 2498560 }, { "epoch": 0.02, "learning_rate": 9.082750957668656e-06, "loss": 3.8392, "step": 2499072 }, { "epoch": 0.02, "learning_rate": 9.074365010158134e-06, "loss": 3.8518, "step": 2499584 }, { "epoch": 0.02, "learning_rate": 9.065979062647614e-06, "loss": 3.8414, "step": 2500096 }, { "epoch": 0.02, "learning_rate": 9.057593115137094e-06, "loss": 3.8456, "step": 2500608 }, { "epoch": 0.02, "learning_rate": 9.049207167626574e-06, "loss": 3.8483, "step": 2501120 }, { "epoch": 0.02, "learning_rate": 9.040821220116054e-06, "loss": 3.851, "step": 2501632 }, { "epoch": 0.02, "learning_rate": 9.032451651409265e-06, "loss": 3.8436, "step": 2502144 }, { "epoch": 0.02, "learning_rate": 9.024065703898746e-06, "loss": 3.8488, "step": 2502656 }, { "epoch": 0.02, "learning_rate": 9.015679756388225e-06, "loss": 3.8483, "step": 2503168 }, { "epoch": 0.02, "learning_rate": 9.007293808877705e-06, "loss": 3.8453, "step": 2503680 }, { "epoch": 0.02, "learning_rate": 8.998907861367186e-06, "loss": 3.8342, "step": 2504192 }, { "epoch": 0.02, "learning_rate": 8.990521913856664e-06, "loss": 3.8517, "step": 2504704 }, { "epoch": 0.02, "learning_rate": 8.982135966346144e-06, "loss": 3.8469, "step": 2505216 }, { "epoch": 0.02, "learning_rate": 8.973766397639357e-06, "loss": 3.853, "step": 2505728 }, { "epoch": 0.02, "learning_rate": 8.965380450128837e-06, "loss": 3.8384, "step": 2506240 }, { "epoch": 0.02, "learning_rate": 8.956994502618315e-06, "loss": 3.8516, "step": 2506752 }, { "epoch": 0.02, "learning_rate": 8.948608555107795e-06, "loss": 3.84, "step": 2507264 }, { "epoch": 0.02, "learning_rate": 8.940238986401008e-06, "loss": 3.8459, "step": 2507776 }, { "epoch": 0.02, "learning_rate": 8.931853038890488e-06, "loss": 3.831, "step": 2508288 }, { "epoch": 0.02, "learning_rate": 8.923467091379967e-06, "loss": 3.8587, "step": 2508800 }, { "epoch": 0.02, "learning_rate": 8.915081143869447e-06, "loss": 3.8596, "step": 2509312 }, { "epoch": 0.02, "learning_rate": 8.906695196358927e-06, "loss": 3.8452, "step": 2509824 }, { "epoch": 0.02, "learning_rate": 8.898309248848406e-06, "loss": 3.8359, "step": 2510336 }, { "epoch": 0.02, "learning_rate": 8.889923301337887e-06, "loss": 3.8587, "step": 2510848 }, { "epoch": 0.02, "learning_rate": 8.881537353827367e-06, "loss": 3.8475, "step": 2511360 }, { "epoch": 0.02, "learning_rate": 8.873167785120578e-06, "loss": 3.8469, "step": 2511872 }, { "epoch": 0.02, "learning_rate": 8.864781837610058e-06, "loss": 3.8462, "step": 2512384 }, { "epoch": 0.02, "learning_rate": 8.856395890099538e-06, "loss": 3.8596, "step": 2512896 }, { "epoch": 0.02, "learning_rate": 8.848026321392749e-06, "loss": 3.8474, "step": 2513408 }, { "epoch": 0.02, "learning_rate": 8.839640373882229e-06, "loss": 3.8478, "step": 2513920 }, { "epoch": 0.02, "learning_rate": 8.831254426371709e-06, "loss": 3.8368, "step": 2514432 }, { "epoch": 0.02, "learning_rate": 8.822868478861189e-06, "loss": 3.8531, "step": 2514944 }, { "epoch": 0.02, "learning_rate": 8.814482531350669e-06, "loss": 3.8497, "step": 2515456 }, { "epoch": 0.02, "learning_rate": 8.806096583840149e-06, "loss": 3.8412, "step": 2515968 }, { "epoch": 0.02, "learning_rate": 8.797710636329628e-06, "loss": 3.863, "step": 2516480 }, { "epoch": 0.02, "learning_rate": 8.789341067622841e-06, "loss": 3.8427, "step": 2516992 }, { "epoch": 0.02, "learning_rate": 8.78095512011232e-06, "loss": 3.8487, "step": 2517504 }, { "epoch": 0.02, "learning_rate": 8.7725691726018e-06, "loss": 3.8501, "step": 2518016 }, { "epoch": 0.02, "learning_rate": 8.764183225091279e-06, "loss": 3.8464, "step": 2518528 }, { "epoch": 0.03, "eval_loss": 4.02862024307251, "eval_runtime": 301.1282, "eval_samples_per_second": 1267.204, "eval_steps_per_second": 39.601, "step": 2518560 }, { "epoch": 0.0, "learning_rate": 8.75579727758076e-06, "loss": 3.839, "step": 2519040 }, { "epoch": 0.0, "learning_rate": 8.747411330070239e-06, "loss": 3.8509, "step": 2519552 }, { "epoch": 0.0, "learning_rate": 8.739025382559719e-06, "loss": 3.8578, "step": 2520064 }, { "epoch": 0.0, "learning_rate": 8.730639435049199e-06, "loss": 3.8526, "step": 2520576 }, { "epoch": 0.0, "learning_rate": 8.722253487538679e-06, "loss": 3.856, "step": 2521088 }, { "epoch": 0.0, "learning_rate": 8.713867540028159e-06, "loss": 3.8416, "step": 2521600 }, { "epoch": 0.0, "learning_rate": 8.705481592517639e-06, "loss": 3.8451, "step": 2522112 }, { "epoch": 0.0, "learning_rate": 8.697095645007119e-06, "loss": 3.8437, "step": 2522624 }, { "epoch": 0.0, "learning_rate": 8.688709697496599e-06, "loss": 3.8574, "step": 2523136 }, { "epoch": 0.0, "learning_rate": 8.680323749986079e-06, "loss": 3.8449, "step": 2523648 }, { "epoch": 0.0, "learning_rate": 8.671937802475557e-06, "loss": 3.8525, "step": 2524160 }, { "epoch": 0.0, "learning_rate": 8.663551854965039e-06, "loss": 3.8565, "step": 2524672 }, { "epoch": 0.0, "learning_rate": 8.65518228625825e-06, "loss": 3.8418, "step": 2525184 }, { "epoch": 0.0, "learning_rate": 8.64679633874773e-06, "loss": 3.8427, "step": 2525696 }, { "epoch": 0.0, "learning_rate": 8.63841039123721e-06, "loss": 3.8335, "step": 2526208 }, { "epoch": 0.0, "learning_rate": 8.63002444372669e-06, "loss": 3.842, "step": 2526720 }, { "epoch": 0.0, "learning_rate": 8.62163849621617e-06, "loss": 3.8428, "step": 2527232 }, { "epoch": 0.0, "learning_rate": 8.61325254870565e-06, "loss": 3.8429, "step": 2527744 }, { "epoch": 0.0, "learning_rate": 8.604866601195129e-06, "loss": 3.8423, "step": 2528256 }, { "epoch": 0.0, "learning_rate": 8.596480653684609e-06, "loss": 3.8683, "step": 2528768 }, { "epoch": 0.0, "learning_rate": 8.58811108497782e-06, "loss": 3.8435, "step": 2529280 }, { "epoch": 0.0, "learning_rate": 8.5797251374673e-06, "loss": 3.848, "step": 2529792 }, { "epoch": 0.0, "learning_rate": 8.57133918995678e-06, "loss": 3.8544, "step": 2530304 }, { "epoch": 0.0, "learning_rate": 8.562969621249992e-06, "loss": 3.8483, "step": 2530816 }, { "epoch": 0.0, "learning_rate": 8.554600052543203e-06, "loss": 3.8406, "step": 2531328 }, { "epoch": 0.0, "learning_rate": 8.546214105032681e-06, "loss": 3.8377, "step": 2531840 }, { "epoch": 0.0, "learning_rate": 8.537828157522163e-06, "loss": 3.8452, "step": 2532352 }, { "epoch": 0.0, "learning_rate": 8.529442210011643e-06, "loss": 3.8455, "step": 2532864 }, { "epoch": 0.0, "learning_rate": 8.521056262501121e-06, "loss": 3.831, "step": 2533376 }, { "epoch": 0.01, "learning_rate": 8.512670314990603e-06, "loss": 3.8483, "step": 2533888 }, { "epoch": 0.01, "learning_rate": 8.504284367480083e-06, "loss": 3.8396, "step": 2534400 }, { "epoch": 0.01, "learning_rate": 8.495898419969563e-06, "loss": 3.8531, "step": 2534912 }, { "epoch": 0.01, "learning_rate": 8.487512472459041e-06, "loss": 3.8513, "step": 2535424 }, { "epoch": 0.01, "learning_rate": 8.479126524948523e-06, "loss": 3.8363, "step": 2535936 }, { "epoch": 0.01, "learning_rate": 8.470756956241733e-06, "loss": 3.8528, "step": 2536448 }, { "epoch": 0.01, "learning_rate": 8.462371008731212e-06, "loss": 3.8615, "step": 2536960 }, { "epoch": 0.01, "learning_rate": 8.453985061220693e-06, "loss": 3.8345, "step": 2537472 }, { "epoch": 0.01, "learning_rate": 8.445599113710173e-06, "loss": 3.8495, "step": 2537984 }, { "epoch": 0.01, "learning_rate": 8.437213166199653e-06, "loss": 3.8438, "step": 2538496 }, { "epoch": 0.01, "learning_rate": 8.428827218689132e-06, "loss": 3.8387, "step": 2539008 }, { "epoch": 0.01, "learning_rate": 8.420441271178613e-06, "loss": 3.8452, "step": 2539520 }, { "epoch": 0.01, "learning_rate": 8.412055323668093e-06, "loss": 3.8569, "step": 2540032 }, { "epoch": 0.01, "learning_rate": 8.403685754961304e-06, "loss": 3.8522, "step": 2540544 }, { "epoch": 0.01, "learning_rate": 8.395299807450784e-06, "loss": 3.8429, "step": 2541056 }, { "epoch": 0.01, "learning_rate": 8.386913859940264e-06, "loss": 3.8532, "step": 2541568 }, { "epoch": 0.01, "learning_rate": 