{ "best_metric": 3.9507577419281006, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-reconstruction/transformer/2/checkpoints/checkpoint-228960", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 228960, "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": 10.9415, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8131, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1794, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9713, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8122, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7062, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6008, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5311, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4432, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.3918, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3443, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.312, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2581, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.1975, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1677, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1181, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.0986, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0757, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0358, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0114, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 4.9973, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9687, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9431, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9252, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9137, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.8794, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8654, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8568, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8275, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.8075, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.7977, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740117521192533e-05, "loss": 4.791, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731731573682013e-05, "loss": 4.7781, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.761, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7515, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7469, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7256, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 4.6986, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 4.6967, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 4.6713, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6802, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6665, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.665, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6436, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6448, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6295, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6224, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6262, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5883, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5962, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5985, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.592, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5678, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5586, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5509, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5438, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.559, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5216, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5367, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5287, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5084, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5169, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.493, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4902, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4897, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.4991, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4688, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4724, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.455, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.465, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4693, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4655, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4461, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4578, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4616, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.437, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4317, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.426, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4186, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4255, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4063, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4245, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4178, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 4.4033, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.3872, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 4.394, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 4.395, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 4.3967, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3834, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3868, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3765, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3678, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.3641, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3699, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 4.3634, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 4.3638, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 4.3492, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3475, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3568, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3561, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3453, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3407, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3323, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3305, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3331, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.9119786708666285e-05, "loss": 4.3094, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.3195, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910303119244898e-05, "loss": 4.3237, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.909464524493846e-05, "loss": 4.3213, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908625929742794e-05, "loss": 4.3099, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907787334991742e-05, "loss": 4.3189, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.90694874024069e-05, "loss": 4.2973, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906110145489638e-05, "loss": 4.3237, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.905273188618959e-05, "loss": 4.2905, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.904434593867907e-05, "loss": 4.3027, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903595999116855e-05, "loss": 4.3027, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902757404365803e-05, "loss": 4.308, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.901920447495124e-05, "loss": 4.2977, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.901081852744072e-05, "loss": 4.2886, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.90024325799302e-05, "loss": 4.2911, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994046632419686e-05, "loss": 4.2942, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985660684909166e-05, "loss": 4.2785, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977274737398646e-05, "loss": 4.2786, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968888789888125e-05, "loss": 4.2749, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960502842377605e-05, "loss": 4.2934, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952133273670815e-05, "loss": 4.2635, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943747326160294e-05, "loss": 4.2684, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935361378649774e-05, "loss": 4.2657, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2703, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.8918605862432463e-05, "loss": 4.2603, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.8910219914921943e-05, "loss": 4.2772, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.8901833967411423e-05, "loss": 4.2668, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.88934480199009e-05, "loss": 4.2601, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888506207239038e-05, "loss": 4.2511, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887667612487986e-05, "loss": 4.2656, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886829017736934e-05, "loss": 