{ "best_metric": 3.972667694091797, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/superlative-quantifier/transformer/4/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": 11.0538, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8148, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1895, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9764, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8108, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7001, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6017, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5273, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4508, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4119, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3616, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3115, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2729, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2256, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1867, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1552, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1153, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0953, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.06, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0461, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0247, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9905, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9635, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9441, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9328, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.9047, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8826, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8632, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8646, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8267, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8195, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8144, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7965, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7827, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7806, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7606, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7547, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 4.7215, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 4.7195, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 4.6989, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 4.6939, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6886, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6818, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6606, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6649, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6488, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.65, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6486, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.6183, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.6064, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958085003370758e-05, "loss": 4.6179, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957246408619706e-05, "loss": 4.6162, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956407813868654e-05, "loss": 4.5919, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5858, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5844, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.564, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5726, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5469, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5554, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5482, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5454, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.52, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5378, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.5088, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946349590497149e-05, "loss": 4.5185, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945510995746097e-05, "loss": 4.5176, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.5094, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4903, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4826, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4797, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 4.4915, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404794272397856e-05, "loss": 4.4851, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4665, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4791, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4807, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.463, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4603, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4521, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.452, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4337, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4356, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4317, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4447, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4321, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.4108, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4172, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.414, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.4189, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.413, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.4, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.4002, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.3916, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3813, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3762, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3801, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3892, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.3795, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3645, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.365, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3709, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916173282502262e-05, "loss": 4.3711, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.91533468775121e-05, "loss": 4.3621, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914496093000158e-05, "loss": 4.3582, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913657498249106e-05, "loss": 4.348, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3565, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3344, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3399, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3439, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3347, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3317, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.3328, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3244, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3285, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.3245, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.317, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3265, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3236, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019237232558704e-05, "loss": 4.3166, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010851285048184e-05, "loss": 4.3207, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900246533753767e-05, "loss": 4.3079, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899407939002715e-05, "loss": 4.3075, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985693442516624e-05, "loss": 4.2983, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977307495006104e-05, "loss": 4.2993, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968921547495584e-05, "loss": 4.2978, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2977, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.294, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2958, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2942, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2813, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2887, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2891, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2713, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2616, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888509482999785e-05, "loss": 4.2706, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887670888248733e-05, "loss": 