{ "best_metric": 3.863309860229492, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/superlative-quantifier/transformer/2/checkpoints/checkpoint-839520", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 1908000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.9302, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8188, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1906, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.984, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8202, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7093, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6114, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5357, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.458, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4169, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.367, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3165, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989936862987376e-05, "loss": 5.2771, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2283, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1883, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.156, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1163, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0957, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0587, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0439, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0241, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9897, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9634, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9414, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9305, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.9035, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.88, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8601, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8631, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.827, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8175, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8139, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.794, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.782, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7801, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7588, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7544, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.72, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7175, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6971, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6912, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6867, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6796, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6601, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6631, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6458, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6482, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.647, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.6167, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.6073, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958085003370758e-05, "loss": 4.6152, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957246408619706e-05, "loss": 4.6147, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956407813868654e-05, "loss": 4.5893, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5837, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5817, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5632, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5713, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.545, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5539, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5452, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5421, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5183, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5349, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.5059, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.5163, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5142, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.5066, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4884, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4799, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4762, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4883, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4829, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4666, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4765, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4778, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.462, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4572, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4485, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4496, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4318, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4348, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4301, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4426, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4281, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.41, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.415, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4113, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.4149, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.4099, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3992, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.3962, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.3902, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3788, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3729, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.378, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3855, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.3759, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3633, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3624, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3671, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916173282502262e-05, "loss": 4.3689, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.91533468775121e-05, "loss": 4.359, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914496093000158e-05, "loss": 4.3543, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913657498249106e-05, "loss": 4.3449, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3549, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3329, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.338, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3412, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3321, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.329, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.3293, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3219, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3243, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.322, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.315, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3238, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3207, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019237232558704e-05, "loss": 4.3142, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010851285048184e-05, "loss": 4.3151, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900246533753767e-05, "loss": 4.3051, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899407939002715e-05, "loss": 4.3052, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985693442516624e-05, "loss": 4.2969, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977307495006104e-05, "loss": 4.2963, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968921547495584e-05, "loss": 4.2954, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2948, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2919, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2924, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2898, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2784, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2876, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2866, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2683, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2593, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.268, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.2813, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2819, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2675, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.264, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884316509244525e-05, "loss": 4.2692, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883477914493473e-05, "loss": 4.2702, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882639319742421e-05, "loss": 4.2605, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881800724991369e-05, "loss": 4.2528, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.2576, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.2511, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879286578618586e-05, "loss": 4.2492, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878447983867534e-05, "loss": 4.258, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877609389116482e-05, "loss": 4.2421, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.2531, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.2492, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.8750952427436986e-05, "loss": 4.2306, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.220055103302002, "eval_runtime": 305.3236, "eval_samples_per_second": 1249.792, "eval_steps_per_second": 39.057, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.8742566479926466e-05, "loss": 4.2358, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.8734180532415946e-05, "loss": 4.2273, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.8725794584905426e-05, "loss": 4.2397, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2308, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.2353, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.8700653121177595e-05, "loss": 4.2195, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.8692267173667075e-05, "loss": 4.2165, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683881226156555e-05, "loss": 4.2018, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.2335, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.2206, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865873976242873e-05, "loss": 4.2147, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865035381491821e-05, "loss": 4.2215, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.864198424621142e-05, "loss": 4.2081, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.86335982987009e-05, "loss": 4.204, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862521235119038e-05, "loss": 4.2005, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861682640367986e-05, "loss": 4.2002, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860844045616934e-05, "loss": 4.1968, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860005450865882e-05, "loss": 4.1914, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.85916685611483e-05, "loss": 4.2045, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858328261363778e-05, "loss": 4.21, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574913044930995e-05, "loss": 4.194, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566527097420475e-05, "loss": 4.1849, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558141149909955e-05, "loss": 4.1878, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549755202399435e-05, "loss": 4.1923, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.8541385633692644e-05, "loss": 4.1832, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.8532999686182124e-05, "loss": 4.1737, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.8524613738671604e-05, "loss": 4.1762, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.8516227791161084e-05, "loss": 4.1862, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850785822245429e-05, "loss": 4.1631, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849947227494377e-05, "loss": 4.1681, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849108632743325e-05, "loss": 4.1754, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848270037992273e-05, "loss": 4.1744, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1785, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1706, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845755891619491e-05, "loss": 4.17, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844917296868439e-05, "loss": 4.1746, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.152, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1616, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1466, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.1504, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1541, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1562, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1527, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1476, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83737485775009e-05, "loss": 4.1494, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1511, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1526, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1382, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834022116626255e-05, "loss": 4.1334, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833185159755576e-05, "loss": 4.1443, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832346565004524e-05, "loss": 4.1532, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831507970253472e-05, "loss": 4.1341, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.83066937550242e-05, "loss": 4.1357, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829830780751368e-05, "loss": 4.1331, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828992186000316e-05, "loss": 4.1249, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.1337, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273166343785856e-05, "loss": 4.12, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264780396275336e-05, "loss": 4.1333, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256394448764816e-05, "loss": 4.1292, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1263, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.8239638932547505e-05, "loss": 4.1108, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231252985036985e-05, "loss": 4.1325, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222867037526465e-05, "loss": 4.1058, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.1211, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.8206111521309154e-05, "loss": 4.1242, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.8197725573798634e-05, "loss": 4.1211, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189339626288114e-05, "loss": 4.1063, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.1045, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817258411007081e-05, "loss": 4.1031, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816419816256029e-05, "loss": 4.1141, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815581221504977e-05, "loss": 4.1159, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.1097, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813905669883246e-05, "loss": 4.1183, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813067075132194e-05, "loss": 4.1166, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812228480381141e-05, "loss": 4.1133, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811389885630089e-05, "loss": 4.1005, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810552928759411e-05, "loss": 4.1105, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809714334008359e-05, "loss": 4.1097, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808875739257306e-05, "loss": 4.0883, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808037144506255e-05, "loss": 4.1083, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807200187635576e-05, "loss": 4.0932, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.8063615928845243e-05, "loss": 4.1136, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.8055229981334717e-05, "loss": 4.1024, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.8046844033824197e-05, "loss": 4.0809, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803847446511741e-05, "loss": 4.0979, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030088517606886e-05, "loss": 4.0888, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021702570096366e-05, "loss": 4.1019, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013316622585846e-05, "loss": 4.0933, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800494705387906e-05, "loss": 4.0885, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996561106368535e-05, "loss": 4.09, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988175158858015e-05, "loss": 4.0819, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979789211347494e-05, "loss": 4.0761, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797140326383698e-05, "loss": 4.0748, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.0811, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795464774761967e-05, "loss": 4.091, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794626180010915e-05, "loss": 4.0823, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793787585259863e-05, "loss": 4.0729, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0735, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.0813, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791271801006707e-05, "loss": 4.0874, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790433206255655e-05, "loss": 4.0773, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789594611504603e-05, "loss": 4.0753, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.0701, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.0792, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708046513182e-05, "loss": 4.0576, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.0683, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854049135100895e-05, "loss": 4.0726, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845663187590375e-05, "loss": 4.0649, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837277240079855e-05, "loss": 4.0598, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828891292569335e-05, "loss": 4.0634, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820505345058815e-05, "loss": 4.0637, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812119397548295e-05, "loss": 4.0611, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803733450037775e-05, "loss": 4.0655, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795363881330984e-05, "loss": 4.0596, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786977933820464e-05, "loss": 4.0716, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778591986309944e-05, "loss": 4.0695, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777022241760315e-05, "loss": 4.0642, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776183647009263e-05, "loss": 4.0629, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775345052258212e-05, "loss": 4.0601, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.77450645750716e-05, "loss": 4.0575, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773667862756108e-05, "loss": 4.0515, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772829268005055e-05, "loss": 4.0517, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.771990673254003e-05, "loss": 4.0565, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771152078502951e-05, "loss": 4.0566, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770315121632272e-05, "loss": 4.0532, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.76947652688122e-05, "loss": 4.0555, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768637932130168e-05, "loss": 4.0495, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.767799337379116e-05, "loss": 4.0507, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766962380508437e-05, "loss": 4.0499, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766123785757386e-05, "loss": 4.0589, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765285191006334e-05, "loss": 4.0414, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764446596255282e-05, "loss": 4.031, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636096393846026e-05, "loss": 4.0382, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.7627710446335506e-05, "loss": 4.0548, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.7619324498824986e-05, "loss": 4.0538, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610938551314466e-05, "loss": 4.0476, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602568982607675e-05, "loss": 4.0416, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594183035097155e-05, "loss": 4.0509, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585797087586635e-05, "loss": 4.048, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577411140076115e-05, "loss": 4.0449, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569041571369324e-05, "loss": 4.0379, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756067200266254e-05, "loss": 4.0387, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755228605515202e-05, "loss": 4.0399, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.75439001076415e-05, "loss": 4.0315, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753551416013098e-05, "loss": 4.0499, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752712821262046e-05, "loss": 4.0312, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751875864391367e-05, "loss": 4.0413, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751037269640315e-05, "loss": 4.0393, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750198674889263e-05, "loss": 4.0253, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.047743320465088, "eval_runtime": 308.0601, "eval_samples_per_second": 1238.69, "eval_steps_per_second": 38.71, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749360080138211e-05, "loss": 4.0303, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748521485387159e-05, "loss": 4.0236, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747682890636107e-05, "loss": 4.033, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746844295885055e-05, "loss": 4.0287, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.746005701134003e-05, "loss": 4.037, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745167106382951e-05, "loss": 4.0209, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744328511631899e-05, "loss": 4.0188, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434899168808475e-05, "loss": 4.0065, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426513221297955e-05, "loss": 4.039, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418127273787435e-05, "loss": 4.0264, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.740974132627691e-05, "loss": 4.0146, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401371757570124e-05, "loss": 4.0322, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739301856766706e-05, "loss": 4.0135, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738463262015654e-05, "loss": 4.0175, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737624667264602e-05, "loss": 4.0076, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.73678607251355e-05, "loss": 4.0099, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735947477762498e-05, "loss": 4.0145, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735108883011446e-05, "loss": 4.0055, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734270288260394e-05, "loss": 4.0217, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733431693509343e-05, "loss": 4.0238, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732593098758291e-05, "loss": 4.012, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731754504007238e-05, "loss": 4.0072, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730915909256186e-05, "loss": 4.0095, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730078952385508e-05, "loss": 4.0136, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729240357634456e-05, "loss": 4.0009, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728401762883403e-05, "loss": 4.0015, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727563168132351e-05, "loss": 3.9962, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726726211261673e-05, "loss": 4.0139, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725887616510621e-05, "loss": 3.9876, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725049021759568e-05, "loss": 3.9968, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724210427008517e-05, "loss": 4.0034, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723373470137838e-05, "loss": 4.0051, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225348753867856e-05, "loss": 4.0056, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216962806357336e-05, "loss": 4.0027, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208576858846816e-05, "loss": 3.998, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720020729014003e-05, "loss": 4.0074, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191821342629505e-05, "loss": 3.99, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183435395118985e-05, "loss": 3.9936, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175049447608465e-05, "loss": 3.9792, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716667987890168e-05, "loss": 3.9877, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715831031019489e-05, "loss": 3.9857, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714992436268437e-05, "loss": 3.9968, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714153841517385e-05, "loss": 3.9899, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713315246766333e-05, "loss": 3.9869, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712476652015281e-05, "loss": 3.9902, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711638057264229e-05, "loss": 3.9915, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7108011003935505e-05, "loss": 3.9921, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709962505642498e-05, "loss": 3.9798, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709123910891446e-05, "loss": 3.9729, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708285316140394e-05, "loss": 3.9937, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707446721389342e-05, "loss": 3.9927, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.70660812663829e-05, "loss": 3.9812, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705769531887238e-05, "loss": 3.9818, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704930937136186e-05, "loss": 3.9754, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.7040939802655074e-05, "loss": 3.9734, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.7032553855144554e-05, "loss": 3.9832, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024167907634034e-05, "loss": 3.9681, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015781960123514e-05, "loss": 3.9813, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007396012612994e-05, "loss": 3.9791, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6999010065102474e-05, "loss": 3.9724, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990624117591954e-05, "loss": 3.9627, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698225454888516e-05, "loss": 3.9839, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697386860137464e-05, "loss": 3.9611, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696548265386412e-05, "loss": 3.9724, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.69570967063536e-05, "loss": 3.973, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694872713764681e-05, "loss": 3.9775, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694034119013629e-05, "loss": 3.9591, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693195524262577e-05, "loss": 3.9627, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692356929511526e-05, "loss": 3.9537, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691519972640847e-05, "loss": 3.9724, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690681377889795e-05, "loss": 3.9753, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689842783138743e-05, "loss": 3.9689, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689004188387691e-05, "loss": 3.9736, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688165593636639e-05, "loss": 3.973, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687326998885587e-05, "loss": 3.9779, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864900420149076e-05, "loss": 3.9563, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856514472638556e-05, "loss": 3.9703, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848128525128036e-05, "loss": 3.9732, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683974257761751e-05, "loss": 3.9526, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831373008910725e-05, "loss": 3.9679, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822987061400205e-05, "loss": 3.9562, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681460111388969e-05, "loss": 3.9784, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806215166379165e-05, "loss": 3.9658, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797829218868645e-05, "loss": 3.9463, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789443271358125e-05, "loss": 3.9599, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781057323847605e-05, "loss": 3.9579, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772687755140814e-05, "loss": 3.9656, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764301807630294e-05, "loss": 3.96, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755915860119774e-05, "loss": 3.956, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747529912609254e-05, "loss": 3.9573, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739143965098734e-05, "loss": 3.9513, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730758017588214e-05, "loss": 3.9479, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.6722372070077694e-05, "loss": 3.9392, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.6713986122567174e-05, "loss": 3.952, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670563293266412e-05, "loss": 3.9613, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.66972469851536e-05, "loss": 3.955, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668886103764308e-05, "loss": 3.9434, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668047509013256e-05, "loss": 3.9473, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667208914262204e-05, "loss": 3.9492, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666370319511152e-05, "loss": 3.961, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655317247601e-05, "loss": 3.9527, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664693130009048e-05, "loss": 3.9501, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663856173138369e-05, "loss": 3.9414, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66301921626769e-05, "loss": 3.9555, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.6621806215166383e-05, "loss": 3.9313, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.6613420267655863e-05, "loss": 3.9461, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660505069894907e-05, "loss": 3.9446, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659666475143855e-05, "loss": 3.9443, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658827880392803e-05, "loss": 3.9358, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657989285641751e-05, "loss": 3.9413, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657150690890699e-05, "loss": 3.9407, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656312096139647e-05, "loss": 3.9415, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655473501388595e-05, "loss": 3.9425, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654634906637543e-05, "loss": 3.9399, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653797949766864e-05, "loss": 3.9472, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652959355015812e-05, "loss": 3.9489, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.65212076026476e-05, "loss": 3.9477, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651282165513708e-05, "loss": 3.9431, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.65044520864303e-05, "loss": 3.9404, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649606613891978e-05, "loss": 3.9344, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648768019140926e-05, "loss": 3.9349, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647929424389874e-05, "loss": 3.936, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647090829638822e-05, "loss": 3.9333, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462538727681426e-05, "loss": 3.9427, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454152780170906e-05, "loss": 3.9347, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445766832660386e-05, "loss": 3.9405, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437380885149866e-05, "loss": 3.936, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429011316443075e-05, "loss": 3.9335, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420625368932555e-05, "loss": 3.9306, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412239421422035e-05, "loss": 3.9469, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640385347391152e-05, "loss": 3.9258, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395467526401e-05, "loss": 3.9242, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387081578890475e-05, "loss": 3.9195, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378695631379955e-05, "loss": 3.9389, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637032606267317e-05, "loss": 3.9397, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636194011516265e-05, "loss": 3.9381, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353554167652124e-05, "loss": 3.9278, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345168220141604e-05, "loss": 3.9406, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336782272631084e-05, "loss": 3.9333, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328396325120564e-05, "loss": 3.9361, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320010377610043e-05, "loss": 3.9257, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631164080890326e-05, "loss": 3.93, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630325486139274e-05, "loss": 3.9297, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629486891388222e-05, "loss": 3.9184, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.62864829663717e-05, "loss": 3.9387, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627811339766491e-05, "loss": 3.9284, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626972745015439e-05, "loss": 3.9272, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626134150264387e-05, "loss": 3.9297, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625295555513335e-05, "loss": 3.9163, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.972442626953125, "eval_runtime": 310.6739, "eval_samples_per_second": 1228.269, "eval_steps_per_second": 38.384, "step": 228960 }, { "epoch": 0.0, "learning_rate": 4.624456960762283e-05, "loss": 3.9209, "step": 229376 }, { "epoch": 0.0, "learning_rate": 4.623618366011231e-05, "loss": 3.9174, "step": 229888 }, { "epoch": 0.0, "learning_rate": 4.622779771260179e-05, "loss": 3.924, "step": 230400 }, { "epoch": 0.0, "learning_rate": 4.621941176509127e-05, "loss": 3.9221, "step": 230912 }, { "epoch": 0.0, "learning_rate": 4.621102581758075e-05, "loss": 3.9342, "step": 231424 }, { "epoch": 0.0, "learning_rate": 4.620263987007023e-05, "loss": 3.915, "step": 231936 }, { "epoch": 0.0, "learning_rate": 4.619425392255971e-05, "loss": 3.9104, "step": 232448 }, { "epoch": 0.0, "learning_rate": 4.618586797504919e-05, "loss": 3.9024, "step": 232960 }, { "epoch": 0.0, "learning_rate": 4.6177498406342404e-05, "loss": 3.9296, "step": 233472 }, { "epoch": 0.0, "learning_rate": 4.6169112458831884e-05, "loss": 3.9246, "step": 233984 }, { "epoch": 0.0, "learning_rate": 4.6160726511321364e-05, "loss": 3.9059, "step": 234496 }, { "epoch": 0.0, "learning_rate": 4.615234056381084e-05, "loss": 3.928, "step": 235008 }, { "epoch": 0.0, "learning_rate": 4.614397099510405e-05, "loss": 3.912, "step": 235520 }, { "epoch": 0.0, "learning_rate": 4.613558504759353e-05, "loss": 3.9142, "step": 236032 }, { "epoch": 0.0, "learning_rate": 4.6127199100083006e-05, "loss": 3.9079, "step": 236544 }, { "epoch": 0.0, "learning_rate": 4.6118813152572486e-05, "loss": 3.9071, "step": 237056 }, { "epoch": 0.0, "learning_rate": 4.6110427205061966e-05, "loss": 3.9103, "step": 237568 }, { "epoch": 0.0, "learning_rate": 4.6102041257551446e-05, "loss": 3.9052, "step": 238080 }, { "epoch": 0.0, "learning_rate": 4.6093655310040926e-05, "loss": 3.9198, "step": 238592 }, { "epoch": 0.0, "learning_rate": 4.6085269362530406e-05, "loss": 3.9196, "step": 239104 }, { "epoch": 0.0, "learning_rate": 4.607688341501989e-05, "loss": 3.9149, "step": 239616 }, { "epoch": 0.0, "learning_rate": 4.60685138463131e-05, "loss": 3.9094, "step": 240128 }, { "epoch": 0.0, "learning_rate": 4.606012789880258e-05, "loss": 3.9054, "step": 240640 }, { "epoch": 0.0, "learning_rate": 4.605174195129206e-05, "loss": 3.9164, "step": 241152 }, { "epoch": 0.0, "learning_rate": 4.604335600378154e-05, "loss": 3.8995, "step": 241664 }, { "epoch": 0.0, "learning_rate": 4.603498643507475e-05, "loss": 3.9041, "step": 242176 }, { "epoch": 0.0, "learning_rate": 4.602660048756423e-05, "loss": 3.8986, "step": 242688 }, { "epoch": 0.0, "learning_rate": 4.601821454005371e-05, "loss": 3.9125, "step": 243200 }, { "epoch": 0.0, "learning_rate": 4.600982859254319e-05, "loss": 3.8906, "step": 243712 }, { "epoch": 0.01, "learning_rate": 4.600144264503267e-05, "loss": 3.8974, "step": 244224 }, { "epoch": 0.01, "learning_rate": 4.599307307632588e-05, "loss": 3.9088, "step": 244736 }, { "epoch": 0.01, "learning_rate": 4.598468712881536e-05, "loss": 3.904, "step": 245248 }, { "epoch": 0.01, "learning_rate": 4.5976301181304846e-05, "loss": 3.9083, "step": 245760 }, { "epoch": 0.01, "learning_rate": 4.5967915233794326e-05, "loss": 3.9078, "step": 246272 }, { "epoch": 0.01, "learning_rate": 4.5959529286283806e-05, "loss": 3.9006, "step": 246784 }, { "epoch": 0.01, "learning_rate": 4.5951143338773286e-05, "loss": 3.9093, "step": 247296 }, { "epoch": 0.01, "learning_rate": 4.5942773770066495e-05, "loss": 3.8979, "step": 247808 }, { "epoch": 0.01, "learning_rate": 4.5934387822555975e-05, "loss": 3.8913, "step": 248320 }, { "epoch": 0.01, "learning_rate": 4.5926001875045455e-05, "loss": 3.8866, "step": 248832 }, { "epoch": 0.01, "learning_rate": 4.5917615927534935e-05, "loss": 3.8929, "step": 249344 }, { "epoch": 0.01, "learning_rate": 4.5909246358828144e-05, "loss": 3.8911, "step": 249856 }, { "epoch": 0.01, "learning_rate": 4.5900860411317624e-05, "loss": 3.9055, "step": 250368 }, { "epoch": 0.01, "learning_rate": 4.5892474463807104e-05, "loss": 3.894, "step": 250880 }, { "epoch": 0.01, "learning_rate": 4.5884088516296584e-05, "loss": 3.8931, "step": 251392 }, { "epoch": 0.01, "learning_rate": 4.5875702568786064e-05, "loss": 3.8997, "step": 251904 }, { "epoch": 0.01, "learning_rate": 4.5867316621275544e-05, "loss": 3.8933, "step": 252416 }, { "epoch": 0.01, "learning_rate": 4.585894705256876e-05, "loss": 3.9027, "step": 252928 }, { "epoch": 0.01, "learning_rate": 4.585056110505824e-05, "loss": 3.8867, "step": 253440 }, { "epoch": 0.01, "learning_rate": 4.584217515754772e-05, "loss": 3.8743, "step": 253952 }, { "epoch": 0.01, "learning_rate": 4.58337892100372e-05, "loss": 3.9054, "step": 254464 }, { "epoch": 0.01, "learning_rate": 4.582540326252667e-05, "loss": 3.8967, "step": 254976 }, { "epoch": 0.01, "learning_rate": 4.581703369381989e-05, "loss": 3.8952, "step": 255488 }, { "epoch": 0.01, "learning_rate": 4.580864774630937e-05, "loss": 3.8865, "step": 256000 }, { "epoch": 0.01, "learning_rate": 4.580026179879884e-05, "loss": 3.8853, "step": 256512 }, { "epoch": 0.01, "learning_rate": 4.579187585128832e-05, "loss": 3.8809, "step": 257024 }, { "epoch": 0.01, "learning_rate": 4.57834899037778e-05, "loss": 3.8904, "step": 257536 }, { "epoch": 0.01, "learning_rate": 4.577512033507102e-05, "loss": 3.879, "step": 258048 }, { "epoch": 0.01, "learning_rate": 4.57667343875605e-05, "loss": 3.8857, "step": 258560 }, { "epoch": 0.01, "learning_rate": 4.575834844004998e-05, "loss": 3.894, "step": 259072 }, { "epoch": 0.01, "learning_rate": 4.574996249253946e-05, "loss": 3.881, "step": 259584 }, { "epoch": 0.01, "learning_rate": 4.574157654502894e-05, "loss": 3.872, "step": 260096 }, { "epoch": 0.01, "learning_rate": 4.573319059751842e-05, "loss": 3.8979, "step": 260608 }, { "epoch": 0.01, "learning_rate": 4.57248046500079e-05, "loss": 3.872, "step": 261120 }, { "epoch": 0.01, "learning_rate": 4.5716435081301106e-05, "loss": 3.8805, "step": 261632 }, { "epoch": 0.01, "learning_rate": 4.5708049133790586e-05, "loss": 3.8883, "step": 262144 }, { "epoch": 0.01, "learning_rate": 4.5699663186280066e-05, "loss": 3.8911, "step": 262656 }, { "epoch": 0.01, "learning_rate": 4.5691277238769546e-05, "loss": 3.8715, "step": 263168 }, { "epoch": 0.01, "learning_rate": 4.5682907670062755e-05, "loss": 3.8768, "step": 263680 }, { "epoch": 0.01, "learning_rate": 4.5674521722552235e-05, "loss": 3.863, "step": 264192 }, { "epoch": 0.01, "learning_rate": 4.5666135775041715e-05, "loss": 3.8889, "step": 264704 }, { "epoch": 0.01, "learning_rate": 4.56577498275312e-05, "loss": 3.8861, "step": 265216 }, { "epoch": 0.01, "learning_rate": 4.564936388002068e-05, "loss": 3.8827, "step": 265728 }, { "epoch": 0.01, "learning_rate": 4.564099431131389e-05, "loss": 3.8844, "step": 266240 }, { "epoch": 0.01, "learning_rate": 