8.378527912429744e-06, "loss": 3.8432, "step": 2542080 }, { "epoch": 0.01, "learning_rate": 8.370158343722955e-06, "loss": 3.8516, "step": 2542592 }, { "epoch": 0.01, "learning_rate": 8.361788775016165e-06, "loss": 3.8314, "step": 2543104 }, { "epoch": 0.01, "learning_rate": 8.353402827505647e-06, "loss": 3.8415, "step": 2543616 }, { "epoch": 0.01, "learning_rate": 8.345016879995127e-06, "loss": 3.8536, "step": 2544128 }, { "epoch": 0.01, "learning_rate": 8.336630932484605e-06, "loss": 3.8526, "step": 2544640 }, { "epoch": 0.01, "learning_rate": 8.328244984974085e-06, "loss": 3.8429, "step": 2545152 }, { "epoch": 0.01, "learning_rate": 8.319859037463567e-06, "loss": 3.8376, "step": 2545664 }, { "epoch": 0.01, "learning_rate": 8.311473089953045e-06, "loss": 3.8477, "step": 2546176 }, { "epoch": 0.01, "learning_rate": 8.303087142442525e-06, "loss": 3.8327, "step": 2546688 }, { "epoch": 0.01, "learning_rate": 8.294701194932005e-06, "loss": 3.8572, "step": 2547200 }, { "epoch": 0.01, "learning_rate": 8.286331626225218e-06, "loss": 3.8421, "step": 2547712 }, { "epoch": 0.01, "learning_rate": 8.277945678714696e-06, "loss": 3.8596, "step": 2548224 }, { "epoch": 0.01, "learning_rate": 8.269559731204177e-06, "loss": 3.8468, "step": 2548736 }, { "epoch": 0.01, "learning_rate": 8.261173783693657e-06, "loss": 3.8425, "step": 2549248 }, { "epoch": 0.01, "learning_rate": 8.252787836183136e-06, "loss": 3.8435, "step": 2549760 }, { "epoch": 0.01, "learning_rate": 8.244401888672616e-06, "loss": 3.8488, "step": 2550272 }, { "epoch": 0.01, "learning_rate": 8.236032319965828e-06, "loss": 3.8384, "step": 2550784 }, { "epoch": 0.01, "learning_rate": 8.227646372455308e-06, "loss": 3.8383, "step": 2551296 }, { "epoch": 0.01, "learning_rate": 8.219260424944788e-06, "loss": 3.8559, "step": 2551808 }, { "epoch": 0.01, "learning_rate": 8.210874477434268e-06, "loss": 3.842, "step": 2552320 }, { "epoch": 0.01, "learning_rate": 8.202488529923748e-06, "loss": 3.8336, "step": 2552832 }, { "epoch": 0.01, "learning_rate": 8.194102582413226e-06, "loss": 3.837, "step": 2553344 }, { "epoch": 0.01, "learning_rate": 8.185716634902708e-06, "loss": 3.8369, "step": 2553856 }, { "epoch": 0.01, "learning_rate": 8.177330687392188e-06, "loss": 3.855, "step": 2554368 }, { "epoch": 0.01, "learning_rate": 8.168961118685399e-06, "loss": 3.855, "step": 2554880 }, { "epoch": 0.01, "learning_rate": 8.160575171174879e-06, "loss": 3.8417, "step": 2555392 }, { "epoch": 0.01, "learning_rate": 8.15220560246809e-06, "loss": 3.8455, "step": 2555904 }, { "epoch": 0.01, "learning_rate": 8.14381965495757e-06, "loss": 3.8512, "step": 2556416 }, { "epoch": 0.01, "learning_rate": 8.13543370744705e-06, "loss": 3.8468, "step": 2556928 }, { "epoch": 0.01, "learning_rate": 8.12704775993653e-06, "loss": 3.8456, "step": 2557440 }, { "epoch": 0.01, "learning_rate": 8.118661812426009e-06, "loss": 3.851, "step": 2557952 }, { "epoch": 0.01, "learning_rate": 8.110275864915489e-06, "loss": 3.8474, "step": 2558464 }, { "epoch": 0.01, "learning_rate": 8.101889917404969e-06, "loss": 3.8555, "step": 2558976 }, { "epoch": 0.01, "learning_rate": 8.09352034869818e-06, "loss": 3.8449, "step": 2559488 }, { "epoch": 0.01, "learning_rate": 8.085134401187661e-06, "loss": 3.8465, "step": 2560000 }, { "epoch": 0.01, "learning_rate": 8.07674845367714e-06, "loss": 3.8521, "step": 2560512 }, { "epoch": 0.01, "learning_rate": 8.06836250616662e-06, "loss": 3.851, "step": 2561024 }, { "epoch": 0.01, "learning_rate": 8.0599765586561e-06, "loss": 3.8344, "step": 2561536 }, { "epoch": 0.01, "learning_rate": 8.05159061114558e-06, "loss": 3.8468, "step": 2562048 }, { "epoch": 0.01, "learning_rate": 8.04320466363506e-06, "loss": 3.8465, "step": 2562560 }, { "epoch": 0.01, "learning_rate": 8.03481871612454e-06, "loss": 3.8513, "step": 2563072 }, { "epoch": 0.01, "learning_rate": 8.02643276861402e-06, "loss": 3.8466, "step": 2563584 }, { "epoch": 0.01, "learning_rate": 