4.2837, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.284, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.268, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2674, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2733, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2722, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2656, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2565, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809654060010626e-05, "loss": 4.2592, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801268112500106e-05, "loss": 4.2545, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2508, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2613, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877611026996855e-05, "loss": 4.2442, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.2561, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.2517, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875096880624072e-05, "loss": 4.2348, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.220964431762695, "eval_runtime": 303.1793, "eval_samples_per_second": 1258.632, "eval_steps_per_second": 39.333, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.87425828587302e-05, "loss": 4.2391, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873419691121968e-05, "loss": 4.2309, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.242, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2332, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.2376, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2232, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2183, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.2064, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2353, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.2232, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.2166, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.224, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642000625015155e-05, "loss": 4.2093, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633614677504635e-05, "loss": 4.2059, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.2034, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.2011, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.2007, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.196, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.2071, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.2126, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.196, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1889, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.1905, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.1945, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.187, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.1768, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.1796, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.1905, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.8507841843650564e-05, "loss": 4.1658, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849947227494377e-05, "loss": 4.1725, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849108632743325e-05, "loss": 4.1775, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.1775, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847431443241221e-05, "loss": 4.1813, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1732, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.1711, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1777, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844078702117387e-05, "loss": 4.1536, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1631, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1503, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.1544, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840725960993552e-05, "loss": 4.1552, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1588, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1562, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1495, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.15, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.8365346251186646e-05, "loss": 4.154, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1548, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1401, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834020478745882e-05, "loss": 4.1343, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.8331818839948295e-05, "loss": 4.1474, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832344927124151e-05, "loss": 4.1547, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.137, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830667737622047e-05, "loss": 4.137, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.1356, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289905481199424e-05, "loss": 4.128, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.1336, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.1216, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.1335, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.1329, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1282, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.114, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823123660623325e-05, "loss": 4.1348, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822285065872273e-05, "loss": 4.1094, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.1242, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820609514250542e-05, "loss": 4.1273, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.1231, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818932324748438e-05, "loss": 4.1085, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.1076, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172567731267074e-05, "loss": 4.1061, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.1156, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155795836246034e-05, "loss": 4.1186, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.1109, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.1197, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1193, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.1167, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811389885630089e-05, "loss": 4.1025, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810551290879037e-05, "loss": 4.1117, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809712696127985e-05, "loss": 4.1095, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.092, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808037144506255e-05, "loss": 4.1087, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807198549755203e-05, "loss": 4.0956, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.1176, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805521360253099e-05, "loss": 4.1048, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.8046844033824197e-05, "loss": 4.0826, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.8038458086313677e-05, "loss": 4.1004, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.0902, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021686191292636e-05, "loss": 4.1041, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013316622585846e-05, "loss": 4.0961, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004930675075325e-05, "loss": 4.0906, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996544727564805e-05, "loss": 4.0927, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988158780054285e-05, "loss": 4.0844, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979789211347494e-05, "loss": 4.0779, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797140326383698e-05, "loss": 4.0773, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.0837, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795464774761967e-05, "loss": 4.0933, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794626180010915e-05, "loss": 4.0837, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793787585259863e-05, "loss": 4.0743, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0754, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.0828, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791271801006707e-05, "loss": 4.0874, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790433206255655e-05, "loss": 4.0797, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789594611504603e-05, "loss": 4.0764, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.0727, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.0804, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708046513182e-05, "loss": 4.059, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.0722, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854049135100895e-05, "loss": 4.0753, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845663187590375e-05, "loss": 