4.563260836380337e-05, "loss": 3.8873, "step": 266752 }, { "epoch": 0.01, "learning_rate": 4.562422241629285e-05, "loss": 3.8938, "step": 267264 }, { "epoch": 0.01, "learning_rate": 4.561583646878233e-05, "loss": 3.8702, "step": 267776 }, { "epoch": 0.01, "learning_rate": 4.560746690007554e-05, "loss": 3.8835, "step": 268288 }, { "epoch": 0.01, "learning_rate": 4.559908095256502e-05, "loss": 3.8881, "step": 268800 }, { "epoch": 0.01, "learning_rate": 4.55906950050545e-05, "loss": 3.866, "step": 269312 }, { "epoch": 0.01, "learning_rate": 4.558230905754398e-05, "loss": 3.8838, "step": 269824 }, { "epoch": 0.01, "learning_rate": 4.557392311003346e-05, "loss": 3.8743, "step": 270336 }, { "epoch": 0.01, "learning_rate": 4.556555354132667e-05, "loss": 3.8886, "step": 270848 }, { "epoch": 0.01, "learning_rate": 4.5557167593816156e-05, "loss": 3.8823, "step": 271360 }, { "epoch": 0.01, "learning_rate": 4.5548781646305635e-05, "loss": 3.8642, "step": 271872 }, { "epoch": 0.01, "learning_rate": 4.5540395698795115e-05, "loss": 3.8761, "step": 272384 }, { "epoch": 0.01, "learning_rate": 4.5532026130088325e-05, "loss": 3.8729, "step": 272896 }, { "epoch": 0.01, "learning_rate": 4.5523640182577804e-05, "loss": 3.8846, "step": 273408 }, { "epoch": 0.01, "learning_rate": 4.5515254235067284e-05, "loss": 3.8731, "step": 273920 }, { "epoch": 0.01, "learning_rate": 4.5506868287556764e-05, "loss": 3.8711, "step": 274432 }, { "epoch": 0.02, "learning_rate": 4.5498498718849973e-05, "loss": 3.8738, "step": 274944 }, { "epoch": 0.02, "learning_rate": 4.5490112771339453e-05, "loss": 3.8725, "step": 275456 }, { "epoch": 0.02, "learning_rate": 4.5481726823828933e-05, "loss": 3.8668, "step": 275968 }, { "epoch": 0.02, "learning_rate": 4.547334087631841e-05, "loss": 3.8568, "step": 276480 }, { "epoch": 0.02, "learning_rate": 4.546495492880789e-05, "loss": 3.8702, "step": 276992 }, { "epoch": 0.02, "learning_rate": 4.545658536010111e-05, "loss": 3.8796, "step": 277504 }, { "epoch": 0.02, "learning_rate": 4.544819941259059e-05, "loss": 3.8789, "step": 278016 }, { "epoch": 0.02, "learning_rate": 4.543981346508007e-05, "loss": 3.8565, "step": 278528 }, { "epoch": 0.02, "learning_rate": 4.543142751756955e-05, "loss": 3.8679, "step": 279040 }, { "epoch": 0.02, "learning_rate": 4.542305794886276e-05, "loss": 3.8675, "step": 279552 }, { "epoch": 0.02, "learning_rate": 4.541467200135224e-05, "loss": 3.88, "step": 280064 }, { "epoch": 0.02, "learning_rate": 4.540628605384172e-05, "loss": 3.8702, "step": 280576 }, { "epoch": 0.02, "learning_rate": 4.53979001063312e-05, "loss": 3.8701, "step": 281088 }, { "epoch": 0.02, "learning_rate": 4.538951415882068e-05, "loss": 3.8609, "step": 281600 }, { "epoch": 0.02, "learning_rate": 4.538114459011389e-05, "loss": 3.8759, "step": 282112 }, { "epoch": 0.02, "learning_rate": 4.537275864260337e-05, "loss": 3.852, "step": 282624 }, { "epoch": 0.02, "learning_rate": 4.536437269509285e-05, "loss": 3.8675, "step": 283136 }, { "epoch": 0.02, "learning_rate": 4.535600312638606e-05, "loss": 3.8639, "step": 283648 }, { "epoch": 0.02, "learning_rate": 4.534761717887554e-05, "loss": 3.866, "step": 284160 }, { "epoch": 0.02, "learning_rate": 4.533923123136502e-05, "loss": 3.8567, "step": 284672 }, { "epoch": 0.02, "learning_rate": 4.53308452838545e-05, "loss": 3.8699, "step": 285184 }, { "epoch": 0.02, "learning_rate": 4.5322459336343976e-05, "loss": 3.8573, "step": 285696 }, { "epoch": 0.02, "learning_rate": 4.5314073388833456e-05, "loss": 3.8634, "step": 286208 }, { "epoch": 0.02, "learning_rate": 4.5305687441322936e-05, "loss": 3.8637, "step": 286720 }, { "epoch": 0.02, "learning_rate": 4.5297301493812416e-05, "loss": 3.8639, "step": 287232 }, { "epoch": 0.02, "learning_rate": 4.5288931925105625e-05, "loss": 3.8696, "step": 287744 }, { "epoch": 0.02, "learning_rate": 4.5280545977595105e-05, "loss": 3.8701, "step": 288256 }, { "epoch": 0.02, "learning_rate": 4.5272160030084585e-05, "loss": 3.8672, "step": 288768 }, { "epoch": 0.02, "learning_rate": 4.5263774082574065e-05, "loss": 3.869, "step": 289280 }, { "epoch": 0.02, "learning_rate": 4.525540451386728e-05, "loss": 3.8641, "step": 289792 }, { "epoch": 0.02, "learning_rate": 4.524701856635676e-05, "loss": 3.8573, "step": 290304 }, { "epoch": 0.02, "learning_rate": 4.523863261884624e-05, "loss": 3.8545, "step": 290816 }, { "epoch": 0.02, "learning_rate": 4.523024667133572e-05, "loss": 3.8572, "step": 291328 }, { "epoch": 0.02, "learning_rate": 4.52218607238252e-05, "loss": 3.8604, "step": 291840 }, { "epoch": 0.02, "learning_rate": 4.521349115511841e-05, "loss": 3.8641, "step": 292352 }, { "epoch": 0.02, "learning_rate": 4.520510520760789e-05, "loss": 3.857, "step": 292864 }, { "epoch": 0.02, "learning_rate": 4.519671926009737e-05, "loss": 3.8643, "step": 293376 }, { "epoch": 0.02, "learning_rate": 4.518833331258685e-05, "loss": 3.8561, "step": 293888 }, { "epoch": 0.02, "learning_rate": 4.517996374388006e-05, "loss": 3.8575, "step": 294400 }, { "epoch": 0.02, "learning_rate": 4.517157779636954e-05, "loss": 3.8556, "step": 294912 }, { "epoch": 0.02, "learning_rate": 4.516319184885902e-05, "loss": 3.8692, "step": 295424 }, { "epoch": 0.02, "learning_rate": 4.51548059013485e-05, "loss": 3.8543, "step": 295936 }, { "epoch": 0.02, "learning_rate": 4.5146419953837985e-05, "loss": 3.847, "step": 296448 }, { "epoch": 0.02, "learning_rate": 4.5138050385131194e-05, "loss": 3.8415, "step": 296960 }, { "epoch": 0.02, "learning_rate": 4.5129664437620674e-05, "loss": 3.8623, "step": 297472 }, { "epoch": 0.02, "learning_rate": 4.5121278490110154e-05, "loss": 3.864, "step": 297984 }, { "epoch": 0.02, "learning_rate": 4.5112892542599634e-05, "loss": 3.8663, "step": 298496 }, { "epoch": 0.02, "learning_rate": 4.510452297389284e-05, "loss": 3.8554, "step": 299008 }, { "epoch": 0.02, "learning_rate": 4.509613702638232e-05, "loss": 3.8657, "step": 299520 }, { "epoch": 0.02, "learning_rate": 4.50877510788718e-05, "loss": 3.8581, "step": 300032 }, { "epoch": 0.02, "learning_rate": 4.507936513136128e-05, "loss": 3.8592, "step": 300544 }, { "epoch": 0.02, "learning_rate": 4.507097918385076e-05, "loss": 3.8529, "step": 301056 }, { "epoch": 0.02, "learning_rate": 4.506260961514397e-05, "loss": 3.8554, "step": 301568 }, { "epoch": 0.02, "learning_rate": 4.505422366763345e-05, "loss": 3.8581, "step": 302080 }, { "epoch": 0.02, "learning_rate": 4.504583772012293e-05, "loss": 3.8431, "step": 302592 }, { "epoch": 0.02, "learning_rate": 4.503745177261242e-05, "loss": 3.8655, "step": 303104 }, { "epoch": 0.02, "learning_rate": 4.502908220390563e-05, "loss": 3.8586, "step": 303616 }, { "epoch": 0.02, "learning_rate": 4.502069625639511e-05, "loss": 3.8515, "step": 304128 }, { "epoch": 0.02, "learning_rate": 4.501231030888459e-05, "loss": 3.8521, "step": 304640 }, { "epoch": 0.02, "learning_rate": 4.500392436137407e-05, "loss": 3.8489, "step": 305152 }, { "epoch": 0.03, "eval_loss": 3.929913282394409, "eval_runtime": 303.7543, "eval_samples_per_second": 1256.249, "eval_steps_per_second": 39.259, "step": 305280 }, { "epoch": 1.0, "learning_rate": 4.499553841386355e-05, "loss": 3.8502, "step": 305664 }, { "epoch": 1.0, "learning_rate": 4.498716884515676e-05, "loss": 3.8476, "step": 306176 }, { "epoch": 1.0, "learning_rate": 4.497878289764624e-05, "loss": 3.8522, "step": 306688 }, { "epoch": 1.0, "learning_rate": 4.497039695013572e-05, "loss": 3.8494, "step": 307200 }, { "epoch": 1.0, "learning_rate": 4.4962027381428926e-05, "loss": 3.8617, "step": 307712 }, { "epoch": 1.0, "learning_rate": 4.4953641433918406e-05, "loss": 3.8474, "step": 308224 }, { "epoch": 1.0, "learning_rate": 4.4945255486407886e-05, "loss": 3.8369, "step": 308736 }, { "epoch": 1.0, "learning_rate": 4.493686953889737e-05, "loss": 3.837, "step": 309248 }, { "epoch": 1.0, "learning_rate": 4.492848359138685e-05, "loss": 3.8549, "step": 309760 }, { "epoch": 1.0, "learning_rate": 4.492011402268006e-05, "loss": 3.8529, "step": 310272 }, { "epoch": 1.0, "learning_rate": 4.491172807516954e-05, "loss": 3.8388, "step": 310784 }, { "epoch": 1.0, "learning_rate": 4.490334212765902e-05, "loss": 3.8538, "step": 311296 }, { "epoch": 1.0, "learning_rate": 4.489497255895223e-05, "loss": 3.8434, "step": 311808 }, { "epoch": 1.0, "learning_rate": 4.488658661144171e-05, "loss": 3.8469, "step": 312320 }, { "epoch": 1.0, "learning_rate": 4.487820066393119e-05, "loss": 3.8371, "step": 312832 }, { "epoch": 1.0, "learning_rate": 4.486981471642067e-05, "loss": 3.8388, "step": 313344 }, { "epoch": 1.0, "learning_rate": 4.486142876891015e-05, "loss": 3.8364, "step": 313856 }, { "epoch": 1.0, "learning_rate": 4.485304282139963e-05, "loss": 3.8347, "step": 314368 }, { "epoch": 1.0, "learning_rate": 4.484465687388911e-05, "loss": 3.8508, "step": 314880 }, { "epoch": 1.0, "learning_rate": 4.483627092637859e-05, "loss": 3.8503, "step": 315392 }, { "epoch": 1.0, "learning_rate": 4.4827901357671806e-05, "loss": 3.8474, "step": 315904 }, { "epoch": 1.0, "learning_rate": 4.4819515410161286e-05, "loss": 3.8432, "step": 316416 }, { "epoch": 1.0, "learning_rate": 4.481112946265076e-05, "loss": 3.8354, "step": 316928 }, { "epoch": 1.0, "learning_rate": 4.480274351514024e-05, "loss": 3.8453, "step": 317440 }, { "epoch": 1.0, "learning_rate": 4.4794373946433455e-05, "loss": 3.8348, "step": 317952 }, { "epoch": 1.0, "learning_rate": 4.4785987998922935e-05, "loss": 3.8364, "step": 318464 }, { "epoch": 1.0, "learning_rate": 4.477760205141241e-05, "loss": 3.8296, "step": 318976 }, { "epoch": 1.0, "learning_rate": 4.476921610390189e-05, "loss": 3.8407, "step": 319488 }, { "epoch": 1.0, "learning_rate": 4.4760846535195104e-05, "loss": 3.8284, "step": 320000 }, { "epoch": 1.0, "learning_rate": 4.475246058768458e-05, "loss": 3.8253, "step": 320512 }, { "epoch": 1.01, "learning_rate": 4.4744074640174064e-05, "loss": 3.8424, "step": 321024 }, { "epoch": 1.01, "learning_rate": 4.4735688692663544e-05, "loss": 3.8335, "step": 321536 }, { "epoch": 1.01, "learning_rate": 4.4727302745153024e-05, "loss": 3.8439, "step": 322048 }, { "epoch": 1.01, "learning_rate": 4.471893317644623e-05, "loss": 3.8429, "step": 322560 }, { "epoch": 1.01, "learning_rate": 4.471054722893571e-05, "loss": 3.8313, "step": 323072 }, { "epoch": 1.01, "learning_rate": 4.470216128142519e-05, "loss": 3.8432, "step": 323584 }, { "epoch": 1.01, "learning_rate": 4.469377533391467e-05, "loss": 3.8348, "step": 324096 }, { "epoch": 1.01, "learning_rate": 4.468540576520788e-05, "loss": 3.8247, "step": 324608 }, { "epoch": 1.01, "learning_rate": 4.467701981769736e-05, "loss": 3.8178, "step": 325120 }, { "epoch": 1.01, "learning_rate": 4.466863387018684e-05, "loss": 3.8252, "step": 325632 }, { "epoch": 1.01, "learning_rate": 4.466024792267632e-05, "loss": 3.8265, "step": 326144 }, { "epoch": 1.01, "learning_rate": 4.465187835396953e-05, "loss": 3.8403, "step": 326656 }, { "epoch": 1.01, "learning_rate": 4.464349240645902e-05, "loss": 3.8289, "step": 327168 }, { "epoch": 1.01, "learning_rate": 4.46351064589485e-05, "loss": 3.8271, "step": 327680 }, { "epoch": 1.01, "learning_rate": 4.462672051143798e-05, "loss": 3.8367, "step": 328192 }, { "epoch": 1.01, "learning_rate": 4.4618350942731186e-05, "loss": 3.8302, "step": 328704 }, { "epoch": 1.01, "learning_rate": 4.4609964995220666e-05, "loss": 3.8352, "step": 329216 }, { "epoch": 1.01, "learning_rate": 4.4601579047710146e-05, "loss": 3.82, "step": 329728 }, { "epoch": 1.01, "learning_rate": 4.4593193100199626e-05, "loss": 3.807, "step": 330240 }, { "epoch": 1.01, "learning_rate": 4.4584823531492835e-05, "loss": 3.8394, "step": 330752 }, { "epoch": 1.01, "learning_rate": 4.4576437583982315e-05, "loss": 3.836, "step": 331264 }, { "epoch": 1.01, "learning_rate": 4.4568051636471795e-05, "loss": 3.8295, "step": 331776 }, { "epoch": 1.01, "learning_rate": 4.4559665688961275e-05, "loss": 3.8229, "step": 332288 }, { "epoch": 1.01, "learning_rate": 4.4551296120254484e-05, "loss": 3.8199, "step": 332800 }, { "epoch": 1.01, "learning_rate": 4.454291017274397e-05, "loss": 3.815, "step": 333312 }, { "epoch": 1.01, "learning_rate": 4.453452422523345e-05, "loss": 3.8246, "step": 333824 }, { "epoch": 1.01, "learning_rate": 4.452613827772293e-05, "loss": 3.8176, "step": 334336 }, { "epoch": 1.01, "learning_rate": 4.451776870901614e-05, "loss": 3.8202, "step": 334848 }, { "epoch": 1.01, "learning_rate": 4.450938276150562e-05, "loss": 3.8297, "step": 335360 }, { "epoch": 1.01, "learning_rate": 4.45009968139951e-05, "loss": 3.8217, "step": 335872 }, { "epoch": 1.01, "learning_rate": 4.449261086648458e-05, "loss": 3.81, "step": 336384 }, { "epoch": 1.01, "learning_rate": 4.448424129777779e-05, "loss": 3.8346, "step": 336896 }, { "epoch": 1.01, "learning_rate": 4.447585535026727e-05, "loss": 3.8093, "step": 337408 }, { "epoch": 1.01, "learning_rate": 4.446746940275675e-05, "loss": 3.8114, "step": 337920 }, { "epoch": 1.01, "learning_rate": 4.445908345524623e-05, "loss": 3.8272, "step": 338432 }, { "epoch": 1.01, "learning_rate": 4.445071388653944e-05, "loss": 3.83, "step": 338944 }, { "epoch": 1.01, "learning_rate": 4.4442327939028925e-05, "loss": 3.8069, "step": 339456 }, { "epoch": 1.01, "learning_rate": 4.4433941991518405e-05, "loss": 3.8149, "step": 339968 }, { "epoch": 1.01, "learning_rate": 4.4425556044007885e-05, "loss": 3.8016, "step": 340480 }, { "epoch": 1.01, "learning_rate": 4.4417186475301094e-05, "loss": 3.8235, "step": 340992 }, { "epoch": 1.01, "learning_rate": 4.4408800527790574e-05, "loss": 3.8268, "step": 341504 }, { "epoch": 1.01, "learning_rate": 4.4400414580280054e-05, "loss": 3.8152, "step": 342016 }, { "epoch": 1.01, "learning_rate": 4.4392028632769534e-05, "loss": 3.8224, "step": 342528 }, { "epoch": 1.01, "learning_rate": 4.438365906406274e-05, "loss": 3.8243, "step": 343040 }, { "epoch": 1.01, "learning_rate": 4.437527311655222e-05, "loss": 3.8372, "step": 343552 }, { "epoch": 1.01, "learning_rate": 4.43668871690417e-05, "loss": 3.8086, "step": 344064 }, { "epoch": 1.01, "learning_rate": 4.435850122153118e-05, "loss": 3.8229, "step": 344576 }, { "epoch": 1.01, "learning_rate": 4.435013165282439e-05, "loss": 3.8257, "step": 345088 }, { "epoch": 1.01, "learning_rate": 4.434174570531388e-05, "loss": 3.8046, "step": 345600 }, { "epoch": 1.01, "learning_rate": 4.433335975780336e-05, "loss": 3.8239, "step": 346112 }, { "epoch": 1.01, "learning_rate": 4.432497381029284e-05, "loss": 3.8152, "step": 346624 }, { "epoch": 1.01, "learning_rate": 4.431660424158605e-05, "loss": 3.8258, "step": 347136 }, { "epoch": 1.01, "learning_rate": 4.430821829407553e-05, "loss": 3.8217, "step": 347648 }, { "epoch": 1.01, "learning_rate": 4.429983234656501e-05, "loss": 3.8052, "step": 348160 }, { "epoch": 1.01, "learning_rate": 4.429144639905449e-05, "loss": 3.8101, "step": 348672 }, { "epoch": 1.01, "learning_rate": 4.4283076830347696e-05, "loss": 3.8109, "step": 349184 }, { "epoch": 1.01, "learning_rate": 4.4274690882837176e-05, "loss": 3.8278, "step": 349696 }, { "epoch": 1.01, "learning_rate": 4.4266304935326656e-05, "loss": 3.812, "step": 350208 }, { "epoch": 1.01, "learning_rate": 4.4257918987816136e-05, "loss": 3.8097, "step": 350720 }, { "epoch": 1.02, "learning_rate": 4.4249549419109345e-05, "loss": 3.8116, "step": 351232 }, { "epoch": 1.02, "learning_rate": 4.424116347159883e-05, "loss": 3.8159, "step": 351744 }, { "epoch": 1.02, "learning_rate": 4.423277752408831e-05, "loss": 3.8077, "step": 352256 }, { "epoch": 1.02, "learning_rate": 4.422439157657779e-05, "loss": 3.7953, "step": 352768 }, { "epoch": 1.02, "learning_rate": 4.421600562906727e-05, "loss": 3.8121, "step": 353280 }, { "epoch": 1.02, "learning_rate": 4.420763606036048e-05, "loss": 3.8187, "step": 353792 }, { "epoch": 1.02, "learning_rate": 4.419925011284996e-05, "loss": 3.8185, "step": 354304 }, { "epoch": 1.02, "learning_rate": 4.419086416533944e-05, "loss": 3.7958, "step": 354816 }, { "epoch": 1.02, "learning_rate": 4.418247821782892e-05, "loss": 3.8078, "step": 355328 }, { "epoch": 1.02, "learning_rate": 4.417410864912213e-05, "loss": 3.8077, "step": 355840 }, { "epoch": 1.02, "learning_rate": 4.416572270161161e-05, "loss": 3.817, "step": 356352 }, { "epoch": 1.02, "learning_rate": 4.415733675410109e-05, "loss": 3.8152, "step": 356864 }, { "epoch": 1.02, "learning_rate": 4.414895080659057e-05, "loss": 3.8104, "step": 357376 }, { "epoch": 1.02, "learning_rate": 4.414058123788378e-05, "loss": 3.804, "step": 357888 }, { "epoch": 1.02, "learning_rate": 4.4132195290373266e-05, "loss": 3.8152, "step": 358400 }, { "epoch": 1.02, "learning_rate": 4.4123809342862746e-05, "loss": 3.7943, "step": 358912 }, { "epoch": 1.02, "learning_rate": 4.4115423395352226e-05, "loss": 3.8096, "step": 359424 }, { "epoch": 1.02, "learning_rate": 4.4107053826645435e-05, "loss": 3.8031, "step": 359936 }, { "epoch": 1.02, "learning_rate": 4.4098667879134915e-05, "loss": 3.8114, "step": 360448 }, { "epoch": 1.02, "learning_rate": 4.4090281931624395e-05, "loss": 3.7944, "step": 360960 }, { "epoch": 1.02, "learning_rate": 4.4081895984113875e-05, "loss": 3.8125, "step": 361472 }, { "epoch": 1.02, "learning_rate": 4.4073526415407084e-05, "loss": 3.8016, "step": 361984 }, { "epoch": 1.02, "learning_rate": 4.4065140467896564e-05, "loss": 3.8057, "step": 362496 }, { "epoch": 1.02, "learning_rate": 4.4056754520386044e-05, "loss": 3.8053, "step": 363008 }, { "epoch": 1.02, "learning_rate": 4.4048368572875524e-05, "loss": 3.8053, "step": 363520 }, { "epoch": 1.02, "learning_rate": 4.403999900416873e-05, "loss": 3.811, "step": 364032 }, { "epoch": 1.02, "learning_rate": 4.403161305665822e-05, "loss": 3.8154, "step": 364544 }, { "epoch": 1.02, "learning_rate": 4.40232271091477e-05, "loss": 3.8115, "step": 365056 }, { "epoch": 1.02, "learning_rate": 4.401484116163718e-05, "loss": 3.8104, "step": 365568 }, { "epoch": 1.02, "learning_rate": 4.400647159293039e-05, "loss": 3.8074, "step": 366080 }, { "epoch": 1.02, "learning_rate": 4.399808564541987e-05, "loss": 3.802, "step": 366592 }, { "epoch": 1.02, "learning_rate": 4.398969969790935e-05, "loss": 3.7933, "step": 367104 }, { "epoch": 1.02, "learning_rate": 4.398131375039883e-05, "loss": 3.8071, "step": 367616 }, { "epoch": 1.02, "learning_rate": 4.397294418169204e-05, "loss": 3.7999, "step": 368128 }, { "epoch": 1.02, "learning_rate": 4.396455823418152e-05, "loss": 3.8062, "step": 368640 }, { "epoch": 1.02, "learning_rate": 4.3956172286671e-05, "loss": 3.8017, "step": 369152 }, { "epoch": 1.02, "learning_rate": 4.394778633916048e-05, "loss": 3.8063, "step": 369664 }, { "epoch": 1.02, "learning_rate": 4.3939416770453686e-05, "loss": 3.8017, "step": 370176 }, { "epoch": 1.02, "learning_rate": 4.393103082294317e-05, "loss": 3.8013, "step": 370688 }, { "epoch": 1.02, "learning_rate": 4.392264487543265e-05, "loss": 3.7985, "step": 371200 }, { "epoch": 1.02, "learning_rate": 4.391425892792213e-05, "loss": 3.8112, "step": 371712 }, { "epoch": 1.02, "learning_rate": 4.390588935921534e-05, "loss": 3.8017, "step": 372224 }, { "epoch": 1.02, "learning_rate": 4.389750341170482e-05, "loss": 3.7933, "step": 372736 }, { "epoch": 1.02, "learning_rate": 4.38891174641943e-05, "loss": 3.7833, "step": 373248 }, { "epoch": 1.02, "learning_rate": 4.388073151668378e-05, "loss": 3.8063, "step": 373760 }, { "epoch": 1.02, "learning_rate": 4.387236194797699e-05, "loss": 3.8064, "step": 374272 }, { "epoch": 1.02, "learning_rate": 4.386397600046647e-05, "loss": 3.8082, "step": 374784 }, { "epoch": 1.02, "learning_rate": 4.385559005295595e-05, "loss": 3.8015, "step": 375296 }, { "epoch": 1.02, "learning_rate": 4.3847204105445424e-05, "loss": 3.8084, "step": 375808 }, { "epoch": 1.02, "learning_rate": 4.383883453673864e-05, "loss": 3.8016, "step": 376320 }, { "epoch": 1.02, "learning_rate": 4.383044858922813e-05, "loss": 3.8076, "step": 376832 }, { "epoch": 1.02, "learning_rate": 4.382206264171761e-05, "loss": 3.7973, "step": 377344 }, { "epoch": 1.02, "learning_rate": 4.381367669420708e-05, "loss": 3.8002, "step": 377856 }, { "epoch": 1.02, "learning_rate": 4.3805307125500296e-05, "loss": 3.7995, "step": 378368 }, { "epoch": 1.02, "learning_rate": 4.3796921177989776e-05, "loss": 3.7933, "step": 378880 }, { "epoch": 1.02, "learning_rate": 4.3788535230479256e-05, "loss": 3.8081, "step": 379392 }, { "epoch": 1.02, "learning_rate": 4.378014928296873e-05, "loss": 3.8047, "step": 379904 }, { "epoch": 1.02, "learning_rate": 4.3771779714261945e-05, "loss": 3.7992, "step": 380416 }, { "epoch": 1.02, "learning_rate": 4.3763393766751425e-05, "loss": 3.7965, "step": 380928 }, { "epoch": 1.02, "learning_rate": 4.37550078192409e-05, "loss": 3.7989, "step": 381440 }, { "epoch": 1.03, "eval_loss": 3.903867244720459, "eval_runtime": 305.6576, "eval_samples_per_second": 1248.426, "eval_steps_per_second": 39.014, "step": 381600 }, { "epoch": 0.0, "learning_rate": 4.374662187173038e-05, "loss": 3.795, "step": 381952 }, { "epoch": 0.0, "learning_rate": 4.3738235924219865e-05, "loss": 3.7905, "step": 382464 }, { "epoch": 0.0, "learning_rate": 4.3729849976709345e-05, "loss": 3.7989, "step": 382976 }, { "epoch": 0.0, "learning_rate": 4.3721464029198824e-05, "loss": 3.7929, "step": 383488 }, { "epoch": 0.0, "learning_rate": 4.3713078081688304e-05, "loss": 3.8068, "step": 384000 }, { "epoch": 0.0, "learning_rate": 4.3704692134177784e-05, "loss": 3.7937, "step": 384512 }, { "epoch": 0.0, "learning_rate": 4.3696306186667264e-05, "loss": 3.7848, "step": 385024 }, { "epoch": 0.0, "learning_rate": 4.3687920239156744e-05, "loss": 3.7809, "step": 385536 }, { "epoch": 0.0, "learning_rate": 4.3679550670449953e-05, "loss": 3.8005, "step": 386048 }, { "epoch": 0.0, "learning_rate": 4.367116472293943e-05, "loss": 3.7983, "step": 386560 }, { "epoch": 0.0, "learning_rate": 4.366277877542891e-05, "loss": 3.7878, "step": 387072 }, { "epoch": 0.0, "learning_rate": 4.365439282791839e-05, "loss": 3.7971, "step": 387584 }, { "epoch": 0.0, "learning_rate": 4.364605601681907e-05, "loss": 3.7935, "step": 388096 }, { "epoch": 0.0, "learning_rate": 4.363767006930855e-05, "loss": 3.7913, "step": 388608 }, { "epoch": 0.0, "learning_rate": 4.362928412179803e-05, "loss": 3.7855, "step": 389120 }, { "epoch": 0.0, "learning_rate": 4.362089817428751e-05, "loss": 3.7814, "step": 389632 }, { "epoch": 0.0, "learning_rate": 4.361251222677699e-05, "loss": 3.7861, "step": 390144 }, { "epoch": 0.0, "learning_rate": 4.360412627926647e-05, "loss": 3.7799, "step": 390656 }, { "epoch": 0.0, "learning_rate": 4.359574033175595e-05, "loss": 3.7984, "step": 391168 }, { "epoch": 0.0, "learning_rate": 4.358735438424543e-05, "loss": 3.7999, "step": 391680 }, { "epoch": 0.0, "learning_rate": 4.357896843673491e-05, "loss": 3.7974, "step": 392192 }, { "epoch": 0.0, "learning_rate": 4.357058248922439e-05, "loss": 3.7889, "step": 392704 }, { "epoch": 0.0, "learning_rate": 4.356219654171387e-05, "loss": 3.7858, "step": 393216 }, { "epoch": 0.0, "learning_rate": 4.355381059420335e-05, "loss": 3.7901, "step": 393728 }, { "epoch": 0.0, "learning_rate": 4.3545441025496556e-05, "loss": 3.7816, "step": 394240 }, { "epoch": 0.0, "learning_rate": 4.3537055077986036e-05, "loss": 3.7856, "step": 394752 }, { "epoch": 0.0, "learning_rate": 4.3528669130475516e-05, "loss": 3.7736, "step": 395264 }, { "epoch": 0.0, "learning_rate": 4.3520283182964996e-05, "loss": 3.7915, "step": 395776 }, { "epoch": 0.0, "learning_rate": 4.351191361425821e-05, "loss": 3.7803, "step": 396288 }, { "epoch": 0.0, "learning_rate": 4.350352766674769e-05, "loss": 3.7739, "step": 396800 }, { "epoch": 0.01, "learning_rate": 4.349514171923717e-05, "loss": 3.7864, "step": 397312 }, { "epoch": 0.01, "learning_rate": 4.348675577172665e-05, "loss": 3.7888, "step": 397824 }, { "epoch": 0.01, "learning_rate": 4.347838620301986e-05, "loss": 3.7939, "step": 398336 }, { "epoch": 0.01, "learning_rate": 4.347000025550934e-05, "loss": 3.7883, "step": 398848 }, { "epoch": 0.01, "learning_rate": 4.346161430799882e-05, "loss": 3.7797, "step": 399360 }, { "epoch": 0.01, "learning_rate": 4.34532283604883e-05, "loss": 3.7911, "step": 399872 }, { "epoch": 0.01, "learning_rate": 4.344485879178151e-05, "loss": 3.7876, "step": 400384 }, { "epoch": 0.01, "learning_rate": 4.343647284427099e-05, "loss": 3.7707, "step": 400896 }, { "epoch": 0.01, "learning_rate": 4.342808689676047e-05, "loss": 3.7707, "step": 401408 }, { "epoch": 0.01, "learning_rate": 4.341970094924995e-05, "loss": 3.7719, "step": 401920 }, { "epoch": 0.01, "learning_rate": 4.3411331380543165e-05, "loss": 3.7784, "step": 402432 }, { "epoch": 0.01, "learning_rate": 4.3402945433032645e-05, "loss": 3.7884, "step": 402944 }, { "epoch": 0.01, "learning_rate": 4.3394559485522125e-05, "loss": 3.781, "step": 403456 }, { "epoch": 0.01, "learning_rate": 4.3386173538011605e-05, "loss": 3.7745, "step": 403968 }, { "epoch": 0.01, "learning_rate": 4.3377803969304814e-05, "loss": 3.7858, "step": 404480 }, { "epoch": 0.01, "learning_rate": 4.3369418021794294e-05, "loss": 3.7772, "step": 404992 }, { "epoch": 0.01, "learning_rate": 4.3361032074283774e-05, "loss": 3.7896, "step": 405504 }, { "epoch": 0.01, "learning_rate": 4.3352646126773254e-05, "loss": 3.7697, "step": 406016 }, { "epoch": 0.01, "learning_rate": 4.334427655806646e-05, "loss": 3.7544, "step": 406528 }, { "epoch": 0.01, "learning_rate": 4.333589061055594e-05, "loss": 3.7915, "step": 407040 }, { "epoch": 0.01, "learning_rate": 4.332750466304542e-05, "loss": 3.7825, "step": 407552 }, { "epoch": 0.01, "learning_rate": 4.33191187155349e-05, "loss": 3.7818, "step": 408064 }, { "epoch": 0.01, "learning_rate": 4.331074914682812e-05, "loss": 3.7765, "step": 408576 }, { "epoch": 0.01, "learning_rate": 4.33023631993176e-05, "loss": 3.773, "step": 409088 }, { "epoch": 0.01, "learning_rate": 4.329397725180708e-05, "loss": 3.7643, "step": 409600 }, { "epoch": 0.01, "learning_rate": 4.328559130429656e-05, "loss": 3.7751, "step": 410112 }, { "epoch": 0.01, "learning_rate": 4.327722173558977e-05, "loss": 3.7675, "step": 410624 }, { "epoch": 0.01, "learning_rate": 4.326883578807925e-05, "loss": 3.773, "step": 411136 }, { "epoch": 0.01, "learning_rate": 4.326044984056873e-05, "loss": 3.7794, "step": 411648 }, { "epoch": 0.01, "learning_rate": 4.325208027186194e-05, "loss": 3.772, "step": 412160 }, { "epoch": 0.01, "learning_rate": 4.324369432435142e-05, "loss": 3.7625, "step": 412672 }, { "epoch": 0.01, "learning_rate": 4.32353083768409e-05, "loss": 3.7836, "step": 413184 }, { "epoch": 0.01, "learning_rate": 4.322692242933038e-05, "loss": 3.7625, "step": 413696 }, { "epoch": 0.01, "learning_rate": 4.321855286062359e-05, "loss": 3.763, "step": 414208 }, { "epoch": 0.01, "learning_rate": 4.321016691311307e-05, "loss": 3.7796, "step": 414720 }, { "epoch": 0.01, "learning_rate": 4.320178096560255e-05, "loss": 3.78, "step": 415232 }, { "epoch": 0.01, "learning_rate": 4.319339501809203e-05, "loss": 3.7566, "step": 415744 }, { "epoch": 0.01, "learning_rate": 4.318502544938524e-05, "loss": 3.7678, "step": 416256 }, { "epoch": 0.01, "learning_rate": 4.317663950187472e-05, "loss": 3.7541, "step": 416768 }, { "epoch": 0.01, "learning_rate": 4.31682535543642e-05, "loss": 3.7735, "step": 417280 }, { "epoch": 0.01, "learning_rate": 4.315986760685368e-05, "loss": 3.7765, "step": 417792 }, { "epoch": 0.01, "learning_rate": 4.315149803814689e-05, "loss": 3.7732, "step": 418304 }, { "epoch": 0.01, "learning_rate": 4.314311209063637e-05, "loss": 3.7721, "step": 418816 }, { "epoch": 0.01, "learning_rate": 4.313472614312585e-05, "loss": 3.7768, "step": 419328 }, { "epoch": 0.01, "learning_rate": 4.312634019561533e-05, "loss": 3.7855, "step": 419840 }, { "epoch": 0.01, "learning_rate": 4.3117970626908546e-05, "loss": 3.7621, "step": 420352 }, { "epoch": 0.01, "learning_rate": 4.3109584679398026e-05, "loss": 3.779, "step": 420864 }, { "epoch": 0.01, "learning_rate": 4.3101198731887506e-05, "loss": 3.7774, "step": 421376 }, { "epoch": 0.01, "learning_rate": 4.309281278437698e-05, "loss": 3.7571, "step": 421888 }, { "epoch": 0.01, "learning_rate": 4.3084443215670195e-05, "loss": 3.7772, "step": 422400 }, { "epoch": 0.01, "learning_rate": 4.3076057268159675e-05, "loss": 3.766, "step": 422912 }, { "epoch": 0.01, "learning_rate": 4.3067671320649155e-05, "loss": 3.7785, "step": 423424 }, { "epoch": 0.01, "learning_rate": 4.305928537313863e-05, "loss": 3.7749, "step": 423936 }, { "epoch": 0.01, "learning_rate": 4.3050915804431844e-05, "loss": 3.7602, "step": 424448 }, { "epoch": 0.01, "learning_rate": 4.3042529856921324e-05, "loss": 3.7586, "step": 424960 }, { "epoch": 0.01, "learning_rate": 4.3034143909410804e-05, "loss": 3.7637, "step": 425472 }, { "epoch": 0.01, "learning_rate": 4.3025757961900284e-05, "loss": 3.7802, "step": 425984 }, { "epoch": 0.01, "learning_rate": 4.30173883931935e-05, "loss": 3.7646, "step": 426496 }, { "epoch": 0.01, "learning_rate": 4.300900244568298e-05, "loss": 3.7648, "step": 427008 }, { "epoch": 0.02, "learning_rate": 4.300061649817245e-05, "loss": 3.7633, "step": 427520 }, { "epoch": 0.02, "learning_rate": 4.299223055066193e-05, "loss": 3.7696, "step": 428032 }, { "epoch": 0.02, "learning_rate": 4.298386098195515e-05, "loss": 3.7612, "step": 428544 }, { "epoch": 0.02, "learning_rate": 4.297547503444463e-05, "loss": 3.7476, "step": 429056 }, { "epoch": 0.02, "learning_rate": 4.29670890869341e-05, "loss": 3.7648, "step": 429568 }, { "epoch": 0.02, "learning_rate": 4.295870313942358e-05, "loss": 3.7717, "step": 430080 }, { "epoch": 0.02, "learning_rate": 4.29503335707168e-05, "loss": 3.7734, "step": 430592 }, { "epoch": 0.02, "learning_rate": 4.294194762320628e-05, "loss": 3.7541, "step": 431104 }, { "epoch": 0.02, "learning_rate": 4.293356167569576e-05, "loss": 3.7574, "step": 431616 }, { "epoch": 0.02, "learning_rate": 4.292517572818524e-05, "loss": 3.7631, "step": 432128 }, { "epoch": 0.02, "learning_rate": 4.2916806159478454e-05, "loss": 3.7671, "step": 432640 }, { "epoch": 0.02, "learning_rate": 4.290842021196793e-05, "loss": 3.7738, "step": 433152 }, { "epoch": 0.02, "learning_rate": 4.290003426445741e-05, "loss": 3.7594, "step": 433664 }, { "epoch": 0.02, "learning_rate": 4.289164831694689e-05, "loss": 3.7623, "step": 434176 }, { "epoch": 0.02, "learning_rate": 4.28832787482401e-05, "loss": 3.7671, "step": 434688 }, { "epoch": 0.02, "learning_rate": 4.2874892800729576e-05, "loss": 3.7505, "step": 435200 }, { "epoch": 0.02, "learning_rate": 4.2866506853219056e-05, "loss": 3.7609, "step": 435712 }, { "epoch": 0.02, "learning_rate": 4.2858120905708536e-05, "loss": 3.755, "step": 436224 }, { "epoch": 0.02, "learning_rate": 4.284975133700175e-05, "loss": 3.7676, "step": 436736 }, { "epoch": 0.02, "learning_rate": 4.2841365389491225e-05, "loss": 3.7502, "step": 437248 }, { "epoch": 0.02, "learning_rate": 4.283297944198071e-05, "loss": 3.7673, "step": 437760 }, { "epoch": 0.02, "learning_rate": 4.282459349447019e-05, "loss": 3.7554, "step": 438272 }, { "epoch": 0.02, "learning_rate": 4.28162239257634e-05, "loss": 3.7612, "step": 438784 }, { "epoch": 0.02, "learning_rate": 4.280783797825288e-05, "loss": 3.7587, "step": 439296 }, { "epoch": 0.02, "learning_rate": 4.279945203074236e-05, "loss": 3.7624, "step": 439808 }, { "epoch": 0.02, "learning_rate": 4.2791082462035576e-05, "loss": 3.7603, "step": 440320 }, { "epoch": 0.02, "learning_rate": 4.278269651452505e-05, "loss": 3.7729, "step": 440832 }, { "epoch": 0.02, "learning_rate": 4.277431056701453e-05, "loss": 3.7653, "step": 441344 }, { "epoch": 0.02, "learning_rate": 4.276592461950401e-05, "loss": 3.7673, "step": 441856 }, { "epoch": 0.02, "learning_rate": 4.275753867199349e-05, "loss": 3.7593, "step": 442368 }, { "epoch": 0.02, "learning_rate": 4.274915272448297e-05, "loss": 3.7621, "step": 442880 }, { "epoch": 0.02, "learning_rate": 4.274076677697245e-05, "loss": 3.7491, "step": 443392 }, { "epoch": 0.02, "learning_rate": 4.2732397208265665e-05, "loss": 3.7567, "step": 443904 }, { "epoch": 0.02, "learning_rate": 4.2724011260755145e-05, "loss": 3.7569, "step": 444416 }, { "epoch": 0.02, "learning_rate": 4.2715625313244625e-05, "loss": 3.7617, "step": 444928 }, { "epoch": 0.02, "learning_rate": 4.2707239365734105e-05, "loss": 3.7614, "step": 445440 }, { "epoch": 0.02, "learning_rate": 4.2698869797027314e-05, "loss": 3.7593, "step": 445952 }, { "epoch": 0.02, "learning_rate": 4.2690483849516794e-05, "loss": 3.7577, "step": 446464 }, { "epoch": 0.02, "learning_rate": 4.2682097902006274e-05, "loss": 3.7591, "step": 446976 }, { "epoch": 0.02, "learning_rate": 4.2673711954495754e-05, "loss": 3.756, "step": 447488 }, { "epoch": 0.02, "learning_rate": 4.266534238578896e-05, "loss": 3.7633, "step": 448000 }, { "epoch": 0.02, "learning_rate": 4.265695643827844e-05, "loss": 3.7568, "step": 448512 }, { "epoch": 0.02, "learning_rate": 4.264857049076792e-05, "loss": 3.7509, "step": 449024 }, { "epoch": 0.02, "learning_rate": 4.26401845432574e-05, "loss": 3.7373, "step": 449536 }, { "epoch": 0.02, "learning_rate": 4.263181497455062e-05, "loss": 3.765, "step": 450048 }, { "epoch": 0.02, "learning_rate": 4.26234290270401e-05, "loss": 3.7602, "step": 450560 }, { "epoch": 0.02, "learning_rate": 4.261504307952958e-05, "loss": 3.7644, "step": 451072 }, { "epoch": 0.02, "learning_rate": 4.260665713201906e-05, "loss": 3.7573, "step": 451584 }, { "epoch": 0.02, "learning_rate": 4.259828756331227e-05, "loss": 3.7621, "step": 452096 }, { "epoch": 0.02, "learning_rate": 4.258990161580175e-05, "loss": 3.7545, "step": 452608 }, { "epoch": 0.02, "learning_rate": 4.258151566829123e-05, "loss": 3.7686, "step": 453120 }, { "epoch": 0.02, "learning_rate": 4.257312972078071e-05, "loss": 3.7497, "step": 453632 }, { "epoch": 0.02, "learning_rate": 4.256476015207392e-05, "loss": 3.756, "step": 454144 }, { "epoch": 0.02, "learning_rate": 4.25563742045634e-05, "loss": 3.756, "step": 454656 }, { "epoch": 0.02, "learning_rate": 4.254798825705288e-05, "loss": 3.7499, "step": 455168 }, { "epoch": 0.02, "learning_rate": 4.253960230954236e-05, "loss": 3.766, "step": 455680 }, { "epoch": 0.02, "learning_rate": 4.253123274083557e-05, "loss": 3.7573, "step": 456192 }, { "epoch": 0.02, "learning_rate": 4.252284679332505e-05, "loss": 3.762, "step": 456704 }, { "epoch": 0.02, "learning_rate": 4.251446084581453e-05, "loss": 3.7486, "step": 457216 }, { "epoch": 0.02, "learning_rate": 4.250607489830401e-05, "loss": 3.7564, "step": 457728 }, { "epoch": 0.03, "eval_loss": 3.8884012699127197, "eval_runtime": 306.1308, "eval_samples_per_second": 1246.497, "eval_steps_per_second": 38.954, "step": 457920 }, { "epoch": 1.0, "learning_rate": 4.249770532959722e-05, "loss": 3.7517, "step": 458240 }, { "epoch": 1.0, "learning_rate": 4.24893193820867e-05, "loss": 3.7488, "step": 458752 }, { "epoch": 1.0, "learning_rate": 4.248093343457618e-05, "loss": 3.7541, "step": 459264 }, { "epoch": 1.0, "learning_rate": 4.247254748706566e-05, "loss": 3.7512, "step": 459776 }, { "epoch": 1.0, "learning_rate": 4.246417791835887e-05, "loss": 3.7645, "step": 460288 }, { "epoch": 1.0, "learning_rate": 4.245579197084835e-05, "loss": 3.7511, "step": 460800 }, { "epoch": 1.0, "learning_rate": 4.244740602333783e-05, "loss": 3.7446, "step": 461312 }, { "epoch": 1.0, "learning_rate": 4.243902007582731e-05, "loss": 3.7368, "step": 461824 }, { "epoch": 1.0, "learning_rate": 4.243065050712052e-05, "loss": 3.7578, "step": 462336 }, { "epoch": 1.0, "learning_rate": 4.2422264559610006e-05, "loss": 3.7543, "step": 462848 }, { "epoch": 1.0, "learning_rate": 4.2413878612099486e-05, "loss": 3.7469, "step": 463360 }, { "epoch": 1.0, "learning_rate": 4.2405492664588966e-05, "loss": 3.7544, "step": 463872 }, { "epoch": 1.0, "learning_rate": 4.2397139474685904e-05, "loss": 3.7511, "step": 464384 }, { "epoch": 1.0, "learning_rate": 4.2388753527175384e-05, "loss": 3.7494, "step": 464896 }, { "epoch": 1.0, "learning_rate": 4.2380367579664864e-05, "loss": 3.7413, "step": 465408 }, { "epoch": 1.0, "learning_rate": 4.2371981632154344e-05, "loss": 3.7411, "step": 465920 }, { "epoch": 1.0, "learning_rate": 4.2363595684643824e-05, "loss": 3.7434, "step": 466432 }, { "epoch": 1.0, "learning_rate": 4.2355209737133304e-05, "loss": 3.7409, "step": 466944 }, { "epoch": 1.0, "learning_rate": 4.2346823789622784e-05, "loss": 3.7521, "step": 467456 }, { "epoch": 1.0, "learning_rate": 4.2338437842112264e-05, "loss": 3.757, "step": 467968 }, { "epoch": 1.0, "learning_rate": 4.2330051894601744e-05, "loss": 3.7547, "step": 468480 }, { "epoch": 1.0, "learning_rate": 4.2321665947091224e-05, "loss": 3.748, "step": 468992 }, { "epoch": 1.0, "learning_rate": 4.2313279999580704e-05, "loss": 3.7442, "step": 469504 }, { "epoch": 1.0, "learning_rate": 4.2304894052070184e-05, "loss": 3.7464, "step": 470016 }, { "epoch": 1.0, "learning_rate": 4.22965244833634e-05, "loss": 3.7434, "step": 470528 }, { "epoch": 1.0, "learning_rate": 4.228813853585288e-05, "loss": 3.7461, "step": 471040 }, { "epoch": 1.0, "learning_rate": 4.227975258834236e-05, "loss": 3.7293, "step": 471552 }, { "epoch": 1.0, "learning_rate": 4.227136664083183e-05, "loss": 3.7522, "step": 472064 }, { "epoch": 1.0, "learning_rate": 4.226299707212505e-05, "loss": 3.741, "step": 472576 }, { "epoch": 1.0, "learning_rate": 4.225461112461453e-05, "loss": 3.7325, "step": 473088 }, { "epoch": 1.01, "learning_rate": 4.2246225177104e-05, "loss": 3.7428, "step": 473600 }, { "epoch": 1.01, "learning_rate": 4.223783922959348e-05, "loss": 3.7511, "step": 474112 }, { "epoch": 1.01, "learning_rate": 4.22294696608867e-05, "loss": 3.7475, "step": 474624 }, { "epoch": 1.01, "learning_rate": 4.222108371337618e-05, "loss": 3.7491, "step": 475136 }, { "epoch": 1.01, "learning_rate": 4.221269776586566e-05, "loss": 3.7386, "step": 475648 }, { "epoch": 1.01, "learning_rate": 4.220431181835514e-05, "loss": 3.7519, "step": 476160 }, { "epoch": 1.01, "learning_rate": 4.2195942249648353e-05, "loss": 3.7441, "step": 476672 }, { "epoch": 1.01, "learning_rate": 4.2187556302137833e-05, "loss": 3.731, "step": 477184 }, { "epoch": 1.01, "learning_rate": 4.217917035462731e-05, "loss": 3.732, "step": 477696 }, { "epoch": 1.01, "learning_rate": 4.217080078592052e-05, "loss": 3.7294, "step": 478208 }, { "epoch": 1.01, "learning_rate": 4.216241483841e-05, "loss": 3.739, "step": 478720 }, { "epoch": 1.01, "learning_rate": 4.2154028890899476e-05, "loss": 3.7488, "step": 479232 }, { "epoch": 1.01, "learning_rate": 4.2145642943388956e-05, "loss": 3.7374, "step": 479744 }, { "epoch": 1.01, "learning_rate": 4.213727337468217e-05, "loss": 3.7364, "step": 480256 }, { "epoch": 1.01, "learning_rate": 4.212888742717165e-05, "loss": 3.7425, "step": 480768 }, { "epoch": 1.01, "learning_rate": 4.212050147966113e-05, "loss": 3.7355, "step": 481280 }, { "epoch": 1.01, "learning_rate": 4.211211553215061e-05, "loss": 3.7487, "step": 481792 }, { "epoch": 1.01, "learning_rate": 4.210374596344383e-05, "loss": 3.7323, "step": 482304 }, { "epoch": 1.01, "learning_rate": 4.209536001593331e-05, "loss": 3.7092, "step": 482816 }, { "epoch": 1.01, "learning_rate": 4.208697406842278e-05, "loss": 3.7513, "step": 483328 }, { "epoch": 1.01, "learning_rate": 4.207858812091226e-05, "loss": 3.7434, "step": 483840 }, { "epoch": 1.01, "learning_rate": 4.2070218552205476e-05, "loss": 3.742, "step": 484352 }, { "epoch": 1.01, "learning_rate": 4.206183260469495e-05, "loss": 3.7349, "step": 484864 }, { "epoch": 1.01, "learning_rate": 4.205344665718443e-05, "loss": 3.7338, "step": 485376 }, { "epoch": 1.01, "learning_rate": 4.204506070967391e-05, "loss": 3.7243, "step": 485888 }, { "epoch": 1.01, "learning_rate": 4.2036691140967125e-05, "loss": 3.7374, "step": 486400 }, { "epoch": 1.01, "learning_rate": 4.2028305193456605e-05, "loss": 3.7304, "step": 486912 }, { "epoch": 1.01, "learning_rate": 4.2019919245946085e-05, "loss": 3.7308, "step": 487424 }, { "epoch": 1.01, "learning_rate": 4.2011533298435565e-05, "loss": 3.7395, "step": 487936 }, { "epoch": 1.01, "learning_rate": 4.200316372972878e-05, "loss": 3.734, "step": 488448 }, { "epoch": 1.01, "learning_rate": 4.1994777782218254e-05, "loss": 3.7215, "step": 488960 }, { "epoch": 1.01, "learning_rate": 4.1986391834707734e-05, "loss": 3.7427, "step": 489472 }, { "epoch": 1.01, "learning_rate": 4.1978005887197214e-05, "loss": 3.7226, "step": 489984 }, { "epoch": 1.01, "learning_rate": 4.196963631849042e-05, "loss": 3.7285, "step": 490496 }, { "epoch": 1.01, "learning_rate": 4.19612503709799e-05, "loss": 3.7395, "step": 491008 }, { "epoch": 1.01, "learning_rate": 4.195286442346938e-05, "loss": 3.7392, "step": 491520 }, { "epoch": 1.01, "learning_rate": 4.194447847595886e-05, "loss": 3.7205, "step": 492032 }, { "epoch": 1.01, "learning_rate": 4.193610890725207e-05, "loss": 3.7258, "step": 492544 }, { "epoch": 1.01, "learning_rate": 4.192772295974156e-05, "loss": 3.7154, "step": 493056 }, { "epoch": 1.01, "learning_rate": 4.191933701223104e-05, "loss": 3.7356, "step": 493568 }, { "epoch": 1.01, "learning_rate": 4.191096744352425e-05, "loss": 3.7365, "step": 494080 }, { "epoch": 1.01, "learning_rate": 4.190258149601373e-05, "loss": 3.7345, "step": 494592 }, { "epoch": 1.01, "learning_rate": 4.189419554850321e-05, "loss": 3.7336, "step": 495104 }, { "epoch": 1.01, "learning_rate": 4.188580960099269e-05, "loss": 3.7348, "step": 495616 }, { "epoch": 1.01, "learning_rate": 4.187742365348217e-05, "loss": 3.7477, "step": 496128 }, { "epoch": 1.01, "learning_rate": 4.186903770597165e-05, "loss": 3.7258, "step": 496640 }, { "epoch": 1.01, "learning_rate": 4.186065175846113e-05, "loss": 3.7368, "step": 497152 }, { "epoch": 1.01, "learning_rate": 4.185226581095061e-05, "loss": 3.7377, "step": 497664 }, { "epoch": 1.01, "learning_rate": 4.1843896242243817e-05, "loss": 3.7202, "step": 498176 }, { "epoch": 1.01, "learning_rate": 4.1835510294733297e-05, "loss": 3.7352, "step": 498688 }, { "epoch": 1.01, "learning_rate": 4.1827124347222776e-05, "loss": 3.7338, "step": 499200 }, { "epoch": 1.01, "learning_rate": 4.1818738399712256e-05, "loss": 3.7332, "step": 499712 }, { "epoch": 1.01, "learning_rate": 4.181036883100547e-05, "loss": 3.7374, "step": 500224 }, { "epoch": 1.01, "learning_rate": 4.180198288349495e-05, "loss": 3.722, "step": 500736 }, { "epoch": 1.01, "learning_rate": 4.179359693598443e-05, "loss": 3.7215, "step": 501248 }, { "epoch": 1.01, "learning_rate": 4.178521098847391e-05, "loss": 3.7263, "step": 501760 }, { "epoch": 1.01, "learning_rate": 4.177684141976712e-05, "loss": 3.7366, "step": 502272 }, { "epoch": 1.01, "learning_rate": 4.17684554722566e-05, "loss": 3.7287, "step": 502784 }, { "epoch": 1.01, "learning_rate": 