8.01806319990723e-06, "loss": 3.8389, "step": 2564096 }, { "epoch": 0.02, "learning_rate": 8.00967725239671e-06, "loss": 3.8467, "step": 2564608 }, { "epoch": 0.02, "learning_rate": 8.00129130488619e-06, "loss": 3.8395, "step": 2565120 }, { "epoch": 0.02, "learning_rate": 7.99290535737567e-06, "loss": 3.8504, "step": 2565632 }, { "epoch": 0.02, "learning_rate": 7.98451940986515e-06, "loss": 3.8395, "step": 2566144 }, { "epoch": 0.02, "learning_rate": 7.97613346235463e-06, "loss": 3.8457, "step": 2566656 }, { "epoch": 0.02, "learning_rate": 7.967763893647843e-06, "loss": 3.8577, "step": 2567168 }, { "epoch": 0.02, "learning_rate": 7.95937794613732e-06, "loss": 3.8461, "step": 2567680 }, { "epoch": 0.02, "learning_rate": 7.9509919986268e-06, "loss": 3.8268, "step": 2568192 }, { "epoch": 0.02, "learning_rate": 7.942606051116282e-06, "loss": 3.8455, "step": 2568704 }, { "epoch": 0.02, "learning_rate": 7.93422010360576e-06, "loss": 3.8489, "step": 2569216 }, { "epoch": 0.02, "learning_rate": 7.92583415609524e-06, "loss": 3.8511, "step": 2569728 }, { "epoch": 0.02, "learning_rate": 7.91744820858472e-06, "loss": 3.8438, "step": 2570240 }, { "epoch": 0.02, "learning_rate": 7.909078639877933e-06, "loss": 3.8417, "step": 2570752 }, { "epoch": 0.02, "learning_rate": 7.900692692367411e-06, "loss": 3.8376, "step": 2571264 }, { "epoch": 0.02, "learning_rate": 7.892306744856893e-06, "loss": 3.8527, "step": 2571776 }, { "epoch": 0.02, "learning_rate": 7.883920797346373e-06, "loss": 3.8298, "step": 2572288 }, { "epoch": 0.02, "learning_rate": 7.875551228639584e-06, "loss": 3.8423, "step": 2572800 }, { "epoch": 0.02, "learning_rate": 7.867165281129064e-06, "loss": 3.8495, "step": 2573312 }, { "epoch": 0.02, "learning_rate": 7.858779333618544e-06, "loss": 3.85, "step": 2573824 }, { "epoch": 0.02, "learning_rate": 7.850393386108024e-06, "loss": 3.8296, "step": 2574336 }, { "epoch": 0.02, "learning_rate": 7.842007438597502e-06, "loss": 3.8423, "step": 2574848 }, { "epoch": 0.02, "learning_rate": 7.833621491086983e-06, "loss": 3.8333, "step": 2575360 }, { "epoch": 0.02, "learning_rate": 7.825251922380194e-06, "loss": 3.8501, "step": 2575872 }, { "epoch": 0.02, "learning_rate": 7.816865974869674e-06, "loss": 3.8388, "step": 2576384 }, { "epoch": 0.02, "learning_rate": 7.808480027359154e-06, "loss": 3.8352, "step": 2576896 }, { "epoch": 0.02, "learning_rate": 7.800094079848634e-06, "loss": 3.8525, "step": 2577408 }, { "epoch": 0.02, "learning_rate": 7.791708132338114e-06, "loss": 3.8476, "step": 2577920 }, { "epoch": 0.02, "learning_rate": 7.783338563631325e-06, "loss": 3.8421, "step": 2578432 }, { "epoch": 0.02, "learning_rate": 7.774952616120805e-06, "loss": 3.8444, "step": 2578944 }, { "epoch": 0.02, "learning_rate": 7.766566668610285e-06, "loss": 3.8443, "step": 2579456 }, { "epoch": 0.02, "learning_rate": 7.758180721099766e-06, "loss": 3.8456, "step": 2579968 }, { "epoch": 0.02, "learning_rate": 7.749794773589245e-06, "loss": 3.8286, "step": 2580480 }, { "epoch": 0.02, "learning_rate": 7.741408826078725e-06, "loss": 3.8523, "step": 2580992 }, { "epoch": 0.02, "learning_rate": 7.733039257371937e-06, "loss": 3.8406, "step": 2581504 }, { "epoch": 0.02, "learning_rate": 7.724653309861415e-06, "loss": 3.8488, "step": 2582016 }, { "epoch": 0.02, "learning_rate": 7.716267362350895e-06, "loss": 3.8397, "step": 2582528 }, { "epoch": 0.02, "learning_rate": 7.707881414840375e-06, "loss": 3.8442, "step": 2583040 }, { "epoch": 0.02, "learning_rate": 7.699511846133588e-06, "loss": 3.8382, "step": 2583552 }, { "epoch": 0.02, "learning_rate": 7.691142277426799e-06, "loss": 3.8427, "step": 2584064 }, { "epoch": 0.02, "learning_rate": 7.682756329916279e-06, "loss": 3.8259, "step": 2584576 }, { "epoch": 0.02, "learning_rate": 7.674370382405759e-06, "loss": 3.8595, "step": 2585088 }, { "epoch": 0.02, "learning_rate": 7.665984434895238e-06, "loss": 3.8515, "step": 2585600 }, { "epoch": 