4.0669, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837277240079855e-05, "loss": 4.0632, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828891292569335e-05, "loss": 4.0659, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820505345058815e-05, "loss": 4.0647, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812119397548295e-05, "loss": 4.0641, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803749828841504e-05, "loss": 4.0659, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795363881330984e-05, "loss": 4.0625, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786977933820464e-05, "loss": 4.0735, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778591986309944e-05, "loss": 4.0714, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777022241760315e-05, "loss": 4.0662, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776183647009263e-05, "loss": 4.0666, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775345052258212e-05, "loss": 4.0617, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.77450645750716e-05, "loss": 4.0594, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773667862756108e-05, "loss": 4.0525, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772829268005055e-05, "loss": 4.0525, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771990673254003e-05, "loss": 4.0575, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771152078502951e-05, "loss": 4.0588, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770315121632272e-05, "loss": 4.0555, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.76947652688122e-05, "loss": 4.0561, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768637932130168e-05, "loss": 4.0527, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.76780097525949e-05, "loss": 4.0524, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766962380508437e-05, "loss": 4.0509, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766123785757386e-05, "loss": 4.0602, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765285191006334e-05, "loss": 4.0422, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764448234135655e-05, "loss": 4.0328, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636096393846026e-05, "loss": 4.0396, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.7627710446335506e-05, "loss": 4.0573, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.7619324498824986e-05, "loss": 4.0544, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610954930118195e-05, "loss": 4.0492, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602568982607675e-05, "loss": 4.0428, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594183035097155e-05, "loss": 4.053, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585797087586635e-05, "loss": 4.0502, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577427518879844e-05, "loss": 4.0471, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569041571369324e-05, "loss": 4.0394, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756065562385881e-05, "loss": 4.0412, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755226967634829e-05, "loss": 4.043, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543916486445236e-05, "loss": 4.0315, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535530538934716e-05, "loss": 4.0513, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527144591424196e-05, "loss": 4.0327, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751875864391367e-05, "loss": 4.0425, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751037269640315e-05, "loss": 4.0412, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750198674889263e-05, "loss": 4.0286, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.048327445983887, "eval_runtime": 302.7368, "eval_samples_per_second": 1260.471, "eval_steps_per_second": 39.391, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749360080138211e-05, "loss": 4.0323, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748521485387159e-05, "loss": 4.0275, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747682890636107e-05, "loss": 4.0353, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746844295885055e-05, "loss": 4.0317, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.746005701134003e-05, "loss": 4.0392, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745167106382951e-05, "loss": 4.0241, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744328511631899e-05, "loss": 4.0214, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434899168808475e-05, "loss": 4.0089, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426513221297955e-05, "loss": 4.0413, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418127273787435e-05, "loss": 4.0279, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740974132627691e-05, "loss": 4.0169, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401371757570124e-05, "loss": 4.0348, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739301856766706e-05, "loss": 4.0142, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738463262015654e-05, "loss": 4.0194, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737624667264602e-05, "loss": 4.009, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.73678607251355e-05, "loss": 4.0105, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735947477762498e-05, "loss": 4.0167, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735108883011446e-05, "loss": 4.0064, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734270288260394e-05, "loss": 4.0225, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733431693509343e-05, "loss": 4.0253, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732593098758291e-05, "loss": 4.0143, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731754504007238e-05, "loss": 4.0101, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730915909256186e-05, "loss": 4.0095, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730078952385508e-05, "loss": 4.0139, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729240357634456e-05, "loss": 4.0046, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728401762883403e-05, "loss": 4.0047, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727563168132351e-05, "loss": 3.9978, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726726211261673e-05, "loss": 4.0162, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725887616510621e-05, "loss": 3.988, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725049021759568e-05, "loss": 4.0005, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724210427008517e-05, "loss": 4.0056, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723373470137838e-05, "loss": 4.0066, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225348753867856e-05, "loss": 4.0055, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216962806357336e-05, "loss": 4.0036, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208576858846816e-05, "loss": 3.9995, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200190911336296e-05, "loss": 4.01, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191804963825775e-05, "loss": 3.9899, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183419016315255e-05, "loss": 3.9959, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175033068804735e-05, "loss": 3.981, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166663500097945e-05, "loss": 3.9908, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158277552587424e-05, "loss": 3.9856, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149891605076904e-05, "loss": 3.999, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141505657566384e-05, "loss": 3.9916, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.71331360888596e-05, "loss": 3.9882, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712475014134908e-05, "loss": 3.9918, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711636419383856e-05, "loss": 3.9931, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710797824632804e-05, "loss": 3.9946, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709960867762125e-05, "loss": 3.9798, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709122273011073e-05, "loss": 3.9734, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708283678260021e-05, "loss": 3.9945, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707445083508969e-05, "loss": 3.9948, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.70660812663829e-05, "loss": 3.9833, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705769531887238e-05, "loss": 3.9834, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704930937136186e-05, "loss": 3.9764, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704092342385134e-05, "loss": 