4.176006952474608e-05, "loss": 3.7247, "step": 503296 }, { "epoch": 1.02, "learning_rate": 4.175168357723556e-05, "loss": 3.7277, "step": 503808 }, { "epoch": 1.02, "learning_rate": 4.174331400852877e-05, "loss": 3.7332, "step": 504320 }, { "epoch": 1.02, "learning_rate": 4.173492806101825e-05, "loss": 3.7233, "step": 504832 }, { "epoch": 1.02, "learning_rate": 4.172654211350773e-05, "loss": 3.7088, "step": 505344 }, { "epoch": 1.02, "learning_rate": 4.171815616599721e-05, "loss": 3.7271, "step": 505856 }, { "epoch": 1.02, "learning_rate": 4.1709786597290426e-05, "loss": 3.7303, "step": 506368 }, { "epoch": 1.02, "learning_rate": 4.1701400649779906e-05, "loss": 3.7356, "step": 506880 }, { "epoch": 1.02, "learning_rate": 4.1693014702269386e-05, "loss": 3.7168, "step": 507392 }, { "epoch": 1.02, "learning_rate": 4.1684628754758866e-05, "loss": 3.7208, "step": 507904 }, { "epoch": 1.02, "learning_rate": 4.1676259186052075e-05, "loss": 3.7255, "step": 508416 }, { "epoch": 1.02, "learning_rate": 4.1667873238541555e-05, "loss": 3.7277, "step": 508928 }, { "epoch": 1.02, "learning_rate": 4.1659487291031035e-05, "loss": 3.7375, "step": 509440 }, { "epoch": 1.02, "learning_rate": 4.1651101343520515e-05, "loss": 3.7234, "step": 509952 }, { "epoch": 1.02, "learning_rate": 4.1642731774813724e-05, "loss": 3.7255, "step": 510464 }, { "epoch": 1.02, "learning_rate": 4.1634345827303204e-05, "loss": 3.7295, "step": 510976 }, { "epoch": 1.02, "learning_rate": 4.1625959879792684e-05, "loss": 3.7127, "step": 511488 }, { "epoch": 1.02, "learning_rate": 4.1617573932282164e-05, "loss": 3.7246, "step": 512000 }, { "epoch": 1.02, "learning_rate": 4.160920436357538e-05, "loss": 3.7147, "step": 512512 }, { "epoch": 1.02, "learning_rate": 4.160081841606486e-05, "loss": 3.7343, "step": 513024 }, { "epoch": 1.02, "learning_rate": 4.159243246855434e-05, "loss": 3.7127, "step": 513536 }, { "epoch": 1.02, "learning_rate": 4.158404652104382e-05, "loss": 3.7285, "step": 514048 }, { "epoch": 1.02, "learning_rate": 4.157567695233703e-05, "loss": 3.7198, "step": 514560 }, { "epoch": 1.02, "learning_rate": 4.156729100482651e-05, "loss": 3.7215, "step": 515072 }, { "epoch": 1.02, "learning_rate": 4.155890505731599e-05, "loss": 3.7226, "step": 515584 }, { "epoch": 1.02, "learning_rate": 4.155051910980547e-05, "loss": 3.7261, "step": 516096 }, { "epoch": 1.02, "learning_rate": 4.154214954109868e-05, "loss": 3.7233, "step": 516608 }, { "epoch": 1.02, "learning_rate": 4.153376359358816e-05, "loss": 3.7338, "step": 517120 }, { "epoch": 1.02, "learning_rate": 4.152537764607764e-05, "loss": 3.7224, "step": 517632 }, { "epoch": 1.02, "learning_rate": 4.151700807737085e-05, "loss": 3.7363, "step": 518144 }, { "epoch": 1.02, "learning_rate": 4.150862212986033e-05, "loss": 3.7227, "step": 518656 }, { "epoch": 1.02, "learning_rate": 4.150023618234981e-05, "loss": 3.7215, "step": 519168 }, { "epoch": 1.02, "learning_rate": 4.149185023483929e-05, "loss": 3.7188, "step": 519680 }, { "epoch": 1.02, "learning_rate": 4.14834806661325e-05, "loss": 3.7182, "step": 520192 }, { "epoch": 1.02, "learning_rate": 4.147509471862198e-05, "loss": 3.7175, "step": 520704 }, { "epoch": 1.02, "learning_rate": 4.146670877111146e-05, "loss": 3.7258, "step": 521216 }, { "epoch": 1.02, "learning_rate": 4.145832282360094e-05, "loss": 3.7207, "step": 521728 }, { "epoch": 1.02, "learning_rate": 4.144995325489415e-05, "loss": 3.7257, "step": 522240 }, { "epoch": 1.02, "learning_rate": 4.144156730738363e-05, "loss": 3.7206, "step": 522752 }, { "epoch": 1.02, "learning_rate": 4.143318135987311e-05, "loss": 3.7234, "step": 523264 }, { "epoch": 1.02, "learning_rate": 4.142479541236259e-05, "loss": 3.7227, "step": 523776 }, { "epoch": 1.02, "learning_rate": 4.141642584365581e-05, "loss": 3.7214, "step": 524288 }, { "epoch": 1.02, "learning_rate": 4.140803989614529e-05, "loss": 3.7176, "step": 524800 }, { "epoch": 1.02, "learning_rate": 4.139965394863477e-05, "loss": 3.7185, "step": 525312 }, { "epoch": 1.02, "learning_rate": 4.139126800112425e-05, "loss": 3.7003, "step": 525824 }, { "epoch": 1.02, "learning_rate": 4.1382898432417456e-05, "loss": 3.7281, "step": 526336 }, { "epoch": 1.02, "learning_rate": 4.1374512484906936e-05, "loss": 3.724, "step": 526848 }, { "epoch": 1.02, "learning_rate": 4.1366126537396416e-05, "loss": 3.7312, "step": 527360 }, { "epoch": 1.02, "learning_rate": 4.1357740589885896e-05, "loss": 3.7169, "step": 527872 }, { "epoch": 1.02, "learning_rate": 4.1349371021179105e-05, "loss": 3.7278, "step": 528384 }, { "epoch": 1.02, "learning_rate": 4.1340985073668585e-05, "loss": 3.7233, "step": 528896 }, { "epoch": 1.02, "learning_rate": 4.1332599126158065e-05, "loss": 3.7323, "step": 529408 }, { "epoch": 1.02, "learning_rate": 4.1324213178647545e-05, "loss": 3.7127, "step": 529920 }, { "epoch": 1.02, "learning_rate": 4.131584360994076e-05, "loss": 3.716, "step": 530432 }, { "epoch": 1.02, "learning_rate": 4.130745766243024e-05, "loss": 3.7222, "step": 530944 }, { "epoch": 1.02, "learning_rate": 4.129907171491972e-05, "loss": 3.7176, "step": 531456 }, { "epoch": 1.02, "learning_rate": 4.12906857674092e-05, "loss": 3.7251, "step": 531968 }, { "epoch": 1.02, "learning_rate": 4.128231619870241e-05, "loss": 3.7233, "step": 532480 }, { "epoch": 1.02, "learning_rate": 4.127393025119189e-05, "loss": 3.7247, "step": 532992 }, { "epoch": 1.02, "learning_rate": 4.126554430368137e-05, "loss": 3.7125, "step": 533504 }, { "epoch": 1.02, "learning_rate": 4.125715835617085e-05, "loss": 3.7234, "step": 534016 }, { "epoch": 1.03, "eval_loss": 3.878814697265625, "eval_runtime": 306.2043, "eval_samples_per_second": 1246.198, "eval_steps_per_second": 38.945, "step": 534240 }, { "epoch": 0.0, "learning_rate": 4.124877240866032e-05, "loss": 3.7192, "step": 534528 }, { "epoch": 0.0, "learning_rate": 4.12403864611498e-05, "loss": 3.7182, "step": 535040 }, { "epoch": 0.0, "learning_rate": 4.123200051363928e-05, "loss": 3.7139, "step": 535552 }, { "epoch": 0.0, "learning_rate": 4.122361456612876e-05, "loss": 3.716, "step": 536064 }, { "epoch": 0.0, "learning_rate": 4.121524499742198e-05, "loss": 3.7274, "step": 536576 }, { "epoch": 0.0, "learning_rate": 4.120685904991146e-05, "loss": 3.7176, "step": 537088 }, { "epoch": 0.0, "learning_rate": 4.119847310240094e-05, "loss": 3.7099, "step": 537600 }, { "epoch": 0.0, "learning_rate": 4.119008715489042e-05, "loss": 3.7064, "step": 538112 }, { "epoch": 0.0, "learning_rate": 4.11817012073799e-05, "loss": 3.7172, "step": 538624 }, { "epoch": 0.0, "learning_rate": 4.117331525986938e-05, "loss": 3.7212, "step": 539136 }, { "epoch": 0.0, "learning_rate": 4.116492931235886e-05, "loss": 3.7085, "step": 539648 }, { "epoch": 0.0, "learning_rate": 4.115654336484834e-05, "loss": 3.7167, "step": 540160 }, { "epoch": 0.0, "learning_rate": 4.1148190174945276e-05, "loss": 3.7215, "step": 540672 }, { "epoch": 0.0, "learning_rate": 4.1139804227434756e-05, "loss": 3.7107, "step": 541184 }, { "epoch": 0.0, "learning_rate": 4.1131418279924236e-05, "loss": 3.7094, "step": 541696 }, { "epoch": 0.0, "learning_rate": 4.1123032332413716e-05, "loss": 3.7061, "step": 542208 }, { "epoch": 0.0, "learning_rate": 4.1114646384903196e-05, "loss": 3.7088, "step": 542720 }, { "epoch": 0.0, "learning_rate": 4.110626043739268e-05, "loss": 3.7055, "step": 543232 }, { "epoch": 0.0, "learning_rate": 4.109787448988216e-05, "loss": 3.7136, "step": 543744 }, { "epoch": 0.0, "learning_rate": 4.108948854237164e-05, "loss": 3.7256, "step": 544256 }, { "epoch": 0.0, "learning_rate": 4.108110259486112e-05, "loss": 3.7208, "step": 544768 }, { "epoch": 0.0, "learning_rate": 4.10727166473506e-05, "loss": 3.7145, "step": 545280 }, { "epoch": 0.0, "learning_rate": 4.106433069984008e-05, "loss": 3.7082, "step": 545792 }, { "epoch": 0.0, "learning_rate": 4.105594475232956e-05, "loss": 3.7096, "step": 546304 }, { "epoch": 0.0, "learning_rate": 4.104757518362277e-05, "loss": 3.709, "step": 546816 }, { "epoch": 0.0, "learning_rate": 4.103918923611225e-05, "loss": 3.7102, "step": 547328 }, { "epoch": 0.0, "learning_rate": 4.103080328860173e-05, "loss": 3.6971, "step": 547840 }, { "epoch": 0.0, "learning_rate": 4.102241734109121e-05, "loss": 3.7181, "step": 548352 }, { "epoch": 0.0, "learning_rate": 4.101404777238442e-05, "loss": 3.7074, "step": 548864 }, { "epoch": 0.0, "learning_rate": 4.10056618248739e-05, "loss": 3.7004, "step": 549376 }, { "epoch": 0.01, "learning_rate": 4.099727587736338e-05, "loss": 3.7023, "step": 549888 }, { "epoch": 0.01, "learning_rate": 4.0988906308656597e-05, "loss": 3.7181, "step": 550400 }, { "epoch": 0.01, "learning_rate": 4.0980520361146076e-05, "loss": 3.7137, "step": 550912 }, { "epoch": 0.01, "learning_rate": 4.0972134413635556e-05, "loss": 3.7148, "step": 551424 }, { "epoch": 0.01, "learning_rate": 4.0963748466125036e-05, "loss": 3.7046, "step": 551936 }, { "epoch": 0.01, "learning_rate": 4.0955362518614516e-05, "loss": 3.7127, "step": 552448 }, { "epoch": 0.01, "learning_rate": 4.094697657110399e-05, "loss": 3.7153, "step": 552960 }, { "epoch": 0.01, "learning_rate": 4.0938607002397205e-05, "loss": 3.696, "step": 553472 }, { "epoch": 0.01, "learning_rate": 4.0930221054886685e-05, "loss": 3.6967, "step": 553984 }, { "epoch": 0.01, "learning_rate": 4.092183510737616e-05, "loss": 3.6946, "step": 554496 }, { "epoch": 0.01, "learning_rate": 4.091344915986564e-05, "loss": 3.7053, "step": 555008 }, { "epoch": 0.01, "learning_rate": 4.090506321235512e-05, "loss": 3.7114, "step": 555520 }, { "epoch": 0.01, "learning_rate": 4.08966772648446e-05, "loss": 3.7081, "step": 556032 }, { "epoch": 0.01, "learning_rate": 4.0888291317334085e-05, "loss": 3.7008, "step": 556544 }, { "epoch": 0.01, "learning_rate": 4.0879905369823565e-05, "loss": 3.7086, "step": 557056 }, { "epoch": 0.01, "learning_rate": 4.0871535801116774e-05, "loss": 3.7026, "step": 557568 }, { "epoch": 0.01, "learning_rate": 4.0863149853606254e-05, "loss": 3.7113, "step": 558080 }, { "epoch": 0.01, "learning_rate": 4.0854763906095734e-05, "loss": 3.704, "step": 558592 }, { "epoch": 0.01, "learning_rate": 4.0846377958585214e-05, "loss": 3.6763, "step": 559104 }, { "epoch": 0.01, "learning_rate": 4.083800838987842e-05, "loss": 3.7138, "step": 559616 }, { "epoch": 0.01, "learning_rate": 4.08296224423679e-05, "loss": 3.7078, "step": 560128 }, { "epoch": 0.01, "learning_rate": 4.082123649485738e-05, "loss": 3.7117, "step": 560640 }, { "epoch": 0.01, "learning_rate": 4.081285054734686e-05, "loss": 3.7015, "step": 561152 }, { "epoch": 0.01, "learning_rate": 4.080448097864007e-05, "loss": 3.6965, "step": 561664 }, { "epoch": 0.01, "learning_rate": 4.079609503112955e-05, "loss": 3.6948, "step": 562176 }, { "epoch": 0.01, "learning_rate": 4.078770908361904e-05, "loss": 3.7029, "step": 562688 }, { "epoch": 0.01, "learning_rate": 4.077932313610852e-05, "loss": 3.7003, "step": 563200 }, { "epoch": 0.01, "learning_rate": 4.077095356740173e-05, "loss": 3.6929, "step": 563712 }, { "epoch": 0.01, "learning_rate": 4.076256761989121e-05, "loss": 3.7048, "step": 564224 }, { "epoch": 0.01, "learning_rate": 4.075418167238069e-05, "loss": 3.7037, "step": 564736 }, { "epoch": 0.01, "learning_rate": 4.074579572487017e-05, "loss": 3.6854, "step": 565248 }, { "epoch": 0.01, "learning_rate": 4.073742615616338e-05, "loss": 3.7091, "step": 565760 }, { "epoch": 0.01, "learning_rate": 4.072904020865286e-05, "loss": 3.6941, "step": 566272 }, { "epoch": 0.01, "learning_rate": 4.072065426114234e-05, "loss": 3.6905, "step": 566784 }, { "epoch": 0.01, "learning_rate": 4.071226831363182e-05, "loss": 3.7052, "step": 567296 }, { "epoch": 0.01, "learning_rate": 4.0703898744925026e-05, "loss": 3.7074, "step": 567808 }, { "epoch": 0.01, "learning_rate": 4.0695512797414506e-05, "loss": 3.6868, "step": 568320 }, { "epoch": 0.01, "learning_rate": 4.068712684990399e-05, "loss": 3.6942, "step": 568832 }, { "epoch": 0.01, "learning_rate": 4.06787572811972e-05, "loss": 3.6816, "step": 569344 }, { "epoch": 0.01, "learning_rate": 4.067037133368668e-05, "loss": 3.7005, "step": 569856 }, { "epoch": 0.01, "learning_rate": 4.066200176497989e-05, "loss": 3.7041, "step": 570368 }, { "epoch": 0.01, "learning_rate": 4.065361581746937e-05, "loss": 3.7027, "step": 570880 }, { "epoch": 0.01, "learning_rate": 4.064522986995885e-05, "loss": 3.6983, "step": 571392 }, { "epoch": 0.01, "learning_rate": 4.063684392244833e-05, "loss": 3.7022, "step": 571904 }, { "epoch": 0.01, "learning_rate": 4.062845797493781e-05, "loss": 3.7165, "step": 572416 }, { "epoch": 0.01, "learning_rate": 4.062007202742729e-05, "loss": 3.6895, "step": 572928 }, { "epoch": 0.01, "learning_rate": 4.061168607991677e-05, "loss": 3.7059, "step": 573440 }, { "epoch": 0.01, "learning_rate": 4.060330013240625e-05, "loss": 3.7055, "step": 573952 }, { "epoch": 0.01, "learning_rate": 4.059493056369946e-05, "loss": 3.6877, "step": 574464 }, { "epoch": 0.01, "learning_rate": 4.0586544616188946e-05, "loss": 3.7028, "step": 574976 }, { "epoch": 0.01, "learning_rate": 4.0578158668678426e-05, "loss": 3.7018, "step": 575488 }, { "epoch": 0.01, "learning_rate": 4.0569772721167906e-05, "loss": 3.7006, "step": 576000 }, { "epoch": 0.01, "learning_rate": 4.0561403152461115e-05, "loss": 3.7083, "step": 576512 }, { "epoch": 0.01, "learning_rate": 4.0553017204950595e-05, "loss": 3.6853, "step": 577024 }, { "epoch": 0.01, "learning_rate": 4.0544631257440075e-05, "loss": 3.6906, "step": 577536 }, { "epoch": 0.01, "learning_rate": 4.0536245309929555e-05, "loss": 3.6932, "step": 578048 }, { "epoch": 0.01, "learning_rate": 4.0527875741222764e-05, "loss": 3.7045, "step": 578560 }, { "epoch": 0.01, "learning_rate": 4.0519489793712244e-05, "loss": 3.6938, "step": 579072 }, { "epoch": 0.01, "learning_rate": 4.0511103846201724e-05, "loss": 3.6966, "step": 579584 }, { "epoch": 0.02, "learning_rate": 4.0502717898691204e-05, "loss": 3.6988, "step": 580096 }, { "epoch": 0.02, "learning_rate": 4.049434832998441e-05, "loss": 3.694, "step": 580608 }, { "epoch": 0.02, "learning_rate": 4.04859623824739e-05, "loss": 3.6933, "step": 581120 }, { "epoch": 0.02, "learning_rate": 4.047757643496338e-05, "loss": 3.6777, "step": 581632 }, { "epoch": 0.02, "learning_rate": 4.046919048745286e-05, "loss": 3.6927, "step": 582144 }, { "epoch": 0.02, "learning_rate": 4.046082091874607e-05, "loss": 3.6986, "step": 582656 }, { "epoch": 0.02, "learning_rate": 4.045243497123555e-05, "loss": 3.705, "step": 583168 }, { "epoch": 0.02, "learning_rate": 4.044404902372503e-05, "loss": 3.6852, "step": 583680 }, { "epoch": 0.02, "learning_rate": 4.043566307621451e-05, "loss": 3.6866, "step": 584192 }, { "epoch": 0.02, "learning_rate": 4.042729350750772e-05, "loss": 3.6938, "step": 584704 }, { "epoch": 0.02, "learning_rate": 4.04189075599972e-05, "loss": 3.6952, "step": 585216 }, { "epoch": 0.02, "learning_rate": 4.041052161248668e-05, "loss": 3.7002, "step": 585728 }, { "epoch": 0.02, "learning_rate": 4.040213566497616e-05, "loss": 3.6967, "step": 586240 }, { "epoch": 0.02, "learning_rate": 4.039376609626937e-05, "loss": 3.6933, "step": 586752 }, { "epoch": 0.02, "learning_rate": 4.0385380148758853e-05, "loss": 3.6938, "step": 587264 }, { "epoch": 0.02, "learning_rate": 4.0376994201248333e-05, "loss": 3.6872, "step": 587776 }, { "epoch": 0.02, "learning_rate": 4.036862463254154e-05, "loss": 3.6891, "step": 588288 }, { "epoch": 0.02, "learning_rate": 4.036023868503102e-05, "loss": 3.684, "step": 588800 }, { "epoch": 0.02, "learning_rate": 4.03518527375205e-05, "loss": 3.7033, "step": 589312 }, { "epoch": 0.02, "learning_rate": 4.034346679000998e-05, "loss": 3.6823, "step": 589824 }, { "epoch": 0.02, "learning_rate": 4.033508084249946e-05, "loss": 3.6947, "step": 590336 }, { "epoch": 0.02, "learning_rate": 4.032669489498894e-05, "loss": 3.688, "step": 590848 }, { "epoch": 0.02, "learning_rate": 4.0318308947478415e-05, "loss": 3.6941, "step": 591360 }, { "epoch": 0.02, "learning_rate": 4.0309922999967895e-05, "loss": 3.6889, "step": 591872 }, { "epoch": 0.02, "learning_rate": 4.030155343126111e-05, "loss": 3.6942, "step": 592384 }, { "epoch": 0.02, "learning_rate": 4.029318386255432e-05, "loss": 3.6899, "step": 592896 }, { "epoch": 0.02, "learning_rate": 4.028479791504381e-05, "loss": 3.7053, "step": 593408 }, { "epoch": 0.02, "learning_rate": 4.027641196753329e-05, "loss": 3.6907, "step": 593920 }, { "epoch": 0.02, "learning_rate": 4.026802602002277e-05, "loss": 3.7044, "step": 594432 }, { "epoch": 0.02, "learning_rate": 4.0259656451315976e-05, "loss": 3.6898, "step": 594944 }, { "epoch": 0.02, "learning_rate": 4.0251270503805456e-05, "loss": 3.691, "step": 595456 }, { "epoch": 0.02, "learning_rate": 4.0242884556294936e-05, "loss": 3.6872, "step": 595968 }, { "epoch": 0.02, "learning_rate": 4.0234498608784416e-05, "loss": 3.6914, "step": 596480 }, { "epoch": 0.02, "learning_rate": 4.022611266127389e-05, "loss": 3.6839, "step": 596992 }, { "epoch": 0.02, "learning_rate": 4.021772671376337e-05, "loss": 3.6945, "step": 597504 }, { "epoch": 0.02, "learning_rate": 4.020934076625285e-05, "loss": 3.685, "step": 598016 }, { "epoch": 0.02, "learning_rate": 4.020095481874233e-05, "loss": 3.693, "step": 598528 }, { "epoch": 0.02, "learning_rate": 4.0192585250035545e-05, "loss": 3.6931, "step": 599040 }, { "epoch": 0.02, "learning_rate": 4.0184199302525025e-05, "loss": 3.6877, "step": 599552 }, { "epoch": 0.02, "learning_rate": 4.0175813355014505e-05, "loss": 3.6923, "step": 600064 }, { "epoch": 0.02, "learning_rate": 4.0167427407503985e-05, "loss": 3.6957, "step": 600576 }, { "epoch": 0.02, "learning_rate": 4.0159057838797194e-05, "loss": 3.683, "step": 601088 }, { "epoch": 0.02, "learning_rate": 4.0150671891286674e-05, "loss": 3.6885, "step": 601600 }, { "epoch": 0.02, "learning_rate": 4.0142285943776154e-05, "loss": 3.6681, "step": 602112 }, { "epoch": 0.02, "learning_rate": 4.0133899996265634e-05, "loss": 3.6978, "step": 602624 }, { "epoch": 0.02, "learning_rate": 4.012553042755884e-05, "loss": 3.6929, "step": 603136 }, { "epoch": 0.02, "learning_rate": 4.011714448004832e-05, "loss": 3.6969, "step": 603648 }, { "epoch": 0.02, "learning_rate": 4.01087585325378e-05, "loss": 3.6876, "step": 604160 }, { "epoch": 0.02, "learning_rate": 4.010037258502728e-05, "loss": 3.694, "step": 604672 }, { "epoch": 0.02, "learning_rate": 4.009200301632049e-05, "loss": 3.6922, "step": 605184 }, { "epoch": 0.02, "learning_rate": 4.008361706880998e-05, "loss": 3.6993, "step": 605696 }, { "epoch": 0.02, "learning_rate": 4.007523112129946e-05, "loss": 3.682, "step": 606208 }, { "epoch": 0.02, "learning_rate": 4.006684517378894e-05, "loss": 3.6888, "step": 606720 }, { "epoch": 0.02, "learning_rate": 4.005847560508215e-05, "loss": 3.69, "step": 607232 }, { "epoch": 0.02, "learning_rate": 4.005008965757163e-05, "loss": 3.6923, "step": 607744 }, { "epoch": 0.02, "learning_rate": 4.004170371006111e-05, "loss": 3.6921, "step": 608256 }, { "epoch": 0.02, "learning_rate": 4.003331776255059e-05, "loss": 3.6892, "step": 608768 }, { "epoch": 0.02, "learning_rate": 4.0024948193843797e-05, "loss": 3.6961, "step": 609280 }, { "epoch": 0.02, "learning_rate": 4.0016562246333276e-05, "loss": 3.6802, "step": 609792 }, { "epoch": 0.02, "learning_rate": 4.0008176298822756e-05, "loss": 3.6968, "step": 610304 }, { "epoch": 0.03, "eval_loss": 3.871347188949585, "eval_runtime": 305.8402, "eval_samples_per_second": 1247.681, "eval_steps_per_second": 38.991, "step": 610560 }, { "epoch": 1.0, "learning_rate": 3.9999790351312236e-05, "loss": 3.6801, "step": 610816 }, { "epoch": 1.0, "learning_rate": 3.9991420782605445e-05, "loss": 3.6841, "step": 611328 }, { "epoch": 1.0, "learning_rate": 3.998303483509493e-05, "loss": 3.6876, "step": 611840 }, { "epoch": 1.0, "learning_rate": 3.997464888758441e-05, "loss": 3.6863, "step": 612352 }, { "epoch": 1.0, "learning_rate": 3.996627931887762e-05, "loss": 3.6977, "step": 612864 }, { "epoch": 1.0, "learning_rate": 3.99578933713671e-05, "loss": 3.6876, "step": 613376 }, { "epoch": 1.0, "learning_rate": 3.994950742385658e-05, "loss": 3.6785, "step": 613888 }, { "epoch": 1.0, "learning_rate": 3.994112147634606e-05, "loss": 3.6762, "step": 614400 }, { "epoch": 1.0, "learning_rate": 3.993273552883554e-05, "loss": 3.6866, "step": 614912 }, { "epoch": 1.0, "learning_rate": 3.992434958132502e-05, "loss": 3.6914, "step": 615424 }, { "epoch": 1.0, "learning_rate": 3.99159636338145e-05, "loss": 3.6838, "step": 615936 }, { "epoch": 1.0, "learning_rate": 3.990757768630398e-05, "loss": 3.6853, "step": 616448 }, { "epoch": 1.0, "learning_rate": 3.989922449640092e-05, "loss": 3.6913, "step": 616960 }, { "epoch": 1.0, "learning_rate": 3.98908385488904e-05, "loss": 3.6798, "step": 617472 }, { "epoch": 1.0, "learning_rate": 3.9882452601379886e-05, "loss": 3.6791, "step": 617984 }, { "epoch": 1.0, "learning_rate": 3.9874066653869366e-05, "loss": 3.6756, "step": 618496 }, { "epoch": 1.0, "learning_rate": 3.9865680706358846e-05, "loss": 3.6813, "step": 619008 }, { "epoch": 1.0, "learning_rate": 3.9857294758848326e-05, "loss": 3.676, "step": 619520 }, { "epoch": 1.0, "learning_rate": 3.9848908811337806e-05, "loss": 3.6839, "step": 620032 }, { "epoch": 1.0, "learning_rate": 3.9840522863827286e-05, "loss": 3.6941, "step": 620544 }, { "epoch": 1.0, "learning_rate": 3.9832136916316766e-05, "loss": 3.6914, "step": 621056 }, { "epoch": 1.0, "learning_rate": 3.9823750968806246e-05, "loss": 3.6812, "step": 621568 }, { "epoch": 1.0, "learning_rate": 3.9815365021295726e-05, "loss": 3.6799, "step": 622080 }, { "epoch": 1.0, "learning_rate": 3.98069790737852e-05, "loss": 3.6812, "step": 622592 }, { "epoch": 1.0, "learning_rate": 3.9798609505078415e-05, "loss": 3.6774, "step": 623104 }, { "epoch": 1.0, "learning_rate": 3.9790223557567895e-05, "loss": 3.6809, "step": 623616 }, { "epoch": 1.0, "learning_rate": 3.978183761005737e-05, "loss": 3.6693, "step": 624128 }, { "epoch": 1.0, "learning_rate": 3.9773451662546854e-05, "loss": 3.6889, "step": 624640 }, { "epoch": 1.0, "learning_rate": 3.976508209384007e-05, "loss": 3.6793, "step": 625152 }, { "epoch": 1.0, "learning_rate": 3.975669614632955e-05, "loss": 3.6667, "step": 625664 }, { "epoch": 1.01, "learning_rate": 3.9748310198819023e-05, "loss": 3.6739, "step": 626176 }, { "epoch": 1.01, "learning_rate": 3.973994063011224e-05, "loss": 3.6897, "step": 626688 }, { "epoch": 1.01, "learning_rate": 3.973155468260172e-05, "loss": 3.6878, "step": 627200 }, { "epoch": 1.01, "learning_rate": 3.97231687350912e-05, "loss": 3.6842, "step": 627712 }, { "epoch": 1.01, "learning_rate": 3.971478278758067e-05, "loss": 3.6775, "step": 628224 }, { "epoch": 1.01, "learning_rate": 3.970639684007015e-05, "loss": 3.6778, "step": 628736 }, { "epoch": 1.01, "learning_rate": 3.969801089255963e-05, "loss": 3.6902, "step": 629248 }, { "epoch": 1.01, "learning_rate": 3.968962494504911e-05, "loss": 3.6694, "step": 629760 }, { "epoch": 1.01, "learning_rate": 3.968123899753859e-05, "loss": 3.6655, "step": 630272 }, { "epoch": 1.01, "learning_rate": 3.967286942883181e-05, "loss": 3.6686, "step": 630784 }, { "epoch": 1.01, "learning_rate": 3.966448348132129e-05, "loss": 3.6719, "step": 631296 }, { "epoch": 1.01, "learning_rate": 3.965609753381077e-05, "loss": 3.6825, "step": 631808 }, { "epoch": 1.01, "learning_rate": 3.964771158630025e-05, "loss": 3.6729, "step": 632320 }, { "epoch": 1.01, "learning_rate": 3.963934201759346e-05, "loss": 3.6802, "step": 632832 }, { "epoch": 1.01, "learning_rate": 3.963095607008294e-05, "loss": 3.674, "step": 633344 }, { "epoch": 1.01, "learning_rate": 3.962257012257242e-05, "loss": 3.6716, "step": 633856 }, { "epoch": 1.01, "learning_rate": 3.96141841750619e-05, "loss": 3.6865, "step": 634368 }, { "epoch": 1.01, "learning_rate": 3.9605814606355106e-05, "loss": 3.6732, "step": 634880 }, { "epoch": 1.01, "learning_rate": 3.9597428658844586e-05, "loss": 3.6513, "step": 635392 }, { "epoch": 1.01, "learning_rate": 3.9589042711334066e-05, "loss": 3.6851, "step": 635904 }, { "epoch": 1.01, "learning_rate": 3.9580656763823546e-05, "loss": 3.6775, "step": 636416 }, { "epoch": 1.01, "learning_rate": 3.957228719511676e-05, "loss": 3.6839, "step": 636928 }, { "epoch": 1.01, "learning_rate": 3.956390124760624e-05, "loss": 3.6739, "step": 637440 }, { "epoch": 1.01, "learning_rate": 3.955551530009572e-05, "loss": 3.6666, "step": 637952 }, { "epoch": 1.01, "learning_rate": 3.954714573138893e-05, "loss": 3.6649, "step": 638464 }, { "epoch": 1.01, "learning_rate": 3.953875978387841e-05, "loss": 3.6718, "step": 638976 }, { "epoch": 1.01, "learning_rate": 3.953037383636789e-05, "loss": 3.6757, "step": 639488 }, { "epoch": 1.01, "learning_rate": 3.952198788885737e-05, "loss": 3.6608, "step": 640000 }, { "epoch": 1.01, "learning_rate": 3.951361832015058e-05, "loss": 3.6803, "step": 640512 }, { "epoch": 1.01, "learning_rate": 3.950523237264006e-05, "loss": 3.6724, "step": 641024 }, { "epoch": 1.01, "learning_rate": 3.949684642512954e-05, "loss": 3.6611, "step": 641536 }, { "epoch": 1.01, "learning_rate": 3.948846047761902e-05, "loss": 3.6792, "step": 642048 }, { "epoch": 1.01, "learning_rate": 3.948009090891223e-05, "loss": 3.6627, "step": 642560 }, { "epoch": 1.01, "learning_rate": 3.947170496140171e-05, "loss": 3.6625, "step": 643072 }, { "epoch": 1.01, "learning_rate": 3.9463319013891195e-05, "loss": 3.6752, "step": 643584 }, { "epoch": 1.01, "learning_rate": 3.9454933066380675e-05, "loss": 3.6806, "step": 644096 }, { "epoch": 1.01, "learning_rate": 3.9446563497673884e-05, "loss": 3.6521, "step": 644608 }, { "epoch": 1.01, "learning_rate": 3.9438177550163364e-05, "loss": 3.6713, "step": 645120 }, { "epoch": 1.01, "learning_rate": 3.9429791602652844e-05, "loss": 3.6552, "step": 645632 }, { "epoch": 1.01, "learning_rate": 3.9421422033946053e-05, "loss": 3.6715, "step": 646144 }, { "epoch": 1.01, "learning_rate": 3.9413036086435533e-05, "loss": 3.6782, "step": 646656 }, { "epoch": 1.01, "learning_rate": 3.940465013892501e-05, "loss": 3.6685, "step": 647168 }, { "epoch": 1.01, "learning_rate": 3.939626419141449e-05, "loss": 3.6745, "step": 647680 }, { "epoch": 1.01, "learning_rate": 3.938787824390397e-05, "loss": 3.6703, "step": 648192 }, { "epoch": 1.01, "learning_rate": 3.937949229639345e-05, "loss": 3.6903, "step": 648704 }, { "epoch": 1.01, "learning_rate": 3.937110634888293e-05, "loss": 3.6604, "step": 649216 }, { "epoch": 1.01, "learning_rate": 3.936272040137241e-05, "loss": 3.6776, "step": 649728 }, { "epoch": 1.01, "learning_rate": 3.935435083266563e-05, "loss": 3.6736, "step": 650240 }, { "epoch": 1.01, "learning_rate": 3.934596488515511e-05, "loss": 3.6654, "step": 650752 }, { "epoch": 1.01, "learning_rate": 3.933757893764459e-05, "loss": 3.6732, "step": 651264 }, { "epoch": 1.01, "learning_rate": 3.932919299013407e-05, "loss": 3.6709, "step": 651776 }, { "epoch": 1.01, "learning_rate": 3.932080704262355e-05, "loss": 3.6719, "step": 652288 }, { "epoch": 1.01, "learning_rate": 3.931242109511303e-05, "loss": 3.6805, "step": 652800 }, { "epoch": 1.01, "learning_rate": 3.93040351476025e-05, "loss": 3.6559, "step": 653312 }, { "epoch": 1.01, "learning_rate": 3.929564920009198e-05, "loss": 3.6625, "step": 653824 }, { "epoch": 1.01, "learning_rate": 3.92872796313852e-05, "loss": 3.6652, "step": 654336 }, { "epoch": 1.01, "learning_rate": 3.927891006267841e-05, "loss": 3.6774, "step": 654848 }, { "epoch": 1.01, "learning_rate": 3.927052411516789e-05, "loss": 3.6642, "step": 655360 }, { "epoch": 1.01, "learning_rate": 3.926213816765737e-05, "loss": 3.667, "step": 655872 }, { "epoch": 1.02, "learning_rate": 3.925375222014685e-05, "loss": 3.672, "step": 656384 }, { "epoch": 1.02, "learning_rate": 3.9245366272636333e-05, "loss": 3.666, "step": 656896 }, { "epoch": 1.02, "learning_rate": 3.923698032512581e-05, "loss": 3.6635, "step": 657408 }, { "epoch": 1.02, "learning_rate": 3.922861075641902e-05, "loss": 3.65, "step": 657920 }, { "epoch": 1.02, "learning_rate": 3.92202248089085e-05, "loss": 3.6645, "step": 658432 }, { "epoch": 1.02, "learning_rate": 3.9211838861397976e-05, "loss": 3.6694, "step": 658944 }, { "epoch": 1.02, "learning_rate": 3.9203452913887456e-05, "loss": 3.6765, "step": 659456 }, { "epoch": 1.02, "learning_rate": 3.9195066966376936e-05, "loss": 3.6592, "step": 659968 }, { "epoch": 1.02, "learning_rate": 3.9186681018866416e-05, "loss": 3.6599, "step": 660480 }, { "epoch": 1.02, "learning_rate": 3.9178295071355896e-05, "loss": 3.6632, "step": 660992 }, { "epoch": 1.02, "learning_rate": 3.9169909123845375e-05, "loss": 3.6712, "step": 661504 }, { "epoch": 1.02, "learning_rate": 3.9161539555138585e-05, "loss": 3.6731, "step": 662016 }, { "epoch": 1.02, "learning_rate": 3.915315360762807e-05, "loss": 3.6667, "step": 662528 }, { "epoch": 1.02, "learning_rate": 3.914476766011755e-05, "loss": 3.6688, "step": 663040 }, { "epoch": 1.02, "learning_rate": 3.913638171260703e-05, "loss": 3.6632, "step": 663552 }, { "epoch": 1.02, "learning_rate": 3.912801214390024e-05, "loss": 3.6607, "step": 664064 }, { "epoch": 1.02, "learning_rate": 3.911964257519345e-05, "loss": 3.6578, "step": 664576 }, { "epoch": 1.02, "learning_rate": 3.911125662768293e-05, "loss": 3.6598, "step": 665088 }, { "epoch": 1.02, "learning_rate": 3.910287068017241e-05, "loss": 3.6766, "step": 665600 }, { "epoch": 1.02, "learning_rate": 3.909448473266189e-05, "loss": 3.6544, "step": 666112 }, { "epoch": 1.02, "learning_rate": 3.908609878515137e-05, "loss": 3.6636, "step": 666624 }, { "epoch": 1.02, "learning_rate": 3.907771283764085e-05, "loss": 3.6565, "step": 667136 }, { "epoch": 1.02, "learning_rate": 3.906932689013033e-05, "loss": 3.6715, "step": 667648 }, { "epoch": 1.02, "learning_rate": 3.906095732142354e-05, "loss": 3.6638, "step": 668160 }, { "epoch": 1.02, "learning_rate": 3.9052571373913025e-05, "loss": 3.6654, "step": 668672 }, { "epoch": 1.02, "learning_rate": 3.9044185426402505e-05, "loss": 3.6633, "step": 669184 }, { "epoch": 1.02, "learning_rate": 3.9035799478891985e-05, "loss": 3.6755, "step": 669696 }, { "epoch": 1.02, "learning_rate": 3.9027429910185194e-05, "loss": 3.6661, "step": 670208 }, { "epoch": 1.02, "learning_rate": 3.9019043962674674e-05, "loss": 3.6724, "step": 670720 }, { "epoch": 1.02, "learning_rate": 3.9010658015164154e-05, "loss": 3.664, "step": 671232 }, { "epoch": 1.02, "learning_rate": 3.9002272067653634e-05, "loss": 3.6635, "step": 671744 }, { "epoch": 1.02, "learning_rate": 3.8993886120143114e-05, "loss": 3.6607, "step": 672256 }, { "epoch": 1.02, "learning_rate": 3.8985500172632594e-05, "loss": 3.6628, "step": 672768 }, { "epoch": 1.02, "learning_rate": 3.8977114225122074e-05, "loss": 3.6574, "step": 673280 }, { "epoch": 1.02, "learning_rate": 3.8968728277611554e-05, "loss": 3.664, "step": 673792 }, { "epoch": 1.02, "learning_rate": 3.896035870890476e-05, "loss": 3.6605, "step": 674304 }, { "epoch": 1.02, "learning_rate": 3.895197276139424e-05, "loss": 3.6675, "step": 674816 }, { "epoch": 1.02, "learning_rate": 3.894358681388372e-05, "loss": 3.6649, "step": 675328 }, { "epoch": 1.02, "learning_rate": 3.893521724517694e-05, "loss": 3.6652, "step": 675840 }, { "epoch": 1.02, "learning_rate": 3.892683129766642e-05, "loss": 3.6617, "step": 676352 }, { "epoch": 1.02, "learning_rate": 3.89184453501559e-05, "loss": 3.6701, "step": 676864 }, { "epoch": 1.02, "learning_rate": 3.891005940264538e-05, "loss": 3.6546, "step": 677376 }, { "epoch": 1.02, "learning_rate": 3.890167345513486e-05, "loss": 3.6646, "step": 677888 }, { "epoch": 1.02, "learning_rate": 3.889328750762434e-05, "loss": 3.6383, "step": 678400 }, { "epoch": 1.02, "learning_rate": 3.888490156011381e-05, "loss": 3.6706, "step": 678912 }, { "epoch": 1.02, "learning_rate": 3.887653199140703e-05, "loss": 3.6649, "step": 679424 }, { "epoch": 1.02, "learning_rate": 3.886814604389651e-05, "loss": 3.6738, "step": 679936 }, { "epoch": 1.02, "learning_rate": 3.885976009638599e-05, "loss": 3.6557, "step": 680448 }, { "epoch": 1.02, "learning_rate": 3.885137414887546e-05, "loss": 3.6694, "step": 680960 }, { "epoch": 1.02, "learning_rate": 3.8843004580168676e-05, "loss": 3.6636, "step": 681472 }, { "epoch": 1.02, "learning_rate": 3.8834618632658156e-05, "loss": 3.6749, "step": 681984 }, { "epoch": 1.02, "learning_rate": 3.882623268514764e-05, "loss": 3.6545, "step": 682496 }, { "epoch": 1.02, "learning_rate": 3.8817846737637116e-05, "loss": 3.6599, "step": 683008 }, { "epoch": 1.02, "learning_rate": 3.880947716893033e-05, "loss": 3.6611, "step": 683520 }, { "epoch": 1.02, "learning_rate": 3.880109122141981e-05, "loss": 3.6705, "step": 684032 }, { "epoch": 1.02, "learning_rate": 3.8792705273909285e-05, "loss": 3.6603, "step": 684544 }, { "epoch": 1.02, "learning_rate": 3.8784319326398765e-05, "loss": 3.6608, "step": 685056 }, { "epoch": 1.02, "learning_rate": 3.877594975769198e-05, "loss": 3.6687, "step": 685568 }, { "epoch": 1.02, "learning_rate": 3.876756381018146e-05, "loss": 3.6577, "step": 686080 }, { "epoch": 1.02, "learning_rate": 3.8759177862670934e-05, "loss": 3.6681, "step": 686592 }, { "epoch": 1.03, "eval_loss": 3.8674252033233643, "eval_runtime": 305.8831, "eval_samples_per_second": 1247.506, "eval_steps_per_second": 38.985, "step": 686880 }, { "epoch": 0.0, "learning_rate": 3.8750791915160414e-05, "loss": 3.654, "step": 687104 }, { "epoch": 0.0, "learning_rate": 3.8742405967649894e-05, "loss": 3.6613, "step": 687616 }, { "epoch": 0.0, "learning_rate": 3.873402002013938e-05, "loss": 3.6558, "step": 688128 }, { "epoch": 0.0, "learning_rate": 3.872563407262886e-05, "loss": 3.6634, "step": 688640 }, { "epoch": 0.0, "learning_rate": 3.871726450392207e-05, "loss": 3.6746, "step": 689152 }, { "epoch": 0.0, "learning_rate": 3.870887855641155e-05, "loss": 3.6581, "step": 689664 }, { "epoch": 0.0, "learning_rate": 3.870049260890103e-05, "loss": 3.6532, "step": 690176 }, { "epoch": 0.0, "learning_rate": 3.869210666139051e-05, "loss": 3.6507, "step": 690688 }, { "epoch": 0.0, "learning_rate": 3.868372071387999e-05, "loss": 3.6624, "step": 691200 }, { "epoch": 0.0, "learning_rate": 3.867533476636947e-05, "loss": 3.6645, "step": 691712 }, { "epoch": 0.0, "learning_rate": 3.866694881885895e-05, "loss": 3.6541, "step": 692224 }, { "epoch": 0.0, "learning_rate": 3.865856287134843e-05, "loss": 3.6583, "step": 692736 }, { "epoch": 0.0, "learning_rate": 3.865020968144537e-05, "loss": 3.6663, "step": 693248 }, { "epoch": 0.0, "learning_rate": 3.864182373393485e-05, "loss": 3.653, "step": 693760 }, { "epoch": 0.0, "learning_rate": 3.8633437786424334e-05, "loss": 3.6527, "step": 694272 }, { "epoch": 0.0, "learning_rate": 3.8625051838913814e-05, "loss": 3.647, "step": 694784 }, { "epoch": 0.0, "learning_rate": 3.8616665891403294e-05, "loss": 3.6572, "step": 695296 }, { "epoch": 0.0, "learning_rate": 3.8608279943892774e-05, "loss": 3.6506, "step": 695808 }, { "epoch": 0.0, "learning_rate": 3.8599893996382254e-05, "loss": 3.6515, "step": 696320 }, { "epoch": 0.0, "learning_rate": 3.8591508048871734e-05, "loss": 3.6676, "step": 696832 }, { "epoch": 0.0, "learning_rate": 3.8583122101361214e-05, "loss": 3.6659, "step": 697344 }, { "epoch": 0.0, "learning_rate": 3.8574736153850694e-05, "loss": 3.6564, "step": 697856 }, { "epoch": 0.0, "learning_rate": 3.8566350206340174e-05, "loss": 3.6539, "step": 698368 }, { "epoch": 0.0, "learning_rate": 3.855796425882965e-05, "loss": 3.6547, "step": 698880 }, { "epoch": 0.0, "learning_rate": 3.854959469012286e-05, "loss": 3.6556, "step": 699392 }, { "epoch": 0.0, "learning_rate": 3.854120874261234e-05, "loss": 3.6537, "step": 699904 }, { "epoch": 0.0, "learning_rate": 3.853282279510182e-05, "loss": 3.6417, "step": 700416 }, { "epoch": 0.0, "learning_rate": 3.85244368475913e-05, "loss": 3.6602, "step": 700928 }, { "epoch": 0.0, "learning_rate": 3.851606727888452e-05, "loss": 3.6568, "step": 701440 }, { "epoch": 0.0, "learning_rate": 3.8507681331374e-05, "loss": 3.6411, "step": 701952 }, { "epoch": 0.01, "learning_rate": 3.849929538386347e-05, "loss": 3.6493, "step": 702464 }, { "epoch": 0.01, "learning_rate": 3.849092581515669e-05, "loss": 3.6581, "step": 702976 }, { "epoch": 0.01, "learning_rate": 3.848253986764617e-05, "loss": 3.6586, "step": 703488 }, { "epoch": 0.01, "learning_rate": 3.847415392013565e-05, "loss": 3.6627, "step": 704000 }, { "epoch": 0.01, "learning_rate": 3.846576797262512e-05, "loss": 3.6557, "step": 704512 }, { "epoch": 0.01, "learning_rate": 3.84573820251146e-05, "loss": 3.6486, "step": 705024 }, { "epoch": 0.01, "learning_rate": 3.844899607760408e-05, "loss": 3.6669, "step": 705536 }, { "epoch": 0.01, "learning_rate": 3.844061013009356e-05, "loss": 3.6424, "step": 706048 }, { "epoch": 0.01, "learning_rate": 3.843222418258304e-05, "loss": 3.6415, "step": 706560 }, { "epoch": 0.01, "learning_rate": 3.842385461387626e-05, "loss": 3.6428, "step": 707072 }, { "epoch": 0.01, "learning_rate": 3.841546866636574e-05, "loss": 3.6462, "step": 707584 }, { "epoch": 0.01, "learning_rate": 3.840708271885522e-05, "loss": 3.6544, "step": 708096 }, { "epoch": 0.01, "learning_rate": 3.8398696771344697e-05, "loss": 3.649, "step": 708608 }, { "epoch": 0.01, "learning_rate": 3.8390327202637906e-05, "loss": 3.6527, "step": 709120 }, { "epoch": 0.01, "learning_rate": 3.8381941255127386e-05, "loss": 3.6494, "step": 709632 }, { "epoch": 0.01, "learning_rate": 3.8373555307616866e-05, "loss": 3.6469, "step": 710144 }, { "epoch": 0.01, "learning_rate": 3.8365169360106346e-05, "loss": 3.6582, "step": 710656 }, { "epoch": 0.01, "learning_rate": 3.8356799791399555e-05, "loss": 3.6528, "step": 711168 }, { "epoch": 0.01, "learning_rate": 3.8348413843889035e-05, "loss": 3.6275, "step": 711680 }, { "epoch": 0.01, "learning_rate": 3.8340027896378515e-05, "loss": 3.6568, "step": 712192 }, { "epoch": 0.01, "learning_rate": 3.8331641948867994e-05, "loss": 3.6542, "step": 712704 }, { "epoch": 0.01, "learning_rate": 3.832327238016121e-05, "loss": 3.6596, "step": 713216 }, { "epoch": 0.01, "learning_rate": 3.831488643265069e-05, "loss": 3.6466, "step": 713728 }, { "epoch": 0.01, "learning_rate": 3.830650048514017e-05, "loss": 3.6431, "step": 714240 }, { "epoch": 0.01, "learning_rate": 3.829811453762965e-05, "loss": 3.6356, "step": 714752 }, { "epoch": 0.01, "learning_rate": 3.828974496892286e-05, "loss": 3.6474, "step": 715264 }, { "epoch": 0.01, "learning_rate": 3.828135902141234e-05, "loss": 3.649, "step": 715776 }, { "epoch": 0.01, "learning_rate": 3.827297307390182e-05, "loss": 3.6388, "step": 716288 }, { "epoch": 0.01, "learning_rate": 3.826460350519503e-05, "loss": 3.6514, "step": 716800 }, { "epoch": 0.01, "learning_rate": 3.825621755768451e-05, "loss": 3.6482, "step": 717312 }, { "epoch": 0.01, "learning_rate": 3.824783161017399e-05, "loss": 3.6393, "step": 717824 }, { "epoch": 0.01, "learning_rate": 3.823944566266347e-05, "loss": 3.6489, "step": 718336 }, { "epoch": 0.01, "learning_rate": 3.823107609395668e-05, "loss": 3.6388, "step": 718848 }, { "epoch": 0.01, "learning_rate": 3.822269014644616e-05, "loss": 3.6397, "step": 719360 }, { "epoch": 0.01, "learning_rate": 3.821432057773937e-05, "loss": 3.6444, "step": 719872 }, { "epoch": 0.01, "learning_rate": 3.820593463022885e-05, "loss": 3.6557, "step": 720384 }, { "epoch": 0.01, "learning_rate": 3.819754868271833e-05, "loss": 3.633, "step": 720896 }, { "epoch": 0.01, "learning_rate": 3.818916273520781e-05, "loss": 3.6453, "step": 721408 }, { "epoch": 0.01, "learning_rate": 3.818077678769729e-05, "loss": 3.6253, "step": 721920 }, { "epoch": 0.01, "learning_rate": 3.81724072189905e-05, "loss": 3.6477, "step": 722432 }, { "epoch": 0.01, "learning_rate": 3.816402127147998e-05, "loss": 3.6519, "step": 722944 }, { "epoch": 0.01, "learning_rate": 3.815563532396946e-05, "loss": 3.6476, "step": 723456 }, { "epoch": 0.01, "learning_rate": 3.814724937645894e-05, "loss": 3.6457, "step": 723968 }, { "epoch": 0.01, "learning_rate": 3.813886342894842e-05, "loss": 3.6473, "step": 724480 }, { "epoch": 0.01, "learning_rate": 3.81304774814379e-05, "loss": 3.6634, "step": 724992 }, { "epoch": 0.01, "learning_rate": 3.812209153392738e-05, "loss": 3.6382, "step": 725504 }, { "epoch": 0.01, "learning_rate": 3.811370558641686e-05, "loss": 3.6541, "step": 726016 }, { "epoch": 0.01, "learning_rate": 3.810533601771008e-05, "loss": 3.6428, "step": 726528 }, { "epoch": 0.01, "learning_rate": 3.809695007019956e-05, "loss": 3.6426, "step": 727040 }, { "epoch": 0.01, "learning_rate": 3.808856412268904e-05, "loss": 3.6476, "step": 727552 }, { "epoch": 0.01, "learning_rate": 3.808017817517852e-05, "loss": 3.6437, "step": 728064 }, { "epoch": 0.01, "learning_rate": 3.8071792227668e-05, "loss": 3.6494, "step": 728576 }, { "epoch": 0.01, "learning_rate": 3.8063422658961207e-05, "loss": 3.6577, "step": 729088 }, { "epoch": 0.01, "learning_rate": 3.8055036711450686e-05, "loss": 3.6299, "step": 729600 }, { "epoch": 0.01, "learning_rate": 3.8046650763940166e-05, "loss": 3.64, "step": 730112 }, { "epoch": 0.01, "learning_rate": 3.8038264816429646e-05, "loss": 3.6382, "step": 730624 }, { "epoch": 0.01, "learning_rate": 3.8029895247722855e-05, "loss": 3.6541, "step": 731136 }, { "epoch": 0.01, "learning_rate": 3.8021509300212335e-05, "loss": 3.6379, "step": 731648 }, { "epoch": 0.01, "learning_rate": 3.8013123352701815e-05, "loss": 3.6465, "step": 732160 }, { "epoch": 0.02, "learning_rate": 3.8004737405191295e-05, "loss": 3.6461, "step": 732672 }, { "epoch": 0.02, "learning_rate": 3.799635145768078e-05, "loss": 3.6428, "step": 733184 }, { "epoch": 0.02, "learning_rate": 3.7987965510170255e-05, "loss": 3.6375, "step": 733696 }, { "epoch": 0.02, "learning_rate": 3.7979579562659735e-05, "loss": 3.6287, "step": 734208 }, { "epoch": 0.02, "learning_rate": 3.7971193615149215e-05, "loss": 3.6374, "step": 734720 }, { "epoch": 0.02, "learning_rate": 3.796282404644243e-05, "loss": 3.647, "step": 735232 }, { "epoch": 0.02, "learning_rate": 3.7954438098931904e-05, "loss": 3.6542, "step": 735744 }, { "epoch": 0.02, "learning_rate": 3.7946052151421384e-05, "loss": 3.6313, "step": 736256 }, { "epoch": 0.02, "learning_rate": 3.7937666203910864e-05, "loss": 3.638, "step": 736768 }, { "epoch": 0.02, "learning_rate": 3.792929663520407e-05, "loss": 3.6392, "step": 737280 }, { "epoch": 0.02, "learning_rate": 3.792091068769355e-05, "loss": 3.6445, "step": 737792 }, { "epoch": 0.02, "learning_rate": 3.791252474018303e-05, "loss": 3.6488, "step": 738304 }, { "epoch": 0.02, "learning_rate": 3.790413879267252e-05, "loss": 3.6433, "step": 738816 }, { "epoch": 0.02, "learning_rate": 3.789576922396573e-05, "loss": 3.6437, "step": 739328 }, { "epoch": 0.02, "learning_rate": 