0.02, "learning_rate": 7.657598487384718e-06, "loss": 3.8441, "step": 2586112 }, { "epoch": 0.02, "learning_rate": 7.649212539874198e-06, "loss": 3.8369, "step": 2586624 }, { "epoch": 0.02, "learning_rate": 7.64084297116741e-06, "loss": 3.8522, "step": 2587136 }, { "epoch": 0.02, "learning_rate": 7.632457023656889e-06, "loss": 3.8492, "step": 2587648 }, { "epoch": 0.02, "learning_rate": 7.624071076146369e-06, "loss": 3.8421, "step": 2588160 }, { "epoch": 0.02, "learning_rate": 7.615685128635849e-06, "loss": 3.8396, "step": 2588672 }, { "epoch": 0.02, "learning_rate": 7.60729918112533e-06, "loss": 3.8525, "step": 2589184 }, { "epoch": 0.02, "learning_rate": 7.598913233614809e-06, "loss": 3.8457, "step": 2589696 }, { "epoch": 0.02, "learning_rate": 7.590527286104289e-06, "loss": 3.8539, "step": 2590208 }, { "epoch": 0.02, "learning_rate": 7.582141338593769e-06, "loss": 3.8328, "step": 2590720 }, { "epoch": 0.02, "learning_rate": 7.573755391083248e-06, "loss": 3.849, "step": 2591232 }, { "epoch": 0.02, "learning_rate": 7.565369443572729e-06, "loss": 3.8475, "step": 2591744 }, { "epoch": 0.02, "learning_rate": 7.556983496062209e-06, "loss": 3.8375, "step": 2592256 }, { "epoch": 0.02, "learning_rate": 7.548613927355419e-06, "loss": 3.8589, "step": 2592768 }, { "epoch": 0.02, "learning_rate": 7.5402279798448995e-06, "loss": 3.8418, "step": 2593280 }, { "epoch": 0.02, "learning_rate": 7.5318420323343794e-06, "loss": 3.8482, "step": 2593792 }, { "epoch": 0.02, "learning_rate": 7.52345608482386e-06, "loss": 3.8462, "step": 2594304 }, { "epoch": 0.02, "learning_rate": 7.515070137313339e-06, "loss": 3.8457, "step": 2594816 }, { "epoch": 0.03, "eval_loss": 4.027451515197754, "eval_runtime": 298.7739, "eval_samples_per_second": 1277.19, "eval_steps_per_second": 39.913, "step": 2594880 }, { "epoch": 1.0, "learning_rate": 7.506684189802819e-06, "loss": 3.8417, "step": 2595328 }, { "epoch": 1.0, "learning_rate": 7.498298242292299e-06, "loss": 3.8484, "step": 2595840 }, { "epoch": 1.0, "learning_rate": 7.48992867358551e-06, "loss": 3.8517, "step": 2596352 }, { "epoch": 1.0, "learning_rate": 7.48154272607499e-06, "loss": 3.8514, "step": 2596864 }, { "epoch": 1.0, "learning_rate": 7.473156778564471e-06, "loss": 3.8579, "step": 2597376 }, { "epoch": 1.0, "learning_rate": 7.4647872098576824e-06, "loss": 3.8362, "step": 2597888 }, { "epoch": 1.0, "learning_rate": 7.456401262347161e-06, "loss": 3.8399, "step": 2598400 }, { "epoch": 1.0, "learning_rate": 7.4480153148366415e-06, "loss": 3.8418, "step": 2598912 }, { "epoch": 1.0, "learning_rate": 7.4396293673261215e-06, "loss": 3.8544, "step": 2599424 }, { "epoch": 1.0, "learning_rate": 7.4312434198156006e-06, "loss": 3.8424, "step": 2599936 }, { "epoch": 1.0, "learning_rate": 7.4228574723050805e-06, "loss": 3.8491, "step": 2600448 }, { "epoch": 1.0, "learning_rate": 7.414471524794561e-06, "loss": 3.8522, "step": 2600960 }, { "epoch": 1.0, "learning_rate": 7.406101956087773e-06, "loss": 3.8379, "step": 2601472 }, { "epoch": 1.0, "learning_rate": 7.397716008577252e-06, "loss": 3.8411, "step": 2601984 }, { "epoch": 1.0, "learning_rate": 7.389330061066732e-06, "loss": 3.8291, "step": 2602496 }, { "epoch": 1.0, "learning_rate": 7.380944113556212e-06, "loss": 3.8385, "step": 2603008 }, { "epoch": 1.0, "learning_rate": 7.372558166045691e-06, "loss": 3.8412, "step": 2603520 }, { "epoch": 1.0, "learning_rate": 7.364172218535172e-06, "loss": 3.8403, "step": 2604032 }, { "epoch": 1.0, "learning_rate": 7.355786271024652e-06, "loss": 3.8387, "step": 2604544 }, { "epoch": 1.0, "learning_rate": 7.347400323514133e-06, "loss": 3.8645, "step": 2605056 }, { "epoch": 1.0, "learning_rate": 7.339030754807343e-06, "loss": 3.8423, "step": 2605568 }, { "epoch": 1.0, "learning_rate": 7.3306448072968225e-06, "loss": 3.8435, "step": 2606080 }, { "epoch": 1.0, "learning_rate": 7.322258859786303e-06, "loss": 3.8496, "step": 2606592 }, { "epoch": 1.0, "learning_rate": 