4.2566, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885992060866256e-05, "loss": 4.2623, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2454, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.258, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.249, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2545, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2349, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.880962130240316e-05, "loss": 4.254, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880123535489264e-05, "loss": 4.2355, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.2194, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.2496, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2336, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.87677079436543e-05, "loss": 4.2343, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875932199614378e-05, "loss": 4.2328, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875093604863326e-05, "loss": 4.2206, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.190104007720947, "eval_runtime": 524.2618, "eval_samples_per_second": 727.863, "eval_steps_per_second": 22.746, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874255010112274e-05, "loss": 4.2013, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873416415361222e-05, "loss": 4.2069, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2293, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717408637394906e-05, "loss": 4.213, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709022689884386e-05, "loss": 4.2193, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700636742373866e-05, "loss": 4.2089, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.2026, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.1972, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.2025, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.1999, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.2122, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.2065, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642000625015155e-05, "loss": 4.1916, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633614677504635e-05, "loss": 4.1838, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.1773, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.1754, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.1878, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.1794, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.1738, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.1922, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.1786, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.1744, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558157528713684e-05, "loss": 4.1771, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.1886, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.1588, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.1648, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.1763, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851624416996481e-05, "loss": 4.1626, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850785822245429e-05, "loss": 4.1523, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849947227494377e-05, "loss": 4.1523, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.166, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1611, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1584, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1578, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.1582, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1564, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.1416, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843240107366335e-05, "loss": 4.1437, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842401512615282e-05, "loss": 4.1299, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.84156291786423e-05, "loss": 4.1423, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840724323113178e-05, "loss": 4.1389, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398873662425e-05, "loss": 4.1497, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839048771491447e-05, "loss": 4.1354, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838210176740395e-05, "loss": 4.1426, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837371581989343e-05, "loss": 4.1367, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836532987238292e-05, "loss": 4.135, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.8356960303676126e-05, "loss": 4.1443, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.8348574356165606e-05, "loss": 4.1137, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.8340188408655086e-05, "loss": 4.1238, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331802461144566e-05, "loss": 4.1376, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.8323432892437775e-05, "loss": 4.1345, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.8315046944927255e-05, "loss": 4.1198, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.8306660997416735e-05, "loss": 4.1147, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298275049906215e-05, "loss": 4.1157, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289889102395695e-05, "loss": 4.1059, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281519533688904e-05, "loss": 4.1291, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273133586178384e-05, "loss": 4.1051, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.826474763866787e-05, "loss": 4.1243, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825636169115735e-05, "loss": 4.1154, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824797574364683e-05, "loss": 4.1026, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823960617494004e-05, "loss": 4.11, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823122022742952e-05, "loss": 4.1002, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222834279919e-05, "loss": 4.0981, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821446471121221e-05, "loss": 4.1017, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820607876370169e-05, "loss": 4.118, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819769281619117e-05, "loss": 4.0894, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818930686868065e-05, "loss": 4.0969, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818092092117013e-05, "loss": 4.0807, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817255135246334e-05, "loss": 4.0978, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816416540495282e-05, "loss": 4.108, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155779457442305e-05, "loss": 4.1015, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147393509931785e-05, "loss": 4.0937, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8139023941224994e-05, "loss": 4.1029, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.8130637993714474e-05, "loss": 4.1105, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.8122252046203954e-05, "loss": 4.0896, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.0889, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810549652998664e-05, "loss": 4.0909, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809711058247612e-05, "loss": 4.0846, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.80887246349656e-05, "loss": 4.0909, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808033868745508e-05, "loss": 4.0806, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807195273994456e-05, "loss": 4.0939, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806356679243404e-05, "loss": 4.0892, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805518084492352e-05, "loss": 4.0859, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804681127621674e-05, "loss": 4.0693, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803842532870622e-05, "loss": 4.0767, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.80300393811957e-05, "loss": 4.0835, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802165343368518e-05, "loss": 4.0836, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801328386497839e-05, "loss": 4.0807, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800489791746787e-05, "loss": 4.0758, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799651196995735e-05, "loss": 4.0792, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798812602244683e-05, "loss": 4.0689, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979756453740036e-05, "loss": 4.0628, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971370506229516e-05, "loss": 4.0782, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7962984558718996e-05, "loss": 4.0699, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.7954598611208476e-05, "loss": 4.0737, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794622904250169e-05, "loss": 4.0667, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793784309499117e-05, "loss": 4.0583, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792945714748065e-05, "loss": 