3.788738327645521e-05, "loss": 3.6401, "step": 739840 }, { "epoch": 0.02, "learning_rate": 3.787899732894469e-05, "loss": 3.6414, "step": 740352 }, { "epoch": 0.02, "learning_rate": 3.7870627760237905e-05, "loss": 3.6321, "step": 740864 }, { "epoch": 0.02, "learning_rate": 3.786224181272738e-05, "loss": 3.6374, "step": 741376 }, { "epoch": 0.02, "learning_rate": 3.785385586521686e-05, "loss": 3.6485, "step": 741888 }, { "epoch": 0.02, "learning_rate": 3.784546991770634e-05, "loss": 3.6351, "step": 742400 }, { "epoch": 0.02, "learning_rate": 3.783708397019582e-05, "loss": 3.6378, "step": 742912 }, { "epoch": 0.02, "learning_rate": 3.78286980226853e-05, "loss": 3.6336, "step": 743424 }, { "epoch": 0.02, "learning_rate": 3.782031207517478e-05, "loss": 3.6433, "step": 743936 }, { "epoch": 0.02, "learning_rate": 3.781192612766426e-05, "loss": 3.6372, "step": 744448 }, { "epoch": 0.02, "learning_rate": 3.7803556558957474e-05, "loss": 3.6418, "step": 744960 }, { "epoch": 0.02, "learning_rate": 3.779518699025068e-05, "loss": 3.6411, "step": 745472 }, { "epoch": 0.02, "learning_rate": 3.778680104274016e-05, "loss": 3.653, "step": 745984 }, { "epoch": 0.02, "learning_rate": 3.777841509522964e-05, "loss": 3.6391, "step": 746496 }, { "epoch": 0.02, "learning_rate": 3.777002914771912e-05, "loss": 3.6449, "step": 747008 }, { "epoch": 0.02, "learning_rate": 3.776165957901233e-05, "loss": 3.6454, "step": 747520 }, { "epoch": 0.02, "learning_rate": 3.775327363150181e-05, "loss": 3.6355, "step": 748032 }, { "epoch": 0.02, "learning_rate": 3.774488768399129e-05, "loss": 3.6419, "step": 748544 }, { "epoch": 0.02, "learning_rate": 3.773650173648077e-05, "loss": 3.6334, "step": 749056 }, { "epoch": 0.02, "learning_rate": 3.772811578897025e-05, "loss": 3.6336, "step": 749568 }, { "epoch": 0.02, "learning_rate": 3.771972984145973e-05, "loss": 3.6409, "step": 750080 }, { "epoch": 0.02, "learning_rate": 3.771134389394921e-05, "loss": 3.6381, "step": 750592 }, { "epoch": 0.02, "learning_rate": 3.770295794643869e-05, "loss": 3.6434, "step": 751104 }, { "epoch": 0.02, "learning_rate": 3.769458837773191e-05, "loss": 3.6396, "step": 751616 }, { "epoch": 0.02, "learning_rate": 3.7686218809025116e-05, "loss": 3.6445, "step": 752128 }, { "epoch": 0.02, "learning_rate": 3.7677832861514596e-05, "loss": 3.6355, "step": 752640 }, { "epoch": 0.02, "learning_rate": 3.7669446914004076e-05, "loss": 3.6475, "step": 753152 }, { "epoch": 0.02, "learning_rate": 3.7661060966493556e-05, "loss": 3.6325, "step": 753664 }, { "epoch": 0.02, "learning_rate": 3.7652675018983036e-05, "loss": 3.6384, "step": 754176 }, { "epoch": 0.02, "learning_rate": 3.7644289071472516e-05, "loss": 3.6133, "step": 754688 }, { "epoch": 0.02, "learning_rate": 3.7635903123961996e-05, "loss": 3.6469, "step": 755200 }, { "epoch": 0.02, "learning_rate": 3.7627517176451476e-05, "loss": 3.6396, "step": 755712 }, { "epoch": 0.02, "learning_rate": 3.7619163986548414e-05, "loss": 3.652, "step": 756224 }, { "epoch": 0.02, "learning_rate": 3.7610778039037894e-05, "loss": 3.6322, "step": 756736 }, { "epoch": 0.02, "learning_rate": 3.760239209152738e-05, "loss": 3.6435, "step": 757248 }, { "epoch": 0.02, "learning_rate": 3.759400614401686e-05, "loss": 3.6364, "step": 757760 }, { "epoch": 0.02, "learning_rate": 3.758562019650634e-05, "loss": 3.6552, "step": 758272 }, { "epoch": 0.02, "learning_rate": 3.757725062779955e-05, "loss": 3.6335, "step": 758784 }, { "epoch": 0.02, "learning_rate": 3.756886468028903e-05, "loss": 3.6347, "step": 759296 }, { "epoch": 0.02, "learning_rate": 3.756047873277851e-05, "loss": 3.639, "step": 759808 }, { "epoch": 0.02, "learning_rate": 3.755209278526799e-05, "loss": 3.6445, "step": 760320 }, { "epoch": 0.02, "learning_rate": 3.754370683775747e-05, "loss": 3.6362, "step": 760832 }, { "epoch": 0.02, "learning_rate": 3.753532089024695e-05, "loss": 3.6362, "step": 761344 }, { "epoch": 0.02, "learning_rate": 3.752695132154016e-05, "loss": 3.6423, "step": 761856 }, { "epoch": 0.02, "learning_rate": 3.751856537402964e-05, "loss": 3.639, "step": 762368 }, { "epoch": 0.02, "learning_rate": 3.751017942651912e-05, "loss": 3.6431, "step": 762880 }, { "epoch": 0.03, "eval_loss": 3.8649113178253174, "eval_runtime": 311.1998, "eval_samples_per_second": 1226.193, "eval_steps_per_second": 38.319, "step": 763200 }, { "epoch": 1.0, "learning_rate": 3.75017934790086e-05, "loss": 3.6258, "step": 763392 }, { "epoch": 1.0, "learning_rate": 3.749340753149808e-05, "loss": 3.6355, "step": 763904 }, { "epoch": 1.0, "learning_rate": 3.748502158398756e-05, "loss": 3.6357, "step": 764416 }, { "epoch": 1.0, "learning_rate": 3.7476652015280774e-05, "loss": 3.637, "step": 764928 }, { "epoch": 1.0, "learning_rate": 3.7468266067770254e-05, "loss": 3.6495, "step": 765440 }, { "epoch": 1.0, "learning_rate": 3.7459880120259734e-05, "loss": 3.6328, "step": 765952 }, { "epoch": 1.0, "learning_rate": 3.745149417274921e-05, "loss": 3.634, "step": 766464 }, { "epoch": 1.0, "learning_rate": 3.744310822523869e-05, "loss": 3.6282, "step": 766976 }, { "epoch": 1.0, "learning_rate": 3.74347386565319e-05, "loss": 3.6336, "step": 767488 }, { "epoch": 1.0, "learning_rate": 3.742635270902138e-05, "loss": 3.6399, "step": 768000 }, { "epoch": 1.0, "learning_rate": 3.7417966761510856e-05, "loss": 3.636, "step": 768512 }, { "epoch": 1.0, "learning_rate": 3.7409580814000336e-05, "loss": 3.6352, "step": 769024 }, { "epoch": 1.0, "learning_rate": 3.740122762409728e-05, "loss": 3.6438, "step": 769536 }, { "epoch": 1.0, "learning_rate": 3.739284167658677e-05, "loss": 3.6308, "step": 770048 }, { "epoch": 1.0, "learning_rate": 3.738445572907625e-05, "loss": 3.6286, "step": 770560 }, { "epoch": 1.0, "learning_rate": 3.737606978156573e-05, "loss": 3.6207, "step": 771072 }, { "epoch": 1.0, "learning_rate": 3.736768383405521e-05, "loss": 3.6369, "step": 771584 }, { "epoch": 1.0, "learning_rate": 3.735929788654468e-05, "loss": 3.6288, "step": 772096 }, { "epoch": 1.0, "learning_rate": 3.735091193903416e-05, "loss": 3.6296, "step": 772608 }, { "epoch": 1.0, "learning_rate": 3.734252599152364e-05, "loss": 3.6425, "step": 773120 }, { "epoch": 1.0, "learning_rate": 3.733414004401312e-05, "loss": 3.6435, "step": 773632 }, { "epoch": 1.0, "learning_rate": 3.73257540965026e-05, "loss": 3.6333, "step": 774144 }, { "epoch": 1.0, "learning_rate": 3.731736814899208e-05, "loss": 3.6285, "step": 774656 }, { "epoch": 1.0, "learning_rate": 3.730898220148156e-05, "loss": 3.6324, "step": 775168 }, { "epoch": 1.0, "learning_rate": 3.730061263277477e-05, "loss": 3.6327, "step": 775680 }, { "epoch": 1.0, "learning_rate": 3.729222668526425e-05, "loss": 3.6319, "step": 776192 }, { "epoch": 1.0, "learning_rate": 3.728384073775374e-05, "loss": 3.6179, "step": 776704 }, { "epoch": 1.0, "learning_rate": 3.727545479024322e-05, "loss": 3.6367, "step": 777216 }, { "epoch": 1.0, "learning_rate": 3.7267085221536426e-05, "loss": 3.633, "step": 777728 }, { "epoch": 1.0, "learning_rate": 3.7258699274025906e-05, "loss": 3.6189, "step": 778240 }, { "epoch": 1.01, "learning_rate": 3.7250313326515386e-05, "loss": 3.6264, "step": 778752 }, { "epoch": 1.01, "learning_rate": 3.7241943757808595e-05, "loss": 3.6358, "step": 779264 }, { "epoch": 1.01, "learning_rate": 3.7233557810298075e-05, "loss": 3.6316, "step": 779776 }, { "epoch": 1.01, "learning_rate": 3.7225171862787555e-05, "loss": 3.643, "step": 780288 }, { "epoch": 1.01, "learning_rate": 3.7216785915277035e-05, "loss": 3.6321, "step": 780800 }, { "epoch": 1.01, "learning_rate": 3.7208399967766515e-05, "loss": 3.6247, "step": 781312 }, { "epoch": 1.01, "learning_rate": 3.7200014020255995e-05, "loss": 3.6475, "step": 781824 }, { "epoch": 1.01, "learning_rate": 3.7191628072745475e-05, "loss": 3.6152, "step": 782336 }, { "epoch": 1.01, "learning_rate": 3.718325850403869e-05, "loss": 3.6189, "step": 782848 }, { "epoch": 1.01, "learning_rate": 3.717487255652817e-05, "loss": 3.6229, "step": 783360 }, { "epoch": 1.01, "learning_rate": 3.716648660901765e-05, "loss": 3.6233, "step": 783872 }, { "epoch": 1.01, "learning_rate": 3.715810066150713e-05, "loss": 3.6274, "step": 784384 }, { "epoch": 1.01, "learning_rate": 3.714971471399661e-05, "loss": 3.6291, "step": 784896 }, { "epoch": 1.01, "learning_rate": 3.714132876648609e-05, "loss": 3.631, "step": 785408 }, { "epoch": 1.01, "learning_rate": 3.713294281897557e-05, "loss": 3.6268, "step": 785920 }, { "epoch": 1.01, "learning_rate": 3.712455687146504e-05, "loss": 3.6238, "step": 786432 }, { "epoch": 1.01, "learning_rate": 3.711618730275826e-05, "loss": 3.6336, "step": 786944 }, { "epoch": 1.01, "learning_rate": 3.710780135524774e-05, "loss": 3.6289, "step": 787456 }, { "epoch": 1.01, "learning_rate": 3.709941540773722e-05, "loss": 3.6084, "step": 787968 }, { "epoch": 1.01, "learning_rate": 3.709104583903043e-05, "loss": 3.6341, "step": 788480 }, { "epoch": 1.01, "learning_rate": 3.708265989151991e-05, "loss": 3.6293, "step": 788992 }, { "epoch": 1.01, "learning_rate": 3.707427394400939e-05, "loss": 3.6362, "step": 789504 }, { "epoch": 1.01, "learning_rate": 3.706588799649887e-05, "loss": 3.6251, "step": 790016 }, { "epoch": 1.01, "learning_rate": 3.705750204898835e-05, "loss": 3.6228, "step": 790528 }, { "epoch": 1.01, "learning_rate": 3.704911610147783e-05, "loss": 3.6133, "step": 791040 }, { "epoch": 1.01, "learning_rate": 3.704073015396731e-05, "loss": 3.6204, "step": 791552 }, { "epoch": 1.01, "learning_rate": 3.703236058526052e-05, "loss": 3.6291, "step": 792064 }, { "epoch": 1.01, "learning_rate": 3.702397463775e-05, "loss": 3.6172, "step": 792576 }, { "epoch": 1.01, "learning_rate": 3.701558869023948e-05, "loss": 3.6277, "step": 793088 }, { "epoch": 1.01, "learning_rate": 3.700720274272896e-05, "loss": 3.6251, "step": 793600 }, { "epoch": 1.01, "learning_rate": 3.6998833174022166e-05, "loss": 3.6173, "step": 794112 }, { "epoch": 1.01, "learning_rate": 3.6990447226511646e-05, "loss": 3.6249, "step": 794624 }, { "epoch": 1.01, "learning_rate": 3.6982061279001126e-05, "loss": 3.6169, "step": 795136 }, { "epoch": 1.01, "learning_rate": 3.6973675331490606e-05, "loss": 3.6188, "step": 795648 }, { "epoch": 1.01, "learning_rate": 3.696528938398009e-05, "loss": 3.6188, "step": 796160 }, { "epoch": 1.01, "learning_rate": 3.69569198152733e-05, "loss": 3.6323, "step": 796672 }, { "epoch": 1.01, "learning_rate": 3.694853386776278e-05, "loss": 3.6107, "step": 797184 }, { "epoch": 1.01, "learning_rate": 3.694014792025226e-05, "loss": 3.6243, "step": 797696 }, { "epoch": 1.01, "learning_rate": 3.693176197274174e-05, "loss": 3.6024, "step": 798208 }, { "epoch": 1.01, "learning_rate": 3.692337602523122e-05, "loss": 3.6225, "step": 798720 }, { "epoch": 1.01, "learning_rate": 3.691500645652443e-05, "loss": 3.627, "step": 799232 }, { "epoch": 1.01, "learning_rate": 3.690662050901391e-05, "loss": 3.6287, "step": 799744 }, { "epoch": 1.01, "learning_rate": 3.689823456150339e-05, "loss": 3.6217, "step": 800256 }, { "epoch": 1.01, "learning_rate": 3.688984861399287e-05, "loss": 3.6238, "step": 800768 }, { "epoch": 1.01, "learning_rate": 3.688146266648235e-05, "loss": 3.6413, "step": 801280 }, { "epoch": 1.01, "learning_rate": 3.687307671897183e-05, "loss": 3.616, "step": 801792 }, { "epoch": 1.01, "learning_rate": 3.686469077146131e-05, "loss": 3.6358, "step": 802304 }, { "epoch": 1.01, "learning_rate": 3.6856321202754526e-05, "loss": 3.6194, "step": 802816 }, { "epoch": 1.01, "learning_rate": 3.6847935255244006e-05, "loss": 3.6205, "step": 803328 }, { "epoch": 1.01, "learning_rate": 3.6839549307733486e-05, "loss": 3.6256, "step": 803840 }, { "epoch": 1.01, "learning_rate": 3.6831163360222966e-05, "loss": 3.6189, "step": 804352 }, { "epoch": 1.01, "learning_rate": 3.6822777412712446e-05, "loss": 3.6286, "step": 804864 }, { "epoch": 1.01, "learning_rate": 3.6814407844005655e-05, "loss": 3.6342, "step": 805376 }, { "epoch": 1.01, "learning_rate": 3.6806021896495135e-05, "loss": 3.6148, "step": 805888 }, { "epoch": 1.01, "learning_rate": 3.6797635948984615e-05, "loss": 3.6129, "step": 806400 }, { "epoch": 1.01, "learning_rate": 3.6789250001474095e-05, "loss": 3.6157, "step": 806912 }, { "epoch": 1.01, "learning_rate": 3.6780880432767304e-05, "loss": 3.6288, "step": 807424 }, { "epoch": 1.01, "learning_rate": 3.6772494485256784e-05, "loss": 3.6174, "step": 807936 }, { "epoch": 1.01, "learning_rate": 3.6764108537746264e-05, "loss": 3.6249, "step": 808448 }, { "epoch": 1.01, "learning_rate": 3.6755722590235744e-05, "loss": 3.6232, "step": 808960 }, { "epoch": 1.02, "learning_rate": 3.674733664272523e-05, "loss": 3.6226, "step": 809472 }, { "epoch": 1.02, "learning_rate": 3.6738950695214704e-05, "loss": 3.6141, "step": 809984 }, { "epoch": 1.02, "learning_rate": 3.673058112650792e-05, "loss": 3.609, "step": 810496 }, { "epoch": 1.02, "learning_rate": 3.67221951789974e-05, "loss": 3.6126, "step": 811008 }, { "epoch": 1.02, "learning_rate": 3.671380923148688e-05, "loss": 3.6269, "step": 811520 }, { "epoch": 1.02, "learning_rate": 3.670542328397635e-05, "loss": 3.6291, "step": 812032 }, { "epoch": 1.02, "learning_rate": 3.669703733646583e-05, "loss": 3.6117, "step": 812544 }, { "epoch": 1.02, "learning_rate": 3.668865138895531e-05, "loss": 3.6145, "step": 813056 }, { "epoch": 1.02, "learning_rate": 3.668028182024853e-05, "loss": 3.6169, "step": 813568 }, { "epoch": 1.02, "learning_rate": 3.6671895872738e-05, "loss": 3.6243, "step": 814080 }, { "epoch": 1.02, "learning_rate": 3.666350992522748e-05, "loss": 3.6279, "step": 814592 }, { "epoch": 1.02, "learning_rate": 3.665512397771697e-05, "loss": 3.618, "step": 815104 }, { "epoch": 1.02, "learning_rate": 3.664673803020645e-05, "loss": 3.6225, "step": 815616 }, { "epoch": 1.02, "learning_rate": 3.663835208269593e-05, "loss": 3.6192, "step": 816128 }, { "epoch": 1.02, "learning_rate": 3.662998251398914e-05, "loss": 3.6155, "step": 816640 }, { "epoch": 1.02, "learning_rate": 3.662159656647862e-05, "loss": 3.6127, "step": 817152 }, { "epoch": 1.02, "learning_rate": 3.66132106189681e-05, "loss": 3.6183, "step": 817664 }, { "epoch": 1.02, "learning_rate": 3.660482467145758e-05, "loss": 3.6221, "step": 818176 }, { "epoch": 1.02, "learning_rate": 3.6596455102750786e-05, "loss": 3.6137, "step": 818688 }, { "epoch": 1.02, "learning_rate": 3.6588069155240266e-05, "loss": 3.6154, "step": 819200 }, { "epoch": 1.02, "learning_rate": 3.6579683207729746e-05, "loss": 3.6114, "step": 819712 }, { "epoch": 1.02, "learning_rate": 3.6571297260219226e-05, "loss": 3.6184, "step": 820224 }, { "epoch": 1.02, "learning_rate": 3.6562911312708706e-05, "loss": 3.6183, "step": 820736 }, { "epoch": 1.02, "learning_rate": 3.6554525365198186e-05, "loss": 3.6182, "step": 821248 }, { "epoch": 1.02, "learning_rate": 3.65461557964914e-05, "loss": 3.6179, "step": 821760 }, { "epoch": 1.02, "learning_rate": 3.653776984898088e-05, "loss": 3.6321, "step": 822272 }, { "epoch": 1.02, "learning_rate": 3.652938390147036e-05, "loss": 3.6219, "step": 822784 }, { "epoch": 1.02, "learning_rate": 3.652099795395984e-05, "loss": 3.6201, "step": 823296 }, { "epoch": 1.02, "learning_rate": 3.651261200644932e-05, "loss": 3.6231, "step": 823808 }, { "epoch": 1.02, "learning_rate": 3.650424243774253e-05, "loss": 3.6165, "step": 824320 }, { "epoch": 1.02, "learning_rate": 3.649585649023201e-05, "loss": 3.623, "step": 824832 }, { "epoch": 1.02, "learning_rate": 3.648747054272149e-05, "loss": 3.6069, "step": 825344 }, { "epoch": 1.02, "learning_rate": 3.647908459521097e-05, "loss": 3.6127, "step": 825856 }, { "epoch": 1.02, "learning_rate": 3.647071502650418e-05, "loss": 3.6186, "step": 826368 }, { "epoch": 1.02, "learning_rate": 3.646232907899366e-05, "loss": 3.6198, "step": 826880 }, { "epoch": 1.02, "learning_rate": 3.645394313148314e-05, "loss": 3.6169, "step": 827392 }, { "epoch": 1.02, "learning_rate": 3.644555718397262e-05, "loss": 3.6203, "step": 827904 }, { "epoch": 1.02, "learning_rate": 3.64371712364621e-05, "loss": 3.6201, "step": 828416 }, { "epoch": 1.02, "learning_rate": 3.6428785288951587e-05, "loss": 3.6146, "step": 828928 }, { "epoch": 1.02, "learning_rate": 3.6420415720244796e-05, "loss": 3.6204, "step": 829440 }, { "epoch": 1.02, "learning_rate": 3.6412029772734276e-05, "loss": 3.617, "step": 829952 }, { "epoch": 1.02, "learning_rate": 3.6403643825223756e-05, "loss": 3.6138, "step": 830464 }, { "epoch": 1.02, "learning_rate": 3.6395257877713236e-05, "loss": 3.5928, "step": 830976 }, { "epoch": 1.02, "learning_rate": 3.6386888309006445e-05, "loss": 3.6279, "step": 831488 }, { "epoch": 1.02, "learning_rate": 3.6378502361495925e-05, "loss": 3.6165, "step": 832000 }, { "epoch": 1.02, "learning_rate": 3.6370116413985405e-05, "loss": 3.6285, "step": 832512 }, { "epoch": 1.02, "learning_rate": 3.6361730466474884e-05, "loss": 3.6114, "step": 833024 }, { "epoch": 1.02, "learning_rate": 3.635334451896436e-05, "loss": 3.619, "step": 833536 }, { "epoch": 1.02, "learning_rate": 3.634495857145384e-05, "loss": 3.6155, "step": 834048 }, { "epoch": 1.02, "learning_rate": 3.6336572623943324e-05, "loss": 3.6371, "step": 834560 }, { "epoch": 1.02, "learning_rate": 3.6328186676432804e-05, "loss": 3.6064, "step": 835072 }, { "epoch": 1.02, "learning_rate": 3.6319817107726013e-05, "loss": 3.6153, "step": 835584 }, { "epoch": 1.02, "learning_rate": 3.631143116021549e-05, "loss": 3.6185, "step": 836096 }, { "epoch": 1.02, "learning_rate": 3.630306159150871e-05, "loss": 3.6216, "step": 836608 }, { "epoch": 1.02, "learning_rate": 3.629467564399819e-05, "loss": 3.6148, "step": 837120 }, { "epoch": 1.02, "learning_rate": 3.628628969648766e-05, "loss": 3.6164, "step": 837632 }, { "epoch": 1.02, "learning_rate": 3.627790374897714e-05, "loss": 3.6177, "step": 838144 }, { "epoch": 1.02, "learning_rate": 3.626951780146662e-05, "loss": 3.6228, "step": 838656 }, { "epoch": 1.02, "learning_rate": 3.62611318539561e-05, "loss": 3.6175, "step": 839168 }, { "epoch": 1.03, "eval_loss": 3.863309860229492, "eval_runtime": 317.3238, "eval_samples_per_second": 1202.529, "eval_steps_per_second": 37.58, "step": 839520 }, { "epoch": 0.0, "learning_rate": 3.625276228524931e-05, "loss": 3.6141, "step": 839680 }, { "epoch": 0.0, "learning_rate": 3.624437633773879e-05, "loss": 3.6124, "step": 840192 }, { "epoch": 0.0, "learning_rate": 3.623599039022828e-05, "loss": 3.6128, "step": 840704 }, { "epoch": 0.0, "learning_rate": 3.622760444271776e-05, "loss": 3.6172, "step": 841216 }, { "epoch": 0.0, "learning_rate": 3.621921849520724e-05, "loss": 3.6222, "step": 841728 }, { "epoch": 0.0, "learning_rate": 3.621084892650045e-05, "loss": 3.6133, "step": 842240 }, { "epoch": 0.0, "learning_rate": 3.620246297898993e-05, "loss": 3.6154, "step": 842752 }, { "epoch": 0.0, "learning_rate": 3.619407703147941e-05, "loss": 3.6074, "step": 843264 }, { "epoch": 0.0, "learning_rate": 3.618569108396889e-05, "loss": 3.6099, "step": 843776 }, { "epoch": 0.0, "learning_rate": 3.6177321515262096e-05, "loss": 3.6169, "step": 844288 }, { "epoch": 0.0, "learning_rate": 3.6168935567751576e-05, "loss": 3.6169, "step": 844800 }, { "epoch": 0.0, "learning_rate": 3.6160549620241056e-05, "loss": 3.613, "step": 845312 }, { "epoch": 0.0, "learning_rate": 3.6152180051534265e-05, "loss": 3.6275, "step": 845824 }, { "epoch": 0.0, "learning_rate": 3.6143794104023745e-05, "loss": 3.6038, "step": 846336 }, { "epoch": 0.0, "learning_rate": 3.613540815651323e-05, "loss": 3.6087, "step": 846848 }, { "epoch": 0.0, "learning_rate": 3.612702220900271e-05, "loss": 3.6009, "step": 847360 }, { "epoch": 0.0, "learning_rate": 3.611863626149219e-05, "loss": 3.6158, "step": 847872 }, { "epoch": 0.0, "learning_rate": 3.611025031398167e-05, "loss": 3.6045, "step": 848384 }, { "epoch": 0.0, "learning_rate": 3.610186436647115e-05, "loss": 3.6103, "step": 848896 }, { "epoch": 0.0, "learning_rate": 3.609347841896063e-05, "loss": 3.6182, "step": 849408 }, { "epoch": 0.0, "learning_rate": 3.608510885025384e-05, "loss": 3.6225, "step": 849920 }, { "epoch": 0.0, "learning_rate": 3.607672290274332e-05, "loss": 3.6134, "step": 850432 }, { "epoch": 0.0, "learning_rate": 3.60683369552328e-05, "loss": 3.6061, "step": 850944 }, { "epoch": 0.0, "learning_rate": 3.605995100772228e-05, "loss": 3.6131, "step": 851456 }, { "epoch": 0.0, "learning_rate": 3.605158143901549e-05, "loss": 3.6139, "step": 851968 }, { "epoch": 0.0, "learning_rate": 3.604319549150497e-05, "loss": 3.6091, "step": 852480 }, { "epoch": 0.0, "learning_rate": 3.603480954399445e-05, "loss": 3.5974, "step": 852992 }, { "epoch": 0.0, "learning_rate": 3.602642359648393e-05, "loss": 3.6131, "step": 853504 }, { "epoch": 0.0, "learning_rate": 3.6018054027777145e-05, "loss": 3.6118, "step": 854016 }, { "epoch": 0.0, "learning_rate": 3.6009668080266625e-05, "loss": 3.5951, "step": 854528 }, { "epoch": 0.01, "learning_rate": 3.6001282132756105e-05, "loss": 3.6076, "step": 855040 }, { "epoch": 0.01, "learning_rate": 3.5992896185245585e-05, "loss": 3.6156, "step": 855552 }, { "epoch": 0.01, "learning_rate": 3.5984510237735065e-05, "loss": 3.6096, "step": 856064 }, { "epoch": 0.01, "learning_rate": 3.5976140669028274e-05, "loss": 3.6208, "step": 856576 }, { "epoch": 0.01, "learning_rate": 3.5967754721517754e-05, "loss": 3.6109, "step": 857088 }, { "epoch": 0.01, "learning_rate": 3.5959368774007234e-05, "loss": 3.6061, "step": 857600 }, { "epoch": 0.01, "learning_rate": 3.595099920530044e-05, "loss": 3.6283, "step": 858112 }, { "epoch": 0.01, "learning_rate": 3.594261325778992e-05, "loss": 3.5915, "step": 858624 }, { "epoch": 0.01, "learning_rate": 3.59342273102794e-05, "loss": 3.6002, "step": 859136 }, { "epoch": 0.01, "learning_rate": 3.592584136276888e-05, "loss": 3.6039, "step": 859648 }, { "epoch": 0.01, "learning_rate": 3.591745541525837e-05, "loss": 3.6011, "step": 860160 }, { "epoch": 0.01, "learning_rate": 3.590906946774785e-05, "loss": 3.6066, "step": 860672 }, { "epoch": 0.01, "learning_rate": 3.590069989904106e-05, "loss": 3.6123, "step": 861184 }, { "epoch": 0.01, "learning_rate": 3.589231395153054e-05, "loss": 3.6079, "step": 861696 }, { "epoch": 0.01, "learning_rate": 3.588392800402002e-05, "loss": 3.6074, "step": 862208 }, { "epoch": 0.01, "learning_rate": 3.58755420565095e-05, "loss": 3.5997, "step": 862720 }, { "epoch": 0.01, "learning_rate": 3.586717248780271e-05, "loss": 3.6103, "step": 863232 }, { "epoch": 0.01, "learning_rate": 3.585878654029219e-05, "loss": 3.611, "step": 863744 }, { "epoch": 0.01, "learning_rate": 3.585040059278167e-05, "loss": 3.587, "step": 864256 }, { "epoch": 0.01, "learning_rate": 3.584201464527114e-05, "loss": 3.6104, "step": 864768 }, { "epoch": 0.01, "learning_rate": 3.583364507656436e-05, "loss": 3.609, "step": 865280 }, { "epoch": 0.01, "learning_rate": 3.582525912905384e-05, "loss": 3.6141, "step": 865792 }, { "epoch": 0.01, "learning_rate": 3.581687318154332e-05, "loss": 3.6052, "step": 866304 }, { "epoch": 0.01, "learning_rate": 3.58084872340328e-05, "loss": 3.6026, "step": 866816 }, { "epoch": 0.01, "learning_rate": 3.580011766532601e-05, "loss": 3.5959, "step": 867328 }, { "epoch": 0.01, "learning_rate": 3.579173171781549e-05, "loss": 3.5989, "step": 867840 }, { "epoch": 0.01, "learning_rate": 3.578334577030497e-05, "loss": 3.6104, "step": 868352 }, { "epoch": 0.01, "learning_rate": 3.5774959822794446e-05, "loss": 3.5938, "step": 868864 }, { "epoch": 0.01, "learning_rate": 3.5766573875283926e-05, "loss": 3.6077, "step": 869376 }, { "epoch": 0.01, "learning_rate": 3.575820430657714e-05, "loss": 3.6023, "step": 869888 }, { "epoch": 0.01, "learning_rate": 3.5749818359066615e-05, "loss": 3.6001, "step": 870400 }, { "epoch": 0.01, "learning_rate": 3.5741432411556095e-05, "loss": 3.6006, "step": 870912 }, { "epoch": 0.01, "learning_rate": 3.5733046464045575e-05, "loss": 3.5994, "step": 871424 }, { "epoch": 0.01, "learning_rate": 3.572466051653506e-05, "loss": 3.6007, "step": 871936 }, { "epoch": 0.01, "learning_rate": 3.571629094782827e-05, "loss": 3.5923, "step": 872448 }, { "epoch": 0.01, "learning_rate": 3.570790500031775e-05, "loss": 3.6154, "step": 872960 }, { "epoch": 0.01, "learning_rate": 3.569951905280723e-05, "loss": 3.5938, "step": 873472 }, { "epoch": 0.01, "learning_rate": 3.569113310529671e-05, "loss": 3.5945, "step": 873984 }, { "epoch": 0.01, "learning_rate": 3.568274715778619e-05, "loss": 3.5869, "step": 874496 }, { "epoch": 0.01, "learning_rate": 3.567436121027567e-05, "loss": 3.6014, "step": 875008 }, { "epoch": 0.01, "learning_rate": 3.566599164156888e-05, "loss": 3.6062, "step": 875520 }, { "epoch": 0.01, "learning_rate": 3.565760569405836e-05, "loss": 3.609, "step": 876032 }, { "epoch": 0.01, "learning_rate": 3.564921974654784e-05, "loss": 3.605, "step": 876544 }, { "epoch": 0.01, "learning_rate": 3.564083379903732e-05, "loss": 3.6034, "step": 877056 }, { "epoch": 0.01, "learning_rate": 3.56324478515268e-05, "loss": 3.6176, "step": 877568 }, { "epoch": 0.01, "learning_rate": 3.562407828282001e-05, "loss": 3.5978, "step": 878080 }, { "epoch": 0.01, "learning_rate": 3.5615692335309495e-05, "loss": 3.6161, "step": 878592 }, { "epoch": 0.01, "learning_rate": 3.5607306387798975e-05, "loss": 3.5984, "step": 879104 }, { "epoch": 0.01, "learning_rate": 3.5598920440288455e-05, "loss": 3.5989, "step": 879616 }, { "epoch": 0.01, "learning_rate": 3.5590550871581664e-05, "loss": 3.602, "step": 880128 }, { "epoch": 0.01, "learning_rate": 3.5582164924071144e-05, "loss": 3.5978, "step": 880640 }, { "epoch": 0.01, "learning_rate": 3.5573778976560624e-05, "loss": 3.6068, "step": 881152 }, { "epoch": 0.01, "learning_rate": 3.5565393029050104e-05, "loss": 3.6175, "step": 881664 }, { "epoch": 0.01, "learning_rate": 3.5557007081539584e-05, "loss": 3.5978, "step": 882176 }, { "epoch": 0.01, "learning_rate": 3.5548621134029064e-05, "loss": 3.5882, "step": 882688 }, { "epoch": 0.01, "learning_rate": 3.554025156532227e-05, "loss": 3.5956, "step": 883200 }, { "epoch": 0.01, "learning_rate": 3.553186561781175e-05, "loss": 3.607, "step": 883712 }, { "epoch": 0.01, "learning_rate": 3.552347967030123e-05, "loss": 3.6007, "step": 884224 }, { "epoch": 0.01, "learning_rate": 3.551509372279071e-05, "loss": 3.603, "step": 884736 }, { "epoch": 0.01, "learning_rate": 3.550670777528019e-05, "loss": 3.6046, "step": 885248 }, { "epoch": 0.02, "learning_rate": 3.549833820657341e-05, "loss": 3.6039, "step": 885760 }, { "epoch": 0.02, "learning_rate": 3.548995225906289e-05, "loss": 3.5918, "step": 886272 }, { "epoch": 0.02, "learning_rate": 3.548156631155237e-05, "loss": 3.5869, "step": 886784 }, { "epoch": 0.02, "learning_rate": 3.547318036404185e-05, "loss": 3.5961, "step": 887296 }, { "epoch": 0.02, "learning_rate": 3.546479441653133e-05, "loss": 3.6014, "step": 887808 }, { "epoch": 0.02, "learning_rate": 3.545642484782454e-05, "loss": 3.6152, "step": 888320 }, { "epoch": 0.02, "learning_rate": 3.544803890031402e-05, "loss": 3.5874, "step": 888832 }, { "epoch": 0.02, "learning_rate": 3.54396529528035e-05, "loss": 3.5963, "step": 889344 }, { "epoch": 0.02, "learning_rate": 3.543126700529298e-05, "loss": 3.5989, "step": 889856 }, { "epoch": 0.02, "learning_rate": 3.542288105778245e-05, "loss": 3.5988, "step": 890368 }, { "epoch": 0.02, "learning_rate": 3.5414511489075666e-05, "loss": 3.606, "step": 890880 }, { "epoch": 0.02, "learning_rate": 3.5406125541565146e-05, "loss": 3.5998, "step": 891392 }, { "epoch": 0.02, "learning_rate": 3.539773959405463e-05, "loss": 3.6041, "step": 891904 }, { "epoch": 0.02, "learning_rate": 3.5389353646544106e-05, "loss": 3.5959, "step": 892416 }, { "epoch": 0.02, "learning_rate": 3.538098407783732e-05, "loss": 3.5973, "step": 892928 }, { "epoch": 0.02, "learning_rate": 3.53725981303268e-05, "loss": 3.5935, "step": 893440 }, { "epoch": 0.02, "learning_rate": 3.5364212182816275e-05, "loss": 3.597, "step": 893952 }, { "epoch": 0.02, "learning_rate": 3.5355826235305755e-05, "loss": 3.6056, "step": 894464 }, { "epoch": 0.02, "learning_rate": 3.534745666659897e-05, "loss": 3.5929, "step": 894976 }, { "epoch": 0.02, "learning_rate": 3.533907071908845e-05, "loss": 3.5946, "step": 895488 }, { "epoch": 0.02, "learning_rate": 3.5330684771577924e-05, "loss": 3.5888, "step": 896000 }, { "epoch": 0.02, "learning_rate": 3.5322298824067404e-05, "loss": 3.5982, "step": 896512 }, { "epoch": 0.02, "learning_rate": 3.5313912876556884e-05, "loss": 3.5987, "step": 897024 }, { "epoch": 0.02, "learning_rate": 3.530552692904637e-05, "loss": 3.6009, "step": 897536 }, { "epoch": 0.02, "learning_rate": 3.529715736033958e-05, "loss": 3.5969, "step": 898048 }, { "epoch": 0.02, "learning_rate": 3.528877141282906e-05, "loss": 3.6047, "step": 898560 }, { "epoch": 0.02, "learning_rate": 3.528038546531854e-05, "loss": 3.6051, "step": 899072 }, { "epoch": 0.02, "learning_rate": 3.527199951780802e-05, "loss": 3.6043, "step": 899584 }, { "epoch": 0.02, "learning_rate": 3.52636135702975e-05, "loss": 3.6037, "step": 900096 }, { "epoch": 0.02, "learning_rate": 3.525524400159071e-05, "loss": 3.597, "step": 900608 }, { "epoch": 0.02, "learning_rate": 3.524685805408019e-05, "loss": 3.5993, "step": 901120 }, { "epoch": 0.02, "learning_rate": 3.523847210656967e-05, "loss": 3.5912, "step": 901632 }, { "epoch": 0.02, "learning_rate": 3.523008615905915e-05, "loss": 3.5927, "step": 902144 }, { "epoch": 0.02, "learning_rate": 3.522171659035236e-05, "loss": 3.5998, "step": 902656 }, { "epoch": 0.02, "learning_rate": 3.521333064284184e-05, "loss": 3.601, "step": 903168 }, { "epoch": 0.02, "learning_rate": 3.5204944695331324e-05, "loss": 3.5984, "step": 903680 }, { "epoch": 0.02, "learning_rate": 3.5196558747820804e-05, "loss": 3.5993, "step": 904192 }, { "epoch": 0.02, "learning_rate": 3.5188189179114013e-05, "loss": 3.6007, "step": 904704 }, { "epoch": 0.02, "learning_rate": 3.5179803231603493e-05, "loss": 3.5958, "step": 905216 }, { "epoch": 0.02, "learning_rate": 3.5171417284092973e-05, "loss": 3.6008, "step": 905728 }, { "epoch": 0.02, "learning_rate": 3.516303133658245e-05, "loss": 3.5962, "step": 906240 }, { "epoch": 0.02, "learning_rate": 3.515466176787566e-05, "loss": 3.5971, "step": 906752 }, { "epoch": 0.02, "learning_rate": 3.514627582036514e-05, "loss": 3.5706, "step": 907264 }, { "epoch": 0.02, "learning_rate": 3.513788987285462e-05, "loss": 3.6063, "step": 907776 }, { "epoch": 0.02, "learning_rate": 3.51295039253441e-05, "loss": 3.5962, "step": 908288 }, { "epoch": 0.02, "learning_rate": 3.512111797783358e-05, "loss": 3.6114, "step": 908800 }, { "epoch": 0.02, "learning_rate": 3.511274840912679e-05, "loss": 3.5962, "step": 909312 }, { "epoch": 0.02, "learning_rate": 3.510436246161628e-05, "loss": 3.5972, "step": 909824 }, { "epoch": 0.02, "learning_rate": 3.509597651410576e-05, "loss": 3.5991, "step": 910336 }, { "epoch": 0.02, "learning_rate": 3.508759056659524e-05, "loss": 3.6131, "step": 910848 }, { "epoch": 0.02, "learning_rate": 3.507920461908472e-05, "loss": 3.5867, "step": 911360 }, { "epoch": 0.02, "learning_rate": 3.507083505037793e-05, "loss": 3.5989, "step": 911872 }, { "epoch": 0.02, "learning_rate": 3.506244910286741e-05, "loss": 3.5942, "step": 912384 }, { "epoch": 0.02, "learning_rate": 3.505406315535689e-05, "loss": 3.5998, "step": 912896 }, { "epoch": 0.02, "learning_rate": 3.504567720784637e-05, "loss": 3.5976, "step": 913408 }, { "epoch": 0.02, "learning_rate": 3.5037307639139576e-05, "loss": 3.5978, "step": 913920 }, { "epoch": 0.02, "learning_rate": 3.5028921691629056e-05, "loss": 3.5953, "step": 914432 }, { "epoch": 0.02, "learning_rate": 3.5020535744118536e-05, "loss": 3.6039, "step": 914944 }, { "epoch": 0.02, "learning_rate": 3.5012149796608016e-05, "loss": 3.598, "step": 915456 }, { "epoch": 0.03, "eval_loss": 3.864187717437744, "eval_runtime": 306.8833, "eval_samples_per_second": 1243.44, "eval_steps_per_second": 38.858, "step": 915840 }, { "epoch": 0.0, "learning_rate": 3.5003763849097496e-05, "loss": 3.6003, "step": 915968 }, { "epoch": 0.0, "learning_rate": 3.4995377901586976e-05, "loss": 3.5928, "step": 916480 }, { "epoch": 0.0, "learning_rate": 3.4986991954076456e-05, "loss": 3.5912, "step": 916992 }, { "epoch": 0.0, "learning_rate": 3.4978606006565936e-05, "loss": 3.6002, "step": 917504 }, { "epoch": 0.0, "learning_rate": 3.4970220059055416e-05, "loss": 3.6014, "step": 918016 }, { "epoch": 0.0, "learning_rate": 3.496185049034863e-05, "loss": 3.5989, "step": 918528 }, { "epoch": 0.0, "learning_rate": 3.495346454283811e-05, "loss": 3.5959, "step": 919040 }, { "epoch": 0.0, "learning_rate": 3.4945078595327585e-05, "loss": 3.5857, "step": 919552 }, { "epoch": 0.0, "learning_rate": 3.4936692647817065e-05, "loss": 3.59, "step": 920064 }, { "epoch": 0.0, "learning_rate": 3.492832307911028e-05, "loss": 3.605, "step": 920576 }, { "epoch": 0.0, "learning_rate": 3.491993713159976e-05, "loss": 3.5936, "step": 921088 }, { "epoch": 0.0, "learning_rate": 3.4911551184089234e-05, "loss": 3.5912, "step": 921600 }, { "epoch": 0.0, "learning_rate": 3.490318161538245e-05, "loss": 3.6106, "step": 922112 }, { "epoch": 0.0, "learning_rate": 3.489479566787193e-05, "loss": 3.5852, "step": 922624 }, { "epoch": 0.0, "learning_rate": 3.488640972036141e-05, "loss": 3.5869, "step": 923136 }, { "epoch": 0.0, "learning_rate": 3.487802377285089e-05, "loss": 3.5833, "step": 923648 }, { "epoch": 0.0, "learning_rate": 3.486963782534037e-05, "loss": 3.5948, "step": 924160 }, { "epoch": 0.0, "learning_rate": 3.486125187782985e-05, "loss": 3.5855, "step": 924672 }, { "epoch": 0.0, "learning_rate": 3.485286593031933e-05, "loss": 3.5933, "step": 925184 }, { "epoch": 0.0, "learning_rate": 3.484447998280881e-05, "loss": 3.6003, "step": 925696 }, { "epoch": 0.0, "learning_rate": 3.483611041410202e-05, "loss": 3.5998, "step": 926208 }, { "epoch": 0.0, "learning_rate": 3.48277244665915e-05, "loss": 3.5971, "step": 926720 }, { "epoch": 0.0, "learning_rate": 3.481933851908098e-05, "loss": 3.5857, "step": 927232 }, { "epoch": 0.0, "learning_rate": 3.481095257157046e-05, "loss": 3.5917, "step": 927744 }, { "epoch": 0.0, "learning_rate": 3.480258300286367e-05, "loss": 3.599, "step": 928256 }, { "epoch": 0.0, "learning_rate": 3.479419705535315e-05, "loss": 3.5887, "step": 928768 }, { "epoch": 0.0, "learning_rate": 3.4785811107842634e-05, "loss": 3.5786, "step": 929280 }, { "epoch": 0.0, "learning_rate": 3.4777425160332114e-05, "loss": 3.5907, "step": 929792 }, { "epoch": 0.0, "learning_rate": 3.476905559162532e-05, "loss": 3.5933, "step": 930304 }, { "epoch": 0.0, "learning_rate": 3.47606696441148e-05, "loss": 3.5783, "step": 930816 }, { "epoch": 0.01, "learning_rate": 3.475228369660428e-05, "loss": 3.5885, "step": 931328 }, { "epoch": 0.01, "learning_rate": 3.474389774909376e-05, "loss": 3.5921, "step": 931840 }, { "epoch": 0.01, "learning_rate": 3.473551180158324e-05, "loss": 3.5946, "step": 932352 }, { "epoch": 0.01, "learning_rate": 3.472714223287645e-05, "loss": 3.598, "step": 932864 }, { "epoch": 0.01, "learning_rate": 3.471875628536593e-05, "loss": 3.592, "step": 933376 }, { "epoch": 0.01, "learning_rate": 3.471037033785541e-05, "loss": 3.5908, "step": 933888 }, { "epoch": 0.01, "learning_rate": 3.470198439034489e-05, "loss": 3.6045, "step": 934400 }, { "epoch": 0.01, "learning_rate": 3.46936148216381e-05, "loss": 3.5739, "step": 934912 }, { "epoch": 0.01, "learning_rate": 3.468522887412759e-05, "loss": 3.5808, "step": 935424 }, { "epoch": 0.01, "learning_rate": 3.467684292661707e-05, "loss": 3.5882, "step": 935936 }, { "epoch": 0.01, "learning_rate": 3.466845697910655e-05, "loss": 3.5787, "step": 936448 }, { "epoch": 0.01, "learning_rate": 3.466008741039976e-05, "loss": 3.5895, "step": 936960 }, { "epoch": 0.01, "learning_rate": 3.4651701462889237e-05, "loss": 3.5923, "step": 937472 }, { "epoch": 0.01, "learning_rate": 3.4643315515378717e-05, "loss": 3.589, "step": 937984 }, { "epoch": 0.01, "learning_rate": 3.4634929567868196e-05, "loss": 3.587, "step": 938496 }, { "epoch": 0.01, "learning_rate": 3.4626543620357676e-05, "loss": 3.5863, "step": 939008 }, { "epoch": 0.01, "learning_rate": 3.4618174051650886e-05, "loss": 3.5887, "step": 939520 }, { "epoch": 0.01, "learning_rate": 3.4609788104140365e-05, "loss": 3.5971, "step": 940032 }, { "epoch": 0.01, "learning_rate": 3.4601402156629845e-05, "loss": 3.5643, "step": 940544 }, { "epoch": 0.01, "learning_rate": 3.4593016209119325e-05, "loss": 3.5878, "step": 941056 }, { "epoch": 0.01, "learning_rate": 3.4584630261608805e-05, "loss": 3.5935, "step": 941568 }, { "epoch": 0.01, "learning_rate": 3.457626069290202e-05, "loss": 3.5967, "step": 942080 }, { "epoch": 0.01, "learning_rate": 3.45678747453915e-05, "loss": 3.5866, "step": 942592 }, { "epoch": 0.01, "learning_rate": 3.455948879788098e-05, "loss": 3.5798, "step": 943104 }, { "epoch": 0.01, "learning_rate": 3.455110285037046e-05, "loss": 3.5793, "step": 943616 }, { "epoch": 0.01, "learning_rate": 3.454273328166367e-05, "loss": 3.5775, "step": 944128 }, { "epoch": 0.01, "learning_rate": 3.453434733415315e-05, "loss": 3.5893, "step": 944640 }, { "epoch": 0.01, "learning_rate": 3.452596138664263e-05, "loss": 3.5773, "step": 945152 }, { "epoch": 0.01, "learning_rate": 3.451757543913211e-05, "loss": 3.5905, "step": 945664 }, { "epoch": 0.01, "learning_rate": 3.450918949162159e-05, "loss": 3.5811, "step": 946176 }, { "epoch": 0.01, "learning_rate": 3.45008199229148e-05, "loss": 3.5829, "step": 946688 }, { "epoch": 0.01, "learning_rate": 3.449243397540428e-05, "loss": 3.5787, "step": 947200 }, { "epoch": 0.01, "learning_rate": 3.448404802789376e-05, "loss": 3.5839, "step": 947712 }, { "epoch": 0.01, "learning_rate": 3.447566208038324e-05, "loss": 3.58, "step": 948224 }, { "epoch": 0.01, "learning_rate": 3.4467292511676455e-05, "loss": 3.5747, "step": 948736 }, { "epoch": 0.01, "learning_rate": 3.4458906564165935e-05, "loss": 3.5935, "step": 949248 }, { "epoch": 0.01, "learning_rate": 3.4450520616655415e-05, "loss": 3.5825, "step": 949760 }, { "epoch": 0.01, "learning_rate": 3.4442134669144895e-05, "loss": 3.5759, "step": 950272 }, { "epoch": 0.01, "learning_rate": 3.443374872163437e-05, "loss": 3.5671, "step": 950784 }, { "epoch": 0.01, "learning_rate": 3.4425379152927584e-05, "loss": 3.5854, "step": 951296 }, { "epoch": 0.01, "learning_rate": 3.4416993205417064e-05, "loss": 3.5835, "step": 951808 }, { "epoch": 0.01, "learning_rate": 3.440860725790654e-05, "loss": 3.592, "step": 952320 }, { "epoch": 0.01, "learning_rate": 3.440022131039602e-05, "loss": 3.5817, "step": 952832 }, { "epoch": 0.01, "learning_rate": 3.43918353628855e-05, "loss": 3.5887, "step": 953344 }, { "epoch": 0.01, "learning_rate": 3.438346579417871e-05, "loss": 3.5969, "step": 953856 }, { "epoch": 0.01, "learning_rate": 3.437507984666819e-05, "loss": 3.5841, "step": 954368 }, { "epoch": 0.01, "learning_rate": 3.436669389915767e-05, "loss": 3.5928, "step": 954880 }, { "epoch": 0.01, "learning_rate": 3.435830795164715e-05, "loss": 3.5822, "step": 955392 }, { "epoch": 0.01, "learning_rate": 3.434993838294037e-05, "loss": 3.5802, "step": 955904 }, { "epoch": 0.01, "learning_rate": 3.434155243542984e-05, "loss": 3.5861, "step": 956416 }, { "epoch": 0.01, "learning_rate": 3.433316648791932e-05, "loss": 3.5816, "step": 956928 }, { "epoch": 0.01, "learning_rate": 3.43247805404088e-05, "loss": 3.5835, "step": 957440 }, { "epoch": 0.01, "learning_rate": 3.431641097170201e-05, "loss": 3.5996, "step": 957952 }, { "epoch": 0.01, "learning_rate": 3.430802502419149e-05, "loss": 3.5818, "step": 958464 }, { "epoch": 0.01, "learning_rate": 3.429963907668097e-05, "loss": 3.5704, "step": 958976 }, { "epoch": 0.01, "learning_rate": 3.429125312917045e-05, "loss": 3.5773, "step": 959488 }, { "epoch": 0.01, "learning_rate": 3.4282883560463666e-05, "loss": 3.583, "step": 960000 }, { "epoch": 0.01, "learning_rate": 3.4274497612953146e-05, "loss": 3.5864, "step": 960512 }, { "epoch": 0.01, "learning_rate": 3.4266111665442626e-05, "loss": 3.5816, "step": 961024 }, { "epoch": 0.01, "learning_rate": 3.4257725717932106e-05, "loss": 3.5861, "step": 961536 }, { "epoch": 0.02, "learning_rate": 3.4249339770421586e-05, "loss": 3.5849, "step": 962048 }, { "epoch": 0.02, "learning_rate": 3.4240970201714795e-05, "loss": 3.5739, "step": 962560 }, { "epoch": 0.02, "learning_rate": 3.4232584254204275e-05, "loss": 3.5674, "step": 963072 }, { "epoch": 0.02, "learning_rate": 3.4224198306693755e-05, "loss": 3.5788, "step": 963584 }, { "epoch": 0.02, "learning_rate": 3.4215812359183235e-05, "loss": 3.5824, "step": 964096 }, { "epoch": 0.02, "learning_rate": 3.4207426411672715e-05, "loss": 3.5969, "step": 964608 }, { "epoch": 0.02, "learning_rate": 3.4199056842965924e-05, "loss": 3.569, "step": 965120 }, { "epoch": 0.02, "learning_rate": 3.4190670895455404e-05, "loss": 3.5771, "step": 965632 }, { "epoch": 0.02, "learning_rate": 3.4182284947944884e-05, "loss": 3.5827, "step": 966144 }, { "epoch": 0.02, "learning_rate": 3.4173899000434364e-05, "loss": 3.5819, "step": 966656 }, { "epoch": 0.02, "learning_rate": 3.416552943172758e-05, "loss": 3.5889, "step": 967168 }, { "epoch": 0.02, "learning_rate": 3.415714348421706e-05, "loss": 3.5814, "step": 967680 }, { "epoch": 0.02, "learning_rate": 3.414875753670654e-05, "loss": 3.58, "step": 968192 }, { "epoch": 0.02, "learning_rate": 3.414037158919602e-05, "loss": 3.5819, "step": 968704 }, { "epoch": 0.02, "learning_rate": 3.413200202048923e-05, "loss": 3.5775, "step": 969216 }, { "epoch": 0.02, "learning_rate": 3.412361607297871e-05, "loss": 3.5754, "step": 969728 }, { "epoch": 0.02, "learning_rate": 3.411523012546819e-05, "loss": 3.5824, "step": 970240 }, { "epoch": 0.02, "learning_rate": 3.410684417795767e-05, "loss": 3.5851, "step": 970752 }, { "epoch": 0.02, "learning_rate": 3.409847460925088e-05, "loss": 3.5765, "step": 971264 }, { "epoch": 0.02, "learning_rate": 3.409008866174036e-05, "loss": 3.5733, "step": 971776 }, { "epoch": 0.02, "learning_rate": 3.408170271422984e-05, "loss": 3.5728, "step": 972288 }, { "epoch": 0.02, "learning_rate": 3.407331676671932e-05, "loss": 3.5804, "step": 972800 }, { "epoch": 0.02, "learning_rate": 3.4064947198012534e-05, "loss": 3.58, "step": 973312 }, { "epoch": 0.02, "learning_rate": 3.4056561250502014e-05, "loss": 3.5816, "step": 973824 }, { "epoch": 0.02, "learning_rate": 3.4048175302991494e-05, "loss": 3.5786, "step": 974336 }, { "epoch": 0.02, "learning_rate": 3.4039789355480973e-05, "loss": 3.585, "step": 974848 }, { "epoch": 0.02, "learning_rate": 3.403141978677418e-05, "loss": 3.5905, "step": 975360 }, { "epoch": 0.02, "learning_rate": 3.402303383926366e-05, "loss": 3.5824, "step": 975872 }, { "epoch": 0.02, "learning_rate": 