7.313889291079515e-06, "loss": 3.8476, "step": 2607104 }, { "epoch": 1.0, "learning_rate": 7.305503343568994e-06, "loss": 3.839, "step": 2607616 }, { "epoch": 1.0, "learning_rate": 7.297117396058474e-06, "loss": 3.8328, "step": 2608128 }, { "epoch": 1.0, "learning_rate": 7.288731448547954e-06, "loss": 3.8459, "step": 2608640 }, { "epoch": 1.0, "learning_rate": 7.280345501037433e-06, "loss": 3.837, "step": 2609152 }, { "epoch": 1.0, "learning_rate": 7.271959553526914e-06, "loss": 3.8324, "step": 2609664 }, { "epoch": 1.01, "learning_rate": 7.263573606016394e-06, "loss": 3.8447, "step": 2610176 }, { "epoch": 1.01, "learning_rate": 7.255187658505873e-06, "loss": 3.838, "step": 2610688 }, { "epoch": 1.01, "learning_rate": 7.246818089799085e-06, "loss": 3.85, "step": 2611200 }, { "epoch": 1.01, "learning_rate": 7.238432142288565e-06, "loss": 3.8474, "step": 2611712 }, { "epoch": 1.01, "learning_rate": 7.230046194778045e-06, "loss": 3.8341, "step": 2612224 }, { "epoch": 1.01, "learning_rate": 7.221676626071255e-06, "loss": 3.849, "step": 2612736 }, { "epoch": 1.01, "learning_rate": 7.213290678560736e-06, "loss": 3.8596, "step": 2613248 }, { "epoch": 1.01, "learning_rate": 7.204904731050216e-06, "loss": 3.8305, "step": 2613760 }, { "epoch": 1.01, "learning_rate": 7.196518783539696e-06, "loss": 3.8481, "step": 2614272 }, { "epoch": 1.01, "learning_rate": 7.188132836029175e-06, "loss": 3.8372, "step": 2614784 }, { "epoch": 1.01, "learning_rate": 7.179746888518656e-06, "loss": 3.8386, "step": 2615296 }, { "epoch": 1.01, "learning_rate": 7.171360941008136e-06, "loss": 3.8392, "step": 2615808 }, { "epoch": 1.01, "learning_rate": 7.162974993497615e-06, "loss": 3.8562, "step": 2616320 }, { "epoch": 1.01, "learning_rate": 7.154605424790827e-06, "loss": 3.8463, "step": 2616832 }, { "epoch": 1.01, "learning_rate": 7.146219477280307e-06, "loss": 3.8425, "step": 2617344 }, { "epoch": 1.01, "learning_rate": 7.137833529769787e-06, "loss": 3.8495, "step": 2617856 }, { "epoch": 1.01, "learning_rate": 7.129447582259266e-06, "loss": 3.8377, "step": 2618368 }, { "epoch": 1.01, "learning_rate": 7.1210616347487465e-06, "loss": 3.8512, "step": 2618880 }, { "epoch": 1.01, "learning_rate": 7.112692066041958e-06, "loss": 3.8304, "step": 2619392 }, { "epoch": 1.01, "learning_rate": 7.104306118531437e-06, "loss": 3.8362, "step": 2619904 }, { "epoch": 1.01, "learning_rate": 7.095920171020917e-06, "loss": 3.8492, "step": 2620416 }, { "epoch": 1.01, "learning_rate": 7.087534223510397e-06, "loss": 3.8483, "step": 2620928 }, { "epoch": 1.01, "learning_rate": 7.079148275999878e-06, "loss": 3.8398, "step": 2621440 }, { "epoch": 1.01, "learning_rate": 7.070762328489357e-06, "loss": 3.8379, "step": 2621952 }, { "epoch": 1.01, "learning_rate": 7.062376380978837e-06, "loss": 3.8465, "step": 2622464 }, { "epoch": 1.01, "learning_rate": 7.053990433468318e-06, "loss": 3.83, "step": 2622976 }, { "epoch": 1.01, "learning_rate": 7.04563724356526e-06, "loss": 3.8516, "step": 2623488 }, { "epoch": 1.01, "learning_rate": 7.037251296054739e-06, "loss": 3.8445, "step": 2624000 }, { "epoch": 1.01, "learning_rate": 7.028865348544219e-06, "loss": 3.8534, "step": 2624512 }, { "epoch": 1.01, "learning_rate": 7.0204794010337e-06, "loss": 3.8495, "step": 2625024 }, { "epoch": 1.01, "learning_rate": 7.012093453523179e-06, "loss": 3.8376, "step": 2625536 }, { "epoch": 1.01, "learning_rate": 7.003707506012659e-06, "loss": 3.8388, "step": 2626048 }, { "epoch": 1.01, "learning_rate": 6.995337937305871e-06, "loss": 3.8463, "step": 2626560 }, { "epoch": 1.01, "learning_rate": 6.9869683685990825e-06, "loss": 3.8346, "step": 2627072 }, { "epoch": 1.01, "learning_rate": 6.978582421088562e-06, "loss": 3.8362, "step": 2627584 }, { "epoch": 1.01, "learning_rate": 6.9701964735780415e-06, "loss": 3.8502, "step": 2628096 }, { "epoch": 1.01, "learning_rate": 6.961810526067522e-06, "loss": 3.8424, "step": 2628608 }, { "epoch": 1.01, "learning_rate": 