4.0722, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792107119997013e-05, "loss": 4.0783, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791270163126334e-05, "loss": 4.0662, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790431568375282e-05, "loss": 4.0626, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.78959297362423e-05, "loss": 4.0539, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.7887543788731774e-05, "loss": 4.0603, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787917422002499e-05, "loss": 4.0658, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.787078827251447e-05, "loss": 4.0459, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.0525, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854032756297166e-05, "loss": 4.0583, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845646808786646e-05, "loss": 4.0615, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837260861276126e-05, "loss": 4.0478, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828874913765606e-05, "loss": 4.0537, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782048896625508e-05, "loss": 4.0431, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781210301874456e-05, "loss": 4.0645, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780371707123404e-05, "loss": 4.042, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779533112372352e-05, "loss": 4.0516, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778696155501673e-05, "loss": 4.0577, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777857560750621e-05, "loss": 4.0568, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.7770206038799423e-05, "loss": 4.0511, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.7761820091288903e-05, "loss": 4.041, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.7753434143778383e-05, "loss": 4.0483, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774504819626786e-05, "loss": 4.0529, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773666224875734e-05, "loss": 4.0365, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772827630124682e-05, "loss": 4.041, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.77198903537363e-05, "loss": 4.038, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771150440622578e-05, "loss": 4.0555, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770313483751899e-05, "loss": 4.0288, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769474889000847e-05, "loss": 4.0369, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768636294249795e-05, "loss": 4.0338, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767797699498743e-05, "loss": 4.0376, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766960742628064e-05, "loss": 4.0314, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766122147877012e-05, "loss": 4.0504, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528355312596e-05, "loss": 4.0447, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764444958374909e-05, "loss": 4.0341, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.76360800150423e-05, "loss": 4.026, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.7627710446335506e-05, "loss": 4.0444, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.7619324498824986e-05, "loss": 4.0379, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610938551314466e-05, "loss": 4.0458, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602552603803946e-05, "loss": 4.022, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594166656293426e-05, "loss": 4.0434, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585780708782906e-05, "loss": 4.034, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577394761272386e-05, "loss": 4.0431, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569008813761866e-05, "loss": 4.0242, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560639245055075e-05, "loss": 4.0382, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552253297544555e-05, "loss": 4.0286, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543867350034035e-05, "loss": 4.0157, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753548140252352e-05, "loss": 4.0382, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752711183381673e-05, "loss": 4.0294, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751872588630621e-05, "loss": 4.0266, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751033993879569e-05, "loss": 4.0236, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750195399128517e-05, "loss": 4.0178, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.023409366607666, "eval_runtime": 606.916, "eval_samples_per_second": 628.738, "eval_steps_per_second": 19.649, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749356804377465e-05, "loss": 3.9994, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748518209626413e-05, "loss": 4.0067, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747679614875361e-05, "loss": 4.0297, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.7468410201243084e-05, "loss": 4.0171, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460024253732563e-05, "loss": 4.0258, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451638306222043e-05, "loss": 4.0089, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744325235871152e-05, "loss": 4.0108, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434866411201e-05, "loss": 4.0041, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.742649684249422e-05, "loss": 4.007, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.74181108949837e-05, "loss": 4.014, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740972494747318e-05, "loss": 4.0165, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740133899996266e-05, "loss": 4.0186, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739296943125587e-05, "loss": 4.0043, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738458348374535e-05, "loss": 3.9982, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737619753623483e-05, "loss": 3.998, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736781158872431e-05, "loss": 3.9878, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735942564121379e-05, "loss": 4.0011, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735103969370327e-05, "loss": 3.9961, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734265374619275e-05, "loss": 3.9943, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733428417748596e-05, "loss": 4.0179, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.7325898229975444e-05, "loss": 3.9971, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.7317512282464924e-05, "loss": 4.0003, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.7309126334954404e-05, "loss": 4.0022, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.7300740387443884e-05, "loss": 4.0122, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292354439933364e-05, "loss": 3.9813, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7283968492422844e-05, "loss": 3.9926, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275582544912323e-05, "loss": 4.0001, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726721297620553e-05, "loss": 3.9935, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725884340749874e-05, "loss": 3.984, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725045745998822e-05, "loss": 3.9787, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724208789128143e-05, "loss": 3.9982, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723370194377091e-05, "loss": 3.9973, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.72253159962604e-05, "loss": 3.9864, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721693004874988e-05, "loss": 3.9925, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720854410123936e-05, "loss": 3.9901, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720015815372884e-05, "loss": 3.9881, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719177220621832e-05, "loss": 3.9779, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.71833862587078e-05, "loss": 3.9855, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.717500031119727e-05, "loss": 3.9641, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716661436368675e-05, "loss": 3.9812, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715822841617623e-05, "loss": 3.9808, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714984246866571e-05, "loss": 3.9901, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714147289995892e-05, "loss": 3.9791, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.71330869524484e-05, "loss": 3.9808, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712470100493788e-05, "loss": 3.9828, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116315057427366e-05, "loss": 3.9762, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7107929109916846e-05, "loss": 3.9874, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099543162406326e-05, "loss": 3.9588, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091157214895806e-05, "loss": 3.9749, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082771267385286e-05, "loss": 