3.401464789175314e-05, "loss": 3.5852, "step": 976384 }, { "epoch": 0.02, "learning_rate": 3.400626194424262e-05, "loss": 3.5834, "step": 976896 }, { "epoch": 0.02, "learning_rate": 3.399789237553583e-05, "loss": 3.5762, "step": 977408 }, { "epoch": 0.02, "learning_rate": 3.398950642802531e-05, "loss": 3.5727, "step": 977920 }, { "epoch": 0.02, "learning_rate": 3.398112048051479e-05, "loss": 3.574, "step": 978432 }, { "epoch": 0.02, "learning_rate": 3.397273453300427e-05, "loss": 3.5804, "step": 978944 }, { "epoch": 0.02, "learning_rate": 3.396436496429749e-05, "loss": 3.5815, "step": 979456 }, { "epoch": 0.02, "learning_rate": 3.395597901678697e-05, "loss": 3.5808, "step": 979968 }, { "epoch": 0.02, "learning_rate": 3.394759306927645e-05, "loss": 3.5812, "step": 980480 }, { "epoch": 0.02, "learning_rate": 3.393920712176593e-05, "loss": 3.5808, "step": 980992 }, { "epoch": 0.02, "learning_rate": 3.393082117425541e-05, "loss": 3.5763, "step": 981504 }, { "epoch": 0.02, "learning_rate": 3.3922451605548616e-05, "loss": 3.5847, "step": 982016 }, { "epoch": 0.02, "learning_rate": 3.3914065658038096e-05, "loss": 3.577, "step": 982528 }, { "epoch": 0.02, "learning_rate": 3.3905679710527576e-05, "loss": 3.5812, "step": 983040 }, { "epoch": 0.02, "learning_rate": 3.3897293763017056e-05, "loss": 3.5542, "step": 983552 }, { "epoch": 0.02, "learning_rate": 3.3888924194310265e-05, "loss": 3.5829, "step": 984064 }, { "epoch": 0.02, "learning_rate": 3.3880538246799745e-05, "loss": 3.5823, "step": 984576 }, { "epoch": 0.02, "learning_rate": 3.3872152299289225e-05, "loss": 3.5896, "step": 985088 }, { "epoch": 0.02, "learning_rate": 3.386376635177871e-05, "loss": 3.5798, "step": 985600 }, { "epoch": 0.02, "learning_rate": 3.385538040426819e-05, "loss": 3.5708, "step": 986112 }, { "epoch": 0.02, "learning_rate": 3.38470108355614e-05, "loss": 3.5824, "step": 986624 }, { "epoch": 0.02, "learning_rate": 3.383862488805088e-05, "loss": 3.5964, "step": 987136 }, { "epoch": 0.02, "learning_rate": 3.383023894054036e-05, "loss": 3.569, "step": 987648 }, { "epoch": 0.02, "learning_rate": 3.382186937183357e-05, "loss": 3.5827, "step": 988160 }, { "epoch": 0.02, "learning_rate": 3.381348342432305e-05, "loss": 3.5771, "step": 988672 }, { "epoch": 0.02, "learning_rate": 3.380509747681253e-05, "loss": 3.5816, "step": 989184 }, { "epoch": 0.02, "learning_rate": 3.379671152930201e-05, "loss": 3.5803, "step": 989696 }, { "epoch": 0.02, "learning_rate": 3.378832558179149e-05, "loss": 3.5795, "step": 990208 }, { "epoch": 0.02, "learning_rate": 3.37799560130847e-05, "loss": 3.5798, "step": 990720 }, { "epoch": 0.02, "learning_rate": 3.377157006557418e-05, "loss": 3.5838, "step": 991232 }, { "epoch": 0.02, "learning_rate": 3.3763184118063665e-05, "loss": 3.583, "step": 991744 }, { "epoch": 0.03, "eval_loss": 3.863978147506714, "eval_runtime": 307.2769, "eval_samples_per_second": 1241.847, "eval_steps_per_second": 38.809, "step": 992160 }, { "epoch": 1.0, "learning_rate": 3.3754798170553145e-05, "loss": 3.5692, "step": 992256 }, { "epoch": 1.0, "learning_rate": 3.374641222304262e-05, "loss": 3.5777, "step": 992768 }, { "epoch": 1.0, "learning_rate": 3.3738042654335834e-05, "loss": 3.5711, "step": 993280 }, { "epoch": 1.0, "learning_rate": 3.3729656706825314e-05, "loss": 3.5849, "step": 993792 }, { "epoch": 1.0, "learning_rate": 3.3721270759314794e-05, "loss": 3.584, "step": 994304 }, { "epoch": 1.0, "learning_rate": 3.371288481180427e-05, "loss": 3.5774, "step": 994816 }, { "epoch": 1.0, "learning_rate": 3.3704515243097483e-05, "loss": 3.5775, "step": 995328 }, { "epoch": 1.0, "learning_rate": 3.3696129295586963e-05, "loss": 3.5662, "step": 995840 }, { "epoch": 1.0, "learning_rate": 3.368774334807644e-05, "loss": 3.573, "step": 996352 }, { "epoch": 1.0, "learning_rate": 3.3679357400565917e-05, "loss": 3.585, "step": 996864 }, { "epoch": 1.0, "learning_rate": 3.367098783185913e-05, "loss": 3.5756, "step": 997376 }, { "epoch": 1.0, "learning_rate": 3.366260188434861e-05, "loss": 3.5773, "step": 997888 }, { "epoch": 1.0, "learning_rate": 3.365423231564183e-05, "loss": 3.5891, "step": 998400 }, { "epoch": 1.0, "learning_rate": 3.364584636813131e-05, "loss": 3.5685, "step": 998912 }, { "epoch": 1.0, "learning_rate": 3.363746042062079e-05, "loss": 3.5677, "step": 999424 }, { "epoch": 1.0, "learning_rate": 3.362907447311027e-05, "loss": 3.5655, "step": 999936 }, { "epoch": 1.0, "learning_rate": 3.362068852559974e-05, "loss": 3.5789, "step": 1000448 }, { "epoch": 1.0, "learning_rate": 3.361230257808922e-05, "loss": 3.5683, "step": 1000960 }, { "epoch": 1.0, "learning_rate": 3.36039166305787e-05, "loss": 3.5734, "step": 1001472 }, { "epoch": 1.0, "learning_rate": 3.359553068306818e-05, "loss": 3.5817, "step": 1001984 }, { "epoch": 1.0, "learning_rate": 3.358716111436139e-05, "loss": 3.5854, "step": 1002496 }, { "epoch": 1.0, "learning_rate": 3.357877516685087e-05, "loss": 3.5791, "step": 1003008 }, { "epoch": 1.0, "learning_rate": 3.357038921934035e-05, "loss": 3.5719, "step": 1003520 }, { "epoch": 1.0, "learning_rate": 3.356200327182984e-05, "loss": 3.5731, "step": 1004032 }, { "epoch": 1.0, "learning_rate": 3.3553633703123046e-05, "loss": 3.5832, "step": 1004544 }, { "epoch": 1.0, "learning_rate": 3.3545247755612526e-05, "loss": 3.571, "step": 1005056 }, { "epoch": 1.0, "learning_rate": 3.3536861808102006e-05, "loss": 3.5623, "step": 1005568 }, { "epoch": 1.0, "learning_rate": 3.3528475860591486e-05, "loss": 3.5757, "step": 1006080 }, { "epoch": 1.0, "learning_rate": 3.3520106291884695e-05, "loss": 3.5695, "step": 1006592 }, { "epoch": 1.0, "learning_rate": 3.3511720344374175e-05, "loss": 3.5636, "step": 1007104 }, { "epoch": 1.01, "learning_rate": 3.3503334396863655e-05, "loss": 3.5699, "step": 1007616 }, { "epoch": 1.01, "learning_rate": 3.3494948449353135e-05, "loss": 3.5741, "step": 1008128 }, { "epoch": 1.01, "learning_rate": 3.3486578880646344e-05, "loss": 3.5759, "step": 1008640 }, { "epoch": 1.01, "learning_rate": 3.3478192933135824e-05, "loss": 3.5805, "step": 1009152 }, { "epoch": 1.01, "learning_rate": 3.3469806985625304e-05, "loss": 3.5759, "step": 1009664 }, { "epoch": 1.01, "learning_rate": 3.346142103811479e-05, "loss": 3.5742, "step": 1010176 }, { "epoch": 1.01, "learning_rate": 3.3453051469408e-05, "loss": 3.5858, "step": 1010688 }, { "epoch": 1.01, "learning_rate": 3.344466552189748e-05, "loss": 3.5583, "step": 1011200 }, { "epoch": 1.01, "learning_rate": 3.343627957438696e-05, "loss": 3.5647, "step": 1011712 }, { "epoch": 1.01, "learning_rate": 3.342789362687644e-05, "loss": 3.5698, "step": 1012224 }, { "epoch": 1.01, "learning_rate": 3.341950767936592e-05, "loss": 3.5565, "step": 1012736 }, { "epoch": 1.01, "learning_rate": 3.341113811065913e-05, "loss": 3.5732, "step": 1013248 }, { "epoch": 1.01, "learning_rate": 3.340275216314861e-05, "loss": 3.5767, "step": 1013760 }, { "epoch": 1.01, "learning_rate": 3.339436621563809e-05, "loss": 3.5739, "step": 1014272 }, { "epoch": 1.01, "learning_rate": 3.338598026812757e-05, "loss": 3.5676, "step": 1014784 }, { "epoch": 1.01, "learning_rate": 3.337761069942078e-05, "loss": 3.5711, "step": 1015296 }, { "epoch": 1.01, "learning_rate": 3.336922475191026e-05, "loss": 3.5711, "step": 1015808 }, { "epoch": 1.01, "learning_rate": 3.3360838804399744e-05, "loss": 3.5807, "step": 1016320 }, { "epoch": 1.01, "learning_rate": 3.3352452856889224e-05, "loss": 3.5486, "step": 1016832 }, { "epoch": 1.01, "learning_rate": 3.334408328818243e-05, "loss": 3.5661, "step": 1017344 }, { "epoch": 1.01, "learning_rate": 3.333569734067191e-05, "loss": 3.5807, "step": 1017856 }, { "epoch": 1.01, "learning_rate": 3.332731139316139e-05, "loss": 3.5795, "step": 1018368 }, { "epoch": 1.01, "learning_rate": 3.331892544565087e-05, "loss": 3.5695, "step": 1018880 }, { "epoch": 1.01, "learning_rate": 3.331055587694408e-05, "loss": 3.5587, "step": 1019392 }, { "epoch": 1.01, "learning_rate": 3.330216992943356e-05, "loss": 3.5636, "step": 1019904 }, { "epoch": 1.01, "learning_rate": 3.329378398192304e-05, "loss": 3.5601, "step": 1020416 }, { "epoch": 1.01, "learning_rate": 3.328539803441252e-05, "loss": 3.5737, "step": 1020928 }, { "epoch": 1.01, "learning_rate": 3.3277012086902e-05, "loss": 3.5604, "step": 1021440 }, { "epoch": 1.01, "learning_rate": 3.326864251819521e-05, "loss": 3.5699, "step": 1021952 }, { "epoch": 1.01, "learning_rate": 3.32602565706847e-05, "loss": 3.5656, "step": 1022464 }, { "epoch": 1.01, "learning_rate": 3.325187062317418e-05, "loss": 3.5678, "step": 1022976 }, { "epoch": 1.01, "learning_rate": 3.324348467566366e-05, "loss": 3.5608, "step": 1023488 }, { "epoch": 1.01, "learning_rate": 3.323509872815314e-05, "loss": 3.5687, "step": 1024000 }, { "epoch": 1.01, "learning_rate": 3.322672915944635e-05, "loss": 3.5582, "step": 1024512 }, { "epoch": 1.01, "learning_rate": 3.321834321193583e-05, "loss": 3.555, "step": 1025024 }, { "epoch": 1.01, "learning_rate": 3.320995726442531e-05, "loss": 3.5744, "step": 1025536 }, { "epoch": 1.01, "learning_rate": 3.320157131691479e-05, "loss": 3.5677, "step": 1026048 }, { "epoch": 1.01, "learning_rate": 3.3193201748207996e-05, "loss": 3.5577, "step": 1026560 }, { "epoch": 1.01, "learning_rate": 3.3184815800697476e-05, "loss": 3.5522, "step": 1027072 }, { "epoch": 1.01, "learning_rate": 3.3176429853186956e-05, "loss": 3.5661, "step": 1027584 }, { "epoch": 1.01, "learning_rate": 3.3168043905676436e-05, "loss": 3.5675, "step": 1028096 }, { "epoch": 1.01, "learning_rate": 3.315967433696965e-05, "loss": 3.5783, "step": 1028608 }, { "epoch": 1.01, "learning_rate": 3.315128838945913e-05, "loss": 3.5631, "step": 1029120 }, { "epoch": 1.01, "learning_rate": 3.314290244194861e-05, "loss": 3.5711, "step": 1029632 }, { "epoch": 1.01, "learning_rate": 3.313451649443809e-05, "loss": 3.5793, "step": 1030144 }, { "epoch": 1.01, "learning_rate": 3.31261469257313e-05, "loss": 3.5615, "step": 1030656 }, { "epoch": 1.01, "learning_rate": 3.311776097822078e-05, "loss": 3.5701, "step": 1031168 }, { "epoch": 1.01, "learning_rate": 3.310937503071026e-05, "loss": 3.5694, "step": 1031680 }, { "epoch": 1.01, "learning_rate": 3.310098908319974e-05, "loss": 3.5669, "step": 1032192 }, { "epoch": 1.01, "learning_rate": 3.309261951449295e-05, "loss": 3.5645, "step": 1032704 }, { "epoch": 1.01, "learning_rate": 3.308423356698243e-05, "loss": 3.5649, "step": 1033216 }, { "epoch": 1.01, "learning_rate": 3.307584761947191e-05, "loss": 3.5688, "step": 1033728 }, { "epoch": 1.01, "learning_rate": 3.306746167196139e-05, "loss": 3.581, "step": 1034240 }, { "epoch": 1.01, "learning_rate": 3.305907572445087e-05, "loss": 3.5634, "step": 1034752 }, { "epoch": 1.01, "learning_rate": 3.3050706155744085e-05, "loss": 3.5509, "step": 1035264 }, { "epoch": 1.01, "learning_rate": 3.3042320208233565e-05, "loss": 3.56, "step": 1035776 }, { "epoch": 1.01, "learning_rate": 3.3033934260723045e-05, "loss": 3.5669, "step": 1036288 }, { "epoch": 1.01, "learning_rate": 3.3025548313212525e-05, "loss": 3.5685, "step": 1036800 }, { "epoch": 1.01, "learning_rate": 3.3017178744505734e-05, "loss": 3.5674, "step": 1037312 }, { "epoch": 1.01, "learning_rate": 3.3008792796995214e-05, "loss": 3.5669, "step": 1037824 }, { "epoch": 1.02, "learning_rate": 3.3000406849484694e-05, "loss": 3.5709, "step": 1038336 }, { "epoch": 1.02, "learning_rate": 3.299202090197417e-05, "loss": 3.5548, "step": 1038848 }, { "epoch": 1.02, "learning_rate": 3.298365133326738e-05, "loss": 3.5531, "step": 1039360 }, { "epoch": 1.02, "learning_rate": 3.297526538575686e-05, "loss": 3.5604, "step": 1039872 }, { "epoch": 1.02, "learning_rate": 3.296687943824634e-05, "loss": 3.5605, "step": 1040384 }, { "epoch": 1.02, "learning_rate": 3.295849349073582e-05, "loss": 3.5749, "step": 1040896 }, { "epoch": 1.02, "learning_rate": 3.295012392202904e-05, "loss": 3.5602, "step": 1041408 }, { "epoch": 1.02, "learning_rate": 3.294173797451852e-05, "loss": 3.5577, "step": 1041920 }, { "epoch": 1.02, "learning_rate": 3.2933352027008e-05, "loss": 3.5675, "step": 1042432 }, { "epoch": 1.02, "learning_rate": 3.292496607949747e-05, "loss": 3.5633, "step": 1042944 }, { "epoch": 1.02, "learning_rate": 3.291659651079069e-05, "loss": 3.5708, "step": 1043456 }, { "epoch": 1.02, "learning_rate": 3.290821056328017e-05, "loss": 3.5694, "step": 1043968 }, { "epoch": 1.02, "learning_rate": 3.289982461576964e-05, "loss": 3.5622, "step": 1044480 }, { "epoch": 1.02, "learning_rate": 3.289143866825912e-05, "loss": 3.5635, "step": 1044992 }, { "epoch": 1.02, "learning_rate": 3.288306909955234e-05, "loss": 3.5673, "step": 1045504 }, { "epoch": 1.02, "learning_rate": 3.287468315204182e-05, "loss": 3.5559, "step": 1046016 }, { "epoch": 1.02, "learning_rate": 3.28662972045313e-05, "loss": 3.5628, "step": 1046528 }, { "epoch": 1.02, "learning_rate": 3.285791125702078e-05, "loss": 3.5687, "step": 1047040 }, { "epoch": 1.02, "learning_rate": 3.284954168831399e-05, "loss": 3.5602, "step": 1047552 }, { "epoch": 1.02, "learning_rate": 3.284115574080347e-05, "loss": 3.5558, "step": 1048064 }, { "epoch": 1.02, "learning_rate": 3.2832769793292946e-05, "loss": 3.5568, "step": 1048576 }, { "epoch": 1.02, "learning_rate": 3.2824383845782426e-05, "loss": 3.5615, "step": 1049088 }, { "epoch": 1.02, "learning_rate": 3.281601427707564e-05, "loss": 3.5653, "step": 1049600 }, { "epoch": 1.02, "learning_rate": 3.2807628329565115e-05, "loss": 3.5637, "step": 1050112 }, { "epoch": 1.02, "learning_rate": 3.2799242382054595e-05, "loss": 3.5583, "step": 1050624 }, { "epoch": 1.02, "learning_rate": 3.2790856434544075e-05, "loss": 3.5703, "step": 1051136 }, { "epoch": 1.02, "learning_rate": 3.278248686583729e-05, "loss": 3.5718, "step": 1051648 }, { "epoch": 1.02, "learning_rate": 3.2774100918326764e-05, "loss": 3.5682, "step": 1052160 }, { "epoch": 1.02, "learning_rate": 3.276571497081625e-05, "loss": 3.5701, "step": 1052672 }, { "epoch": 1.02, "learning_rate": 3.275732902330573e-05, "loss": 3.5654, "step": 1053184 }, { "epoch": 1.02, "learning_rate": 3.2748959454598946e-05, "loss": 3.5594, "step": 1053696 }, { "epoch": 1.02, "learning_rate": 3.274057350708842e-05, "loss": 3.5548, "step": 1054208 }, { "epoch": 1.02, "learning_rate": 3.27321875595779e-05, "loss": 3.5607, "step": 1054720 }, { "epoch": 1.02, "learning_rate": 3.272380161206738e-05, "loss": 3.5569, "step": 1055232 }, { "epoch": 1.02, "learning_rate": 3.271543204336059e-05, "loss": 3.5665, "step": 1055744 }, { "epoch": 1.02, "learning_rate": 3.270704609585007e-05, "loss": 3.5677, "step": 1056256 }, { "epoch": 1.02, "learning_rate": 3.269866014833955e-05, "loss": 3.5673, "step": 1056768 }, { "epoch": 1.02, "learning_rate": 3.269027420082903e-05, "loss": 3.5615, "step": 1057280 }, { "epoch": 1.02, "learning_rate": 3.268190463212224e-05, "loss": 3.5574, "step": 1057792 }, { "epoch": 1.02, "learning_rate": 3.267351868461172e-05, "loss": 3.5677, "step": 1058304 }, { "epoch": 1.02, "learning_rate": 3.26651327371012e-05, "loss": 3.5619, "step": 1058816 }, { "epoch": 1.02, "learning_rate": 3.2656746789590684e-05, "loss": 3.5643, "step": 1059328 }, { "epoch": 1.02, "learning_rate": 3.2648360842080164e-05, "loss": 3.5376, "step": 1059840 }, { "epoch": 1.02, "learning_rate": 3.263999127337337e-05, "loss": 3.564, "step": 1060352 }, { "epoch": 1.02, "learning_rate": 3.263160532586285e-05, "loss": 3.5664, "step": 1060864 }, { "epoch": 1.02, "learning_rate": 3.262321937835233e-05, "loss": 3.5723, "step": 1061376 }, { "epoch": 1.02, "learning_rate": 3.261483343084181e-05, "loss": 3.5629, "step": 1061888 }, { "epoch": 1.02, "learning_rate": 3.260644748333129e-05, "loss": 3.5561, "step": 1062400 }, { "epoch": 1.02, "learning_rate": 3.25980779146245e-05, "loss": 3.5627, "step": 1062912 }, { "epoch": 1.02, "learning_rate": 3.258969196711398e-05, "loss": 3.5822, "step": 1063424 }, { "epoch": 1.02, "learning_rate": 3.258130601960346e-05, "loss": 3.5546, "step": 1063936 }, { "epoch": 1.02, "learning_rate": 3.257292007209294e-05, "loss": 3.5661, "step": 1064448 }, { "epoch": 1.02, "learning_rate": 3.256455050338615e-05, "loss": 3.5625, "step": 1064960 }, { "epoch": 1.02, "learning_rate": 3.255616455587564e-05, "loss": 3.5638, "step": 1065472 }, { "epoch": 1.02, "learning_rate": 3.254777860836512e-05, "loss": 3.5642, "step": 1065984 }, { "epoch": 1.02, "learning_rate": 3.25393926608546e-05, "loss": 3.5655, "step": 1066496 }, { "epoch": 1.02, "learning_rate": 3.253102309214781e-05, "loss": 3.5579, "step": 1067008 }, { "epoch": 1.02, "learning_rate": 3.2522637144637287e-05, "loss": 3.5711, "step": 1067520 }, { "epoch": 1.02, "learning_rate": 3.2514251197126767e-05, "loss": 3.5621, "step": 1068032 }, { "epoch": 1.03, "eval_loss": 3.8648340702056885, "eval_runtime": 307.9383, "eval_samples_per_second": 1239.18, "eval_steps_per_second": 38.725, "step": 1068480 }, { "epoch": 0.0, "learning_rate": 3.2505865249616247e-05, "loss": 3.5563, "step": 1068544 }, { "epoch": 0.0, "learning_rate": 3.2497479302105726e-05, "loss": 3.562, "step": 1069056 }, { "epoch": 0.0, "learning_rate": 3.2489093354595206e-05, "loss": 3.5544, "step": 1069568 }, { "epoch": 0.0, "learning_rate": 3.2480707407084686e-05, "loss": 3.5686, "step": 1070080 }, { "epoch": 0.0, "learning_rate": 3.2472337838377895e-05, "loss": 3.5663, "step": 1070592 }, { "epoch": 0.0, "learning_rate": 3.2463951890867375e-05, "loss": 3.5659, "step": 1071104 }, { "epoch": 0.0, "learning_rate": 3.2455565943356855e-05, "loss": 3.5569, "step": 1071616 }, { "epoch": 0.0, "learning_rate": 3.2447179995846335e-05, "loss": 3.551, "step": 1072128 }, { "epoch": 0.0, "learning_rate": 3.243881042713955e-05, "loss": 3.5568, "step": 1072640 }, { "epoch": 0.0, "learning_rate": 3.243042447962903e-05, "loss": 3.5711, "step": 1073152 }, { "epoch": 0.0, "learning_rate": 3.242203853211851e-05, "loss": 3.5592, "step": 1073664 }, { "epoch": 0.0, "learning_rate": 3.241365258460799e-05, "loss": 3.56, "step": 1074176 }, { "epoch": 0.0, "learning_rate": 3.240529939470493e-05, "loss": 3.5736, "step": 1074688 }, { "epoch": 0.0, "learning_rate": 3.239691344719441e-05, "loss": 3.5552, "step": 1075200 }, { "epoch": 0.0, "learning_rate": 3.238852749968389e-05, "loss": 3.5514, "step": 1075712 }, { "epoch": 0.0, "learning_rate": 3.238014155217337e-05, "loss": 3.5475, "step": 1076224 }, { "epoch": 0.0, "learning_rate": 3.237175560466285e-05, "loss": 3.56, "step": 1076736 }, { "epoch": 0.0, "learning_rate": 3.236336965715233e-05, "loss": 3.5539, "step": 1077248 }, { "epoch": 0.0, "learning_rate": 3.235498370964181e-05, "loss": 3.5567, "step": 1077760 }, { "epoch": 0.0, "learning_rate": 3.234659776213129e-05, "loss": 3.5633, "step": 1078272 }, { "epoch": 0.0, "learning_rate": 3.2338228193424505e-05, "loss": 3.5742, "step": 1078784 }, { "epoch": 0.0, "learning_rate": 3.2329842245913985e-05, "loss": 3.5605, "step": 1079296 }, { "epoch": 0.0, "learning_rate": 3.2321456298403465e-05, "loss": 3.5547, "step": 1079808 }, { "epoch": 0.0, "learning_rate": 3.2313070350892945e-05, "loss": 3.5582, "step": 1080320 }, { "epoch": 0.0, "learning_rate": 3.2304700782186154e-05, "loss": 3.56, "step": 1080832 }, { "epoch": 0.0, "learning_rate": 3.2296314834675634e-05, "loss": 3.5587, "step": 1081344 }, { "epoch": 0.0, "learning_rate": 3.2287928887165114e-05, "loss": 3.5459, "step": 1081856 }, { "epoch": 0.0, "learning_rate": 3.2279542939654594e-05, "loss": 3.5575, "step": 1082368 }, { "epoch": 0.0, "learning_rate": 3.22711733709478e-05, "loss": 3.554, "step": 1082880 }, { "epoch": 0.0, "learning_rate": 3.226278742343728e-05, "loss": 3.5485, "step": 1083392 }, { "epoch": 0.01, "learning_rate": 3.225440147592676e-05, "loss": 3.5508, "step": 1083904 }, { "epoch": 0.01, "learning_rate": 3.224601552841624e-05, "loss": 3.5619, "step": 1084416 }, { "epoch": 0.01, "learning_rate": 3.223762958090572e-05, "loss": 3.5555, "step": 1084928 }, { "epoch": 0.01, "learning_rate": 3.222926001219894e-05, "loss": 3.5666, "step": 1085440 }, { "epoch": 0.01, "learning_rate": 3.222087406468842e-05, "loss": 3.5587, "step": 1085952 }, { "epoch": 0.01, "learning_rate": 3.22124881171779e-05, "loss": 3.5562, "step": 1086464 }, { "epoch": 0.01, "learning_rate": 3.220410216966737e-05, "loss": 3.5652, "step": 1086976 }, { "epoch": 0.01, "learning_rate": 3.219573260096059e-05, "loss": 3.5448, "step": 1087488 }, { "epoch": 0.01, "learning_rate": 3.218734665345007e-05, "loss": 3.5537, "step": 1088000 }, { "epoch": 0.01, "learning_rate": 3.217896070593955e-05, "loss": 3.5498, "step": 1088512 }, { "epoch": 0.01, "learning_rate": 3.217057475842902e-05, "loss": 3.5417, "step": 1089024 }, { "epoch": 0.01, "learning_rate": 3.2162205189722236e-05, "loss": 3.5569, "step": 1089536 }, { "epoch": 0.01, "learning_rate": 3.2153819242211716e-05, "loss": 3.5597, "step": 1090048 }, { "epoch": 0.01, "learning_rate": 3.2145433294701196e-05, "loss": 3.5524, "step": 1090560 }, { "epoch": 0.01, "learning_rate": 3.2137047347190676e-05, "loss": 3.5532, "step": 1091072 }, { "epoch": 0.01, "learning_rate": 3.212867777848389e-05, "loss": 3.5537, "step": 1091584 }, { "epoch": 0.01, "learning_rate": 3.212029183097337e-05, "loss": 3.558, "step": 1092096 }, { "epoch": 0.01, "learning_rate": 3.2111905883462845e-05, "loss": 3.5591, "step": 1092608 }, { "epoch": 0.01, "learning_rate": 3.2103519935952325e-05, "loss": 3.5374, "step": 1093120 }, { "epoch": 0.01, "learning_rate": 3.209515036724554e-05, "loss": 3.5507, "step": 1093632 }, { "epoch": 0.01, "learning_rate": 3.208676441973502e-05, "loss": 3.5622, "step": 1094144 }, { "epoch": 0.01, "learning_rate": 3.2078378472224494e-05, "loss": 3.5616, "step": 1094656 }, { "epoch": 0.01, "learning_rate": 3.2069992524713974e-05, "loss": 3.5531, "step": 1095168 }, { "epoch": 0.01, "learning_rate": 3.206162295600719e-05, "loss": 3.5432, "step": 1095680 }, { "epoch": 0.01, "learning_rate": 3.205323700849667e-05, "loss": 3.5485, "step": 1096192 }, { "epoch": 0.01, "learning_rate": 3.204485106098615e-05, "loss": 3.5464, "step": 1096704 }, { "epoch": 0.01, "learning_rate": 3.203646511347563e-05, "loss": 3.5523, "step": 1097216 }, { "epoch": 0.01, "learning_rate": 3.2028095544768846e-05, "loss": 3.5452, "step": 1097728 }, { "epoch": 0.01, "learning_rate": 3.201970959725832e-05, "loss": 3.5559, "step": 1098240 }, { "epoch": 0.01, "learning_rate": 3.20113236497478e-05, "loss": 3.5538, "step": 1098752 }, { "epoch": 0.01, "learning_rate": 3.200293770223728e-05, "loss": 3.547, "step": 1099264 }, { "epoch": 0.01, "learning_rate": 3.1994568133530495e-05, "loss": 3.5413, "step": 1099776 }, { "epoch": 0.01, "learning_rate": 3.198618218601997e-05, "loss": 3.5544, "step": 1100288 }, { "epoch": 0.01, "learning_rate": 3.197779623850945e-05, "loss": 3.5409, "step": 1100800 }, { "epoch": 0.01, "learning_rate": 3.196941029099893e-05, "loss": 3.5415, "step": 1101312 }, { "epoch": 0.01, "learning_rate": 3.1961040722292144e-05, "loss": 3.5564, "step": 1101824 }, { "epoch": 0.01, "learning_rate": 3.1952654774781624e-05, "loss": 3.5522, "step": 1102336 }, { "epoch": 0.01, "learning_rate": 3.1944268827271104e-05, "loss": 3.5428, "step": 1102848 }, { "epoch": 0.01, "learning_rate": 3.1935882879760584e-05, "loss": 3.5346, "step": 1103360 }, { "epoch": 0.01, "learning_rate": 3.192751331105379e-05, "loss": 3.5518, "step": 1103872 }, { "epoch": 0.01, "learning_rate": 3.191912736354327e-05, "loss": 3.551, "step": 1104384 }, { "epoch": 0.01, "learning_rate": 3.191074141603275e-05, "loss": 3.559, "step": 1104896 }, { "epoch": 0.01, "learning_rate": 3.190235546852223e-05, "loss": 3.549, "step": 1105408 }, { "epoch": 0.01, "learning_rate": 3.189398589981544e-05, "loss": 3.5557, "step": 1105920 }, { "epoch": 0.01, "learning_rate": 3.188559995230492e-05, "loss": 3.5583, "step": 1106432 }, { "epoch": 0.01, "learning_rate": 3.18772140047944e-05, "loss": 3.5522, "step": 1106944 }, { "epoch": 0.01, "learning_rate": 3.186882805728388e-05, "loss": 3.5531, "step": 1107456 }, { "epoch": 0.01, "learning_rate": 3.186045848857709e-05, "loss": 3.5506, "step": 1107968 }, { "epoch": 0.01, "learning_rate": 3.185207254106658e-05, "loss": 3.5557, "step": 1108480 }, { "epoch": 0.01, "learning_rate": 3.184368659355606e-05, "loss": 3.5462, "step": 1108992 }, { "epoch": 0.01, "learning_rate": 3.183530064604554e-05, "loss": 3.5493, "step": 1109504 }, { "epoch": 0.01, "learning_rate": 3.1826931077338746e-05, "loss": 3.551, "step": 1110016 }, { "epoch": 0.01, "learning_rate": 3.1818545129828226e-05, "loss": 3.565, "step": 1110528 }, { "epoch": 0.01, "learning_rate": 3.1810159182317706e-05, "loss": 3.5481, "step": 1111040 }, { "epoch": 0.01, "learning_rate": 3.1801773234807186e-05, "loss": 3.5359, "step": 1111552 }, { "epoch": 0.01, "learning_rate": 3.1793403666100395e-05, "loss": 3.5467, "step": 1112064 }, { "epoch": 0.01, "learning_rate": 3.1785017718589875e-05, "loss": 3.5514, "step": 1112576 }, { "epoch": 0.01, "learning_rate": 3.1776631771079355e-05, "loss": 3.553, "step": 1113088 }, { "epoch": 0.01, "learning_rate": 3.1768245823568835e-05, "loss": 3.5536, "step": 1113600 }, { "epoch": 0.01, "learning_rate": 3.1759876254862044e-05, "loss": 3.5503, "step": 1114112 }, { "epoch": 0.02, "learning_rate": 3.175149030735153e-05, "loss": 3.5525, "step": 1114624 }, { "epoch": 0.02, "learning_rate": 3.174310435984101e-05, "loss": 3.5376, "step": 1115136 }, { "epoch": 0.02, "learning_rate": 3.173471841233049e-05, "loss": 3.5382, "step": 1115648 }, { "epoch": 0.02, "learning_rate": 3.17263488436237e-05, "loss": 3.5411, "step": 1116160 }, { "epoch": 0.02, "learning_rate": 3.171796289611318e-05, "loss": 3.5464, "step": 1116672 }, { "epoch": 0.02, "learning_rate": 3.170957694860266e-05, "loss": 3.559, "step": 1117184 }, { "epoch": 0.02, "learning_rate": 3.170119100109214e-05, "loss": 3.5452, "step": 1117696 }, { "epoch": 0.02, "learning_rate": 3.169282143238535e-05, "loss": 3.5384, "step": 1118208 }, { "epoch": 0.02, "learning_rate": 3.168443548487483e-05, "loss": 3.5552, "step": 1118720 }, { "epoch": 0.02, "learning_rate": 3.167604953736431e-05, "loss": 3.5472, "step": 1119232 }, { "epoch": 0.02, "learning_rate": 3.166766358985379e-05, "loss": 3.5576, "step": 1119744 }, { "epoch": 0.02, "learning_rate": 3.1659294021147e-05, "loss": 3.5516, "step": 1120256 }, { "epoch": 0.02, "learning_rate": 3.1650908073636485e-05, "loss": 3.5422, "step": 1120768 }, { "epoch": 0.02, "learning_rate": 3.1642522126125965e-05, "loss": 3.5493, "step": 1121280 }, { "epoch": 0.02, "learning_rate": 3.1634136178615445e-05, "loss": 3.549, "step": 1121792 }, { "epoch": 0.02, "learning_rate": 3.1625750231104925e-05, "loss": 3.5365, "step": 1122304 }, { "epoch": 0.02, "learning_rate": 3.1617380662398134e-05, "loss": 3.5507, "step": 1122816 }, { "epoch": 0.02, "learning_rate": 3.1608994714887614e-05, "loss": 3.5502, "step": 1123328 }, { "epoch": 0.02, "learning_rate": 3.1600608767377094e-05, "loss": 3.546, "step": 1123840 }, { "epoch": 0.02, "learning_rate": 3.1592222819866574e-05, "loss": 3.5399, "step": 1124352 }, { "epoch": 0.02, "learning_rate": 3.158385325115978e-05, "loss": 3.5439, "step": 1124864 }, { "epoch": 0.02, "learning_rate": 3.157546730364926e-05, "loss": 3.5419, "step": 1125376 }, { "epoch": 0.02, "learning_rate": 3.156708135613874e-05, "loss": 3.5495, "step": 1125888 }, { "epoch": 0.02, "learning_rate": 3.155869540862822e-05, "loss": 3.5511, "step": 1126400 }, { "epoch": 0.02, "learning_rate": 3.155032583992144e-05, "loss": 3.5431, "step": 1126912 }, { "epoch": 0.02, "learning_rate": 3.154193989241092e-05, "loss": 3.5535, "step": 1127424 }, { "epoch": 0.02, "learning_rate": 3.15335539449004e-05, "loss": 3.5575, "step": 1127936 }, { "epoch": 0.02, "learning_rate": 3.152516799738988e-05, "loss": 3.5479, "step": 1128448 }, { "epoch": 0.02, "learning_rate": 3.151679842868309e-05, "loss": 3.5514, "step": 1128960 }, { "epoch": 0.02, "learning_rate": 3.150841248117257e-05, "loss": 3.5519, "step": 1129472 }, { "epoch": 0.02, "learning_rate": 3.150002653366205e-05, "loss": 3.5462, "step": 1129984 }, { "epoch": 0.02, "learning_rate": 3.149164058615153e-05, "loss": 3.5368, "step": 1130496 }, { "epoch": 0.02, "learning_rate": 3.1483271017444736e-05, "loss": 3.5469, "step": 1131008 }, { "epoch": 0.02, "learning_rate": 3.1474885069934216e-05, "loss": 3.5439, "step": 1131520 }, { "epoch": 0.02, "learning_rate": 3.1466499122423696e-05, "loss": 3.5494, "step": 1132032 }, { "epoch": 0.02, "learning_rate": 3.1458113174913176e-05, "loss": 3.5498, "step": 1132544 }, { "epoch": 0.02, "learning_rate": 3.144974360620639e-05, "loss": 3.5537, "step": 1133056 }, { "epoch": 0.02, "learning_rate": 3.144135765869587e-05, "loss": 3.5437, "step": 1133568 }, { "epoch": 0.02, "learning_rate": 3.143297171118535e-05, "loss": 3.5415, "step": 1134080 }, { "epoch": 0.02, "learning_rate": 3.142458576367483e-05, "loss": 3.5546, "step": 1134592 }, { "epoch": 0.02, "learning_rate": 3.141621619496804e-05, "loss": 3.5479, "step": 1135104 }, { "epoch": 0.02, "learning_rate": 3.140783024745752e-05, "loss": 3.5466, "step": 1135616 }, { "epoch": 0.02, "learning_rate": 3.1399444299947e-05, "loss": 3.5263, "step": 1136128 }, { "epoch": 0.02, "learning_rate": 3.139105835243648e-05, "loss": 3.5466, "step": 1136640 }, { "epoch": 0.02, "learning_rate": 3.138268878372969e-05, "loss": 3.5512, "step": 1137152 }, { "epoch": 0.02, "learning_rate": 3.137430283621917e-05, "loss": 3.5588, "step": 1137664 }, { "epoch": 0.02, "learning_rate": 3.136591688870865e-05, "loss": 3.5483, "step": 1138176 }, { "epoch": 0.02, "learning_rate": 3.135753094119813e-05, "loss": 3.5379, "step": 1138688 }, { "epoch": 0.02, "learning_rate": 3.1349161372491346e-05, "loss": 3.5486, "step": 1139200 }, { "epoch": 0.02, "learning_rate": 3.1340775424980826e-05, "loss": 3.5626, "step": 1139712 }, { "epoch": 0.02, "learning_rate": 3.1332389477470306e-05, "loss": 3.5434, "step": 1140224 }, { "epoch": 0.02, "learning_rate": 3.1324003529959786e-05, "loss": 3.5491, "step": 1140736 }, { "epoch": 0.02, "learning_rate": 3.1315617582449266e-05, "loss": 3.5482, "step": 1141248 }, { "epoch": 0.02, "learning_rate": 3.1307248013742475e-05, "loss": 3.5505, "step": 1141760 }, { "epoch": 0.02, "learning_rate": 3.1298862066231955e-05, "loss": 3.5464, "step": 1142272 }, { "epoch": 0.02, "learning_rate": 3.1290476118721435e-05, "loss": 3.5479, "step": 1142784 }, { "epoch": 0.02, "learning_rate": 3.1282090171210915e-05, "loss": 3.5396, "step": 1143296 }, { "epoch": 0.02, "learning_rate": 3.1273720602504124e-05, "loss": 3.5596, "step": 1143808 }, { "epoch": 0.02, "learning_rate": 3.1265334654993604e-05, "loss": 3.547, "step": 1144320 }, { "epoch": 0.03, "eval_loss": 3.8658666610717773, "eval_runtime": 307.8951, "eval_samples_per_second": 1239.354, "eval_steps_per_second": 38.731, "step": 1144800 }, { "epoch": 1.0, "learning_rate": 3.1256948707483084e-05, "loss": 3.5398, "step": 1144832 }, { "epoch": 1.0, "learning_rate": 3.1248562759972563e-05, "loss": 3.5455, "step": 1145344 }, { "epoch": 1.0, "learning_rate": 3.124019319126578e-05, "loss": 3.5396, "step": 1145856 }, { "epoch": 1.0, "learning_rate": 3.123180724375526e-05, "loss": 3.5538, "step": 1146368 }, { "epoch": 1.0, "learning_rate": 3.122342129624474e-05, "loss": 3.5532, "step": 1146880 }, { "epoch": 1.0, "learning_rate": 3.121503534873422e-05, "loss": 3.552, "step": 1147392 }, { "epoch": 1.0, "learning_rate": 3.120666578002743e-05, "loss": 3.5403, "step": 1147904 }, { "epoch": 1.0, "learning_rate": 3.119827983251691e-05, "loss": 3.535, "step": 1148416 }, { "epoch": 1.0, "learning_rate": 3.118989388500639e-05, "loss": 3.5374, "step": 1148928 }, { "epoch": 1.0, "learning_rate": 3.118150793749587e-05, "loss": 3.5623, "step": 1149440 }, { "epoch": 1.0, "learning_rate": 3.117313836878908e-05, "loss": 3.5401, "step": 1149952 }, { "epoch": 1.0, "learning_rate": 3.116475242127856e-05, "loss": 3.5444, "step": 1150464 }, { "epoch": 1.0, "learning_rate": 3.115636647376804e-05, "loss": 3.5535, "step": 1150976 }, { "epoch": 1.0, "learning_rate": 3.114799690506125e-05, "loss": 3.5481, "step": 1151488 }, { "epoch": 1.0, "learning_rate": 3.113961095755073e-05, "loss": 3.5339, "step": 1152000 }, { "epoch": 1.0, "learning_rate": 3.113122501004021e-05, "loss": 3.538, "step": 1152512 }, { "epoch": 1.0, "learning_rate": 3.112283906252969e-05, "loss": 3.5371, "step": 1153024 }, { "epoch": 1.0, "learning_rate": 3.1114453115019166e-05, "loss": 3.5386, "step": 1153536 }, { "epoch": 1.0, "learning_rate": 3.1106067167508646e-05, "loss": 3.5424, "step": 1154048 }, { "epoch": 1.0, "learning_rate": 3.1097681219998126e-05, "loss": 3.5484, "step": 1154560 }, { "epoch": 1.0, "learning_rate": 3.108931165129134e-05, "loss": 3.5604, "step": 1155072 }, { "epoch": 1.0, "learning_rate": 3.1080925703780815e-05, "loss": 3.5426, "step": 1155584 }, { "epoch": 1.0, "learning_rate": 3.1072539756270295e-05, "loss": 3.5434, "step": 1156096 }, { "epoch": 1.0, "learning_rate": 3.1064153808759775e-05, "loss": 3.5382, "step": 1156608 }, { "epoch": 1.0, "learning_rate": 3.105578424005299e-05, "loss": 3.5482, "step": 1157120 }, { "epoch": 1.0, "learning_rate": 3.104739829254247e-05, "loss": 3.5384, "step": 1157632 }, { "epoch": 1.0, "learning_rate": 3.103901234503195e-05, "loss": 3.5344, "step": 1158144 }, { "epoch": 1.0, "learning_rate": 3.103062639752143e-05, "loss": 3.541, "step": 1158656 }, { "epoch": 1.0, "learning_rate": 3.102225682881464e-05, "loss": 3.5424, "step": 1159168 }, { "epoch": 1.0, "learning_rate": 3.101387088130412e-05, "loss": 3.5332, "step": 1159680 }, { "epoch": 1.01, "learning_rate": 3.10054849337936e-05, "loss": 3.5325, "step": 1160192 }, { "epoch": 1.01, "learning_rate": 3.099709898628308e-05, "loss": 3.549, "step": 1160704 }, { "epoch": 1.01, "learning_rate": 3.098872941757629e-05, "loss": 3.5404, "step": 1161216 }, { "epoch": 1.01, "learning_rate": 3.098034347006577e-05, "loss": 3.5458, "step": 1161728 }, { "epoch": 1.01, "learning_rate": 3.097195752255525e-05, "loss": 3.5491, "step": 1162240 }, { "epoch": 1.01, "learning_rate": 3.096357157504473e-05, "loss": 3.5413, "step": 1162752 }, { "epoch": 1.01, "learning_rate": 3.095520200633794e-05, "loss": 3.5471, "step": 1163264 }, { "epoch": 1.01, "learning_rate": 3.0946816058827424e-05, "loss": 3.532, "step": 1163776 }, { "epoch": 1.01, "learning_rate": 3.0938430111316904e-05, "loss": 3.5368, "step": 1164288 }, { "epoch": 1.01, "learning_rate": 3.0930044163806384e-05, "loss": 3.5335, "step": 1164800 }, { "epoch": 1.01, "learning_rate": 3.0921674595099593e-05, "loss": 3.5323, "step": 1165312 }, { "epoch": 1.01, "learning_rate": 3.0913288647589073e-05, "loss": 3.5363, "step": 1165824 }, { "epoch": 1.01, "learning_rate": 3.090490270007855e-05, "loss": 3.5483, "step": 1166336 }, { "epoch": 1.01, "learning_rate": 3.089651675256803e-05, "loss": 3.534, "step": 1166848 }, { "epoch": 1.01, "learning_rate": 3.088813080505751e-05, "loss": 3.5422, "step": 1167360 }, { "epoch": 1.01, "learning_rate": 3.087976123635072e-05, "loss": 3.5367, "step": 1167872 }, { "epoch": 1.01, "learning_rate": 3.08713752888402e-05, "loss": 3.5428, "step": 1168384 }, { "epoch": 1.01, "learning_rate": 3.086298934132968e-05, "loss": 3.5443, "step": 1168896 }, { "epoch": 1.01, "learning_rate": 3.085460339381916e-05, "loss": 3.5229, "step": 1169408 }, { "epoch": 1.01, "learning_rate": 3.084623382511238e-05, "loss": 3.5323, "step": 1169920 }, { "epoch": 1.01, "learning_rate": 3.083784787760186e-05, "loss": 3.5446, "step": 1170432 }, { "epoch": 1.01, "learning_rate": 3.082946193009134e-05, "loss": 3.5477, "step": 1170944 }, { "epoch": 1.01, "learning_rate": 3.082107598258082e-05, "loss": 3.5351, "step": 1171456 }, { "epoch": 1.01, "learning_rate": 3.081270641387403e-05, "loss": 3.5323, "step": 1171968 }, { "epoch": 1.01, "learning_rate": 3.080432046636351e-05, "loss": 3.5355, "step": 1172480 }, { "epoch": 1.01, "learning_rate": 3.079593451885299e-05, "loss": 3.5281, "step": 1172992 }, { "epoch": 1.01, "learning_rate": 3.078754857134247e-05, "loss": 3.5366, "step": 1173504 }, { "epoch": 1.01, "learning_rate": 3.0779179002635676e-05, "loss": 3.5305, "step": 1174016 }, { "epoch": 1.01, "learning_rate": 3.0770793055125156e-05, "loss": 3.5416, "step": 1174528 }, { "epoch": 1.01, "learning_rate": 3.0762407107614636e-05, "loss": 3.5358, "step": 1175040 }, { "epoch": 1.01, "learning_rate": 3.0754021160104116e-05, "loss": 3.5337, "step": 1175552 }, { "epoch": 1.01, "learning_rate": 3.074565159139733e-05, "loss": 3.5249, "step": 1176064 }, { "epoch": 1.01, "learning_rate": 3.073726564388681e-05, "loss": 3.5412, "step": 1176576 }, { "epoch": 1.01, "learning_rate": 3.072887969637629e-05, "loss": 3.5242, "step": 1177088 }, { "epoch": 1.01, "learning_rate": 3.072049374886577e-05, "loss": 3.531, "step": 1177600 }, { "epoch": 1.01, "learning_rate": 3.071212418015898e-05, "loss": 3.5407, "step": 1178112 }, { "epoch": 1.01, "learning_rate": 3.070373823264846e-05, "loss": 3.5403, "step": 1178624 }, { "epoch": 1.01, "learning_rate": 3.069535228513794e-05, "loss": 3.5234, "step": 1179136 }, { "epoch": 1.01, "learning_rate": 3.068696633762742e-05, "loss": 3.5217, "step": 1179648 }, { "epoch": 1.01, "learning_rate": 3.067859676892063e-05, "loss": 3.535, "step": 1180160 }, { "epoch": 1.01, "learning_rate": 3.067021082141011e-05, "loss": 3.5351, "step": 1180672 }, { "epoch": 1.01, "learning_rate": 3.066182487389959e-05, "loss": 3.5443, "step": 1181184 }, { "epoch": 1.01, "learning_rate": 3.065343892638907e-05, "loss": 3.53, "step": 1181696 }, { "epoch": 1.01, "learning_rate": 3.0645069357682285e-05, "loss": 3.5453, "step": 1182208 }, { "epoch": 1.01, "learning_rate": 3.0636683410171765e-05, "loss": 3.5396, "step": 1182720 }, { "epoch": 1.01, "learning_rate": 3.0628297462661245e-05, "loss": 3.5397, "step": 1183232 }, { "epoch": 1.01, "learning_rate": 3.0619911515150725e-05, "loss": 3.5392, "step": 1183744 }, { "epoch": 1.01, "learning_rate": 3.0611541946443934e-05, "loss": 3.5377, "step": 1184256 }, { "epoch": 1.01, "learning_rate": 3.0603155998933414e-05, "loss": 3.5404, "step": 1184768 }, { "epoch": 1.01, "learning_rate": 3.0594770051422894e-05, "loss": 3.5287, "step": 1185280 }, { "epoch": 1.01, "learning_rate": 3.0586384103912374e-05, "loss": 3.5351, "step": 1185792 }, { "epoch": 1.01, "learning_rate": 3.0578014535205583e-05, "loss": 3.5361, "step": 1186304 }, { "epoch": 1.01, "learning_rate": 3.056962858769506e-05, "loss": 3.5512, "step": 1186816 }, { "epoch": 1.01, "learning_rate": 3.056124264018454e-05, "loss": 3.5323, "step": 1187328 }, { "epoch": 1.01, "learning_rate": 3.055285669267402e-05, "loss": 3.5288, "step": 1187840 }, { "epoch": 1.01, "learning_rate": 3.054448712396724e-05, "loss": 3.5251, "step": 1188352 }, { "epoch": 1.01, "learning_rate": 3.053610117645672e-05, "loss": 3.5399, "step": 1188864 }, { "epoch": 1.01, "learning_rate": 3.05277152289462e-05, "loss": 3.5345, "step": 1189376 }, { "epoch": 1.01, "learning_rate": 3.051932928143568e-05, "loss": 3.5413, "step": 1189888 }, { "epoch": 1.01, "learning_rate": 3.0510943333925156e-05, "loss": 3.5327, "step": 1190400 }, { "epoch": 1.02, "learning_rate": 3.0502573765218368e-05, "loss": 3.5378, "step": 1190912 }, { "epoch": 1.02, "learning_rate": 3.0494187817707848e-05, "loss": 3.5235, "step": 1191424 }, { "epoch": 1.02, "learning_rate": 3.0485801870197328e-05, "loss": 3.5266, "step": 1191936 }, { "epoch": 1.02, "learning_rate": 3.0477415922686808e-05, "loss": 3.5251, "step": 1192448 }, { "epoch": 1.02, "learning_rate": 3.0469046353980017e-05, "loss": 3.5299, "step": 1192960 }, { "epoch": 1.02, "learning_rate": 3.04606604064695e-05, "loss": 3.5425, "step": 1193472 }, { "epoch": 1.02, "learning_rate": 3.045227445895898e-05, "loss": 3.5361, "step": 1193984 }, { "epoch": 1.02, "learning_rate": 3.044388851144846e-05, "loss": 3.5236, "step": 1194496 }, { "epoch": 1.02, "learning_rate": 3.043551894274167e-05, "loss": 3.5359, "step": 1195008 }, { "epoch": 1.02, "learning_rate": 3.042713299523115e-05, "loss": 3.5355, "step": 1195520 }, { "epoch": 1.02, "learning_rate": 3.041874704772063e-05, "loss": 3.5409, "step": 1196032 }, { "epoch": 1.02, "learning_rate": 3.041036110021011e-05, "loss": 3.5362, "step": 1196544 }, { "epoch": 1.02, "learning_rate": 3.0401991531503322e-05, "loss": 3.53, "step": 1197056 }, { "epoch": 1.02, "learning_rate": 3.03936055839928e-05, "loss": 3.5318, "step": 1197568 }, { "epoch": 1.02, "learning_rate": 3.038521963648228e-05, "loss": 3.5384, "step": 1198080 }, { "epoch": 1.02, "learning_rate": 3.037683368897176e-05, "loss": 3.521, "step": 1198592 }, { "epoch": 1.02, "learning_rate": 3.036846412026497e-05, "loss": 3.5333, "step": 1199104 }, { "epoch": 1.02, "learning_rate": 3.0360078172754454e-05, "loss": 3.5377, "step": 1199616 }, { "epoch": 1.02, "learning_rate": 3.0351692225243934e-05, "loss": 3.5274, "step": 1200128 }, { "epoch": 1.02, "learning_rate": 3.0343306277733414e-05, "loss": 3.5262, "step": 1200640 }, { "epoch": 1.02, "learning_rate": 3.0334936709026623e-05, "loss": 3.5324, "step": 1201152 }, { "epoch": 1.02, "learning_rate": 3.0326550761516103e-05, "loss": 3.5263, "step": 1201664 }, { "epoch": 1.02, "learning_rate": 3.0318164814005583e-05, "loss": 3.5357, "step": 1202176 }, { "epoch": 1.02, "learning_rate": 3.0309778866495063e-05, "loss": 3.5338, "step": 1202688 }, { "epoch": 1.02, "learning_rate": 3.0301409297788275e-05, "loss": 3.5262, "step": 1203200 }, { "epoch": 1.02, "learning_rate": 3.0293023350277755e-05, "loss": 3.5426, "step": 1203712 }, { "epoch": 1.02, "learning_rate": 3.0284637402767235e-05, "loss": 3.5425, "step": 1204224 }, { "epoch": 1.02, "learning_rate": 3.0276251455256715e-05, "loss": 3.5338, "step": 1204736 }, { "epoch": 1.02, "learning_rate": 3.0267881886549924e-05, "loss": 3.5412, "step": 1205248 }, { "epoch": 1.02, "learning_rate": 3.0259495939039408e-05, "loss": 3.534, "step": 1205760 }, { "epoch": 1.02, "learning_rate": 3.0251109991528888e-05, "loss": 3.5307, "step": 1206272 }, { "epoch": 1.02, "learning_rate": 3.0242724044018368e-05, "loss": 3.5259, "step": 1206784 }, { "epoch": 1.02, "learning_rate": 3.0234354475311577e-05, "loss": 3.5275, "step": 1207296 }, { "epoch": 1.02, "learning_rate": 3.0225968527801057e-05, "loss": 3.5289, "step": 1207808 }, { "epoch": 1.02, "learning_rate": 3.0217582580290537e-05, "loss": 3.5324, "step": 1208320 }, { "epoch": 1.02, "learning_rate": 3.0209196632780013e-05, "loss": 3.5316, "step": 1208832 }, { "epoch": 1.02, "learning_rate": 3.020082706407323e-05, "loss": 3.5395, "step": 1209344 }, { "epoch": 1.02, "learning_rate": 3.019244111656271e-05, "loss": 3.5306, "step": 1209856 }, { "epoch": 1.02, "learning_rate": 3.018405516905219e-05, "loss": 