6.953424578557001e-06, "loss": 3.8286, "step": 2629120 }, { "epoch": 1.01, "learning_rate": 6.945038631046481e-06, "loss": 3.8354, "step": 2629632 }, { "epoch": 1.01, "learning_rate": 6.936652683535961e-06, "loss": 3.8313, "step": 2630144 }, { "epoch": 1.01, "learning_rate": 6.9282667360254405e-06, "loss": 3.8518, "step": 2630656 }, { "epoch": 1.01, "learning_rate": 6.9198807885149204e-06, "loss": 3.851, "step": 2631168 }, { "epoch": 1.01, "learning_rate": 6.911511219808132e-06, "loss": 3.8395, "step": 2631680 }, { "epoch": 1.01, "learning_rate": 6.903125272297613e-06, "loss": 3.8472, "step": 2632192 }, { "epoch": 1.01, "learning_rate": 6.894739324787092e-06, "loss": 3.8434, "step": 2632704 }, { "epoch": 1.01, "learning_rate": 6.886353377276572e-06, "loss": 3.8482, "step": 2633216 }, { "epoch": 1.01, "learning_rate": 6.8779838085697836e-06, "loss": 3.8401, "step": 2633728 }, { "epoch": 1.01, "learning_rate": 6.869597861059264e-06, "loss": 3.8493, "step": 2634240 }, { "epoch": 1.01, "learning_rate": 6.861211913548743e-06, "loss": 3.8466, "step": 2634752 }, { "epoch": 1.01, "learning_rate": 6.8528259660382234e-06, "loss": 3.849, "step": 2635264 }, { "epoch": 1.01, "learning_rate": 6.844440018527703e-06, "loss": 3.8406, "step": 2635776 }, { "epoch": 1.01, "learning_rate": 6.836070449820914e-06, "loss": 3.8457, "step": 2636288 }, { "epoch": 1.01, "learning_rate": 6.827684502310394e-06, "loss": 3.8495, "step": 2636800 }, { "epoch": 1.01, "learning_rate": 6.819298554799874e-06, "loss": 3.849, "step": 2637312 }, { "epoch": 1.01, "learning_rate": 6.810912607289355e-06, "loss": 3.8367, "step": 2637824 }, { "epoch": 1.01, "learning_rate": 6.802526659778834e-06, "loss": 3.8429, "step": 2638336 }, { "epoch": 1.01, "learning_rate": 6.794140712268314e-06, "loss": 3.8419, "step": 2638848 }, { "epoch": 1.01, "learning_rate": 6.785754764757794e-06, "loss": 3.8456, "step": 2639360 }, { "epoch": 1.01, "learning_rate": 6.777368817247273e-06, "loss": 3.8463, "step": 2639872 }, { "epoch": 1.01, "learning_rate": 6.769015627344216e-06, "loss": 3.8337, "step": 2640384 }, { "epoch": 1.02, "learning_rate": 6.760629679833696e-06, "loss": 3.8445, "step": 2640896 }, { "epoch": 1.02, "learning_rate": 6.752243732323177e-06, "loss": 3.8401, "step": 2641408 }, { "epoch": 1.02, "learning_rate": 6.743874163616387e-06, "loss": 3.847, "step": 2641920 }, { "epoch": 1.02, "learning_rate": 6.735488216105868e-06, "loss": 3.832, "step": 2642432 }, { "epoch": 1.02, "learning_rate": 6.727102268595348e-06, "loss": 3.8439, "step": 2642944 }, { "epoch": 1.02, "learning_rate": 6.718716321084828e-06, "loss": 3.8553, "step": 2643456 }, { "epoch": 1.02, "learning_rate": 6.710330373574307e-06, "loss": 3.8419, "step": 2643968 }, { "epoch": 1.02, "learning_rate": 6.701944426063788e-06, "loss": 3.8246, "step": 2644480 }, { "epoch": 1.02, "learning_rate": 6.693558478553268e-06, "loss": 3.8432, "step": 2644992 }, { "epoch": 1.02, "learning_rate": 6.685172531042747e-06, "loss": 3.8474, "step": 2645504 }, { "epoch": 1.02, "learning_rate": 6.676786583532227e-06, "loss": 3.8486, "step": 2646016 }, { "epoch": 1.02, "learning_rate": 6.6684006360217075e-06, "loss": 3.8444, "step": 2646528 }, { "epoch": 1.02, "learning_rate": 6.660031067314919e-06, "loss": 3.8358, "step": 2647040 }, { "epoch": 1.02, "learning_rate": 6.651661498608129e-06, "loss": 3.8367, "step": 2647552 }, { "epoch": 1.02, "learning_rate": 6.643275551097609e-06, "loss": 3.8474, "step": 2648064 }, { "epoch": 1.02, "learning_rate": 6.63488960358709e-06, "loss": 3.8299, "step": 2648576 }, { "epoch": 1.02, "learning_rate": 6.626503656076569e-06, "loss": 3.8389, "step": 2649088 }, { "epoch": 1.02, "learning_rate": 6.618134087369781e-06, "loss": 3.8456, "step": 2649600 }, { "epoch": 1.02, "learning_rate": 6.6097481398592605e-06, "loss": 3.8478, "step": 2650112 }, { "epoch": 1.02, "learning_rate": 6.601362192348741e-06, "loss": 3.8258, "step": 2650624 }, { "epoch": 