3.9817, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074418077482224e-05, "loss": 3.9822, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.7066032129971704e-05, "loss": 3.9693, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.7057646182461184e-05, "loss": 3.9621, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.7049260234950664e-05, "loss": 3.967, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040874287440144e-05, "loss": 3.9521, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032488339929624e-05, "loss": 3.9814, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024102392419104e-05, "loss": 3.9608, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015716444908584e-05, "loss": 3.9701, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.70073468762018e-05, "loss": 3.9695, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699896092869128e-05, "loss": 3.9576, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699057498118076e-05, "loss": 3.965, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698218903367024e-05, "loss": 3.9552, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697380308615972e-05, "loss": 3.956, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696543351745293e-05, "loss": 3.955, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695704756994241e-05, "loss": 3.972, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694866162243189e-05, "loss": 3.9525, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694027567492137e-05, "loss": 3.9533, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693188972741085e-05, "loss": 3.9412, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692350377990033e-05, "loss": 3.955, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691511783238981e-05, "loss": 3.963, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690673188487928e-05, "loss": 3.9664, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.68983623161725e-05, "loss": 3.9545, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6889976368661984e-05, "loss": 3.9656, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688159042115146e-05, "loss": 3.9709, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687320447364094e-05, "loss": 3.955, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686483490493415e-05, "loss": 3.946, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685644895742363e-05, "loss": 3.9588, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848063009913106e-05, "loss": 3.9507, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.6839677062402586e-05, "loss": 3.953, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.68313074936958e-05, "loss": 3.9453, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682292154618528e-05, "loss": 3.958, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.6814535598674755e-05, "loss": 3.9608, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806149651164235e-05, "loss": 3.9497, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679778008245745e-05, "loss": 3.9348, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678939413494693e-05, "loss": 3.9437, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678100818743641e-05, "loss": 3.9491, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677262223992589e-05, "loss": 3.9526, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676423629241537e-05, "loss": 3.9479, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675585034490485e-05, "loss": 3.9492, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674746439739433e-05, "loss": 3.9475, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673909482868754e-05, "loss": 3.9398, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673070888117702e-05, "loss": 3.9363, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.67223229336665e-05, "loss": 3.9418, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671393698615598e-05, "loss": 3.9464, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670556741744919e-05, "loss": 3.9484, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697181469938675e-05, "loss": 3.9421, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688795522428155e-05, "loss": 3.9291, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.6680409574917635e-05, "loss": 3.9464, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.6672023627407115e-05, "loss": 3.9547, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663654058700324e-05, "loss": 3.939, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655268111189804e-05, "loss": 3.9414, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.6646882163679284e-05, "loss": 3.9299, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.6638496216168764e-05, "loss": 3.9372, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.6630110268658244e-05, "loss": 3.9448, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621724321147724e-05, "loss": 3.9218, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661335475244093e-05, "loss": 3.931, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660496880493041e-05, "loss": 3.9398, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659658285741989e-05, "loss": 3.9361, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658819690990937e-05, "loss": 3.9258, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657982734120259e-05, "loss": 3.9378, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657144139369207e-05, "loss": 3.9231, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656305544618155e-05, "loss": 3.9437, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655466949867103e-05, "loss": 3.926, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654628355116051e-05, "loss": 3.9293, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653791398245372e-05, "loss": 3.9404, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.65295280349432e-05, "loss": 3.9406, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652114208743268e-05, "loss": 3.9359, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651275613992216e-05, "loss": 3.9255, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650438657121537e-05, "loss": 3.9298, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649600062370485e-05, "loss": 3.9328, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648761467619433e-05, "loss": 3.9253, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647922872868381e-05, "loss": 3.9288, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647085915997702e-05, "loss": 3.9214, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.64624732124665e-05, "loss": 3.9351, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645408726495598e-05, "loss": 3.923, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644570131744546e-05, "loss": 3.922, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643731536993494e-05, "loss": 3.9171, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642894580122815e-05, "loss": 3.9272, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642055985371763e-05, "loss": 3.9156, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641217390620711e-05, "loss": 3.9379, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640378795869659e-05, "loss": 3.9332, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395402011186065e-05, "loss": 3.9251, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638703244247928e-05, "loss": 3.911, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637864649496876e-05, "loss": 3.9354, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637026054745824e-05, "loss": 3.9259, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636187459994772e-05, "loss": 3.9297, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353505031240936e-05, "loss": 3.9155, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345119083730416e-05, "loss": 3.9264, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633673313621989e-05, "loss": 3.9274, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632834718870937e-05, "loss": 3.9372, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6319977620002585e-05, "loss": 3.9196, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631159167249206e-05, "loss": 3.9249, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630320572498154e-05, "loss": 3.9213, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629481977747102e-05, "loss": 3.9072, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286450208764234e-05, "loss": 3.9287, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278064261253714e-05, "loss": 3.927, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.6269678313743194e-05, "loss": 3.9153, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.6261292366232674e-05, "loss": 3.9178, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6252906418722154e-05, "loss": 3.9098, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9507577419281006, "eval_runtime": 304.4686, "eval_samples_per_second": 1253.302, "eval_steps_per_second": 39.167, "step": 228960 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.5894334033308058e+17, "trial_name": null, "trial_params": null }