3.5271, "step": 1210368 }, { "epoch": 1.02, "learning_rate": 3.0175669221541662e-05, "loss": 3.5384, "step": 1210880 }, { "epoch": 1.02, "learning_rate": 3.0167299652834878e-05, "loss": 3.5356, "step": 1211392 }, { "epoch": 1.02, "learning_rate": 3.015891370532436e-05, "loss": 3.5318, "step": 1211904 }, { "epoch": 1.02, "learning_rate": 3.015052775781384e-05, "loss": 3.5148, "step": 1212416 }, { "epoch": 1.02, "learning_rate": 3.0142141810303314e-05, "loss": 3.5287, "step": 1212928 }, { "epoch": 1.02, "learning_rate": 3.013377224159653e-05, "loss": 3.5404, "step": 1213440 }, { "epoch": 1.02, "learning_rate": 3.012538629408601e-05, "loss": 3.5394, "step": 1213952 }, { "epoch": 1.02, "learning_rate": 3.0117000346575487e-05, "loss": 3.5324, "step": 1214464 }, { "epoch": 1.02, "learning_rate": 3.0108614399064967e-05, "loss": 3.5225, "step": 1214976 }, { "epoch": 1.02, "learning_rate": 3.0100244830358183e-05, "loss": 3.534, "step": 1215488 }, { "epoch": 1.02, "learning_rate": 3.0091858882847663e-05, "loss": 3.546, "step": 1216000 }, { "epoch": 1.02, "learning_rate": 3.0083472935337136e-05, "loss": 3.5296, "step": 1216512 }, { "epoch": 1.02, "learning_rate": 3.0075086987826616e-05, "loss": 3.5344, "step": 1217024 }, { "epoch": 1.02, "learning_rate": 3.006671741911983e-05, "loss": 3.5306, "step": 1217536 }, { "epoch": 1.02, "learning_rate": 3.0058331471609315e-05, "loss": 3.5337, "step": 1218048 }, { "epoch": 1.02, "learning_rate": 3.0049945524098788e-05, "loss": 3.529, "step": 1218560 }, { "epoch": 1.02, "learning_rate": 3.0041559576588268e-05, "loss": 3.541, "step": 1219072 }, { "epoch": 1.02, "learning_rate": 3.0033190007881484e-05, "loss": 3.5233, "step": 1219584 }, { "epoch": 1.02, "learning_rate": 3.002480406037096e-05, "loss": 3.5417, "step": 1220096 }, { "epoch": 1.02, "learning_rate": 3.001641811286044e-05, "loss": 3.5315, "step": 1220608 }, { "epoch": 1.03, "learning_rate": 3.000803216534992e-05, "loss": 3.5256, "step": 1221120 }, { "epoch": 1.03, "eval_loss": 3.866699457168579, "eval_runtime": 338.1606, "eval_samples_per_second": 1128.431, "eval_steps_per_second": 35.264, "step": 1221120 }, { "epoch": 0.0, "learning_rate": 2.99996462178394e-05, "loss": 3.532, "step": 1221632 }, { "epoch": 0.0, "learning_rate": 2.999126027032888e-05, "loss": 3.5262, "step": 1222144 }, { "epoch": 0.0, "learning_rate": 2.998287432281836e-05, "loss": 3.5379, "step": 1222656 }, { "epoch": 0.0, "learning_rate": 2.997450475411157e-05, "loss": 3.5337, "step": 1223168 }, { "epoch": 0.0, "learning_rate": 2.9966118806601053e-05, "loss": 3.538, "step": 1223680 }, { "epoch": 0.0, "learning_rate": 2.9957732859090533e-05, "loss": 3.5264, "step": 1224192 }, { "epoch": 0.0, "learning_rate": 2.9949346911580013e-05, "loss": 3.5209, "step": 1224704 }, { "epoch": 0.0, "learning_rate": 2.9940960964069493e-05, "loss": 3.5217, "step": 1225216 }, { "epoch": 0.0, "learning_rate": 2.9932591395362702e-05, "loss": 3.5471, "step": 1225728 }, { "epoch": 0.0, "learning_rate": 2.9924205447852182e-05, "loss": 3.53, "step": 1226240 }, { "epoch": 0.0, "learning_rate": 2.9915819500341662e-05, "loss": 3.5257, "step": 1226752 }, { "epoch": 0.0, "learning_rate": 2.990743355283114e-05, "loss": 3.5357, "step": 1227264 }, { "epoch": 0.0, "learning_rate": 2.9899063984124354e-05, "loss": 3.5349, "step": 1227776 }, { "epoch": 0.0, "learning_rate": 2.9890678036613834e-05, "loss": 3.5224, "step": 1228288 }, { "epoch": 0.0, "learning_rate": 2.9882292089103314e-05, "loss": 3.5226, "step": 1228800 }, { "epoch": 0.0, "learning_rate": 2.9873906141592794e-05, "loss": 3.521, "step": 1229312 }, { "epoch": 0.0, "learning_rate": 2.9865536572886006e-05, "loss": 3.5259, "step": 1229824 }, { "epoch": 0.0, "learning_rate": 2.9857150625375486e-05, "loss": 3.5236, "step": 1230336 }, { "epoch": 0.0, "learning_rate": 2.9848764677864966e-05, "loss": 3.5378, "step": 1230848 }, { "epoch": 0.0, "learning_rate": 2.9840378730354446e-05, "loss": 3.5471, "step": 1231360 }, { "epoch": 0.0, "learning_rate": 2.9832009161647655e-05, "loss": 3.5292, "step": 1231872 }, { "epoch": 0.0, "learning_rate": 2.9823623214137135e-05, "loss": 3.5224, "step": 1232384 }, { "epoch": 0.0, "learning_rate": 2.9815237266626615e-05, "loss": 3.5276, "step": 1232896 }, { "epoch": 0.0, "learning_rate": 2.9806867697919828e-05, "loss": 3.5346, "step": 1233408 }, { "epoch": 0.0, "learning_rate": 2.9798481750409308e-05, "loss": 3.521, "step": 1233920 }, { "epoch": 0.0, "learning_rate": 2.9790095802898788e-05, "loss": 3.5217, "step": 1234432 }, { "epoch": 0.0, "learning_rate": 2.9781709855388268e-05, "loss": 3.5241, "step": 1234944 }, { "epoch": 0.0, "learning_rate": 2.9773340286681477e-05, "loss": 3.534, "step": 1235456 }, { "epoch": 0.0, "learning_rate": 2.9764954339170957e-05, "loss": 3.5155, "step": 1235968 }, { "epoch": 0.01, "learning_rate": 2.975656839166044e-05, "loss": 3.5168, "step": 1236480 }, { "epoch": 0.01, "learning_rate": 2.974818244414992e-05, "loss": 3.5345, "step": 1236992 }, { "epoch": 0.01, "learning_rate": 2.973981287544313e-05, "loss": 3.5291, "step": 1237504 }, { "epoch": 0.01, "learning_rate": 2.973142692793261e-05, "loss": 3.5294, "step": 1238016 }, { "epoch": 0.01, "learning_rate": 2.972304098042209e-05, "loss": 3.5359, "step": 1238528 }, { "epoch": 0.01, "learning_rate": 2.971465503291157e-05, "loss": 3.5247, "step": 1239040 }, { "epoch": 0.01, "learning_rate": 2.970626908540105e-05, "loss": 3.5317, "step": 1239552 }, { "epoch": 0.01, "learning_rate": 2.969789951669426e-05, "loss": 3.5187, "step": 1240064 }, { "epoch": 0.01, "learning_rate": 2.968951356918374e-05, "loss": 3.5247, "step": 1240576 }, { "epoch": 0.01, "learning_rate": 2.968112762167322e-05, "loss": 3.5157, "step": 1241088 }, { "epoch": 0.01, "learning_rate": 2.96727416741627e-05, "loss": 3.516, "step": 1241600 }, { "epoch": 0.01, "learning_rate": 2.966437210545591e-05, "loss": 3.5232, "step": 1242112 }, { "epoch": 0.01, "learning_rate": 2.9655986157945394e-05, "loss": 3.5329, "step": 1242624 }, { "epoch": 0.01, "learning_rate": 2.9647600210434874e-05, "loss": 3.52, "step": 1243136 }, { "epoch": 0.01, "learning_rate": 2.9639214262924354e-05, "loss": 3.5265, "step": 1243648 }, { "epoch": 0.01, "learning_rate": 2.9630844694217563e-05, "loss": 3.5242, "step": 1244160 }, { "epoch": 0.01, "learning_rate": 2.9622458746707043e-05, "loss": 3.5269, "step": 1244672 }, { "epoch": 0.01, "learning_rate": 2.9614072799196523e-05, "loss": 3.5305, "step": 1245184 }, { "epoch": 0.01, "learning_rate": 2.9605686851686003e-05, "loss": 3.5133, "step": 1245696 }, { "epoch": 0.01, "learning_rate": 2.9597317282979215e-05, "loss": 3.5144, "step": 1246208 }, { "epoch": 0.01, "learning_rate": 2.9588931335468695e-05, "loss": 3.5304, "step": 1246720 }, { "epoch": 0.01, "learning_rate": 2.9580545387958175e-05, "loss": 3.535, "step": 1247232 }, { "epoch": 0.01, "learning_rate": 2.9572159440447655e-05, "loss": 3.5188, "step": 1247744 }, { "epoch": 0.01, "learning_rate": 2.9563789871740864e-05, "loss": 3.5197, "step": 1248256 }, { "epoch": 0.01, "learning_rate": 2.9555403924230347e-05, "loss": 3.5221, "step": 1248768 }, { "epoch": 0.01, "learning_rate": 2.9547017976719827e-05, "loss": 3.5121, "step": 1249280 }, { "epoch": 0.01, "learning_rate": 2.9538632029209307e-05, "loss": 3.5209, "step": 1249792 }, { "epoch": 0.01, "learning_rate": 2.9530262460502516e-05, "loss": 3.5156, "step": 1250304 }, { "epoch": 0.01, "learning_rate": 2.9521876512991996e-05, "loss": 3.5261, "step": 1250816 }, { "epoch": 0.01, "learning_rate": 2.9513490565481476e-05, "loss": 3.5234, "step": 1251328 }, { "epoch": 0.01, "learning_rate": 2.9505104617970956e-05, "loss": 3.5228, "step": 1251840 }, { "epoch": 0.01, "learning_rate": 2.949673504926417e-05, "loss": 3.5098, "step": 1252352 }, { "epoch": 0.01, "learning_rate": 2.948834910175365e-05, "loss": 3.5283, "step": 1252864 }, { "epoch": 0.01, "learning_rate": 2.947996315424313e-05, "loss": 3.5091, "step": 1253376 }, { "epoch": 0.01, "learning_rate": 2.947157720673261e-05, "loss": 3.5176, "step": 1253888 }, { "epoch": 0.01, "learning_rate": 2.9463207638025818e-05, "loss": 3.5254, "step": 1254400 }, { "epoch": 0.01, "learning_rate": 2.94548216905153e-05, "loss": 3.5278, "step": 1254912 }, { "epoch": 0.01, "learning_rate": 2.944643574300478e-05, "loss": 3.509, "step": 1255424 }, { "epoch": 0.01, "learning_rate": 2.943804979549426e-05, "loss": 3.5097, "step": 1255936 }, { "epoch": 0.01, "learning_rate": 2.942968022678747e-05, "loss": 3.5164, "step": 1256448 }, { "epoch": 0.01, "learning_rate": 2.942129427927695e-05, "loss": 3.5257, "step": 1256960 }, { "epoch": 0.01, "learning_rate": 2.941290833176643e-05, "loss": 3.5235, "step": 1257472 }, { "epoch": 0.01, "learning_rate": 2.940452238425591e-05, "loss": 3.5186, "step": 1257984 }, { "epoch": 0.01, "learning_rate": 2.9396152815549122e-05, "loss": 3.5284, "step": 1258496 }, { "epoch": 0.01, "learning_rate": 2.9387766868038602e-05, "loss": 3.5294, "step": 1259008 }, { "epoch": 0.01, "learning_rate": 2.9379380920528082e-05, "loss": 3.5225, "step": 1259520 }, { "epoch": 0.01, "learning_rate": 2.9370994973017562e-05, "loss": 3.5234, "step": 1260032 }, { "epoch": 0.01, "learning_rate": 2.9362641783114504e-05, "loss": 3.5231, "step": 1260544 }, { "epoch": 0.01, "learning_rate": 2.9354255835603984e-05, "loss": 3.5293, "step": 1261056 }, { "epoch": 0.01, "learning_rate": 2.9345869888093464e-05, "loss": 3.5104, "step": 1261568 }, { "epoch": 0.01, "learning_rate": 2.9337483940582944e-05, "loss": 3.5231, "step": 1262080 }, { "epoch": 0.01, "learning_rate": 2.9329097993072424e-05, "loss": 3.5192, "step": 1262592 }, { "epoch": 0.01, "learning_rate": 2.9320712045561904e-05, "loss": 3.5357, "step": 1263104 }, { "epoch": 0.01, "learning_rate": 2.9312326098051384e-05, "loss": 3.5208, "step": 1263616 }, { "epoch": 0.01, "learning_rate": 2.930394015054086e-05, "loss": 3.5093, "step": 1264128 }, { "epoch": 0.01, "learning_rate": 2.9295570581834076e-05, "loss": 3.5129, "step": 1264640 }, { "epoch": 0.01, "learning_rate": 2.9287184634323556e-05, "loss": 3.5205, "step": 1265152 }, { "epoch": 0.01, "learning_rate": 2.9278798686813036e-05, "loss": 3.5262, "step": 1265664 }, { "epoch": 0.01, "learning_rate": 2.927041273930251e-05, "loss": 3.5244, "step": 1266176 }, { "epoch": 0.01, "learning_rate": 2.9262026791791993e-05, "loss": 3.5174, "step": 1266688 }, { "epoch": 0.02, "learning_rate": 2.925365722308521e-05, "loss": 3.52, "step": 1267200 }, { "epoch": 0.02, "learning_rate": 2.924527127557469e-05, "loss": 3.5127, "step": 1267712 }, { "epoch": 0.02, "learning_rate": 2.923688532806416e-05, "loss": 3.5094, "step": 1268224 }, { "epoch": 0.02, "learning_rate": 2.922849938055364e-05, "loss": 3.509, "step": 1268736 }, { "epoch": 0.02, "learning_rate": 2.9220129811846857e-05, "loss": 3.5222, "step": 1269248 }, { "epoch": 0.02, "learning_rate": 2.9211743864336334e-05, "loss": 3.5261, "step": 1269760 }, { "epoch": 0.02, "learning_rate": 2.9203357916825814e-05, "loss": 3.5199, "step": 1270272 }, { "epoch": 0.02, "learning_rate": 2.9194971969315294e-05, "loss": 3.5123, "step": 1270784 }, { "epoch": 0.02, "learning_rate": 2.918660240060851e-05, "loss": 3.5188, "step": 1271296 }, { "epoch": 0.02, "learning_rate": 2.9178216453097983e-05, "loss": 3.5213, "step": 1271808 }, { "epoch": 0.02, "learning_rate": 2.9169830505587463e-05, "loss": 3.5268, "step": 1272320 }, { "epoch": 0.02, "learning_rate": 2.9161444558076946e-05, "loss": 3.5223, "step": 1272832 }, { "epoch": 0.02, "learning_rate": 2.9153074989370162e-05, "loss": 3.5182, "step": 1273344 }, { "epoch": 0.02, "learning_rate": 2.9144689041859635e-05, "loss": 3.5152, "step": 1273856 }, { "epoch": 0.02, "learning_rate": 2.9136303094349115e-05, "loss": 3.5269, "step": 1274368 }, { "epoch": 0.02, "learning_rate": 2.9127917146838595e-05, "loss": 3.509, "step": 1274880 }, { "epoch": 0.02, "learning_rate": 2.9119547578131808e-05, "loss": 3.5165, "step": 1275392 }, { "epoch": 0.02, "learning_rate": 2.9111161630621288e-05, "loss": 3.5247, "step": 1275904 }, { "epoch": 0.02, "learning_rate": 2.9102775683110768e-05, "loss": 3.5155, "step": 1276416 }, { "epoch": 0.02, "learning_rate": 2.9094389735600248e-05, "loss": 3.51, "step": 1276928 }, { "epoch": 0.02, "learning_rate": 2.9086020166893457e-05, "loss": 3.519, "step": 1277440 }, { "epoch": 0.02, "learning_rate": 2.9077634219382937e-05, "loss": 3.5167, "step": 1277952 }, { "epoch": 0.02, "learning_rate": 2.9069248271872417e-05, "loss": 3.5179, "step": 1278464 }, { "epoch": 0.02, "learning_rate": 2.90608623243619e-05, "loss": 3.5162, "step": 1278976 }, { "epoch": 0.02, "learning_rate": 2.905249275565511e-05, "loss": 3.5156, "step": 1279488 }, { "epoch": 0.02, "learning_rate": 2.904410680814459e-05, "loss": 3.5252, "step": 1280000 }, { "epoch": 0.02, "learning_rate": 2.903572086063407e-05, "loss": 3.5269, "step": 1280512 }, { "epoch": 0.02, "learning_rate": 2.902733491312355e-05, "loss": 3.5182, "step": 1281024 }, { "epoch": 0.02, "learning_rate": 2.901896534441676e-05, "loss": 3.5296, "step": 1281536 }, { "epoch": 0.02, "learning_rate": 2.901057939690624e-05, "loss": 3.5223, "step": 1282048 }, { "epoch": 0.02, "learning_rate": 2.900219344939572e-05, "loss": 3.515, "step": 1282560 }, { "epoch": 0.02, "learning_rate": 2.89938075018852e-05, "loss": 3.5089, "step": 1283072 }, { "epoch": 0.02, "learning_rate": 2.898543793317841e-05, "loss": 3.5153, "step": 1283584 }, { "epoch": 0.02, "learning_rate": 2.897705198566789e-05, "loss": 3.5176, "step": 1284096 }, { "epoch": 0.02, "learning_rate": 2.896866603815737e-05, "loss": 3.5171, "step": 1284608 }, { "epoch": 0.02, "learning_rate": 2.896028009064685e-05, "loss": 3.5208, "step": 1285120 }, { "epoch": 0.02, "learning_rate": 2.8951910521940063e-05, "loss": 3.5221, "step": 1285632 }, { "epoch": 0.02, "learning_rate": 2.8943524574429543e-05, "loss": 3.5221, "step": 1286144 }, { "epoch": 0.02, "learning_rate": 2.8935138626919023e-05, "loss": 3.5124, "step": 1286656 }, { "epoch": 0.02, "learning_rate": 2.8926752679408503e-05, "loss": 3.5226, "step": 1287168 }, { "epoch": 0.02, "learning_rate": 2.8918383110701715e-05, "loss": 3.5241, "step": 1287680 }, { "epoch": 0.02, "learning_rate": 2.8909997163191195e-05, "loss": 3.5142, "step": 1288192 }, { "epoch": 0.02, "learning_rate": 2.8901611215680675e-05, "loss": 3.5037, "step": 1288704 }, { "epoch": 0.02, "learning_rate": 2.8893225268170155e-05, "loss": 3.5131, "step": 1289216 }, { "epoch": 0.02, "learning_rate": 2.8884855699463364e-05, "loss": 3.5281, "step": 1289728 }, { "epoch": 0.02, "learning_rate": 2.8876469751952844e-05, "loss": 3.5276, "step": 1290240 }, { "epoch": 0.02, "learning_rate": 2.8868083804442324e-05, "loss": 3.5107, "step": 1290752 }, { "epoch": 0.02, "learning_rate": 2.8859697856931804e-05, "loss": 3.5111, "step": 1291264 }, { "epoch": 0.02, "learning_rate": 2.8851328288225016e-05, "loss": 3.5275, "step": 1291776 }, { "epoch": 0.02, "learning_rate": 2.8842942340714496e-05, "loss": 3.5271, "step": 1292288 }, { "epoch": 0.02, "learning_rate": 2.8834556393203976e-05, "loss": 3.5199, "step": 1292800 }, { "epoch": 0.02, "learning_rate": 2.8826170445693456e-05, "loss": 3.5174, "step": 1293312 }, { "epoch": 0.02, "learning_rate": 2.8817800876986665e-05, "loss": 3.5199, "step": 1293824 }, { "epoch": 0.02, "learning_rate": 2.880941492947615e-05, "loss": 3.5187, "step": 1294336 }, { "epoch": 0.02, "learning_rate": 2.880102898196563e-05, "loss": 3.5133, "step": 1294848 }, { "epoch": 0.02, "learning_rate": 2.879264303445511e-05, "loss": 3.5291, "step": 1295360 }, { "epoch": 0.02, "learning_rate": 2.8784273465748318e-05, "loss": 3.5149, "step": 1295872 }, { "epoch": 0.02, "learning_rate": 2.8775887518237798e-05, "loss": 3.528, "step": 1296384 }, { "epoch": 0.02, "learning_rate": 2.8767501570727278e-05, "loss": 3.5199, "step": 1296896 }, { "epoch": 0.02, "learning_rate": 2.8759115623216758e-05, "loss": 3.5086, "step": 1297408 }, { "epoch": 0.03, "eval_loss": 3.8688018321990967, "eval_runtime": 308.3479, "eval_samples_per_second": 1237.534, "eval_steps_per_second": 38.674, "step": 1297440 }, { "epoch": 1.0, "learning_rate": 2.875074605450997e-05, "loss": 3.5154, "step": 1297920 }, { "epoch": 1.0, "learning_rate": 2.874236010699945e-05, "loss": 3.514, "step": 1298432 }, { "epoch": 1.0, "learning_rate": 2.873397415948893e-05, "loss": 3.5233, "step": 1298944 }, { "epoch": 1.0, "learning_rate": 2.872558821197841e-05, "loss": 3.5208, "step": 1299456 }, { "epoch": 1.0, "learning_rate": 2.871720226446789e-05, "loss": 3.5255, "step": 1299968 }, { "epoch": 1.0, "learning_rate": 2.8708832695761102e-05, "loss": 3.5123, "step": 1300480 }, { "epoch": 1.0, "learning_rate": 2.8700446748250582e-05, "loss": 3.5094, "step": 1300992 }, { "epoch": 1.0, "learning_rate": 2.8692060800740062e-05, "loss": 3.5012, "step": 1301504 }, { "epoch": 1.0, "learning_rate": 2.8683674853229542e-05, "loss": 3.533, "step": 1302016 }, { "epoch": 1.0, "learning_rate": 2.867530528452275e-05, "loss": 3.519, "step": 1302528 }, { "epoch": 1.0, "learning_rate": 2.866691933701223e-05, "loss": 3.5105, "step": 1303040 }, { "epoch": 1.0, "learning_rate": 2.865853338950171e-05, "loss": 3.5239, "step": 1303552 }, { "epoch": 1.0, "learning_rate": 2.8650163820794924e-05, "loss": 3.5153, "step": 1304064 }, { "epoch": 1.0, "learning_rate": 2.8641777873284404e-05, "loss": 3.5109, "step": 1304576 }, { "epoch": 1.0, "learning_rate": 2.8633391925773884e-05, "loss": 3.5079, "step": 1305088 }, { "epoch": 1.0, "learning_rate": 2.8625005978263364e-05, "loss": 3.5113, "step": 1305600 }, { "epoch": 1.0, "learning_rate": 2.8616620030752843e-05, "loss": 3.5088, "step": 1306112 }, { "epoch": 1.0, "learning_rate": 2.8608234083242323e-05, "loss": 3.5108, "step": 1306624 }, { "epoch": 1.0, "learning_rate": 2.8599848135731803e-05, "loss": 3.5268, "step": 1307136 }, { "epoch": 1.0, "learning_rate": 2.8591478567025016e-05, "loss": 3.5318, "step": 1307648 }, { "epoch": 1.0, "learning_rate": 2.8583092619514496e-05, "loss": 3.5154, "step": 1308160 }, { "epoch": 1.0, "learning_rate": 2.8574706672003976e-05, "loss": 3.5096, "step": 1308672 }, { "epoch": 1.0, "learning_rate": 2.8566320724493456e-05, "loss": 3.5142, "step": 1309184 }, { "epoch": 1.0, "learning_rate": 2.8557934776982936e-05, "loss": 3.5193, "step": 1309696 }, { "epoch": 1.0, "learning_rate": 2.8549565208276148e-05, "loss": 3.5095, "step": 1310208 }, { "epoch": 1.0, "learning_rate": 2.8541179260765628e-05, "loss": 3.5065, "step": 1310720 }, { "epoch": 1.0, "learning_rate": 2.8532793313255108e-05, "loss": 3.5104, "step": 1311232 }, { "epoch": 1.0, "learning_rate": 2.8524423744548317e-05, "loss": 3.5216, "step": 1311744 }, { "epoch": 1.0, "learning_rate": 2.8516037797037797e-05, "loss": 3.4975, "step": 1312256 }, { "epoch": 1.01, "learning_rate": 2.8507651849527277e-05, "loss": 3.505, "step": 1312768 }, { "epoch": 1.01, "learning_rate": 2.8499265902016757e-05, "loss": 3.5184, "step": 1313280 }, { "epoch": 1.01, "learning_rate": 2.849089633330997e-05, "loss": 3.517, "step": 1313792 }, { "epoch": 1.01, "learning_rate": 2.848251038579945e-05, "loss": 3.5226, "step": 1314304 }, { "epoch": 1.01, "learning_rate": 2.847412443828893e-05, "loss": 3.517, "step": 1314816 }, { "epoch": 1.01, "learning_rate": 2.846573849077841e-05, "loss": 3.5119, "step": 1315328 }, { "epoch": 1.01, "learning_rate": 2.8457352543267886e-05, "loss": 3.5199, "step": 1315840 }, { "epoch": 1.01, "learning_rate": 2.8448982974561102e-05, "loss": 3.503, "step": 1316352 }, { "epoch": 1.01, "learning_rate": 2.8440597027050582e-05, "loss": 3.5127, "step": 1316864 }, { "epoch": 1.01, "learning_rate": 2.8432211079540062e-05, "loss": 3.5005, "step": 1317376 }, { "epoch": 1.01, "learning_rate": 2.8423825132029535e-05, "loss": 3.5047, "step": 1317888 }, { "epoch": 1.01, "learning_rate": 2.841545556332275e-05, "loss": 3.5098, "step": 1318400 }, { "epoch": 1.01, "learning_rate": 2.840706961581223e-05, "loss": 3.5164, "step": 1318912 }, { "epoch": 1.01, "learning_rate": 2.839868366830171e-05, "loss": 3.5135, "step": 1319424 }, { "epoch": 1.01, "learning_rate": 2.8390297720791187e-05, "loss": 3.5086, "step": 1319936 }, { "epoch": 1.01, "learning_rate": 2.8381928152084403e-05, "loss": 3.5128, "step": 1320448 }, { "epoch": 1.01, "learning_rate": 2.8373542204573883e-05, "loss": 3.5143, "step": 1320960 }, { "epoch": 1.01, "learning_rate": 2.8365156257063356e-05, "loss": 3.5139, "step": 1321472 }, { "epoch": 1.01, "learning_rate": 2.835677030955284e-05, "loss": 3.5031, "step": 1321984 }, { "epoch": 1.01, "learning_rate": 2.8348400740846056e-05, "loss": 3.5006, "step": 1322496 }, { "epoch": 1.01, "learning_rate": 2.8340014793335535e-05, "loss": 3.514, "step": 1323008 }, { "epoch": 1.01, "learning_rate": 2.833162884582501e-05, "loss": 3.5206, "step": 1323520 }, { "epoch": 1.01, "learning_rate": 2.832324289831449e-05, "loss": 3.5083, "step": 1324032 }, { "epoch": 1.01, "learning_rate": 2.8314873329607704e-05, "loss": 3.5065, "step": 1324544 }, { "epoch": 1.01, "learning_rate": 2.8306487382097184e-05, "loss": 3.5037, "step": 1325056 }, { "epoch": 1.01, "learning_rate": 2.829810143458666e-05, "loss": 3.502, "step": 1325568 }, { "epoch": 1.01, "learning_rate": 2.828971548707614e-05, "loss": 3.5072, "step": 1326080 }, { "epoch": 1.01, "learning_rate": 2.8281345918369357e-05, "loss": 3.5014, "step": 1326592 }, { "epoch": 1.01, "learning_rate": 2.827295997085883e-05, "loss": 3.5121, "step": 1327104 }, { "epoch": 1.01, "learning_rate": 2.826457402334831e-05, "loss": 3.5107, "step": 1327616 }, { "epoch": 1.01, "learning_rate": 2.8256188075837793e-05, "loss": 3.5058, "step": 1328128 }, { "epoch": 1.01, "learning_rate": 2.824781850713101e-05, "loss": 3.4951, "step": 1328640 }, { "epoch": 1.01, "learning_rate": 2.8239432559620482e-05, "loss": 3.516, "step": 1329152 }, { "epoch": 1.01, "learning_rate": 2.8231046612109962e-05, "loss": 3.4954, "step": 1329664 }, { "epoch": 1.01, "learning_rate": 2.8222660664599442e-05, "loss": 3.5052, "step": 1330176 }, { "epoch": 1.01, "learning_rate": 2.8214291095892658e-05, "loss": 3.5159, "step": 1330688 }, { "epoch": 1.01, "learning_rate": 2.8205905148382135e-05, "loss": 3.5134, "step": 1331200 }, { "epoch": 1.01, "learning_rate": 2.8197519200871615e-05, "loss": 3.4977, "step": 1331712 }, { "epoch": 1.01, "learning_rate": 2.8189133253361095e-05, "loss": 3.4982, "step": 1332224 }, { "epoch": 1.01, "learning_rate": 2.8180763684654304e-05, "loss": 3.5025, "step": 1332736 }, { "epoch": 1.01, "learning_rate": 2.8172377737143784e-05, "loss": 3.5083, "step": 1333248 }, { "epoch": 1.01, "learning_rate": 2.8163991789633264e-05, "loss": 3.5103, "step": 1333760 }, { "epoch": 1.01, "learning_rate": 2.8155605842122747e-05, "loss": 3.5075, "step": 1334272 }, { "epoch": 1.01, "learning_rate": 2.8147236273415956e-05, "loss": 3.5155, "step": 1334784 }, { "epoch": 1.01, "learning_rate": 2.8138850325905436e-05, "loss": 3.5138, "step": 1335296 }, { "epoch": 1.01, "learning_rate": 2.8130464378394916e-05, "loss": 3.5137, "step": 1335808 }, { "epoch": 1.01, "learning_rate": 2.8122078430884396e-05, "loss": 3.5021, "step": 1336320 }, { "epoch": 1.01, "learning_rate": 2.811370886217761e-05, "loss": 3.5146, "step": 1336832 }, { "epoch": 1.01, "learning_rate": 2.810533929347082e-05, "loss": 3.5154, "step": 1337344 }, { "epoch": 1.01, "learning_rate": 2.8096953345960304e-05, "loss": 3.4942, "step": 1337856 }, { "epoch": 1.01, "learning_rate": 2.8088567398449777e-05, "loss": 3.5155, "step": 1338368 }, { "epoch": 1.01, "learning_rate": 2.8080181450939257e-05, "loss": 3.5021, "step": 1338880 }, { "epoch": 1.01, "learning_rate": 2.8071795503428737e-05, "loss": 3.5266, "step": 1339392 }, { "epoch": 1.01, "learning_rate": 2.8063409555918217e-05, "loss": 3.5085, "step": 1339904 }, { "epoch": 1.01, "learning_rate": 2.8055023608407697e-05, "loss": 3.4918, "step": 1340416 }, { "epoch": 1.01, "learning_rate": 2.804663766089718e-05, "loss": 3.506, "step": 1340928 }, { "epoch": 1.01, "learning_rate": 2.803826809219039e-05, "loss": 3.5005, "step": 1341440 }, { "epoch": 1.01, "learning_rate": 2.802988214467987e-05, "loss": 3.5166, "step": 1341952 }, { "epoch": 1.01, "learning_rate": 2.802149619716935e-05, "loss": 3.5088, "step": 1342464 }, { "epoch": 1.01, "learning_rate": 2.801311024965883e-05, "loss": 3.5061, "step": 1342976 }, { "epoch": 1.02, "learning_rate": 2.8004740680952042e-05, "loss": 3.5089, "step": 1343488 }, { "epoch": 1.02, "learning_rate": 2.7996354733441522e-05, "loss": 3.4985, "step": 1344000 }, { "epoch": 1.02, "learning_rate": 2.7987968785931002e-05, "loss": 3.498, "step": 1344512 }, { "epoch": 1.02, "learning_rate": 2.7979582838420482e-05, "loss": 3.4948, "step": 1345024 }, { "epoch": 1.02, "learning_rate": 2.797121326971369e-05, "loss": 3.5082, "step": 1345536 }, { "epoch": 1.02, "learning_rate": 2.796282732220317e-05, "loss": 3.5123, "step": 1346048 }, { "epoch": 1.02, "learning_rate": 2.795444137469265e-05, "loss": 3.5076, "step": 1346560 }, { "epoch": 1.02, "learning_rate": 2.7946055427182134e-05, "loss": 3.4974, "step": 1347072 }, { "epoch": 1.02, "learning_rate": 2.7937685858475343e-05, "loss": 3.5057, "step": 1347584 }, { "epoch": 1.02, "learning_rate": 2.7929299910964823e-05, "loss": 3.5057, "step": 1348096 }, { "epoch": 1.02, "learning_rate": 2.7920913963454303e-05, "loss": 3.5132, "step": 1348608 }, { "epoch": 1.02, "learning_rate": 2.7912528015943783e-05, "loss": 3.507, "step": 1349120 }, { "epoch": 1.02, "learning_rate": 2.7904158447236996e-05, "loss": 3.5044, "step": 1349632 }, { "epoch": 1.02, "learning_rate": 2.7895772499726476e-05, "loss": 3.5043, "step": 1350144 }, { "epoch": 1.02, "learning_rate": 2.7887386552215956e-05, "loss": 3.5122, "step": 1350656 }, { "epoch": 1.02, "learning_rate": 2.7879000604705436e-05, "loss": 3.4935, "step": 1351168 }, { "epoch": 1.02, "learning_rate": 2.7870631035998645e-05, "loss": 3.5081, "step": 1351680 }, { "epoch": 1.02, "learning_rate": 2.7862245088488125e-05, "loss": 3.5097, "step": 1352192 }, { "epoch": 1.02, "learning_rate": 2.7853859140977605e-05, "loss": 3.5023, "step": 1352704 }, { "epoch": 1.02, "learning_rate": 2.7845473193467088e-05, "loss": 3.496, "step": 1353216 }, { "epoch": 1.02, "learning_rate": 2.7837103624760297e-05, "loss": 3.5047, "step": 1353728 }, { "epoch": 1.02, "learning_rate": 2.7828717677249777e-05, "loss": 3.5026, "step": 1354240 }, { "epoch": 1.02, "learning_rate": 2.7820331729739257e-05, "loss": 3.5038, "step": 1354752 }, { "epoch": 1.02, "learning_rate": 2.7811945782228737e-05, "loss": 3.5036, "step": 1355264 }, { "epoch": 1.02, "learning_rate": 2.780357621352195e-05, "loss": 3.4997, "step": 1355776 }, { "epoch": 1.02, "learning_rate": 2.779519026601143e-05, "loss": 3.5137, "step": 1356288 }, { "epoch": 1.02, "learning_rate": 2.778680431850091e-05, "loss": 3.515, "step": 1356800 }, { "epoch": 1.02, "learning_rate": 2.777841837099039e-05, "loss": 3.5069, "step": 1357312 }, { "epoch": 1.02, "learning_rate": 2.77700488022836e-05, "loss": 3.5102, "step": 1357824 }, { "epoch": 1.02, "learning_rate": 2.776166285477308e-05, "loss": 3.5102, "step": 1358336 }, { "epoch": 1.02, "learning_rate": 2.7753276907262558e-05, "loss": 3.5028, "step": 1358848 }, { "epoch": 1.02, "learning_rate": 2.774489095975204e-05, "loss": 3.4962, "step": 1359360 }, { "epoch": 1.02, "learning_rate": 2.773652139104525e-05, "loss": 3.4976, "step": 1359872 }, { "epoch": 1.02, "learning_rate": 2.772813544353473e-05, "loss": 3.505, "step": 1360384 }, { "epoch": 1.02, "learning_rate": 2.771974949602421e-05, "loss": 3.5072, "step": 1360896 }, { "epoch": 1.02, "learning_rate": 2.771136354851369e-05, "loss": 3.5074, "step": 1361408 }, { "epoch": 1.02, "learning_rate": 2.7702993979806903e-05, "loss": 3.5078, "step": 1361920 }, { "epoch": 1.02, "learning_rate": 2.7694608032296383e-05, "loss": 3.5028, "step": 1362432 }, { "epoch": 1.02, "learning_rate": 2.7686222084785863e-05, "loss": 3.5057, "step": 1362944 }, { "epoch": 1.02, "learning_rate": 2.7677836137275343e-05, "loss": 3.5049, "step": 1363456 }, { "epoch": 1.02, "learning_rate": 2.7669466568568552e-05, "loss": 3.5124, "step": 1363968 }, { "epoch": 1.02, "learning_rate": 2.7661080621058032e-05, "loss": 3.5037, "step": 1364480 }, { "epoch": 1.02, "learning_rate": 2.7652694673547512e-05, "loss": 3.4895, "step": 1364992 }, { "epoch": 1.02, "learning_rate": 2.7644308726036995e-05, "loss": 3.4958, "step": 1365504 }, { "epoch": 1.02, "learning_rate": 2.7635939157330204e-05, "loss": 3.5132, "step": 1366016 }, { "epoch": 1.02, "learning_rate": 2.7627553209819684e-05, "loss": 3.5127, "step": 1366528 }, { "epoch": 1.02, "learning_rate": 2.7619167262309164e-05, "loss": 3.503, "step": 1367040 }, { "epoch": 1.02, "learning_rate": 2.7610781314798644e-05, "loss": 3.4961, "step": 1367552 }, { "epoch": 1.02, "learning_rate": 2.7602411746091857e-05, "loss": 3.5164, "step": 1368064 }, { "epoch": 1.02, "learning_rate": 2.7594025798581337e-05, "loss": 3.5102, "step": 1368576 }, { "epoch": 1.02, "learning_rate": 2.7585639851070817e-05, "loss": 3.5091, "step": 1369088 }, { "epoch": 1.02, "learning_rate": 2.7577253903560297e-05, "loss": 3.5064, "step": 1369600 }, { "epoch": 1.02, "learning_rate": 2.7568884334853506e-05, "loss": 3.5042, "step": 1370112 }, { "epoch": 1.02, "learning_rate": 2.7560498387342986e-05, "loss": 3.5063, "step": 1370624 }, { "epoch": 1.02, "learning_rate": 2.7552112439832466e-05, "loss": 3.4975, "step": 1371136 }, { "epoch": 1.02, "learning_rate": 2.754372649232195e-05, "loss": 3.5171, "step": 1371648 }, { "epoch": 1.02, "learning_rate": 2.7535356923615158e-05, "loss": 3.502, "step": 1372160 }, { "epoch": 1.02, "learning_rate": 2.7526970976104638e-05, "loss": 3.5138, "step": 1372672 }, { "epoch": 1.02, "learning_rate": 2.7518585028594118e-05, "loss": 3.5059, "step": 1373184 }, { "epoch": 1.02, "learning_rate": 2.7510199081083598e-05, "loss": 3.495, "step": 1373696 }, { "epoch": 1.03, "eval_loss": 3.870008945465088, "eval_runtime": 308.3151, "eval_samples_per_second": 1237.666, "eval_steps_per_second": 38.678, "step": 1373760 }, { "epoch": 0.0, "learning_rate": 2.7501813133573078e-05, "loss": 3.5063, "step": 1374208 }, { "epoch": 0.0, "learning_rate": 2.7493427186062558e-05, "loss": 3.5015, "step": 1374720 }, { "epoch": 0.0, "learning_rate": 2.7485041238552034e-05, "loss": 3.5066, "step": 1375232 }, { "epoch": 0.0, "learning_rate": 2.7476655291041514e-05, "loss": 3.5063, "step": 1375744 }, { "epoch": 0.0, "learning_rate": 2.746828572233473e-05, "loss": 3.5143, "step": 1376256 }, { "epoch": 0.0, "learning_rate": 2.745989977482421e-05, "loss": 3.5007, "step": 1376768 }, { "epoch": 0.0, "learning_rate": 2.7451513827313687e-05, "loss": 3.4965, "step": 1377280 }, { "epoch": 0.0, "learning_rate": 2.7443127879803167e-05, "loss": 3.4887, "step": 1377792 }, { "epoch": 0.0, "learning_rate": 2.7434758311096383e-05, "loss": 3.5209, "step": 1378304 }, { "epoch": 0.0, "learning_rate": 2.7426372363585856e-05, "loss": 3.5056, "step": 1378816 }, { "epoch": 0.0, "learning_rate": 2.7417986416075336e-05, "loss": 3.4949, "step": 1379328 }, { "epoch": 0.0, "learning_rate": 2.7409600468564816e-05, "loss": 3.514, "step": 1379840 }, { "epoch": 0.0, "learning_rate": 2.7401247278661764e-05, "loss": 3.5015, "step": 1380352 }, { "epoch": 0.0, "learning_rate": 2.7392861331151244e-05, "loss": 3.5001, "step": 1380864 }, { "epoch": 0.0, "learning_rate": 2.7384475383640724e-05, "loss": 3.4929, "step": 1381376 }, { "epoch": 0.0, "learning_rate": 2.7376089436130204e-05, "loss": 3.4966, "step": 1381888 }, { "epoch": 0.0, "learning_rate": 2.7367703488619677e-05, "loss": 3.4982, "step": 1382400 }, { "epoch": 0.0, "learning_rate": 2.7359317541109157e-05, "loss": 3.4929, "step": 1382912 }, { "epoch": 0.0, "learning_rate": 2.735093159359864e-05, "loss": 3.5133, "step": 1383424 }, { "epoch": 0.0, "learning_rate": 2.734254564608812e-05, "loss": 3.5157, "step": 1383936 }, { "epoch": 0.0, "learning_rate": 2.733417607738133e-05, "loss": 3.5047, "step": 1384448 }, { "epoch": 0.0, "learning_rate": 2.732579012987081e-05, "loss": 3.4979, "step": 1384960 }, { "epoch": 0.0, "learning_rate": 2.731740418236029e-05, "loss": 3.5017, "step": 1385472 }, { "epoch": 0.0, "learning_rate": 2.7309034613653505e-05, "loss": 3.5067, "step": 1385984 }, { "epoch": 0.0, "learning_rate": 2.7300648666142982e-05, "loss": 3.4948, "step": 1386496 }, { "epoch": 0.0, "learning_rate": 2.7292262718632462e-05, "loss": 3.4968, "step": 1387008 }, { "epoch": 0.0, "learning_rate": 2.7283876771121942e-05, "loss": 3.4953, "step": 1387520 }, { "epoch": 0.0, "learning_rate": 2.727550720241515e-05, "loss": 3.5094, "step": 1388032 }, { "epoch": 0.0, "learning_rate": 2.726712125490463e-05, "loss": 3.4835, "step": 1388544 }, { "epoch": 0.01, "learning_rate": 2.725873530739411e-05, "loss": 3.4937, "step": 1389056 }, { "epoch": 0.01, "learning_rate": 2.7250349359883594e-05, "loss": 3.5052, "step": 1389568 }, { "epoch": 0.01, "learning_rate": 2.7241979791176803e-05, "loss": 3.5042, "step": 1390080 }, { "epoch": 0.01, "learning_rate": 2.7233593843666283e-05, "loss": 3.5064, "step": 1390592 }, { "epoch": 0.01, "learning_rate": 2.7225207896155763e-05, "loss": 3.5044, "step": 1391104 }, { "epoch": 0.01, "learning_rate": 2.7216821948645243e-05, "loss": 3.4956, "step": 1391616 }, { "epoch": 0.01, "learning_rate": 2.7208452379938456e-05, "loss": 3.5098, "step": 1392128 }, { "epoch": 0.01, "learning_rate": 2.7200066432427935e-05, "loss": 3.4923, "step": 1392640 }, { "epoch": 0.01, "learning_rate": 2.7191680484917415e-05, "loss": 3.4995, "step": 1393152 }, { "epoch": 0.01, "learning_rate": 2.7183294537406895e-05, "loss": 3.4832, "step": 1393664 }, { "epoch": 0.01, "learning_rate": 2.7174924968700104e-05, "loss": 3.4943, "step": 1394176 }, { "epoch": 0.01, "learning_rate": 2.7166539021189584e-05, "loss": 3.4937, "step": 1394688 }, { "epoch": 0.01, "learning_rate": 2.7158153073679064e-05, "loss": 3.5061, "step": 1395200 }, { "epoch": 0.01, "learning_rate": 2.7149767126168544e-05, "loss": 3.4985, "step": 1395712 }, { "epoch": 0.01, "learning_rate": 2.7141397557461757e-05, "loss": 3.4951, "step": 1396224 }, { "epoch": 0.01, "learning_rate": 2.7133011609951237e-05, "loss": 3.5025, "step": 1396736 }, { "epoch": 0.01, "learning_rate": 2.7124625662440717e-05, "loss": 3.5004, "step": 1397248 }, { "epoch": 0.01, "learning_rate": 2.7116239714930197e-05, "loss": 3.4996, "step": 1397760 }, { "epoch": 0.01, "learning_rate": 2.7107870146223406e-05, "loss": 3.4913, "step": 1398272 }, { "epoch": 0.01, "learning_rate": 2.709948419871289e-05, "loss": 3.4825, "step": 1398784 }, { "epoch": 0.01, "learning_rate": 2.709109825120237e-05, "loss": 3.5072, "step": 1399296 }, { "epoch": 0.01, "learning_rate": 2.708271230369185e-05, "loss": 3.503, "step": 1399808 }, { "epoch": 0.01, "learning_rate": 2.7074342734985058e-05, "loss": 3.4969, "step": 1400320 }, { "epoch": 0.01, "learning_rate": 2.7065956787474538e-05, "loss": 3.4951, "step": 1400832 }, { "epoch": 0.01, "learning_rate": 2.7057570839964018e-05, "loss": 3.489, "step": 1401344 }, { "epoch": 0.01, "learning_rate": 2.7049184892453498e-05, "loss": 3.4885, "step": 1401856 }, { "epoch": 0.01, "learning_rate": 2.704081532374671e-05, "loss": 3.4964, "step": 1402368 }, { "epoch": 0.01, "learning_rate": 2.703242937623619e-05, "loss": 3.4885, "step": 1402880 }, { "epoch": 0.01, "learning_rate": 2.702404342872567e-05, "loss": 3.4974, "step": 1403392 }, { "epoch": 0.01, "learning_rate": 2.701565748121515e-05, "loss": 3.4979, "step": 1403904 }, { "epoch": 0.01, "learning_rate": 2.700728791250836e-05, "loss": 3.4899, "step": 1404416 }, { "epoch": 0.01, "learning_rate": 2.6998901964997843e-05, "loss": 3.4828, "step": 1404928 }, { "epoch": 0.01, "learning_rate": 2.6990516017487323e-05, "loss": 3.5055, "step": 1405440 }, { "epoch": 0.01, "learning_rate": 2.6982130069976803e-05, "loss": 3.4844, "step": 1405952 }, { "epoch": 0.01, "learning_rate": 2.6973760501270012e-05, "loss": 3.4927, "step": 1406464 }, { "epoch": 0.01, "learning_rate": 2.6965374553759492e-05, "loss": 3.4978, "step": 1406976 }, { "epoch": 0.01, "learning_rate": 2.6956988606248972e-05, "loss": 3.5022, "step": 1407488 }, { "epoch": 0.01, "learning_rate": 2.694860265873845e-05, "loss": 3.4857, "step": 1408000 }, { "epoch": 0.01, "learning_rate": 2.6940233090031664e-05, "loss": 3.4886, "step": 1408512 }, { "epoch": 0.01, "learning_rate": 2.6931847142521144e-05, "loss": 3.4836, "step": 1409024 }, { "epoch": 0.01, "learning_rate": 2.6923461195010624e-05, "loss": 3.4976, "step": 1409536 }, { "epoch": 0.01, "learning_rate": 2.6915075247500104e-05, "loss": 3.4993, "step": 1410048 }, { "epoch": 0.01, "learning_rate": 2.6906705678793313e-05, "loss": 3.4946, "step": 1410560 }, { "epoch": 0.01, "learning_rate": 2.6898319731282796e-05, "loss": 3.5005, "step": 1411072 }, { "epoch": 0.01, "learning_rate": 2.6889933783772276e-05, "loss": 3.4983, "step": 1411584 }, { "epoch": 0.01, "learning_rate": 2.6881547836261756e-05, "loss": 3.5065, "step": 1412096 }, { "epoch": 0.01, "learning_rate": 2.6873178267554965e-05, "loss": 3.4873, "step": 1412608 }, { "epoch": 0.01, "learning_rate": 2.6864792320044445e-05, "loss": 3.4995, "step": 1413120 }, { "epoch": 0.01, "learning_rate": 2.6856422751337658e-05, "loss": 3.5054, "step": 1413632 }, { "epoch": 0.01, "learning_rate": 2.6848036803827138e-05, "loss": 3.4827, "step": 1414144 }, { "epoch": 0.01, "learning_rate": 2.6839650856316618e-05, "loss": 3.4994, "step": 1414656 }, { "epoch": 0.01, "learning_rate": 2.6831264908806098e-05, "loss": 3.4884, "step": 1415168 }, { "epoch": 0.01, "learning_rate": 2.6822878961295578e-05, "loss": 3.5122, "step": 1415680 }, { "epoch": 0.01, "learning_rate": 2.6814493013785058e-05, "loss": 3.4947, "step": 1416192 }, { "epoch": 0.01, "learning_rate": 2.6806107066274538e-05, "loss": 3.4804, "step": 1416704 }, { "epoch": 0.01, "learning_rate": 2.679773749756775e-05, "loss": 3.4905, "step": 1417216 }, { "epoch": 0.01, "learning_rate": 2.678935155005723e-05, "loss": 3.4921, "step": 1417728 }, { "epoch": 0.01, "learning_rate": 2.678096560254671e-05, "loss": 3.5029, "step": 1418240 }, { "epoch": 0.01, "learning_rate": 2.677257965503619e-05, "loss": 3.4954, "step": 1418752 }, { "epoch": 0.01, "learning_rate": 2.67642100863294e-05, "loss": 3.4921, "step": 1419264 }, { "epoch": 0.02, "learning_rate": 2.675582413881888e-05, "loss": 3.4942, "step": 1419776 }, { "epoch": 0.02, "learning_rate": 2.674743819130836e-05, "loss": 3.4877, "step": 1420288 }, { "epoch": 0.02, "learning_rate": 2.6739052243797842e-05, "loss": 3.4865, "step": 1420800 }, { "epoch": 0.02, "learning_rate": 2.673068267509105e-05, "loss": 3.4781, "step": 1421312 }, { "epoch": 0.02, "learning_rate": 2.672229672758053e-05, "loss": 3.4951, "step": 1421824 }, { "epoch": 0.02, "learning_rate": 2.671391078007001e-05, "loss": 3.4992, "step": 1422336 }, { "epoch": 0.02, "learning_rate": 2.670552483255949e-05, "loss": 3.4958, "step": 1422848 }, { "epoch": 0.02, "learning_rate": 2.6697155263852704e-05, "loss": 3.4873, "step": 1423360 }, { "epoch": 0.02, "learning_rate": 2.6688769316342184e-05, "loss": 3.4938, "step": 1423872 }, { "epoch": 0.02, "learning_rate": 2.6680383368831664e-05, "loss": 3.4894, "step": 1424384 }, { "epoch": 0.02, "learning_rate": 2.6671997421321144e-05, "loss": 3.5035, "step": 1424896 }, { "epoch": 0.02, "learning_rate": 2.6663627852614353e-05, "loss": 3.4936, "step": 1425408 }, { "epoch": 0.02, "learning_rate": 2.6655241905103833e-05, "loss": 3.4938, "step": 1425920 }, { "epoch": 0.02, "learning_rate": 2.6646855957593313e-05, "loss": 3.4903, "step": 1426432 }, { "epoch": 0.02, "learning_rate": 2.6638470010082796e-05, "loss": 3.5017, "step": 1426944 }, { "epoch": 0.02, "learning_rate": 2.6630100441376005e-05, "loss": 3.4778, "step": 1427456 }, { "epoch": 0.02, "learning_rate": 2.6621714493865485e-05, "loss": 3.4969, "step": 1427968 }, { "epoch": 0.02, "learning_rate": 2.6613328546354965e-05, "loss": 3.4904, "step": 1428480 }, { "epoch": 0.02, "learning_rate": 2.6604942598844445e-05, "loss": 3.4951, "step": 1428992 }, { "epoch": 0.02, "learning_rate": 2.6596573030137657e-05, "loss": 3.4825, "step": 1429504 }, { "epoch": 0.02, "learning_rate": 2.6588187082627137e-05, "loss": 3.4935, "step": 1430016 }, { "epoch": 0.02, "learning_rate": 2.6579801135116617e-05, "loss": 3.4883, "step": 1430528 }, { "epoch": 0.02, "learning_rate": 2.6571415187606097e-05, "loss": 3.4915, "step": 1431040 }, { "epoch": 0.02, "learning_rate": 2.6563045618899306e-05, "loss": 3.4917, "step": 1431552 }, { "epoch": 0.02, "learning_rate": 2.6554659671388786e-05, "loss": 3.4908, "step": 1432064 }, { "epoch": 0.02, "learning_rate": 2.6546273723878266e-05, "loss": 3.4989, "step": 1432576 }, { "epoch": 0.02, "learning_rate": 2.653788777636775e-05, "loss": 3.5021, "step": 1433088 }, { "epoch": 0.02, "learning_rate": 2.652951820766096e-05, "loss": 3.4962, "step": 1433600 }, { "epoch": 0.02, "learning_rate": 2.652113226015044e-05, "loss": 3.4998, "step": 1434112 }, { "epoch": 0.02, "learning_rate": 2.651274631263992e-05, "loss": 3.4975, "step": 1434624 }, { "epoch": 0.02, "learning_rate": 2.65043603651294e-05, "loss": 3.4871, "step": 1435136 }, { "epoch": 0.02, "learning_rate": 2.649599079642261e-05, "loss": 3.4866, "step": 1435648 }, { "epoch": 0.02, "learning_rate": 2.648760484891209e-05, "loss": 3.4897, "step": 1436160 }, { "epoch": 0.02, "learning_rate": 2.647921890140157e-05, "loss": 3.488, "step": 1436672 }, { "epoch": 0.02, "learning_rate": 2.647083295389105e-05, "loss": 3.4969, "step": 1437184 }, { "epoch": 0.02, "learning_rate": 2.646246338518426e-05, "loss": 3.4914, "step": 1437696 }, { "epoch": 0.02, "learning_rate": 2.645407743767374e-05, "loss": 3.4977, "step": 1438208 }, { "epoch": 0.02, "learning_rate": 2.644569149016322e-05, "loss": 3.4914, "step": 1438720 }, { "epoch": 0.02, "learning_rate": 2.64373055426527e-05, "loss": 3.4904, "step": 1439232 }, { "epoch": 0.02, "learning_rate": 2.6428935973945912e-05, "loss": 3.4905, "step": 1439744 }, { "epoch": 0.02, "learning_rate": 2.6420550026435392e-05, "loss": 3.5052, "step": 1440256 }, { "epoch": 0.02, "learning_rate": 2.6412164078924872e-05, "loss": 3.4865, "step": 1440768 }, { "epoch": 0.02, "learning_rate": 2.6403778131414352e-05, "loss": 3.4844, "step": 1441280 }, { "epoch": 0.02, "learning_rate": 2.639540856270756e-05, "loss": 3.4793, "step": 1441792 }, { "epoch": 0.02, "learning_rate": 2.6387022615197045e-05, "loss": 3.4985, "step": 1442304 }, { "epoch": 0.02, "learning_rate": 2.6378636667686525e-05, "loss": 3.4984, "step": 1442816 }, { "epoch": 0.02, "learning_rate": 