1.02, "learning_rate": 6.59297624483822e-06, "loss": 3.8416, "step": 2651136 }, { "epoch": 1.02, "learning_rate": 6.5845902973277e-06, "loss": 3.8303, "step": 2651648 }, { "epoch": 1.02, "learning_rate": 6.57620434981718e-06, "loss": 3.8412, "step": 2652160 }, { "epoch": 1.02, "learning_rate": 6.5678184023066595e-06, "loss": 3.8414, "step": 2652672 }, { "epoch": 1.02, "learning_rate": 6.5594324547961394e-06, "loss": 3.8325, "step": 2653184 }, { "epoch": 1.02, "learning_rate": 6.55104650728562e-06, "loss": 3.8478, "step": 2653696 }, { "epoch": 1.02, "learning_rate": 6.542676938578832e-06, "loss": 3.8473, "step": 2654208 }, { "epoch": 1.02, "learning_rate": 6.534307369872042e-06, "loss": 3.8346, "step": 2654720 }, { "epoch": 1.02, "learning_rate": 6.525921422361523e-06, "loss": 3.841, "step": 2655232 }, { "epoch": 1.02, "learning_rate": 6.5175354748510026e-06, "loss": 3.8415, "step": 2655744 }, { "epoch": 1.02, "learning_rate": 6.5091495273404825e-06, "loss": 3.8422, "step": 2656256 }, { "epoch": 1.02, "learning_rate": 6.500763579829962e-06, "loss": 3.828, "step": 2656768 }, { "epoch": 1.02, "learning_rate": 6.4923776323194424e-06, "loss": 3.8468, "step": 2657280 }, { "epoch": 1.02, "learning_rate": 6.483991684808922e-06, "loss": 3.839, "step": 2657792 }, { "epoch": 1.02, "learning_rate": 6.4756057372984015e-06, "loss": 3.8448, "step": 2658304 }, { "epoch": 1.02, "learning_rate": 6.467236168591613e-06, "loss": 3.8388, "step": 2658816 }, { "epoch": 1.02, "learning_rate": 6.458850221081093e-06, "loss": 3.8447, "step": 2659328 }, { "epoch": 1.02, "learning_rate": 6.450464273570574e-06, "loss": 3.8304, "step": 2659840 }, { "epoch": 1.02, "learning_rate": 6.442078326060052e-06, "loss": 3.8416, "step": 2660352 }, { "epoch": 1.02, "learning_rate": 6.433692378549533e-06, "loss": 3.8253, "step": 2660864 }, { "epoch": 1.02, "learning_rate": 6.425322809842745e-06, "loss": 3.8552, "step": 2661376 }, { "epoch": 1.02, "learning_rate": 6.416936862332224e-06, "loss": 3.8465, "step": 2661888 }, { "epoch": 1.02, "learning_rate": 6.408567293625435e-06, "loss": 3.8437, "step": 2662400 }, { "epoch": 1.02, "learning_rate": 6.400181346114915e-06, "loss": 3.8336, "step": 2662912 }, { "epoch": 1.02, "learning_rate": 6.391795398604396e-06, "loss": 3.8482, "step": 2663424 }, { "epoch": 1.02, "learning_rate": 6.383409451093874e-06, "loss": 3.8511, "step": 2663936 }, { "epoch": 1.02, "learning_rate": 6.375023503583355e-06, "loss": 3.8365, "step": 2664448 }, { "epoch": 1.02, "learning_rate": 6.366637556072835e-06, "loss": 3.8406, "step": 2664960 }, { "epoch": 1.02, "learning_rate": 6.358251608562314e-06, "loss": 3.847, "step": 2665472 }, { "epoch": 1.02, "learning_rate": 6.349865661051794e-06, "loss": 3.8414, "step": 2665984 }, { "epoch": 1.02, "learning_rate": 6.341479713541275e-06, "loss": 3.849, "step": 2666496 }, { "epoch": 1.02, "learning_rate": 6.333110144834487e-06, "loss": 3.8327, "step": 2667008 }, { "epoch": 1.02, "learning_rate": 6.324724197323966e-06, "loss": 3.8464, "step": 2667520 }, { "epoch": 1.02, "learning_rate": 6.316338249813446e-06, "loss": 3.8431, "step": 2668032 }, { "epoch": 1.02, "learning_rate": 6.307968681106657e-06, "loss": 3.8353, "step": 2668544 }, { "epoch": 1.02, "learning_rate": 6.2995827335961364e-06, "loss": 3.856, "step": 2669056 }, { "epoch": 1.02, "learning_rate": 6.291196786085616e-06, "loss": 3.8378, "step": 2669568 }, { "epoch": 1.02, "learning_rate": 6.282810838575097e-06, "loss": 3.8436, "step": 2670080 }, { "epoch": 1.02, "learning_rate": 6.274424891064577e-06, "loss": 3.8452, "step": 2670592 }, { "epoch": 1.02, "learning_rate": 6.266038943554056e-06, "loss": 3.8392, "step": 2671104 }, { "epoch": 1.03, "eval_loss": 4.0268874168396, "eval_runtime": 305.3377, "eval_samples_per_second": 1249.734, "eval_steps_per_second": 39.055, "step": 2671200 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.0288196331586556e+18, "trial_name": null, "trial_params": null }