3.9761, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032553855144554e-05, "loss": 3.9821, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024167907634034e-05, "loss": 3.9706, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015781960123514e-05, "loss": 3.9817, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007396012612994e-05, "loss": 3.9812, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.69990264439062e-05, "loss": 3.9749, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699064049639568e-05, "loss": 3.9665, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698225454888516e-05, "loss": 3.9873, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697386860137464e-05, "loss": 3.9627, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696549903266785e-05, "loss": 3.976, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695711308515733e-05, "loss": 3.9765, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694872713764681e-05, "loss": 3.9786, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694034119013629e-05, "loss": 3.9612, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693198800023324e-05, "loss": 3.9644, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692360205272272e-05, "loss": 3.9558, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.69152161052122e-05, "loss": 3.9725, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.6906830157701677e-05, "loss": 3.9762, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.6898444210191157e-05, "loss": 3.9704, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890058262680636e-05, "loss": 3.9741, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881672315170116e-05, "loss": 3.9755, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873286367659596e-05, "loss": 3.9791, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864933177756535e-05, "loss": 3.9599, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856547230246015e-05, "loss": 3.9712, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848161282735495e-05, "loss": 3.9747, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683977533522498e-05, "loss": 3.9537, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683138938771446e-05, "loss": 3.9688, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682300344020394e-05, "loss": 3.9583, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681461749269342e-05, "loss": 3.9806, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.68062315451829e-05, "loss": 3.9672, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679786197647611e-05, "loss": 3.9479, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678947602896559e-05, "loss": 3.9605, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678109008145507e-05, "loss": 3.9591, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677270413394455e-05, "loss": 3.9695, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676433456523776e-05, "loss": 3.9617, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675594861772724e-05, "loss": 3.9562, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674756267021672e-05, "loss": 3.9575, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.67391767227062e-05, "loss": 3.9529, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730807153999415e-05, "loss": 3.948, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722421206488895e-05, "loss": 3.9418, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6714035258978375e-05, "loss": 3.9548, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705649311467855e-05, "loss": 3.9641, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697263363957335e-05, "loss": 3.955, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688877416446815e-05, "loss": 3.9441, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668049146893629e-05, "loss": 3.947, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667210552142577e-05, "loss": 3.9515, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663735952718984e-05, "loss": 3.9628, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665535000520846e-05, "loss": 3.9521, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664696405769794e-05, "loss": 3.9509, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663857811018742e-05, "loss": 3.9432, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663020854148063e-05, "loss": 3.9565, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662182259397011e-05, "loss": 3.9309, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661343664645959e-05, "loss": 3.9487, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660505069894907e-05, "loss": 3.9466, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659668113024229e-05, "loss": 3.9462, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658829518273176e-05, "loss": 3.938, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657990923522124e-05, "loss": 3.9436, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657153966651446e-05, "loss": 3.9419, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656315371900393e-05, "loss": 3.9424, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554784150297146e-05, "loss": 3.9449, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546398202786626e-05, "loss": 3.9431, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6538012255276106e-05, "loss": 3.9487, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.6529626307765586e-05, "loss": 3.9494, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.65212567390588e-05, "loss": 3.9481, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651287079154828e-05, "loss": 3.9475, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650448484403776e-05, "loss": 3.9415, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.6496098896527235e-05, "loss": 3.9366, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.6487712949016715e-05, "loss": 3.9366, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.6479327001506195e-05, "loss": 3.9369, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470941053995675e-05, "loss": 3.9325, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462555106485155e-05, "loss": 3.9438, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454185537778364e-05, "loss": 3.9354, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644581596907158e-05, "loss": 3.9422, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643743002156106e-05, "loss": 3.9364, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642904407405054e-05, "loss": 3.9341, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642065812654002e-05, "loss": 3.9321, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.64122721790295e-05, "loss": 3.9485, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640390261032271e-05, "loss": 3.9269, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639551666281219e-05, "loss": 3.9242, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638713071530167e-05, "loss": 3.9208, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637874476779115e-05, "loss": 3.9386, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637035882028063e-05, "loss": 3.9418, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636197287277011e-05, "loss": 3.9382, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635358692525959e-05, "loss": 3.9289, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634520097774907e-05, "loss": 3.9428, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633683140904228e-05, "loss": 3.933, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632844546153176e-05, "loss": 3.9377, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320059514021244e-05, "loss": 3.9269, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311673566510724e-05, "loss": 3.931, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303303997803934e-05, "loss": 3.9314, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629493442909714e-05, "loss": 3.9189, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628654848158662e-05, "loss": 3.94, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.62781625340761e-05, "loss": 3.9298, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626977658656558e-05, "loss": 3.9294, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626139063905506e-05, "loss": 3.9314, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625302107034827e-05, "loss": 3.9187, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.972667694091797, "eval_runtime": 303.7984, "eval_samples_per_second": 1256.066, "eval_steps_per_second": 39.253, "step": 228960 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.5293807645947085e+17, "trial_name": null, "trial_params": null }