2.6370250720176005e-05, "loss": 3.4949, "step": 1443328 }, { "epoch": 0.02, "learning_rate": 2.6361881151469214e-05, "loss": 3.4851, "step": 1443840 }, { "epoch": 0.02, "learning_rate": 2.6353495203958694e-05, "loss": 3.5037, "step": 1444352 }, { "epoch": 0.02, "learning_rate": 2.6345109256448174e-05, "loss": 3.4941, "step": 1444864 }, { "epoch": 0.02, "learning_rate": 2.633672330893765e-05, "loss": 3.4984, "step": 1445376 }, { "epoch": 0.02, "learning_rate": 2.6328353740230866e-05, "loss": 3.4916, "step": 1445888 }, { "epoch": 0.02, "learning_rate": 2.6319967792720346e-05, "loss": 3.4938, "step": 1446400 }, { "epoch": 0.02, "learning_rate": 2.6311581845209826e-05, "loss": 3.493, "step": 1446912 }, { "epoch": 0.02, "learning_rate": 2.6303195897699303e-05, "loss": 3.4836, "step": 1447424 }, { "epoch": 0.02, "learning_rate": 2.6294826328992515e-05, "loss": 3.5021, "step": 1447936 }, { "epoch": 0.02, "learning_rate": 2.6286440381482e-05, "loss": 3.4932, "step": 1448448 }, { "epoch": 0.02, "learning_rate": 2.627805443397148e-05, "loss": 3.4977, "step": 1448960 }, { "epoch": 0.02, "learning_rate": 2.626966848646095e-05, "loss": 3.4931, "step": 1449472 }, { "epoch": 0.02, "learning_rate": 2.6261298917754167e-05, "loss": 3.4808, "step": 1449984 }, { "epoch": 0.03, "eval_loss": 3.8721539974212646, "eval_runtime": 306.9529, "eval_samples_per_second": 1243.158, "eval_steps_per_second": 38.85, "step": 1450080 }, { "epoch": 1.0, "learning_rate": 2.6252912970243647e-05, "loss": 3.4939, "step": 1450496 }, { "epoch": 1.0, "learning_rate": 2.6244527022733124e-05, "loss": 3.4916, "step": 1451008 }, { "epoch": 1.0, "learning_rate": 2.6236141075222604e-05, "loss": 3.4925, "step": 1451520 }, { "epoch": 1.0, "learning_rate": 2.622777150651582e-05, "loss": 3.4942, "step": 1452032 }, { "epoch": 1.0, "learning_rate": 2.62193855590053e-05, "loss": 3.5052, "step": 1452544 }, { "epoch": 1.0, "learning_rate": 2.6210999611494773e-05, "loss": 3.4904, "step": 1453056 }, { "epoch": 1.0, "learning_rate": 2.6202613663984253e-05, "loss": 3.482, "step": 1453568 }, { "epoch": 1.0, "learning_rate": 2.619424409527747e-05, "loss": 3.4761, "step": 1454080 }, { "epoch": 1.0, "learning_rate": 2.6185858147766952e-05, "loss": 3.5029, "step": 1454592 }, { "epoch": 1.0, "learning_rate": 2.6177472200256425e-05, "loss": 3.4973, "step": 1455104 }, { "epoch": 1.0, "learning_rate": 2.6169086252745905e-05, "loss": 3.4763, "step": 1455616 }, { "epoch": 1.0, "learning_rate": 2.616071668403912e-05, "loss": 3.5011, "step": 1456128 }, { "epoch": 1.0, "learning_rate": 2.615234711533233e-05, "loss": 3.4896, "step": 1456640 }, { "epoch": 1.0, "learning_rate": 2.6143961167821814e-05, "loss": 3.488, "step": 1457152 }, { "epoch": 1.0, "learning_rate": 2.6135575220311294e-05, "loss": 3.4841, "step": 1457664 }, { "epoch": 1.0, "learning_rate": 2.6127189272800773e-05, "loss": 3.4843, "step": 1458176 }, { "epoch": 1.0, "learning_rate": 2.6118803325290247e-05, "loss": 3.4847, "step": 1458688 }, { "epoch": 1.0, "learning_rate": 2.6110417377779727e-05, "loss": 3.4805, "step": 1459200 }, { "epoch": 1.0, "learning_rate": 2.6102031430269207e-05, "loss": 3.5003, "step": 1459712 }, { "epoch": 1.0, "learning_rate": 2.609364548275869e-05, "loss": 3.5016, "step": 1460224 }, { "epoch": 1.0, "learning_rate": 2.60852759140519e-05, "loss": 3.4939, "step": 1460736 }, { "epoch": 1.0, "learning_rate": 2.607688996654138e-05, "loss": 3.4875, "step": 1461248 }, { "epoch": 1.0, "learning_rate": 2.606850401903086e-05, "loss": 3.4872, "step": 1461760 }, { "epoch": 1.0, "learning_rate": 2.6060134450324068e-05, "loss": 3.4958, "step": 1462272 }, { "epoch": 1.0, "learning_rate": 2.605174850281355e-05, "loss": 3.4822, "step": 1462784 }, { "epoch": 1.0, "learning_rate": 2.604336255530303e-05, "loss": 3.4862, "step": 1463296 }, { "epoch": 1.0, "learning_rate": 2.603497660779251e-05, "loss": 3.4805, "step": 1463808 }, { "epoch": 1.0, "learning_rate": 2.602660703908572e-05, "loss": 3.496, "step": 1464320 }, { "epoch": 1.0, "learning_rate": 2.60182210915752e-05, "loss": 3.4743, "step": 1464832 }, { "epoch": 1.01, "learning_rate": 2.600983514406468e-05, "loss": 3.4828, "step": 1465344 }, { "epoch": 1.01, "learning_rate": 2.600144919655416e-05, "loss": 3.4931, "step": 1465856 }, { "epoch": 1.01, "learning_rate": 2.5993079627847373e-05, "loss": 3.4893, "step": 1466368 }, { "epoch": 1.01, "learning_rate": 2.5984693680336853e-05, "loss": 3.4935, "step": 1466880 }, { "epoch": 1.01, "learning_rate": 2.5976307732826333e-05, "loss": 3.4929, "step": 1467392 }, { "epoch": 1.01, "learning_rate": 2.5967921785315813e-05, "loss": 3.485, "step": 1467904 }, { "epoch": 1.01, "learning_rate": 2.595955221660902e-05, "loss": 3.4955, "step": 1468416 }, { "epoch": 1.01, "learning_rate": 2.5951166269098505e-05, "loss": 3.4825, "step": 1468928 }, { "epoch": 1.01, "learning_rate": 2.5942780321587985e-05, "loss": 3.4786, "step": 1469440 }, { "epoch": 1.01, "learning_rate": 2.5934394374077465e-05, "loss": 3.4746, "step": 1469952 }, { "epoch": 1.01, "learning_rate": 2.5926024805370674e-05, "loss": 3.4805, "step": 1470464 }, { "epoch": 1.01, "learning_rate": 2.5917638857860154e-05, "loss": 3.4785, "step": 1470976 }, { "epoch": 1.01, "learning_rate": 2.5909252910349634e-05, "loss": 3.4967, "step": 1471488 }, { "epoch": 1.01, "learning_rate": 2.5900866962839114e-05, "loss": 3.4847, "step": 1472000 }, { "epoch": 1.01, "learning_rate": 2.5892497394132326e-05, "loss": 3.4832, "step": 1472512 }, { "epoch": 1.01, "learning_rate": 2.5884111446621806e-05, "loss": 3.4935, "step": 1473024 }, { "epoch": 1.01, "learning_rate": 2.5875725499111286e-05, "loss": 3.484, "step": 1473536 }, { "epoch": 1.01, "learning_rate": 2.5867339551600766e-05, "loss": 3.4932, "step": 1474048 }, { "epoch": 1.01, "learning_rate": 2.5858969982893975e-05, "loss": 3.4801, "step": 1474560 }, { "epoch": 1.01, "learning_rate": 2.585058403538346e-05, "loss": 3.4665, "step": 1475072 }, { "epoch": 1.01, "learning_rate": 2.584219808787294e-05, "loss": 3.497, "step": 1475584 }, { "epoch": 1.01, "learning_rate": 2.583381214036242e-05, "loss": 3.49, "step": 1476096 }, { "epoch": 1.01, "learning_rate": 2.5825442571655628e-05, "loss": 3.4905, "step": 1476608 }, { "epoch": 1.01, "learning_rate": 2.5817056624145108e-05, "loss": 3.4795, "step": 1477120 }, { "epoch": 1.01, "learning_rate": 2.5808670676634588e-05, "loss": 3.4769, "step": 1477632 }, { "epoch": 1.01, "learning_rate": 2.5800284729124068e-05, "loss": 3.4769, "step": 1478144 }, { "epoch": 1.01, "learning_rate": 2.579191516041728e-05, "loss": 3.4841, "step": 1478656 }, { "epoch": 1.01, "learning_rate": 2.578352921290676e-05, "loss": 3.4777, "step": 1479168 }, { "epoch": 1.01, "learning_rate": 2.577514326539624e-05, "loss": 3.4796, "step": 1479680 }, { "epoch": 1.01, "learning_rate": 2.576675731788572e-05, "loss": 3.4886, "step": 1480192 }, { "epoch": 1.01, "learning_rate": 2.575838774917893e-05, "loss": 3.4788, "step": 1480704 }, { "epoch": 1.01, "learning_rate": 2.5750001801668412e-05, "loss": 3.4697, "step": 1481216 }, { "epoch": 1.01, "learning_rate": 2.5741615854157892e-05, "loss": 3.4938, "step": 1481728 }, { "epoch": 1.01, "learning_rate": 2.5733229906647372e-05, "loss": 3.4712, "step": 1482240 }, { "epoch": 1.01, "learning_rate": 2.572486033794058e-05, "loss": 3.4762, "step": 1482752 }, { "epoch": 1.01, "learning_rate": 2.571647439043006e-05, "loss": 3.4888, "step": 1483264 }, { "epoch": 1.01, "learning_rate": 2.570808844291954e-05, "loss": 3.4915, "step": 1483776 }, { "epoch": 1.01, "learning_rate": 2.569970249540902e-05, "loss": 3.4706, "step": 1484288 }, { "epoch": 1.01, "learning_rate": 2.5691332926702234e-05, "loss": 3.4792, "step": 1484800 }, { "epoch": 1.01, "learning_rate": 2.5682946979191714e-05, "loss": 3.467, "step": 1485312 }, { "epoch": 1.01, "learning_rate": 2.5674561031681194e-05, "loss": 3.4891, "step": 1485824 }, { "epoch": 1.01, "learning_rate": 2.5666175084170674e-05, "loss": 3.485, "step": 1486336 }, { "epoch": 1.01, "learning_rate": 2.5657805515463883e-05, "loss": 3.483, "step": 1486848 }, { "epoch": 1.01, "learning_rate": 2.5649419567953366e-05, "loss": 3.487, "step": 1487360 }, { "epoch": 1.01, "learning_rate": 2.5641033620442846e-05, "loss": 3.4869, "step": 1487872 }, { "epoch": 1.01, "learning_rate": 2.5632647672932326e-05, "loss": 3.4952, "step": 1488384 }, { "epoch": 1.01, "learning_rate": 2.5624278104225535e-05, "loss": 3.4736, "step": 1488896 }, { "epoch": 1.01, "learning_rate": 2.5615892156715015e-05, "loss": 3.4861, "step": 1489408 }, { "epoch": 1.01, "learning_rate": 2.5607522588008227e-05, "loss": 3.4939, "step": 1489920 }, { "epoch": 1.01, "learning_rate": 2.5599136640497707e-05, "loss": 3.4684, "step": 1490432 }, { "epoch": 1.01, "learning_rate": 2.5590750692987187e-05, "loss": 3.486, "step": 1490944 }, { "epoch": 1.01, "learning_rate": 2.5582364745476667e-05, "loss": 3.4792, "step": 1491456 }, { "epoch": 1.01, "learning_rate": 2.5573978797966147e-05, "loss": 3.494, "step": 1491968 }, { "epoch": 1.01, "learning_rate": 2.5565592850455627e-05, "loss": 3.487, "step": 1492480 }, { "epoch": 1.01, "learning_rate": 2.5557206902945107e-05, "loss": 3.468, "step": 1492992 }, { "epoch": 1.01, "learning_rate": 2.5548820955434587e-05, "loss": 3.4788, "step": 1493504 }, { "epoch": 1.01, "learning_rate": 2.55404513867278e-05, "loss": 3.478, "step": 1494016 }, { "epoch": 1.01, "learning_rate": 2.553206543921728e-05, "loss": 3.4907, "step": 1494528 }, { "epoch": 1.01, "learning_rate": 2.552367949170676e-05, "loss": 3.4828, "step": 1495040 }, { "epoch": 1.01, "learning_rate": 2.551530992299997e-05, "loss": 3.4791, "step": 1495552 }, { "epoch": 1.02, "learning_rate": 2.550692397548945e-05, "loss": 3.4791, "step": 1496064 }, { "epoch": 1.02, "learning_rate": 2.549853802797893e-05, "loss": 3.4792, "step": 1496576 }, { "epoch": 1.02, "learning_rate": 2.549015208046841e-05, "loss": 3.4745, "step": 1497088 }, { "epoch": 1.02, "learning_rate": 2.548178251176162e-05, "loss": 3.4653, "step": 1497600 }, { "epoch": 1.02, "learning_rate": 2.54733965642511e-05, "loss": 3.4814, "step": 1498112 }, { "epoch": 1.02, "learning_rate": 2.546501061674058e-05, "loss": 3.4893, "step": 1498624 }, { "epoch": 1.02, "learning_rate": 2.545662466923006e-05, "loss": 3.4876, "step": 1499136 }, { "epoch": 1.02, "learning_rate": 2.5448255100523273e-05, "loss": 3.4691, "step": 1499648 }, { "epoch": 1.02, "learning_rate": 2.5439869153012753e-05, "loss": 3.482, "step": 1500160 }, { "epoch": 1.02, "learning_rate": 2.5431483205502233e-05, "loss": 3.4759, "step": 1500672 }, { "epoch": 1.02, "learning_rate": 2.5423097257991713e-05, "loss": 3.4898, "step": 1501184 }, { "epoch": 1.02, "learning_rate": 2.5414727689284922e-05, "loss": 3.4811, "step": 1501696 }, { "epoch": 1.02, "learning_rate": 2.5406341741774402e-05, "loss": 3.4821, "step": 1502208 }, { "epoch": 1.02, "learning_rate": 2.5397955794263882e-05, "loss": 3.4768, "step": 1502720 }, { "epoch": 1.02, "learning_rate": 2.5389569846753362e-05, "loss": 3.4882, "step": 1503232 }, { "epoch": 1.02, "learning_rate": 2.5381200278046575e-05, "loss": 3.4662, "step": 1503744 }, { "epoch": 1.02, "learning_rate": 2.5372814330536055e-05, "loss": 3.4839, "step": 1504256 }, { "epoch": 1.02, "learning_rate": 2.5364428383025535e-05, "loss": 3.4745, "step": 1504768 }, { "epoch": 1.02, "learning_rate": 2.5356042435515015e-05, "loss": 3.4819, "step": 1505280 }, { "epoch": 1.02, "learning_rate": 2.5347672866808224e-05, "loss": 3.4712, "step": 1505792 }, { "epoch": 1.02, "learning_rate": 2.5339286919297707e-05, "loss": 3.4861, "step": 1506304 }, { "epoch": 1.02, "learning_rate": 2.5330900971787187e-05, "loss": 3.4734, "step": 1506816 }, { "epoch": 1.02, "learning_rate": 2.5322515024276667e-05, "loss": 3.4773, "step": 1507328 }, { "epoch": 1.02, "learning_rate": 2.5314145455569876e-05, "loss": 3.48, "step": 1507840 }, { "epoch": 1.02, "learning_rate": 2.5305759508059356e-05, "loss": 3.4775, "step": 1508352 }, { "epoch": 1.02, "learning_rate": 2.5297373560548836e-05, "loss": 3.4845, "step": 1508864 }, { "epoch": 1.02, "learning_rate": 2.5288987613038316e-05, "loss": 3.49, "step": 1509376 }, { "epoch": 1.02, "learning_rate": 2.528061804433153e-05, "loss": 3.4823, "step": 1509888 }, { "epoch": 1.02, "learning_rate": 2.5272232096821008e-05, "loss": 3.4879, "step": 1510400 }, { "epoch": 1.02, "learning_rate": 2.5263846149310488e-05, "loss": 3.4828, "step": 1510912 }, { "epoch": 1.02, "learning_rate": 2.5255460201799968e-05, "loss": 3.4753, "step": 1511424 }, { "epoch": 1.02, "learning_rate": 2.5247090633093177e-05, "loss": 3.4722, "step": 1511936 }, { "epoch": 1.02, "learning_rate": 2.523870468558266e-05, "loss": 3.4779, "step": 1512448 }, { "epoch": 1.02, "learning_rate": 2.523031873807214e-05, "loss": 3.4789, "step": 1512960 }, { "epoch": 1.02, "learning_rate": 2.522193279056162e-05, "loss": 3.4834, "step": 1513472 }, { "epoch": 1.02, "learning_rate": 2.521356322185483e-05, "loss": 3.4792, "step": 1513984 }, { "epoch": 1.02, "learning_rate": 2.520517727434431e-05, "loss": 3.4857, "step": 1514496 }, { "epoch": 1.02, "learning_rate": 2.519679132683379e-05, "loss": 3.4762, "step": 1515008 }, { "epoch": 1.02, "learning_rate": 2.518840537932327e-05, "loss": 3.4768, "step": 1515520 }, { "epoch": 1.02, "learning_rate": 2.5180035810616482e-05, "loss": 3.4757, "step": 1516032 }, { "epoch": 1.02, "learning_rate": 2.5171649863105962e-05, "loss": 3.4909, "step": 1516544 }, { "epoch": 1.02, "learning_rate": 2.5163263915595442e-05, "loss": 3.4761, "step": 1517056 }, { "epoch": 1.02, "learning_rate": 2.5154877968084915e-05, "loss": 3.4706, "step": 1517568 }, { "epoch": 1.02, "learning_rate": 2.514650839937813e-05, "loss": 3.4649, "step": 1518080 }, { "epoch": 1.02, "learning_rate": 2.5138122451867614e-05, "loss": 3.4846, "step": 1518592 }, { "epoch": 1.02, "learning_rate": 2.5129736504357094e-05, "loss": 3.4866, "step": 1519104 }, { "epoch": 1.02, "learning_rate": 2.5121350556846567e-05, "loss": 3.4849, "step": 1519616 }, { "epoch": 1.02, "learning_rate": 2.5112980988139783e-05, "loss": 3.4754, "step": 1520128 }, { "epoch": 1.02, "learning_rate": 2.5104595040629263e-05, "loss": 3.4911, "step": 1520640 }, { "epoch": 1.02, "learning_rate": 2.5096209093118743e-05, "loss": 3.4808, "step": 1521152 }, { "epoch": 1.02, "learning_rate": 2.508782314560822e-05, "loss": 3.4837, "step": 1521664 }, { "epoch": 1.02, "learning_rate": 2.5079453576901436e-05, "loss": 3.4795, "step": 1522176 }, { "epoch": 1.02, "learning_rate": 2.5071067629390916e-05, "loss": 3.4803, "step": 1522688 }, { "epoch": 1.02, "learning_rate": 2.506268168188039e-05, "loss": 3.4838, "step": 1523200 }, { "epoch": 1.02, "learning_rate": 2.505429573436987e-05, "loss": 3.4695, "step": 1523712 }, { "epoch": 1.02, "learning_rate": 2.5045926165663085e-05, "loss": 3.489, "step": 1524224 }, { "epoch": 1.02, "learning_rate": 2.5037540218152568e-05, "loss": 3.4857, "step": 1524736 }, { "epoch": 1.02, "learning_rate": 2.502915427064204e-05, "loss": 3.4831, "step": 1525248 }, { "epoch": 1.02, "learning_rate": 2.502076832313152e-05, "loss": 3.4787, "step": 1525760 }, { "epoch": 1.02, "learning_rate": 2.5012398754424737e-05, "loss": 3.4732, "step": 1526272 }, { "epoch": 1.03, "eval_loss": 3.872343063354492, "eval_runtime": 306.6327, "eval_samples_per_second": 1244.456, "eval_steps_per_second": 38.89, "step": 1526400 }, { "epoch": 0.0, "learning_rate": 2.5004012806914217e-05, "loss": 3.4778, "step": 1526784 }, { "epoch": 0.0, "learning_rate": 2.4995626859403694e-05, "loss": 3.4799, "step": 1527296 }, { "epoch": 0.0, "learning_rate": 2.4987240911893177e-05, "loss": 3.4806, "step": 1527808 }, { "epoch": 0.0, "learning_rate": 2.4978854964382657e-05, "loss": 3.4829, "step": 1528320 }, { "epoch": 0.0, "learning_rate": 2.4970485395675866e-05, "loss": 3.491, "step": 1528832 }, { "epoch": 0.0, "learning_rate": 2.4962099448165346e-05, "loss": 3.4798, "step": 1529344 }, { "epoch": 0.0, "learning_rate": 2.4953713500654826e-05, "loss": 3.4679, "step": 1529856 }, { "epoch": 0.0, "learning_rate": 2.4945327553144306e-05, "loss": 3.4692, "step": 1530368 }, { "epoch": 0.0, "learning_rate": 2.4936957984437518e-05, "loss": 3.4887, "step": 1530880 }, { "epoch": 0.0, "learning_rate": 2.4928572036926998e-05, "loss": 3.4834, "step": 1531392 }, { "epoch": 0.0, "learning_rate": 2.4920186089416478e-05, "loss": 3.4693, "step": 1531904 }, { "epoch": 0.0, "learning_rate": 2.4911800141905955e-05, "loss": 3.4864, "step": 1532416 }, { "epoch": 0.0, "learning_rate": 2.49034469520029e-05, "loss": 3.478, "step": 1532928 }, { "epoch": 0.0, "learning_rate": 2.489506100449238e-05, "loss": 3.4775, "step": 1533440 }, { "epoch": 0.0, "learning_rate": 2.488667505698186e-05, "loss": 3.4719, "step": 1533952 }, { "epoch": 0.0, "learning_rate": 2.487828910947134e-05, "loss": 3.4738, "step": 1534464 }, { "epoch": 0.0, "learning_rate": 2.486990316196082e-05, "loss": 3.469, "step": 1534976 }, { "epoch": 0.0, "learning_rate": 2.48615172144503e-05, "loss": 3.4685, "step": 1535488 }, { "epoch": 0.0, "learning_rate": 2.485313126693978e-05, "loss": 3.4883, "step": 1536000 }, { "epoch": 0.0, "learning_rate": 2.484474531942926e-05, "loss": 3.4868, "step": 1536512 }, { "epoch": 0.0, "learning_rate": 2.4836375750722472e-05, "loss": 3.4845, "step": 1537024 }, { "epoch": 0.0, "learning_rate": 2.4827989803211952e-05, "loss": 3.4763, "step": 1537536 }, { "epoch": 0.0, "learning_rate": 2.481960385570143e-05, "loss": 3.4736, "step": 1538048 }, { "epoch": 0.0, "learning_rate": 2.481121790819091e-05, "loss": 3.4827, "step": 1538560 }, { "epoch": 0.0, "learning_rate": 2.480284833948412e-05, "loss": 3.4733, "step": 1539072 }, { "epoch": 0.0, "learning_rate": 2.47944623919736e-05, "loss": 3.4749, "step": 1539584 }, { "epoch": 0.0, "learning_rate": 2.478607644446308e-05, "loss": 3.467, "step": 1540096 }, { "epoch": 0.0, "learning_rate": 2.477769049695256e-05, "loss": 3.4792, "step": 1540608 }, { "epoch": 0.0, "learning_rate": 2.4769320928245773e-05, "loss": 3.4666, "step": 1541120 }, { "epoch": 0.0, "learning_rate": 2.476093498073525e-05, "loss": 3.4654, "step": 1541632 }, { "epoch": 0.01, "learning_rate": 2.475254903322473e-05, "loss": 3.4817, "step": 1542144 }, { "epoch": 0.01, "learning_rate": 2.4744179464517946e-05, "loss": 3.4745, "step": 1542656 }, { "epoch": 0.01, "learning_rate": 2.4735793517007426e-05, "loss": 3.485, "step": 1543168 }, { "epoch": 0.01, "learning_rate": 2.4727407569496902e-05, "loss": 3.4825, "step": 1543680 }, { "epoch": 0.01, "learning_rate": 2.4719021621986382e-05, "loss": 3.47, "step": 1544192 }, { "epoch": 0.01, "learning_rate": 2.4710652053279595e-05, "loss": 3.4845, "step": 1544704 }, { "epoch": 0.01, "learning_rate": 2.4702266105769075e-05, "loss": 3.4744, "step": 1545216 }, { "epoch": 0.01, "learning_rate": 2.4693880158258555e-05, "loss": 3.4657, "step": 1545728 }, { "epoch": 0.01, "learning_rate": 2.4685494210748034e-05, "loss": 3.4625, "step": 1546240 }, { "epoch": 0.01, "learning_rate": 2.4677124642041247e-05, "loss": 3.467, "step": 1546752 }, { "epoch": 0.01, "learning_rate": 2.4668738694530724e-05, "loss": 3.4698, "step": 1547264 }, { "epoch": 0.01, "learning_rate": 2.4660352747020203e-05, "loss": 3.4846, "step": 1547776 }, { "epoch": 0.01, "learning_rate": 2.4651966799509683e-05, "loss": 3.4727, "step": 1548288 }, { "epoch": 0.01, "learning_rate": 2.46435972308029e-05, "loss": 3.4719, "step": 1548800 }, { "epoch": 0.01, "learning_rate": 2.4635211283292376e-05, "loss": 3.4814, "step": 1549312 }, { "epoch": 0.01, "learning_rate": 2.4626825335781856e-05, "loss": 3.4734, "step": 1549824 }, { "epoch": 0.01, "learning_rate": 2.4618439388271336e-05, "loss": 3.4785, "step": 1550336 }, { "epoch": 0.01, "learning_rate": 2.4610069819564548e-05, "loss": 3.4657, "step": 1550848 }, { "epoch": 0.01, "learning_rate": 2.4601683872054028e-05, "loss": 3.451, "step": 1551360 }, { "epoch": 0.01, "learning_rate": 2.4593297924543508e-05, "loss": 3.4859, "step": 1551872 }, { "epoch": 0.01, "learning_rate": 2.4584911977032988e-05, "loss": 3.4811, "step": 1552384 }, { "epoch": 0.01, "learning_rate": 2.4576542408326197e-05, "loss": 3.4764, "step": 1552896 }, { "epoch": 0.01, "learning_rate": 2.4568156460815677e-05, "loss": 3.4686, "step": 1553408 }, { "epoch": 0.01, "learning_rate": 2.4559770513305157e-05, "loss": 3.4652, "step": 1553920 }, { "epoch": 0.01, "learning_rate": 2.4551384565794637e-05, "loss": 3.4596, "step": 1554432 }, { "epoch": 0.01, "learning_rate": 2.4543031375891582e-05, "loss": 3.4715, "step": 1554944 }, { "epoch": 0.01, "learning_rate": 2.4534645428381062e-05, "loss": 3.4693, "step": 1555456 }, { "epoch": 0.01, "learning_rate": 2.4526259480870542e-05, "loss": 3.4679, "step": 1555968 }, { "epoch": 0.01, "learning_rate": 2.4517873533360022e-05, "loss": 3.4773, "step": 1556480 }, { "epoch": 0.01, "learning_rate": 2.45094875858495e-05, "loss": 3.4706, "step": 1556992 }, { "epoch": 0.01, "learning_rate": 2.4501101638338982e-05, "loss": 3.458, "step": 1557504 }, { "epoch": 0.01, "learning_rate": 2.4492715690828462e-05, "loss": 3.4815, "step": 1558016 }, { "epoch": 0.01, "learning_rate": 2.4484329743317942e-05, "loss": 3.4582, "step": 1558528 }, { "epoch": 0.01, "learning_rate": 2.447596017461115e-05, "loss": 3.4597, "step": 1559040 }, { "epoch": 0.01, "learning_rate": 2.446757422710063e-05, "loss": 3.4803, "step": 1559552 }, { "epoch": 0.01, "learning_rate": 2.445918827959011e-05, "loss": 3.4804, "step": 1560064 }, { "epoch": 0.01, "learning_rate": 2.445080233207959e-05, "loss": 3.458, "step": 1560576 }, { "epoch": 0.01, "learning_rate": 2.4442432763372803e-05, "loss": 3.4662, "step": 1561088 }, { "epoch": 0.01, "learning_rate": 2.4434046815862283e-05, "loss": 3.4537, "step": 1561600 }, { "epoch": 0.01, "learning_rate": 2.4425660868351763e-05, "loss": 3.4747, "step": 1562112 }, { "epoch": 0.01, "learning_rate": 2.4417274920841243e-05, "loss": 3.4765, "step": 1562624 }, { "epoch": 0.01, "learning_rate": 2.4408905352134452e-05, "loss": 3.4676, "step": 1563136 }, { "epoch": 0.01, "learning_rate": 2.4400519404623932e-05, "loss": 3.4751, "step": 1563648 }, { "epoch": 0.01, "learning_rate": 2.4392133457113416e-05, "loss": 3.4738, "step": 1564160 }, { "epoch": 0.01, "learning_rate": 2.4383747509602895e-05, "loss": 3.49, "step": 1564672 }, { "epoch": 0.01, "learning_rate": 2.4375377940896105e-05, "loss": 3.461, "step": 1565184 }, { "epoch": 0.01, "learning_rate": 2.4366991993385585e-05, "loss": 3.4738, "step": 1565696 }, { "epoch": 0.01, "learning_rate": 2.4358606045875064e-05, "loss": 3.4807, "step": 1566208 }, { "epoch": 0.01, "learning_rate": 2.4350220098364544e-05, "loss": 3.4586, "step": 1566720 }, { "epoch": 0.01, "learning_rate": 2.4341850529657757e-05, "loss": 3.476, "step": 1567232 }, { "epoch": 0.01, "learning_rate": 2.4333464582147237e-05, "loss": 3.4696, "step": 1567744 }, { "epoch": 0.01, "learning_rate": 2.4325078634636717e-05, "loss": 3.4809, "step": 1568256 }, { "epoch": 0.01, "learning_rate": 2.4316692687126197e-05, "loss": 3.4749, "step": 1568768 }, { "epoch": 0.01, "learning_rate": 2.4308323118419406e-05, "loss": 3.4613, "step": 1569280 }, { "epoch": 0.01, "learning_rate": 2.4299937170908886e-05, "loss": 3.4621, "step": 1569792 }, { "epoch": 0.01, "learning_rate": 2.429155122339837e-05, "loss": 3.4647, "step": 1570304 }, { "epoch": 0.01, "learning_rate": 2.428316527588785e-05, "loss": 3.4828, "step": 1570816 }, { "epoch": 0.01, "learning_rate": 2.4274795707181058e-05, "loss": 3.4688, "step": 1571328 }, { "epoch": 0.01, "learning_rate": 2.4266409759670538e-05, "loss": 3.4648, "step": 1571840 }, { "epoch": 0.02, "learning_rate": 2.4258023812160018e-05, "loss": 3.4675, "step": 1572352 }, { "epoch": 0.02, "learning_rate": 2.4249637864649498e-05, "loss": 3.4711, "step": 1572864 }, { "epoch": 0.02, "learning_rate": 2.424126829594271e-05, "loss": 3.4622, "step": 1573376 }, { "epoch": 0.02, "learning_rate": 2.423288234843219e-05, "loss": 3.453, "step": 1573888 }, { "epoch": 0.02, "learning_rate": 2.422449640092167e-05, "loss": 3.4733, "step": 1574400 }, { "epoch": 0.02, "learning_rate": 2.421612683221488e-05, "loss": 3.4741, "step": 1574912 }, { "epoch": 0.02, "learning_rate": 2.420774088470436e-05, "loss": 3.4775, "step": 1575424 }, { "epoch": 0.02, "learning_rate": 2.419935493719384e-05, "loss": 3.4551, "step": 1575936 }, { "epoch": 0.02, "learning_rate": 2.4190968989683323e-05, "loss": 3.4686, "step": 1576448 }, { "epoch": 0.02, "learning_rate": 2.4182599420976532e-05, "loss": 3.464, "step": 1576960 }, { "epoch": 0.02, "learning_rate": 2.4174213473466012e-05, "loss": 3.474, "step": 1577472 }, { "epoch": 0.02, "learning_rate": 2.4165827525955492e-05, "loss": 3.4726, "step": 1577984 }, { "epoch": 0.02, "learning_rate": 2.4157441578444972e-05, "loss": 3.4717, "step": 1578496 }, { "epoch": 0.02, "learning_rate": 2.4149072009738184e-05, "loss": 3.4669, "step": 1579008 }, { "epoch": 0.02, "learning_rate": 2.4140686062227664e-05, "loss": 3.4759, "step": 1579520 }, { "epoch": 0.02, "learning_rate": 2.4132316493520873e-05, "loss": 3.4548, "step": 1580032 }, { "epoch": 0.02, "learning_rate": 2.4123930546010353e-05, "loss": 3.4705, "step": 1580544 }, { "epoch": 0.02, "learning_rate": 2.4115544598499833e-05, "loss": 3.4618, "step": 1581056 }, { "epoch": 0.02, "learning_rate": 2.4107158650989313e-05, "loss": 3.4735, "step": 1581568 }, { "epoch": 0.02, "learning_rate": 2.4098772703478793e-05, "loss": 3.4539, "step": 1582080 }, { "epoch": 0.02, "learning_rate": 2.4090386755968273e-05, "loss": 3.4763, "step": 1582592 }, { "epoch": 0.02, "learning_rate": 2.4082000808457753e-05, "loss": 3.4631, "step": 1583104 }, { "epoch": 0.02, "learning_rate": 2.4073631239750966e-05, "loss": 3.4671, "step": 1583616 }, { "epoch": 0.02, "learning_rate": 2.4065245292240446e-05, "loss": 3.4662, "step": 1584128 }, { "epoch": 0.02, "learning_rate": 2.4056859344729922e-05, "loss": 3.4684, "step": 1584640 }, { "epoch": 0.02, "learning_rate": 2.4048473397219402e-05, "loss": 3.4721, "step": 1585152 }, { "epoch": 0.02, "learning_rate": 2.4040103828512618e-05, "loss": 3.4798, "step": 1585664 }, { "epoch": 0.02, "learning_rate": 2.4031717881002094e-05, "loss": 3.4736, "step": 1586176 }, { "epoch": 0.02, "learning_rate": 2.4023331933491574e-05, "loss": 3.4739, "step": 1586688 }, { "epoch": 0.02, "learning_rate": 2.4014945985981054e-05, "loss": 3.4715, "step": 1587200 }, { "epoch": 0.02, "learning_rate": 2.4006576417274267e-05, "loss": 3.4647, "step": 1587712 }, { "epoch": 0.02, "learning_rate": 2.3998190469763747e-05, "loss": 3.4563, "step": 1588224 }, { "epoch": 0.02, "learning_rate": 2.3989804522253227e-05, "loss": 3.4689, "step": 1588736 }, { "epoch": 0.02, "learning_rate": 2.3981418574742707e-05, "loss": 3.4674, "step": 1589248 }, { "epoch": 0.02, "learning_rate": 2.397304900603592e-05, "loss": 3.4693, "step": 1589760 }, { "epoch": 0.02, "learning_rate": 2.3964663058525396e-05, "loss": 3.4685, "step": 1590272 }, { "epoch": 0.02, "learning_rate": 2.3956277111014876e-05, "loss": 3.4727, "step": 1590784 }, { "epoch": 0.02, "learning_rate": 2.3947891163504356e-05, "loss": 3.4676, "step": 1591296 }, { "epoch": 0.02, "learning_rate": 2.3939521594797568e-05, "loss": 3.467, "step": 1591808 }, { "epoch": 0.02, "learning_rate": 2.393115202609078e-05, "loss": 3.4628, "step": 1592320 }, { "epoch": 0.02, "learning_rate": 2.392276607858026e-05, "loss": 3.4766, "step": 1592832 }, { "epoch": 0.02, "learning_rate": 2.391438013106974e-05, "loss": 3.4695, "step": 1593344 }, { "epoch": 0.02, "learning_rate": 2.3905994183559217e-05, "loss": 3.4622, "step": 1593856 }, { "epoch": 0.02, "learning_rate": 2.38976082360487e-05, "loss": 3.4524, "step": 1594368 }, { "epoch": 0.02, "learning_rate": 2.388922228853818e-05, "loss": 3.4733, "step": 1594880 }, { "epoch": 0.02, "learning_rate": 2.3880852719831393e-05, "loss": 3.4733, "step": 1595392 }, { "epoch": 0.02, "learning_rate": 2.387246677232087e-05, "loss": 3.4726, "step": 1595904 }, { "epoch": 0.02, "learning_rate": 2.386408082481035e-05, "loss": 3.465, "step": 1596416 }, { "epoch": 0.02, "learning_rate": 2.385569487729983e-05, "loss": 3.4769, "step": 1596928 }, { "epoch": 0.02, "learning_rate": 2.384730892978931e-05, "loss": 3.4687, "step": 1597440 }, { "epoch": 0.02, "learning_rate": 2.3838922982278793e-05, "loss": 3.4743, "step": 1597952 }, { "epoch": 0.02, "learning_rate": 2.3830537034768273e-05, "loss": 3.4664, "step": 1598464 }, { "epoch": 0.02, "learning_rate": 2.382215108725775e-05, "loss": 3.4708, "step": 1598976 }, { "epoch": 0.02, "learning_rate": 2.3813781518550962e-05, "loss": 3.4685, "step": 1599488 }, { "epoch": 0.02, "learning_rate": 2.380541194984417e-05, "loss": 3.4609, "step": 1600000 }, { "epoch": 0.02, "learning_rate": 2.3797026002333654e-05, "loss": 3.475, "step": 1600512 }, { "epoch": 0.02, "learning_rate": 2.3788640054823134e-05, "loss": 3.475, "step": 1601024 }, { "epoch": 0.02, "learning_rate": 2.3780254107312614e-05, "loss": 3.4708, "step": 1601536 }, { "epoch": 0.02, "learning_rate": 2.3771868159802094e-05, "loss": 3.4648, "step": 1602048 }, { "epoch": 0.02, "learning_rate": 2.3763482212291574e-05, "loss": 3.4675, "step": 1602560 }, { "epoch": 0.03, "eval_loss": 3.8748133182525635, "eval_runtime": 305.0332, "eval_samples_per_second": 1250.982, "eval_steps_per_second": 39.094, "step": 1602720 }, { "epoch": 0.0, "learning_rate": 2.375509626478105e-05, "loss": 3.4685, "step": 1603072 }, { "epoch": 0.0, "learning_rate": 2.374671031727053e-05, "loss": 3.4673, "step": 1603584 }, { "epoch": 0.0, "learning_rate": 2.3738324369760014e-05, "loss": 3.469, "step": 1604096 }, { "epoch": 0.0, "learning_rate": 2.3729938422249494e-05, "loss": 3.4668, "step": 1604608 }, { "epoch": 0.0, "learning_rate": 2.3721568853542703e-05, "loss": 3.4784, "step": 1605120 }, { "epoch": 0.0, "learning_rate": 2.3713182906032183e-05, "loss": 3.4688, "step": 1605632 }, { "epoch": 0.0, "learning_rate": 2.3704796958521663e-05, "loss": 3.4589, "step": 1606144 }, { "epoch": 0.0, "learning_rate": 2.3696411011011143e-05, "loss": 3.4559, "step": 1606656 }, { "epoch": 0.0, "learning_rate": 2.3688041442304355e-05, "loss": 3.4743, "step": 1607168 }, { "epoch": 0.0, "learning_rate": 2.3679655494793835e-05, "loss": 3.4703, "step": 1607680 }, { "epoch": 0.0, "learning_rate": 2.3671269547283315e-05, "loss": 3.4619, "step": 1608192 }, { "epoch": 0.0, "learning_rate": 2.3662883599772795e-05, "loss": 3.4721, "step": 1608704 }, { "epoch": 0.0, "learning_rate": 2.3654530409869737e-05, "loss": 3.4711, "step": 1609216 }, { "epoch": 0.0, "learning_rate": 2.3646144462359217e-05, "loss": 3.4635, "step": 1609728 }, { "epoch": 0.0, "learning_rate": 2.3637758514848697e-05, "loss": 3.4619, "step": 1610240 }, { "epoch": 0.0, "learning_rate": 2.3629372567338177e-05, "loss": 3.4575, "step": 1610752 }, { "epoch": 0.0, "learning_rate": 2.3620986619827657e-05, "loss": 3.4603, "step": 1611264 }, { "epoch": 0.0, "learning_rate": 2.3612600672317137e-05, "loss": 3.4562, "step": 1611776 }, { "epoch": 0.0, "learning_rate": 2.3604214724806616e-05, "loss": 3.4745, "step": 1612288 }, { "epoch": 0.0, "learning_rate": 2.3595828777296096e-05, "loss": 3.4781, "step": 1612800 }, { "epoch": 0.0, "learning_rate": 2.358745920858931e-05, "loss": 3.4753, "step": 1613312 }, { "epoch": 0.0, "learning_rate": 2.357907326107879e-05, "loss": 3.4659, "step": 1613824 }, { "epoch": 0.0, "learning_rate": 2.357068731356827e-05, "loss": 3.463, "step": 1614336 }, { "epoch": 0.0, "learning_rate": 2.356230136605775e-05, "loss": 3.4669, "step": 1614848 }, { "epoch": 0.0, "learning_rate": 2.355394817615469e-05, "loss": 3.4585, "step": 1615360 }, { "epoch": 0.0, "learning_rate": 2.354556222864417e-05, "loss": 3.4655, "step": 1615872 }, { "epoch": 0.0, "learning_rate": 2.353717628113365e-05, "loss": 3.4528, "step": 1616384 }, { "epoch": 0.0, "learning_rate": 2.352879033362313e-05, "loss": 3.4706, "step": 1616896 }, { "epoch": 0.0, "learning_rate": 2.352040438611261e-05, "loss": 3.4569, "step": 1617408 }, { "epoch": 0.0, "learning_rate": 2.351201843860209e-05, "loss": 3.4533, "step": 1617920 }, { "epoch": 0.01, "learning_rate": 2.350363249109157e-05, "loss": 3.4638, "step": 1618432 }, { "epoch": 0.01, "learning_rate": 2.349524654358105e-05, "loss": 3.4688, "step": 1618944 }, { "epoch": 0.01, "learning_rate": 2.3486876974874263e-05, "loss": 3.4748, "step": 1619456 }, { "epoch": 0.01, "learning_rate": 2.3478491027363743e-05, "loss": 3.468, "step": 1619968 }, { "epoch": 0.01, "learning_rate": 2.3470105079853223e-05, "loss": 3.4573, "step": 1620480 }, { "epoch": 0.01, "learning_rate": 2.34617191323427e-05, "loss": 3.4726, "step": 1620992 }, { "epoch": 0.01, "learning_rate": 2.345334956363591e-05, "loss": 3.467, "step": 1621504 }, { "epoch": 0.01, "learning_rate": 2.344496361612539e-05, "loss": 3.4516, "step": 1622016 }, { "epoch": 0.01, "learning_rate": 2.343657766861487e-05, "loss": 3.4546, "step": 1622528 }, { "epoch": 0.01, "learning_rate": 2.342819172110435e-05, "loss": 3.4513, "step": 1623040 }, { "epoch": 0.01, "learning_rate": 2.3419822152397564e-05, "loss": 3.4605, "step": 1623552 }, { "epoch": 0.01, "learning_rate": 2.3411436204887044e-05, "loss": 3.4704, "step": 1624064 }, { "epoch": 0.01, "learning_rate": 2.3403050257376524e-05, "loss": 3.4655, "step": 1624576 }, { "epoch": 0.01, "learning_rate": 2.3394664309866e-05, "loss": 3.4555, "step": 1625088 }, { "epoch": 0.01, "learning_rate": 2.3386294741159216e-05, "loss": 3.468, "step": 1625600 }, { "epoch": 0.01, "learning_rate": 2.3377908793648696e-05, "loss": 3.4594, "step": 1626112 }, { "epoch": 0.01, "learning_rate": 2.3369522846138173e-05, "loss": 3.4716, "step": 1626624 }, { "epoch": 0.01, "learning_rate": 2.3361153277431385e-05, "loss": 3.4541, "step": 1627136 }, { "epoch": 0.01, "learning_rate": 2.3352767329920865e-05, "loss": 3.4365, "step": 1627648 }, { "epoch": 0.01, "learning_rate": 2.3344381382410345e-05, "loss": 3.4756, "step": 1628160 }, { "epoch": 0.01, "learning_rate": 2.3335995434899825e-05, "loss": 3.4639, "step": 1628672 }, { "epoch": 0.01, "learning_rate": 2.3327625866193038e-05, "loss": 3.4668, "step": 1629184 }, { "epoch": 0.01, "learning_rate": 2.3319239918682518e-05, "loss": 3.459, "step": 1629696 }, { "epoch": 0.01, "learning_rate": 2.3310853971171998e-05, "loss": 3.4547, "step": 1630208 }, { "epoch": 0.01, "learning_rate": 2.3302468023661474e-05, "loss": 3.4487, "step": 1630720 }, { "epoch": 0.01, "learning_rate": 2.3294098454954687e-05, "loss": 3.4588, "step": 1631232 }, { "epoch": 0.01, "learning_rate": 2.328571250744417e-05, "loss": 3.4577, "step": 1631744 }, { "epoch": 0.01, "learning_rate": 2.3277326559933646e-05, "loss": 3.457, "step": 1632256 }, { "epoch": 0.01, "learning_rate": 2.3268940612423126e-05, "loss": 3.4665, "step": 1632768 }, { "epoch": 0.01, "learning_rate": 2.3260554664912606e-05, "loss": 3.4575, "step": 1633280 }, { "epoch": 0.01, "learning_rate": 2.3252168717402086e-05, "loss": 3.4492, "step": 1633792 }, { "epoch": 0.01, "learning_rate": 2.3243782769891566e-05, "loss": 3.4679, "step": 1634304 }, { "epoch": 0.01, "learning_rate": 2.3235396822381046e-05, "loss": 3.4505, "step": 1634816 }, { "epoch": 0.01, "learning_rate": 2.322702725367426e-05, "loss": 3.4488, "step": 1635328 }, { "epoch": 0.01, "learning_rate": 2.321864130616374e-05, "loss": 3.467, "step": 1635840 }, { "epoch": 0.01, "learning_rate": 2.321025535865322e-05, "loss": 3.4689, "step": 1636352 }, { "epoch": 0.01, "learning_rate": 2.32018694111427e-05, "loss": 3.446, "step": 1636864 }, { "epoch": 0.01, "learning_rate": 2.3193499842435908e-05, "loss": 3.4565, "step": 1637376 }, { "epoch": 0.01, "learning_rate": 2.3185113894925388e-05, "loss": 3.4432, "step": 1637888 }, { "epoch": 0.01, "learning_rate": 2.317672794741487e-05, "loss": 3.4596, "step": 1638400 }, { "epoch": 0.01, "learning_rate": 2.316834199990435e-05, "loss": 3.4637, "step": 1638912 }, { "epoch": 0.01, "learning_rate": 2.315997243119756e-05, "loss": 3.4595, "step": 1639424 }, { "epoch": 0.01, "learning_rate": 2.315160286249077e-05, "loss": 3.462, "step": 1639936 }, { "epoch": 0.01, "learning_rate": 2.314321691498025e-05, "loss": 3.4618, "step": 1640448 }, { "epoch": 0.01, "learning_rate": 2.3134830967469732e-05, "loss": 3.4743, "step": 1640960 }, { "epoch": 0.01, "learning_rate": 2.3126445019959212e-05, "loss": 3.4518, "step": 1641472 }, { "epoch": 0.01, "learning_rate": 2.3118059072448692e-05, "loss": 3.4656, "step": 1641984 }, { "epoch": 0.01, "learning_rate": 2.3109673124938172e-05, "loss": 3.4679, "step": 1642496 }, { "epoch": 0.01, "learning_rate": 2.310130355623138e-05, "loss": 3.4459, "step": 1643008 }, { "epoch": 0.01, "learning_rate": 2.309291760872086e-05, "loss": 3.4651, "step": 1643520 }, { "epoch": 0.01, "learning_rate": 2.308453166121034e-05, "loss": 3.4566, "step": 1644032 }, { "epoch": 0.01, "learning_rate": 2.3076145713699825e-05, "loss": 3.4721, "step": 1644544 }, { "epoch": 0.01, "learning_rate": 2.30677597661893e-05, "loss": 3.4645, "step": 1645056 }, { "epoch": 0.01, "learning_rate": 2.305937381867878e-05, "loss": 3.4523, "step": 1645568 }, { "epoch": 0.01, "learning_rate": 2.305098787116826e-05, "loss": 3.4482, "step": 1646080 }, { "epoch": 0.01, "learning_rate": 2.304260192365774e-05, "loss": 3.4541, "step": 1646592 }, { "epoch": 0.01, "learning_rate": 2.3034232354950954e-05, "loss": 3.472, "step": 1647104 }, { "epoch": 0.01, "learning_rate": 2.3025846407440434e-05, "loss": 3.4572, "step": 1647616 }, { "epoch": 0.01, "learning_rate": 2.3017460459929914e-05, "loss": 3.4551, "step": 1648128 }, { "epoch": 0.02, "learning_rate": 2.3009074512419393e-05, "loss": 3.4571, "step": 1648640 }, { "epoch": 0.02, "learning_rate": 2.3000704943712603e-05, "loss": 3.4591, "step": 1649152 }, { "epoch": 0.02, "learning_rate": 2.2992318996202083e-05, "loss": 3.4509, "step": 1649664 }, { "epoch": 0.02, "learning_rate": 2.2983933048691562e-05, "loss": 3.4407, "step": 1650176 }, { "epoch": 0.02, "learning_rate": 2.2975547101181046e-05, "loss": 3.4589, "step": 1650688 }, { "epoch": 0.02, "learning_rate": 2.2967161153670526e-05, "loss": 3.4643, "step": 1651200 }, { "epoch": 0.02, "learning_rate": 2.2958775206160006e-05, "loss": 3.465, "step": 1651712 }, { "epoch": 0.02, "learning_rate": 2.2950389258649482e-05, "loss": 3.447, "step": 1652224 }, { "epoch": 0.02, "learning_rate": 2.2942003311138962e-05, "loss": 3.4554, "step": 1652736 }, { "epoch": 0.02, "learning_rate": 2.2933633742432175e-05, "loss": 3.4548, "step": 1653248 }, { "epoch": 0.02, "learning_rate": 2.2925247794921655e-05, "loss": 3.4609, "step": 1653760 }, { "epoch": 0.02, "learning_rate": 2.2916878226214867e-05, "loss": 3.4661, "step": 1654272 }, { "epoch": 0.02, "learning_rate": 2.2908492278704347e-05, "loss": 3.4553, "step": 1654784 }, { "epoch": 0.02, "learning_rate": 2.2900106331193827e-05, "loss": 3.4597, "step": 1655296 }, { "epoch": 0.02, "learning_rate": 2.2891720383683304e-05, "loss": 3.4616, "step": 1655808 }, { "epoch": 0.02, "learning_rate": 2.2883334436172784e-05, "loss": 3.4464, "step": 1656320 }, { "epoch": 0.02, "learning_rate": 2.2874964867465996e-05, "loss": 3.4579, "step": 1656832 }, { "epoch": 0.02, "learning_rate": 2.286657891995548e-05, "loss": 3.4488, "step": 1657344 }, { "epoch": 0.02, "learning_rate": 2.2858192972444956e-05, "loss": 3.4622, "step": 1657856 }, { "epoch": 0.02, "learning_rate": 2.2849807024934436e-05, "loss": 3.4438, "step": 1658368 }, { "epoch": 0.02, "learning_rate": 2.2841421077423916e-05, "loss": 3.4614, "step": 1658880 }, { "epoch": 0.02, "learning_rate": 2.2833035129913396e-05, "loss": 3.4519, "step": 1659392 }, { "epoch": 0.02, "learning_rate": 2.282466556120661e-05, "loss": 3.4561, "step": 1659904 }, { "epoch": 0.02, "learning_rate": 2.281627961369609e-05, "loss": 3.4536, "step": 1660416 }, { "epoch": 0.02, "learning_rate": 2.2807893666185568e-05, "loss": 3.4595, "step": 1660928 }, { "epoch": 0.02, "learning_rate": 2.2799507718675048e-05, "loss": 3.4587, "step": 1661440 }, { "epoch": 0.02, "learning_rate": 2.2791138149968257e-05, "loss": 3.4718, "step": 1661952 }, { "epoch": 0.02, "learning_rate": 2.2782752202457737e-05, "loss": 3.461, "step": 1662464 }, { "epoch": 0.02, "learning_rate": 2.2774366254947217e-05, "loss": 3.4649, "step": 1662976 }, { "epoch": 0.02, "learning_rate": 2.27659803074367e-05, "loss": 3.4544, "step": 1663488 }, { "epoch": 0.02, "learning_rate": 2.275759435992618e-05, "loss": 3.4595, "step": 1664000 }, { "epoch": 0.02, "learning_rate": 2.274922479121939e-05, "loss": 3.4483, "step": 1664512 }, { "epoch": 0.02, "learning_rate": 2.274083884370887e-05, "loss": 3.4538, "step": 1665024 }, { "epoch": 0.02, "learning_rate": 2.273245289619835e-05, "loss": 3.4561, "step": 1665536 }, { "epoch": 0.02, "learning_rate": 2.272406694868783e-05, "loss": 3.4568, "step": 1666048 }, { "epoch": 0.02, "learning_rate": 2.271568100117731e-05, "loss": 3.4586, "step": 1666560 }, { "epoch": 0.02, "learning_rate": 2.2707311432470522e-05, "loss": 3.4557, "step": 1667072 }, { "epoch": 0.02, "learning_rate": 2.2698925484960002e-05, "loss": 3.4573, "step": 1667584 }, { "epoch": 0.02, "learning_rate": 2.2690539537449482e-05, "loss": 3.4573, "step": 1668096 }, { "epoch": 0.02, "learning_rate": 2.268215358993896e-05, "loss": 3.454, "step": 1668608 }, { "epoch": 0.02, "learning_rate": 2.267376764242844e-05, "loss": 3.4613, "step": 1669120 }, { "epoch": 0.02, "learning_rate": 2.266538169491792e-05, "loss": 3.4567, "step": 1669632 }, { "epoch": 0.02, "learning_rate": 2.26569957474074e-05, "loss": 3.45, "step": 1670144 }, { "epoch": 0.02, "learning_rate": 2.264862617870061e-05, "loss": 3.4394, "step": 1670656 }, { "epoch": 0.02, "learning_rate": 2.264024023119009e-05, "loss": 3.465, "step": 1671168 }, { "epoch": 0.02, "learning_rate": 2.263185428367957e-05, "loss": 3.4615, "step": 1671680 }, { "epoch": 0.02, "learning_rate": 2.262346833616905e-05, "loss": 3.4622, "step": 1672192 }, { "epoch": 0.02, "learning_rate": 2.2615098767462263e-05, "loss": 3.4534, "step": 1672704 }, { "epoch": 0.02, "learning_rate": 2.2606712819951743e-05, "loss": 3.4617, "step": 1673216 }, { "epoch": 0.02, "learning_rate": 2.2598326872441223e-05, "loss": 3.4547, "step": 1673728 }, { "epoch": 0.02, "learning_rate": 2.2589940924930703e-05, "loss": 3.4701, "step": 1674240 }, { "epoch": 0.02, "learning_rate": 2.2581554977420183e-05, "loss": 3.4541, "step": 1674752 }, { "epoch": 0.02, "learning_rate": 2.2573169029909663e-05, "loss": 3.4558, "step": 1675264 }, { "epoch": 0.02, "learning_rate": 2.2564799461202872e-05, "loss": 3.4587, "step": 1675776 }, { "epoch": 0.02, "learning_rate": 2.2556413513692355e-05, "loss": 3.452, "step": 1676288 }, { "epoch": 0.02, "learning_rate": 2.2548027566181835e-05, "loss": 3.4655, "step": 1676800 }, { "epoch": 0.02, "learning_rate": 2.2539641618671315e-05, "loss": 3.4596, "step": 1677312 }, { "epoch": 0.02, "learning_rate": 2.2531255671160792e-05, "loss": 3.4648, "step": 1677824 }, { "epoch": 0.02, "learning_rate": 2.2522886102454004e-05, "loss": 3.45, "step": 1678336 }, { "epoch": 0.02, "learning_rate": 2.2514500154943484e-05, "loss": 3.4571, "step": 1678848 }, { "epoch": 0.03, "eval_loss": 3.876386880874634, "eval_runtime": 305.8818, "eval_samples_per_second": 1247.511, "eval_steps_per_second": 38.986, "step": 1679040 }, { "epoch": 0.0, "learning_rate": 2.2506130586236697e-05, "loss": 3.4598, "step": 1679360 }, { "epoch": 0.0, "learning_rate": 2.2497744638726177e-05, "loss": 3.4559, "step": 1679872 }, { "epoch": 0.0, "learning_rate": 2.2489358691215657e-05, "loss": 3.4568, "step": 1680384 }, { "epoch": 0.0, "learning_rate": 2.2480972743705137e-05, "loss": 3.4557, "step": 1680896 }, { "epoch": 0.0, "learning_rate": 2.2472586796194613e-05, "loss": 3.469, "step": 1681408 }, { "epoch": 0.0, "learning_rate": 2.2464200848684093e-05, "loss": 3.4575, "step": 1681920 }, { "epoch": 0.0, "learning_rate": 2.2455814901173573e-05, "loss": 3.4492, "step": 1682432 }, { "epoch": 0.0, "learning_rate": 2.2447428953663056e-05, "loss": 3.4428, "step": 1682944 }, { "epoch": 0.0, "learning_rate": 2.2439059384956266e-05, "loss": 3.4651, "step": 1683456 }, { "epoch": 0.0, "learning_rate": 2.2430673437445745e-05, "loss": 3.4584, "step": 1683968 }, { "epoch": 0.0, "learning_rate": 2.2422287489935225e-05, "loss": 3.4525, "step": 1684480 }, { "epoch": 0.0, "learning_rate": 2.2413901542424705e-05, "loss": 3.4588, "step": 1684992 }, { "epoch": 0.0, "learning_rate": 2.2405531973717918e-05, "loss": 3.4583, "step": 1685504 }, { "epoch": 0.0, "learning_rate": 2.2397146026207398e-05, "loss": 3.4504, "step": 1686016 }, { "epoch": 0.0, "learning_rate": 2.2388760078696878e-05, "loss": 3.4478, "step": 1686528 }, { "epoch": 0.0, "learning_rate": 2.2380374131186358e-05, "loss": 3.4483, "step": 1687040 }, { "epoch": 0.0, "learning_rate": 2.2372004562479567e-05, "loss": 3.4472, "step": 1687552 }, { "epoch": 0.0, "learning_rate": 2.2363618614969047e-05, "loss": 3.449, "step": 1688064 }, { "epoch": 0.0, "learning_rate": 2.2355232667458527e-05, "loss": 3.4614, "step": 1688576 }, { "epoch": 0.0, "learning_rate": 2.234684671994801e-05, "loss": 3.4655, "step": 1689088 }, { "epoch": 0.0, "learning_rate": 2.233846077243749e-05, "loss": 3.4631, "step": 1689600 }, { "epoch": 0.0, "learning_rate": 2.233007482492697e-05, "loss": 3.4564, "step": 1690112 }, { "epoch": 0.0, "learning_rate": 2.232170525622018e-05, "loss": 3.453, "step": 1690624 }, { "epoch": 0.0, "learning_rate": 2.231331930870966e-05, "loss": 3.4538, "step": 1691136 }, { "epoch": 0.0, "learning_rate": 2.230493336119914e-05, "loss": 3.4512, "step": 1691648 }, { "epoch": 0.0, "learning_rate": 2.229654741368862e-05, "loss": 3.4552, "step": 1692160 }, { "epoch": 0.0, "learning_rate": 2.228817784498183e-05, "loss": 3.4385, "step": 1692672 }, { "epoch": 0.0, "learning_rate": 2.227979189747131e-05, "loss": 3.4597, "step": 1693184 }, { "epoch": 0.0, "learning_rate": 2.227140594996079e-05, "loss": 3.4491, "step": 1693696 }, { "epoch": 0.0, "learning_rate": 2.2263020002450268e-05, "loss": 3.4428, "step": 1694208 }, { "epoch": 0.01, "learning_rate": 2.2254634054939748e-05, "loss": 3.4519, "step": 1694720 }, { "epoch": 0.01, "learning_rate": 2.2246248107429228e-05, "loss": 3.46, "step": 1695232 }, { "epoch": 0.01, "learning_rate": 2.223786215991871e-05, "loss": 3.4565, "step": 1695744 }, { "epoch": 0.01, "learning_rate": 2.222947621240819e-05, "loss": 3.4581, "step": 1696256 }, { "epoch": 0.01, "learning_rate": 2.22211066437014e-05, "loss": 3.4465, "step": 1696768 }, { "epoch": 0.01, "learning_rate": 2.221272069619088e-05, "loss": 3.4613, "step": 1697280 }, { "epoch": 0.01, "learning_rate": 2.220433474868036e-05, "loss": 3.4543, "step": 1697792 }, { "epoch": 0.01, "learning_rate": 2.2195965179973573e-05, "loss": 3.4409, "step": 1698304 }, { "epoch": 0.01, "learning_rate": 2.2187579232463053e-05, "loss": 3.4433, "step": 1698816 }, { "epoch": 0.01, "learning_rate": 2.2179193284952533e-05, "loss": 3.4413, "step": 1699328 }, { "epoch": 0.01, "learning_rate": 2.2170807337442013e-05, "loss": 3.4501, "step": 1699840 }, { "epoch": 0.01, "learning_rate": 2.2162421389931492e-05, "loss": 3.4606, "step": 1700352 }, { "epoch": 0.01, "learning_rate": 2.21540518212247e-05, "loss": 3.4512, "step": 1700864 }, { "epoch": 0.01, "learning_rate": 2.214566587371418e-05, "loss": 3.4484, "step": 1701376 }, { "epoch": 0.01, "learning_rate": 2.2137279926203665e-05, "loss": 3.4547, "step": 1701888 }, { "epoch": 0.01, "learning_rate": 2.2128893978693145e-05, "loss": 3.4482, "step": 1702400 }, { "epoch": 0.01, "learning_rate": 2.2120508031182625e-05, "loss": 3.4613, "step": 1702912 }, { "epoch": 0.01, "learning_rate": 2.21121220836721e-05, "loss": 3.4464, "step": 1703424 }, { "epoch": 0.01, "learning_rate": 2.210373613616158e-05, "loss": 3.4218, "step": 1703936 }, { "epoch": 0.01, "learning_rate": 2.2095366567454794e-05, "loss": 3.4662, "step": 1704448 }, { "epoch": 0.01, "learning_rate": 2.2086980619944274e-05, "loss": 3.4545, "step": 1704960 }, { "epoch": 0.01, "learning_rate": 2.2078594672433754e-05, "loss": 3.457, "step": 1705472 }, { "epoch": 0.01, "learning_rate": 2.2070208724923234e-05, "loss": 3.4461, "step": 1705984 }, { "epoch": 0.01, "learning_rate": 2.2061822777412714e-05, "loss": 3.4445, "step": 1706496 }, { "epoch": 0.01, "learning_rate": 2.2053453208705923e-05, "loss": 3.4379, "step": 1707008 }, { "epoch": 0.01, "learning_rate": 2.2045067261195403e-05, "loss": 3.4508, "step": 1707520 }, { "epoch": 0.01, "learning_rate": 2.2036681313684886e-05, "loss": 3.4457, "step": 1708032 }, { "epoch": 0.01, "learning_rate": 2.2028295366174366e-05, "loss": 3.4466, "step": 1708544 }, { "epoch": 0.01, "learning_rate": 2.2019909418663846e-05, "loss": 3.4519, "step": 1709056 }, { "epoch": 0.01, "learning_rate": 2.2011523471153326e-05, "loss": 3.449, "step": 1709568 }, { "epoch": 0.01, "learning_rate": 2.2003137523642806e-05, "loss": 3.4363, "step": 1710080 }, { "epoch": 0.01, "learning_rate": 2.1994751576132282e-05, "loss": 3.4561, "step": 1710592 }, { "epoch": 0.01, "learning_rate": 2.1986382007425495e-05, "loss": 3.4393, "step": 1711104 }, { "epoch": 0.01, "learning_rate": 2.1977996059914975e-05, "loss": 3.4406, "step": 1711616 }, { "epoch": 0.01, "learning_rate": 2.1969610112404455e-05, "loss": 3.455, "step": 1712128 }, { "epoch": 0.01, "learning_rate": 2.1961224164893935e-05, "loss": 3.4546, "step": 1712640 }, { "epoch": 0.01, "learning_rate": 2.1952854596187147e-05, "loss": 3.4344, "step": 1713152 }, { "epoch": 0.01, "learning_rate": 2.1944468648676627e-05, "loss": 3.4434, "step": 1713664 }, { "epoch": 0.01, "learning_rate": 2.1936082701166104e-05, "loss": 3.4357, "step": 1714176 }, { "epoch": 0.01, "learning_rate": 2.1927696753655587e-05, "loss": 3.4498, "step": 1714688 }, { "epoch": 0.01, "learning_rate": 2.19193271849488e-05, "loss": 3.4524, "step": 1715200 }, { "epoch": 0.01, "learning_rate": 2.191094123743828e-05, "loss": 3.4507, "step": 1715712 }, { "epoch": 0.01, "learning_rate": 2.190257166873149e-05, "loss": 3.4504, "step": 1716224 }, { "epoch": 0.01, "learning_rate": 2.189418572122097e-05, "loss": 3.4487, "step": 1716736 }, { "epoch": 0.01, "learning_rate": 2.188579977371045e-05, "loss": 3.4647, "step": 1717248 }, { "epoch": 0.01, "learning_rate": 2.187741382619993e-05, "loss": 3.442, "step": 1717760 }, { "epoch": 0.01, "learning_rate": 2.186902787868941e-05, "loss": 3.4526, "step": 1718272 }, { "epoch": 0.01, "learning_rate": 2.186064193117889e-05, "loss": 3.4559, "step": 1718784 }, { "epoch": 0.01, "learning_rate": 2.18522723624721e-05, "loss": 3.4357, "step": 1719296 }, { "epoch": 0.01, "learning_rate": 2.1843886414961577e-05, "loss": 3.4509, "step": 1719808 }, { "epoch": 0.01, "learning_rate": 2.1835500467451057e-05, "loss": 3.4521, "step": 1720320 }, { "epoch": 0.01, "learning_rate": 2.182711451994054e-05, "loss": 3.4532, "step": 1720832 }, { "epoch": 0.01, "learning_rate": 2.181872857243002e-05, "loss": 3.4567, "step": 1721344 }, { "epoch": 0.01, "learning_rate": 2.18103426249195e-05, "loss": 3.4407, "step": 1721856 }, { "epoch": 0.01, "learning_rate": 2.180195667740898e-05, "loss": 3.4387, "step": 1722368 }, { "epoch": 0.01, "learning_rate": 2.179357072989846e-05, "loss": 3.443, "step": 1722880 }, { "epoch": 0.01, "learning_rate": 2.178520116119167e-05, "loss": 3.4544, "step": 1723392 }, { "epoch": 0.01, "learning_rate": 2.177681521368115e-05, "loss": 3.4464, "step": 1723904 }, { "epoch": 0.01, "learning_rate": 2.176842926617063e-05, "loss": 3.4443, "step": 1724416 }, { "epoch": 0.02, "learning_rate": 2.176004331866011e-05, "loss": 3.4475, "step": 1724928 }, { "epoch": 0.02, "learning_rate": 2.1751673749953322e-05, "loss": 3.4505, "step": 1725440 }, { "epoch": 0.02, "learning_rate": 2.1743287802442802e-05, "loss": 3.4409, "step": 1725952 }, { "epoch": 0.02, "learning_rate": 2.1734901854932282e-05, "loss": 3.4295, "step": 1726464 }, { "epoch": 0.02, "learning_rate": 2.172651590742176e-05, "loss": 3.449, "step": 1726976 }, { "epoch": 0.02, "learning_rate": 2.1718129959911242e-05, "loss": 3.4491, "step": 1727488 }, { "epoch": 0.02, "learning_rate": 2.1709760391204454e-05, "loss": 3.4536, "step": 1728000 }, { "epoch": 0.02, "learning_rate": 2.1701374443693934e-05, "loss": 3.4371, "step": 1728512 }, { "epoch": 0.02, "learning_rate": 2.169298849618341e-05, "loss": 3.4464, "step": 1729024 }, { "epoch": 0.02, "learning_rate": 2.168460254867289e-05, "loss": 3.445, "step": 1729536 }, { "epoch": 0.02, "learning_rate": 2.167621660116237e-05, "loss": 3.4475, "step": 1730048 }, { "epoch": 0.02, "learning_rate": 2.1667847032455583e-05, "loss": 3.4544, "step": 1730560 }, { "epoch": 0.02, "learning_rate": 2.1659461084945063e-05, "loss": 3.4471, "step": 1731072 }, { "epoch": 0.02, "learning_rate": 2.1651075137434543e-05, "loss": 3.4461, "step": 1731584 }, { "epoch": 0.02, "learning_rate": 2.1642689189924023e-05, "loss": 3.4483, "step": 1732096 }, { "epoch": 0.02, "learning_rate": 2.1634303242413503e-05, "loss": 3.436, "step": 1732608 }, { "epoch": 0.02, "learning_rate": 2.1625933673706712e-05, "loss": 3.4469, "step": 1733120 }, { "epoch": 0.02, "learning_rate": 2.1617547726196196e-05, "loss": 3.4327, "step": 1733632 }, { "epoch": 0.02, "learning_rate": 2.1609161778685675e-05, "loss": 3.4578, "step": 1734144 }, { "epoch": 0.02, "learning_rate": 2.1600775831175155e-05, "loss": 3.4324, "step": 1734656 }, { "epoch": 0.02, "learning_rate": 2.1592389883664635e-05, "loss": 3.449, "step": 1735168 }, { "epoch": 0.02, "learning_rate": 2.1584020314957844e-05, "loss": 3.4407, "step": 1735680 }, { "epoch": 0.02, "learning_rate": 2.1575634367447324e-05, "loss": 3.4453, "step": 1736192 }, { "epoch": 0.02, "learning_rate": 2.1567248419936804e-05, "loss": 3.4432, "step": 1736704 }, { "epoch": 0.02, "learning_rate": 2.1558862472426288e-05, "loss": 3.449, "step": 1737216 }, { "epoch": 0.02, "learning_rate": 2.1550476524915764e-05, "loss": 3.4451, "step": 1737728 }, { "epoch": 0.02, "learning_rate": 2.1542106956208977e-05, "loss": 3.4566, "step": 1738240 }, { "epoch": 0.02, "learning_rate": 2.1533721008698457e-05, "loss": 3.4474, "step": 1738752 }, { "epoch": 0.02, "learning_rate": 2.1525335061187937e-05, "loss": 3.4579, "step": 1739264 }, { "epoch": 0.02, "learning_rate": 2.1516949113677413e-05, "loss": 3.4463, "step": 1739776 }, { "epoch": 0.02, "learning_rate": 2.1508563166166897e-05, "loss": 3.4455, "step": 1740288 }, { "epoch": 0.02, "learning_rate": 2.150019359746011e-05, "loss": 3.442, "step": 1740800 }, { "epoch": 0.02, "learning_rate": 2.1491807649949586e-05, "loss": 3.4395, "step": 1741312 }, { "epoch": 0.02, "learning_rate": 2.1483421702439066e-05, "loss": 3.4431, "step": 1741824 }, { "epoch": 0.02, "learning_rate": 2.1475035754928546e-05, "loss": 3.4468, "step": 1742336 }, { "epoch": 0.02, "learning_rate": 2.1466666186221758e-05, "loss": 3.4436, "step": 1742848 }, { "epoch": 0.02, "learning_rate": 2.1458280238711238e-05, "loss": 3.448, "step": 1743360 }, { "epoch": 0.02, "learning_rate": 2.1449894291200718e-05, "loss": 3.4479, "step": 1743872 }, { "epoch": 0.02, "learning_rate": 2.1441508343690198e-05, "loss": 3.4478, "step": 1744384 }, { "epoch": 0.02, "learning_rate": 2.143313877498341e-05, "loss": 3.4475, "step": 1744896 }, { "epoch": 0.02, "learning_rate": 2.1424752827472887e-05, "loss": 3.4442, "step": 1745408 }, { "epoch": 0.02, "learning_rate": 2.1416366879962367e-05, "loss": 3.443, "step": 1745920 }, { "epoch": 0.02, "learning_rate": 2.140798093245185e-05, "loss": 3.4438, "step": 1746432 }, { "epoch": 0.02, "learning_rate": 2.139959498494133e-05, "loss": 3.4278, "step": 1746944 }, { "epoch": 0.02, "learning_rate": 2.139120903743081e-05, "loss": 3.4521, "step": 1747456 }, { "epoch": 0.02, "learning_rate": 2.138283946872402e-05, "loss": 3.4492, "step": 1747968 }, { "epoch": 0.02, "learning_rate": 2.13744535212135e-05, "loss": 3.4519, "step": 1748480 }, { "epoch": 0.02, "learning_rate": 2.136606757370298e-05, "loss": 3.4392, "step": 1748992 }, { "epoch": 0.02, "learning_rate": 2.135768162619246e-05, "loss": 3.4533, "step": 1749504 }, { "epoch": 0.02, "learning_rate": 2.134931205748567e-05, "loss": 3.4495, "step": 1750016 }, { "epoch": 0.02, "learning_rate": 2.134092610997515e-05, "loss": 3.4558, "step": 1750528 }, { "epoch": 0.02, "learning_rate": 2.133254016246463e-05, "loss": 3.4394, "step": 1751040 }, { "epoch": 0.02, "learning_rate": 2.132415421495411e-05, "loss": 3.4405, "step": 1751552 }, { "epoch": 0.02, "learning_rate": 2.131576826744359e-05, "loss": 3.4485, "step": 1752064 }, { "epoch": 0.02, "learning_rate": 2.1307398698736804e-05, "loss": 3.4447, "step": 1752576 }, { "epoch": 0.02, "learning_rate": 2.1299012751226284e-05, "loss": 3.4494, "step": 1753088 }, { "epoch": 0.02, "learning_rate": 2.1290626803715764e-05, "loss": 3.4517, "step": 1753600 }, { "epoch": 0.02, "learning_rate": 2.128224085620524e-05, "loss": 3.4522, "step": 1754112 }, { "epoch": 0.02, "learning_rate": 2.127385490869472e-05, "loss": 3.4379, "step": 1754624 }, { "epoch": 0.02, "learning_rate": 2.12654689611842e-05, "loss": 3.4518, "step": 1755136 }, { "epoch": 0.03, "eval_loss": 3.8769567012786865, "eval_runtime": 307.414, "eval_samples_per_second": 1241.294, "eval_steps_per_second": 38.791, "step": 1755360 }, { "epoch": 1.0, "learning_rate": 2.1257099392477413e-05, "loss": 3.4398, "step": 1755648 }, { "epoch": 1.0, "learning_rate": 2.1248713444966893e-05, "loss": 3.4486, "step": 1756160 }, { "epoch": 1.0, "learning_rate": 2.1240327497456373e-05, "loss": 3.4424, "step": 1756672 }, { "epoch": 1.0, "learning_rate": 2.1231941549945853e-05, "loss": 3.4424, "step": 1757184 }, { "epoch": 1.0, "learning_rate": 2.1223571981239065e-05, "loss": 3.4554, "step": 1757696 }, { "epoch": 1.0, "learning_rate": 2.1215186033728542e-05, "loss": 3.4478, "step": 1758208 }, { "epoch": 1.0, "learning_rate": 2.1206800086218022e-05, "loss": 3.4385, "step": 1758720 }, { "epoch": 1.0, "learning_rate": 2.1198414138707505e-05, "loss": 3.4367, "step": 1759232 }, { "epoch": 1.0, "learning_rate": 2.1190028191196985e-05, "loss": 3.4466, "step": 1759744 }, { "epoch": 1.0, "learning_rate": 2.1181658622490194e-05, "loss": 3.4506, "step": 1760256 }, { "epoch": 1.0, "learning_rate": 2.1173272674979674e-05, "loss": 3.4392, "step": 1760768 }, { "epoch": 1.0, "learning_rate": 2.1164886727469154e-05, "loss": 3.4487, "step": 1761280 }, { "epoch": 1.0, "learning_rate": 2.1156500779958634e-05, "loss": 3.4519, "step": 1761792 }, { "epoch": 1.0, "learning_rate": 2.1148114832448114e-05, "loss": 3.4378, "step": 1762304 }, { "epoch": 1.0, "learning_rate": 2.1139728884937597e-05, "loss": 3.4408, "step": 1762816 }, { "epoch": 1.0, "learning_rate": 2.1131342937427074e-05, "loss": 3.4364, "step": 1763328 }, { "epoch": 1.0, "learning_rate": 2.1122973368720286e-05, "loss": 3.4361, "step": 1763840 }, { "epoch": 1.0, "learning_rate": 2.1114587421209766e-05, "loss": 3.4356, "step": 1764352 }, { "epoch": 1.0, "learning_rate": 2.1106201473699246e-05, "loss": 3.4458, "step": 1764864 }, { "epoch": 1.0, "learning_rate": 2.1097815526188723e-05, "loss": 3.458, "step": 1765376 }, { "epoch": 1.0, "learning_rate": 2.1089429578678206e-05, "loss": 3.4546, "step": 1765888 }, { "epoch": 1.0, "learning_rate": 2.108106000997142e-05, "loss": 3.4451, "step": 1766400 }, { "epoch": 1.0, "learning_rate": 2.1072674062460895e-05, "loss": 3.439, "step": 1766912 }, { "epoch": 1.0, "learning_rate": 2.1064288114950375e-05, "loss": 3.4417, "step": 1767424 }, { "epoch": 1.0, "learning_rate": 2.1055902167439855e-05, "loss": 3.4406, "step": 1767936 }, { "epoch": 1.0, "learning_rate": 2.1047516219929335e-05, "loss": 3.4427, "step": 1768448 }, { "epoch": 1.0, "learning_rate": 2.1039146651222548e-05, "loss": 3.4275, "step": 1768960 }, { "epoch": 1.0, "learning_rate": 2.1030760703712027e-05, "loss": 3.4501, "step": 1769472 }, { "epoch": 1.0, "learning_rate": 2.1022374756201507e-05, "loss": 3.4385, "step": 1769984 }, { "epoch": 1.0, "learning_rate": 2.1013988808690987e-05, "loss": 3.4328, "step": 1770496 }, { "epoch": 1.01, "learning_rate": 2.1005602861180467e-05, "loss": 3.434, "step": 1771008 }, { "epoch": 1.01, "learning_rate": 2.0997233292473676e-05, "loss": 3.4505, "step": 1771520 }, { "epoch": 1.01, "learning_rate": 2.098884734496316e-05, "loss": 3.4483, "step": 1772032 }, { "epoch": 1.01, "learning_rate": 2.098046139745264e-05, "loss": 3.448, "step": 1772544 }, { "epoch": 1.01, "learning_rate": 2.097207544994212e-05, "loss": 3.4351, "step": 1773056 }, { "epoch": 1.01, "learning_rate": 2.09636895024316e-05, "loss": 3.4461, "step": 1773568 }, { "epoch": 1.01, "learning_rate": 2.0955303554921076e-05, "loss": 3.4467, "step": 1774080 }, { "epoch": 1.01, "learning_rate": 2.0946917607410556e-05, "loss": 3.4322, "step": 1774592 }, { "epoch": 1.01, "learning_rate": 2.0938531659900036e-05, "loss": 3.4319, "step": 1775104 }, { "epoch": 1.01, "learning_rate": 2.093017846999698e-05, "loss": 3.4294, "step": 1775616 }, { "epoch": 1.01, "learning_rate": 2.092179252248646e-05, "loss": 3.4388, "step": 1776128 }, { "epoch": 1.01, "learning_rate": 2.091340657497594e-05, "loss": 3.4457, "step": 1776640 }, { "epoch": 1.01, "learning_rate": 2.090502062746542e-05, "loss": 3.4429, "step": 1777152 }, { "epoch": 1.01, "learning_rate": 2.0896634679954898e-05, "loss": 3.4368, "step": 1777664 }, { "epoch": 1.01, "learning_rate": 2.0888265111248113e-05, "loss": 3.4445, "step": 1778176 }, { "epoch": 1.01, "learning_rate": 2.0879879163737593e-05, "loss": 3.4368, "step": 1778688 }, { "epoch": 1.01, "learning_rate": 2.0871493216227073e-05, "loss": 3.4461, "step": 1779200 }, { "epoch": 1.01, "learning_rate": 2.086310726871655e-05, "loss": 3.4387, "step": 1779712 }, { "epoch": 1.01, "learning_rate": 2.085472132120603e-05, "loss": 3.4111, "step": 1780224 }, { "epoch": 1.01, "learning_rate": 2.0846351752499242e-05, "loss": 3.4504, "step": 1780736 }, { "epoch": 1.01, "learning_rate": 2.0837965804988722e-05, "loss": 3.4445, "step": 1781248 }, { "epoch": 1.01, "learning_rate": 2.0829579857478202e-05, "loss": 3.4476, "step": 1781760 }, { "epoch": 1.01, "learning_rate": 2.0821193909967682e-05, "loss": 3.4339, "step": 1782272 }, { "epoch": 1.01, "learning_rate": 2.0812807962457162e-05, "loss": 3.4314, "step": 1782784 }, { "epoch": 1.01, "learning_rate": 2.080443839375037e-05, "loss": 3.4287, "step": 1783296 }, { "epoch": 1.01, "learning_rate": 2.079605244623985e-05, "loss": 3.4378, "step": 1783808 }, { "epoch": 1.01, "learning_rate": 2.0787666498729335e-05, "loss": 3.4386, "step": 1784320 }, { "epoch": 1.01, "learning_rate": 2.0779280551218815e-05, "loss": 3.4314, "step": 1784832 }, { "epoch": 1.01, "learning_rate": 2.0770894603708295e-05, "loss": 3.4423, "step": 1785344 }, { "epoch": 1.01, "learning_rate": 2.0762525035001504e-05, "loss": 3.4397, "step": 1785856 }, { "epoch": 1.01, "learning_rate": 2.0754139087490984e-05, "loss": 3.4241, "step": 1786368 }, { "epoch": 1.01, "learning_rate": 2.0745753139980464e-05, "loss": 3.4455, "step": 1786880 }, { "epoch": 1.01, "learning_rate": 2.0737367192469943e-05, "loss": 3.4294, "step": 1787392 }, { "epoch": 1.01, "learning_rate": 2.0728997623763156e-05, "loss": 3.4253, "step": 1787904 }, { "epoch": 1.01, "learning_rate": 2.0720611676252636e-05, "loss": 3.4414, "step": 1788416 }, { "epoch": 1.01, "learning_rate": 2.0712225728742116e-05, "loss": 3.4454, "step": 1788928 }, { "epoch": 1.01, "learning_rate": 2.0703839781231596e-05, "loss": 3.4244, "step": 1789440 }, { "epoch": 1.01, "learning_rate": 2.0695470212524805e-05, "loss": 3.4346, "step": 1789952 }, { "epoch": 1.01, "learning_rate": 2.0687084265014285e-05, "loss": 3.4219, "step": 1790464 }, { "epoch": 1.01, "learning_rate": 2.0678698317503768e-05, "loss": 3.4382, "step": 1790976 }, { "epoch": 1.01, "learning_rate": 2.0670312369993248e-05, "loss": 3.4409, "step": 1791488 }, { "epoch": 1.01, "learning_rate": 2.0661942801286457e-05, "loss": 3.4376, "step": 1792000 }, { "epoch": 1.01, "learning_rate": 2.0653556853775937e-05, "loss": 3.4376, "step": 1792512 }, { "epoch": 1.01, "learning_rate": 2.0645170906265417e-05, "loss": 3.4394, "step": 1793024 }, { "epoch": 1.01, "learning_rate": 2.0636784958754897e-05, "loss": 3.4552, "step": 1793536 }, { "epoch": 1.01, "learning_rate": 2.0628399011244377e-05, "loss": 3.4294, "step": 1794048 }, { "epoch": 1.01, "learning_rate": 2.0620013063733857e-05, "loss": 3.4441, "step": 1794560 }, { "epoch": 1.01, "learning_rate": 2.0611627116223337e-05, "loss": 3.444, "step": 1795072 }, { "epoch": 1.01, "learning_rate": 2.060325754751655e-05, "loss": 3.4254, "step": 1795584 }, { "epoch": 1.01, "learning_rate": 2.0594871600006026e-05, "loss": 3.4404, "step": 1796096 }, { "epoch": 1.01, "learning_rate": 2.0586485652495506e-05, "loss": 3.4421, "step": 1796608 }, { "epoch": 1.01, "learning_rate": 2.057809970498499e-05, "loss": 3.4409, "step": 1797120 }, { "epoch": 1.01, "learning_rate": 2.0569730136278202e-05, "loss": 3.4461, "step": 1797632 }, { "epoch": 1.01, "learning_rate": 2.056134418876768e-05, "loss": 3.4242, "step": 1798144 }, { "epoch": 1.01, "learning_rate": 2.055295824125716e-05, "loss": 3.4278, "step": 1798656 }, { "epoch": 1.01, "learning_rate": 2.054457229374664e-05, "loss": 3.4307, "step": 1799168 }, { "epoch": 1.01, "learning_rate": 2.053620272503985e-05, "loss": 3.4431, "step": 1799680 }, { "epoch": 1.01, "learning_rate": 2.052781677752933e-05, "loss": 3.4357, "step": 1800192 }, { "epoch": 1.01, "learning_rate": 2.051943083001881e-05, "loss": 3.4373, "step": 1800704 }, { "epoch": 1.02, "learning_rate": 2.051104488250829e-05, "loss": 3.4387, "step": 1801216 }, { "epoch": 1.02, "learning_rate": 2.05026753138015e-05, "loss": 3.4338, "step": 1801728 }, { "epoch": 1.02, "learning_rate": 2.049428936629098e-05, "loss": 3.4324, "step": 1802240 }, { "epoch": 1.02, "learning_rate": 2.048590341878046e-05, "loss": 3.4183, "step": 1802752 }, { "epoch": 1.02, "learning_rate": 2.0477517471269943e-05, "loss": 3.4356, "step": 1803264 }, { "epoch": 1.02, "learning_rate": 2.0469147902563152e-05, "loss": 3.4393, "step": 1803776 }, { "epoch": 1.02, "learning_rate": 2.0460761955052632e-05, "loss": 3.444, "step": 1804288 }, { "epoch": 1.02, "learning_rate": 2.0452376007542112e-05, "loss": 3.4263, "step": 1804800 }, { "epoch": 1.02, "learning_rate": 2.0443990060031592e-05, "loss": 3.4328, "step": 1805312 }, { "epoch": 1.02, "learning_rate": 2.0435604112521072e-05, "loss": 3.4329, "step": 1805824 }, { "epoch": 1.02, "learning_rate": 2.0427218165010552e-05, "loss": 3.4349, "step": 1806336 }, { "epoch": 1.02, "learning_rate": 2.0418848596303764e-05, "loss": 3.4411, "step": 1806848 }, { "epoch": 1.02, "learning_rate": 2.0410462648793244e-05, "loss": 3.4388, "step": 1807360 }, { "epoch": 1.02, "learning_rate": 2.0402076701282724e-05, "loss": 3.4371, "step": 1807872 }, { "epoch": 1.02, "learning_rate": 2.0393690753772204e-05, "loss": 3.4355, "step": 1808384 }, { "epoch": 1.02, "learning_rate": 2.038530480626168e-05, "loss": 3.4268, "step": 1808896 }, { "epoch": 1.02, "learning_rate": 2.0376935237554893e-05, "loss": 3.4342, "step": 1809408 }, { "epoch": 1.02, "learning_rate": 2.0368549290044377e-05, "loss": 3.4257, "step": 1809920 }, { "epoch": 1.02, "learning_rate": 2.0360163342533857e-05, "loss": 3.4456, "step": 1810432 }, { "epoch": 1.02, "learning_rate": 2.0351777395023333e-05, "loss": 3.423, "step": 1810944 }, { "epoch": 1.02, "learning_rate": 2.0343391447512813e-05, "loss": 3.4368, "step": 1811456 }, { "epoch": 1.02, "learning_rate": 2.0335021878806026e-05, "loss": 3.4299, "step": 1811968 }, { "epoch": 1.02, "learning_rate": 2.0326635931295506e-05, "loss": 3.4387, "step": 1812480 }, { "epoch": 1.02, "learning_rate": 2.0318249983784986e-05, "loss": 3.431, "step": 1812992 }, { "epoch": 1.02, "learning_rate": 2.0309864036274465e-05, "loss": 3.4357, "step": 1813504 }, { "epoch": 1.02, "learning_rate": 2.0301478088763945e-05, "loss": 3.4332, "step": 1814016 }, { "epoch": 1.02, "learning_rate": 2.0293108520057155e-05, "loss": 3.449, "step": 1814528 }, { "epoch": 1.02, "learning_rate": 2.0284722572546634e-05, "loss": 3.4338, "step": 1815040 }, { "epoch": 1.02, "learning_rate": 2.0276336625036114e-05, "loss": 3.4478, "step": 1815552 }, { "epoch": 1.02, "learning_rate": 2.0267950677525598e-05, "loss": 3.4327, "step": 1816064 }, { "epoch": 1.02, "learning_rate": 2.0259581108818807e-05, "loss": 3.435, "step": 1816576 }, { "epoch": 1.02, "learning_rate": 2.0251195161308287e-05, "loss": 3.4305, "step": 1817088 }, { "epoch": 1.02, "learning_rate": 2.0242809213797767e-05, "loss": 3.4324, "step": 1817600 }, { "epoch": 1.02, "learning_rate": 2.0234423266287247e-05, "loss": 3.4291, "step": 1818112 }, { "epoch": 1.02, "learning_rate": 2.0226037318776727e-05, "loss": 3.438, "step": 1818624 }, { "epoch": 1.02, "learning_rate": 2.021766775006994e-05, "loss": 3.4313, "step": 1819136 }, { "epoch": 1.02, "learning_rate": 2.020928180255942e-05, "loss": 3.4373, "step": 1819648 }, { "epoch": 1.02, "learning_rate": 2.02008958550489e-05, "loss": 3.4387, "step": 1820160 }, { "epoch": 1.02, "learning_rate": 2.019250990753838e-05, "loss": 3.4332, "step": 1820672 }, { "epoch": 1.02, "learning_rate": 2.0184140338831588e-05, "loss": 3.436, "step": 1821184 }, { "epoch": 1.02, "learning_rate": 2.0175754391321068e-05, "loss": 3.4377, "step": 1821696 }, { "epoch": 1.02, "learning_rate": 2.016736844381055e-05, "loss": 3.428, "step": 1822208 }, { "epoch": 1.02, "learning_rate": 2.015898249630003e-05, "loss": 3.4358, "step": 1822720 }, { "epoch": 1.02, "learning_rate": 2.015059654878951e-05, "loss": 3.4155, "step": 1823232 }, { "epoch": 1.02, "learning_rate": 2.014222698008272e-05, "loss": 3.4418, "step": 1823744 }, { "epoch": 1.02, "learning_rate": 2.01338410325722e-05, "loss": 3.4378, "step": 1824256 }, { "epoch": 1.02, "learning_rate": 2.012545508506168e-05, "loss": 3.4408, "step": 1824768 }, { "epoch": 1.02, "learning_rate": 2.011706913755116e-05, "loss": 3.4282, "step": 1825280 }, { "epoch": 1.02, "learning_rate": 2.0108699568844373e-05, "loss": 3.4393, "step": 1825792 }, { "epoch": 1.02, "learning_rate": 2.0100313621333853e-05, "loss": 3.4365, "step": 1826304 }, { "epoch": 1.02, "learning_rate": 2.0091927673823333e-05, "loss": 3.4439, "step": 1826816 }, { "epoch": 1.02, "learning_rate": 2.008354172631281e-05, "loss": 3.4305, "step": 1827328 }, { "epoch": 1.02, "learning_rate": 2.007515577880229e-05, "loss": 3.4325, "step": 1827840 }, { "epoch": 1.02, "learning_rate": 2.0066786210095502e-05, "loss": 3.4351, "step": 1828352 }, { "epoch": 1.02, "learning_rate": 2.0058400262584985e-05, "loss": 3.437, "step": 1828864 }, { "epoch": 1.02, "learning_rate": 2.005001431507446e-05, "loss": 3.4375, "step": 1829376 }, { "epoch": 1.02, "learning_rate": 2.004162836756394e-05, "loss": 3.4348, "step": 1829888 }, { "epoch": 1.02, "learning_rate": 2.003324242005342e-05, "loss": 3.443, "step": 1830400 }, { "epoch": 1.02, "learning_rate": 2.002487285134663e-05, "loss": 3.4266, "step": 1830912 }, { "epoch": 1.02, "learning_rate": 2.0016486903836114e-05, "loss": 3.443, "step": 1831424 }, { "epoch": 1.03, "eval_loss": 3.8784711360931396, "eval_runtime": 306.0472, "eval_samples_per_second": 1246.837, "eval_steps_per_second": 38.965, "step": 1831680 }, { "epoch": 0.0, "learning_rate": 2.0008117335129326e-05, "loss": 3.4366, "step": 1831936 }, { "epoch": 0.0, "learning_rate": 1.9999731387618806e-05, "loss": 3.433, "step": 1832448 }, { "epoch": 0.0, "learning_rate": 1.9991345440108283e-05, "loss": 3.4351, "step": 1832960 }, { "epoch": 0.0, "learning_rate": 1.9982959492597763e-05, "loss": 3.4332, "step": 1833472 }, { "epoch": 0.0, "learning_rate": 1.9974573545087243e-05, "loss": 3.4472, "step": 1833984 }, { "epoch": 0.0, "learning_rate": 1.9966203976380455e-05, "loss": 3.4359, "step": 1834496 }, { "epoch": 0.0, "learning_rate": 1.9957818028869935e-05, "loss": 3.4266, "step": 1835008 }, { "epoch": 0.0, "learning_rate": 1.9949432081359415e-05, "loss": 3.4245, "step": 1835520 }, { "epoch": 0.0, "learning_rate": 1.9941046133848895e-05, "loss": 3.4366, "step": 1836032 }, { "epoch": 0.0, "learning_rate": 1.9932676565142104e-05, "loss": 3.4424, "step": 1836544 }, { "epoch": 0.0, "learning_rate": 1.9924290617631584e-05, "loss": 3.4308, "step": 1837056 }, { "epoch": 0.0, "learning_rate": 1.9915904670121068e-05, "loss": 3.4334, "step": 1837568 }, { "epoch": 0.0, "learning_rate": 1.9907518722610548e-05, "loss": 3.4394, "step": 1838080 }, { "epoch": 0.0, "learning_rate": 1.9899132775100028e-05, "loss": 3.4265, "step": 1838592 }, { "epoch": 0.0, "learning_rate": 1.9890763206393237e-05, "loss": 3.4287, "step": 1839104 }, { "epoch": 0.0, "learning_rate": 1.9882377258882717e-05, "loss": 3.4229, "step": 1839616 }, { "epoch": 0.0, "learning_rate": 1.9873991311372197e-05, "loss": 3.4285, "step": 1840128 }, { "epoch": 0.0, "learning_rate": 1.9865605363861677e-05, "loss": 3.4234, "step": 1840640 }, { "epoch": 0.0, "learning_rate": 1.985721941635116e-05, "loss": 3.4356, "step": 1841152 }, { "epoch": 0.0, "learning_rate": 1.984884984764437e-05, "loss": 3.4457, "step": 1841664 }, { "epoch": 0.0, "learning_rate": 1.984046390013385e-05, "loss": 3.4432, "step": 1842176 }, { "epoch": 0.0, "learning_rate": 1.983207795262333e-05, "loss": 3.4342, "step": 1842688 }, { "epoch": 0.0, "learning_rate": 1.982369200511281e-05, "loss": 3.4294, "step": 1843200 }, { "epoch": 0.0, "learning_rate": 1.981532243640602e-05, "loss": 3.4306, "step": 1843712 }, { "epoch": 0.0, "learning_rate": 1.98069364888955e-05, "loss": 3.4297, "step": 1844224 }, { "epoch": 0.0, "learning_rate": 1.979855054138498e-05, "loss": 3.4324, "step": 1844736 }, { "epoch": 0.0, "learning_rate": 1.979016459387446e-05, "loss": 3.4192, "step": 1845248 }, { "epoch": 0.0, "learning_rate": 1.9781778646363938e-05, "loss": 3.4398, "step": 1845760 }, { "epoch": 0.0, "learning_rate": 1.977340907765715e-05, "loss": 3.4289, "step": 1846272 }, { "epoch": 0.0, "learning_rate": 1.976502313014663e-05, "loss": 3.42, "step": 1846784 }, { "epoch": 0.01, "learning_rate": 1.975663718263611e-05, "loss": 3.4197, "step": 1847296 }, { "epoch": 0.01, "learning_rate": 1.974825123512559e-05, "loss": 3.4406, "step": 1847808 }, { "epoch": 0.01, "learning_rate": 1.973986528761507e-05, "loss": 3.4392, "step": 1848320 }, { "epoch": 0.01, "learning_rate": 1.9731495718908283e-05, "loss": 3.4353, "step": 1848832 }, { "epoch": 0.01, "learning_rate": 1.972310977139776e-05, "loss": 3.4268, "step": 1849344 }, { "epoch": 0.01, "learning_rate": 1.971472382388724e-05, "loss": 3.4282, "step": 1849856 }, { "epoch": 0.01, "learning_rate": 1.9706337876376722e-05, "loss": 3.44, "step": 1850368 }, { "epoch": 0.01, "learning_rate": 1.9697968307669935e-05, "loss": 3.4199, "step": 1850880 }, { "epoch": 0.01, "learning_rate": 1.968958236015941e-05, "loss": 3.4179, "step": 1851392 }, { "epoch": 0.01, "learning_rate": 1.968119641264889e-05, "loss": 3.4218, "step": 1851904 }, { "epoch": 0.01, "learning_rate": 1.967281046513837e-05, "loss": 3.4253, "step": 1852416 }, { "epoch": 0.01, "learning_rate": 1.966442451762785e-05, "loss": 3.4338, "step": 1852928 }, { "epoch": 0.01, "learning_rate": 1.9656054948921064e-05, "loss": 3.4273, "step": 1853440 }, { "epoch": 0.01, "learning_rate": 1.9647669001410544e-05, "loss": 3.4322, "step": 1853952 }, { "epoch": 0.01, "learning_rate": 1.9639283053900024e-05, "loss": 3.4287, "step": 1854464 }, { "epoch": 0.01, "learning_rate": 1.9630897106389504e-05, "loss": 3.424, "step": 1854976 }, { "epoch": 0.01, "learning_rate": 1.9622527537682713e-05, "loss": 3.4388, "step": 1855488 }, { "epoch": 0.01, "learning_rate": 1.9614141590172193e-05, "loss": 3.4261, "step": 1856000 }, { "epoch": 0.01, "learning_rate": 1.9605755642661676e-05, "loss": 3.404, "step": 1856512 }, { "epoch": 0.01, "learning_rate": 1.9597369695151156e-05, "loss": 3.4383, "step": 1857024 }, { "epoch": 0.01, "learning_rate": 1.9588983747640636e-05, "loss": 3.4289, "step": 1857536 }, { "epoch": 0.01, "learning_rate": 1.9580614178933845e-05, "loss": 3.439, "step": 1858048 }, { "epoch": 0.01, "learning_rate": 1.9572228231423325e-05, "loss": 3.4253, "step": 1858560 }, { "epoch": 0.01, "learning_rate": 1.9563842283912805e-05, "loss": 3.4198, "step": 1859072 }, { "epoch": 0.01, "learning_rate": 1.9555456336402285e-05, "loss": 3.417, "step": 1859584 }, { "epoch": 0.01, "learning_rate": 1.9547086767695497e-05, "loss": 3.4255, "step": 1860096 }, { "epoch": 0.01, "learning_rate": 1.9538700820184977e-05, "loss": 3.4295, "step": 1860608 }, { "epoch": 0.01, "learning_rate": 1.9530314872674457e-05, "loss": 3.416, "step": 1861120 }, { "epoch": 0.01, "learning_rate": 1.9521928925163937e-05, "loss": 3.4358, "step": 1861632 }, { "epoch": 0.01, "learning_rate": 1.9513542977653414e-05, "loss": 3.4275, "step": 1862144 }, { "epoch": 0.01, "learning_rate": 1.950517340894663e-05, "loss": 3.417, "step": 1862656 }, { "epoch": 0.01, "learning_rate": 1.949678746143611e-05, "loss": 3.434, "step": 1863168 }, { "epoch": 0.01, "learning_rate": 1.948840151392559e-05, "loss": 3.4181, "step": 1863680 }, { "epoch": 0.01, "learning_rate": 1.9480015566415066e-05, "loss": 3.4174, "step": 1864192 }, { "epoch": 0.01, "learning_rate": 1.947164599770828e-05, "loss": 3.4292, "step": 1864704 }, { "epoch": 0.01, "learning_rate": 1.946326005019776e-05, "loss": 3.4379, "step": 1865216 }, { "epoch": 0.01, "learning_rate": 1.945487410268724e-05, "loss": 3.4089, "step": 1865728 }, { "epoch": 0.01, "learning_rate": 1.944648815517672e-05, "loss": 3.4275, "step": 1866240 }, { "epoch": 0.01, "learning_rate": 1.94381022076662e-05, "loss": 3.4126, "step": 1866752 }, { "epoch": 0.01, "learning_rate": 1.942971626015568e-05, "loss": 3.4272, "step": 1867264 }, { "epoch": 0.01, "learning_rate": 1.9421346691448888e-05, "loss": 3.4323, "step": 1867776 }, { "epoch": 0.01, "learning_rate": 1.9412960743938368e-05, "loss": 3.4246, "step": 1868288 }, { "epoch": 0.01, "learning_rate": 1.9404574796427848e-05, "loss": 3.4314, "step": 1868800 }, { "epoch": 0.01, "learning_rate": 1.939618884891733e-05, "loss": 3.425, "step": 1869312 }, { "epoch": 0.01, "learning_rate": 1.938781928021054e-05, "loss": 3.446, "step": 1869824 }, { "epoch": 0.01, "learning_rate": 1.937943333270002e-05, "loss": 3.4161, "step": 1870336 }, { "epoch": 0.01, "learning_rate": 1.93710473851895e-05, "loss": 3.4331, "step": 1870848 }, { "epoch": 0.01, "learning_rate": 1.936266143767898e-05, "loss": 3.4295, "step": 1871360 }, { "epoch": 0.01, "learning_rate": 1.935427549016846e-05, "loss": 3.421, "step": 1871872 }, { "epoch": 0.01, "learning_rate": 1.9345905921461672e-05, "loss": 3.4289, "step": 1872384 }, { "epoch": 0.01, "learning_rate": 1.9337519973951152e-05, "loss": 3.4288, "step": 1872896 }, { "epoch": 0.01, "learning_rate": 1.9329134026440632e-05, "loss": 3.4283, "step": 1873408 }, { "epoch": 0.01, "learning_rate": 1.9320748078930112e-05, "loss": 3.4357, "step": 1873920 }, { "epoch": 0.01, "learning_rate": 1.931237851022332e-05, "loss": 3.4138, "step": 1874432 }, { "epoch": 0.01, "learning_rate": 1.93039925627128e-05, "loss": 3.4194, "step": 1874944 }, { "epoch": 0.01, "learning_rate": 1.9295606615202285e-05, "loss": 3.4196, "step": 1875456 }, { "epoch": 0.01, "learning_rate": 1.9287220667691764e-05, "loss": 3.4356, "step": 1875968 }, { "epoch": 0.01, "learning_rate": 1.9278834720181244e-05, "loss": 3.4226, "step": 1876480 }, { "epoch": 0.01, "learning_rate": 1.927044877267072e-05, "loss": 3.4256, "step": 1876992 }, { "epoch": 0.02, "learning_rate": 1.92620628251602e-05, "loss": 3.43, "step": 1877504 }, { "epoch": 0.02, "learning_rate": 1.9253693256453413e-05, "loss": 3.4239, "step": 1878016 }, { "epoch": 0.02, "learning_rate": 1.9245307308942893e-05, "loss": 3.4213, "step": 1878528 }, { "epoch": 0.02, "learning_rate": 1.9236921361432373e-05, "loss": 3.4081, "step": 1879040 }, { "epoch": 0.02, "learning_rate": 1.9228535413921853e-05, "loss": 3.4233, "step": 1879552 }, { "epoch": 0.02, "learning_rate": 1.9220165845215066e-05, "loss": 3.4305, "step": 1880064 }, { "epoch": 0.02, "learning_rate": 1.9211779897704542e-05, "loss": 3.4327, "step": 1880576 }, { "epoch": 0.02, "learning_rate": 1.9203393950194022e-05, "loss": 3.4169, "step": 1881088 }, { "epoch": 0.02, "learning_rate": 1.9195008002683502e-05, "loss": 3.4209, "step": 1881600 }, { "epoch": 0.02, "learning_rate": 1.9186622055172986e-05, "loss": 3.4227, "step": 1882112 }, { "epoch": 0.02, "learning_rate": 1.9178252486466195e-05, "loss": 3.4269, "step": 1882624 }, { "epoch": 0.02, "learning_rate": 1.9169866538955675e-05, "loss": 3.4292, "step": 1883136 }, { "epoch": 0.02, "learning_rate": 1.9161480591445155e-05, "loss": 3.4259, "step": 1883648 }, { "epoch": 0.02, "learning_rate": 1.9153094643934635e-05, "loss": 3.4288, "step": 1884160 }, { "epoch": 0.02, "learning_rate": 1.9144725075227847e-05, "loss": 3.4223, "step": 1884672 }, { "epoch": 0.02, "learning_rate": 1.9136339127717327e-05, "loss": 3.421, "step": 1885184 }, { "epoch": 0.02, "learning_rate": 1.9127953180206807e-05, "loss": 3.4193, "step": 1885696 }, { "epoch": 0.02, "learning_rate": 1.9119567232696287e-05, "loss": 3.4163, "step": 1886208 }, { "epoch": 0.02, "learning_rate": 1.9111181285185767e-05, "loss": 3.4361, "step": 1886720 }, { "epoch": 0.02, "learning_rate": 1.9102811716478976e-05, "loss": 3.4101, "step": 1887232 }, { "epoch": 0.02, "learning_rate": 1.9094425768968456e-05, "loss": 3.4244, "step": 1887744 }, { "epoch": 0.02, "learning_rate": 1.908603982145794e-05, "loss": 3.4152, "step": 1888256 }, { "epoch": 0.02, "learning_rate": 1.907765387394742e-05, "loss": 3.4299, "step": 1888768 }, { "epoch": 0.02, "learning_rate": 1.9069267926436896e-05, "loss": 3.4209, "step": 1889280 }, { "epoch": 0.02, "learning_rate": 1.9060898357730108e-05, "loss": 3.4255, "step": 1889792 }, { "epoch": 0.02, "learning_rate": 1.9052512410219588e-05, "loss": 3.4226, "step": 1890304 }, { "epoch": 0.02, "learning_rate": 1.9044126462709068e-05, "loss": 3.4367, "step": 1890816 }, { "epoch": 0.02, "learning_rate": 1.9035740515198548e-05, "loss": 3.4265, "step": 1891328 }, { "epoch": 0.02, "learning_rate": 1.902737094649176e-05, "loss": 3.4319, "step": 1891840 }, { "epoch": 0.02, "learning_rate": 1.901898499898124e-05, "loss": 3.4251, "step": 1892352 }, { "epoch": 0.02, "learning_rate": 1.901059905147072e-05, "loss": 3.4245, "step": 1892864 }, { "epoch": 0.02, "learning_rate": 1.9002213103960197e-05, "loss": 3.42, "step": 1893376 }, { "epoch": 0.02, "learning_rate": 1.899384353525341e-05, "loss": 3.4202, "step": 1893888 }, { "epoch": 0.02, "learning_rate": 1.8985457587742893e-05, "loss": 3.4179, "step": 1894400 }, { "epoch": 0.02, "learning_rate": 1.897707164023237e-05, "loss": 3.425, "step": 1894912 }, { "epoch": 0.02, "learning_rate": 1.896868569272185e-05, "loss": 3.4207, "step": 1895424 }, { "epoch": 0.02, "learning_rate": 1.8960316124015062e-05, "loss": 3.427, "step": 1895936 }, { "epoch": 0.02, "learning_rate": 1.8951930176504542e-05, "loss": 3.4241, "step": 1896448 }, { "epoch": 0.02, "learning_rate": 1.894354422899402e-05, "loss": 3.4248, "step": 1896960 }, { "epoch": 0.02, "learning_rate": 1.8935158281483502e-05, "loss": 3.4255, "step": 1897472 }, { "epoch": 0.02, "learning_rate": 1.8926788712776714e-05, "loss": 3.4286, "step": 1897984 }, { "epoch": 0.02, "learning_rate": 1.8918402765266194e-05, "loss": 3.4161, "step": 1898496 }, { "epoch": 0.02, "learning_rate": 1.891001681775567e-05, "loss": 3.4265, "step": 1899008 }, { "epoch": 0.02, "learning_rate": 1.890163087024515e-05, "loss": 3.4039, "step": 1899520 }, { "epoch": 0.02, "learning_rate": 1.889324492273463e-05, "loss": 3.4314, "step": 1900032 }, { "epoch": 0.02, "learning_rate": 1.8884875354027843e-05, "loss": 3.4286, "step": 1900544 }, { "epoch": 0.02, "learning_rate": 1.8876489406517323e-05, "loss": 3.4331, "step": 1901056 }, { "epoch": 0.02, "learning_rate": 1.8868103459006803e-05, "loss": 3.417, "step": 1901568 }, { "epoch": 0.02, "learning_rate": 1.8859717511496283e-05, "loss": 3.4312, "step": 1902080 }, { "epoch": 0.02, "learning_rate": 1.8851331563985763e-05, "loss": 3.4233, "step": 1902592 }, { "epoch": 0.02, "learning_rate": 1.8842961995278972e-05, "loss": 3.4383, "step": 1903104 }, { "epoch": 0.02, "learning_rate": 1.8834576047768455e-05, "loss": 3.4189, "step": 1903616 }, { "epoch": 0.02, "learning_rate": 1.8826190100257935e-05, "loss": 3.4207, "step": 1904128 }, { "epoch": 0.02, "learning_rate": 1.8817820531551145e-05, "loss": 3.4226, "step": 1904640 }, { "epoch": 0.02, "learning_rate": 1.8809434584040624e-05, "loss": 3.4312, "step": 1905152 }, { "epoch": 0.02, "learning_rate": 1.8801048636530104e-05, "loss": 3.4224, "step": 1905664 }, { "epoch": 0.02, "learning_rate": 1.8792662689019584e-05, "loss": 3.4249, "step": 1906176 }, { "epoch": 0.02, "learning_rate": 1.8784276741509064e-05, "loss": 3.432, "step": 1906688 }, { "epoch": 0.02, "learning_rate": 1.8775907172802277e-05, "loss": 3.4208, "step": 1907200 }, { "epoch": 0.02, "learning_rate": 1.8767521225291757e-05, "loss": 3.4294, "step": 1907712 }, { "epoch": 0.03, "eval_loss": 3.880861282348633, "eval_runtime": 303.9922, "eval_samples_per_second": 1255.266, "eval_steps_per_second": 39.228, "step": 1908000 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.2744839704955904e+18, "trial_name": null, "trial_params": null }