{ "best_metric": 3.9104487895965576, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/full2/transformer/1/checkpoints/checkpoint-305280", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 305280, "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": 10.9454, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8259, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1849, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9803, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8167, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7055, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6038, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5334, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4448, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.3954, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3443, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3189, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2639, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.1992, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1743, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.137, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1066, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0804, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0551, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0135, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0066, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.9713, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9507, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9237, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9215, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.8944, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8692, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8503, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8324, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.8222, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.7998, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.7909, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7796, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.9723329247367764e-05, "loss": 4.7645, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7622, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7476, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969820416244367e-05, "loss": 4.733, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.7055, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7012, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6844, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6838, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6677, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6617, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6456, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6513, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6349, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6356, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6256, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5973, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5911, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.6054, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5893, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5748, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5602, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5638, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5468, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5615, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.525, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5379, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5354, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5131, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5289, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5001, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.5001, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4881, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945510995746097e-05, "loss": 4.5029, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4753, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.481, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4663, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4627, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4745, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940482703000532e-05, "loss": 4.4668, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396441082494794e-05, "loss": 4.4581, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388055134984274e-05, "loss": 4.4597, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4643, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4363, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4522, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4266, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4257, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.424, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4271, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4194, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4262, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4109, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3903, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.3918, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4035, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3888, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.92623314375414e-05, "loss": 4.3881, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3925, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.375, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.3815, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3739, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3801, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921203213128201e-05, "loss": 4.3768, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3721, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.3504, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3571, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3499, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3525, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3597, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3371, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914496093000158e-05, "loss": 4.3421, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913657498249106e-05, "loss": 4.3442, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3366, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3252, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3289, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3174, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3167, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.9086292055035406e-05, "loss": 4.3155, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.9077906107524886e-05, "loss": 4.3148, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.9069520160014366e-05, "loss": 4.3079, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.9061134212503846e-05, "loss": 4.3144, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.3044, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3066, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3138, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027606801265495e-05, "loss": 4.31, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.3043, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.295, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.2948, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.2928, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.2805, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977307495006104e-05, "loss": 4.2849, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968921547495584e-05, "loss": 4.2801, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.284, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2741, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2821, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2762, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.8926991809942984e-05, "loss": 4.2694, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2626, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2799, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2705, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2632, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888509482999785e-05, "loss": 4.2629, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887672526129106e-05, "loss": 4.2671, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886833931378054e-05, "loss": 4.2628, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885995336627002e-05, "loss": 4.265, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515674187595e-05, "loss": 4.2548, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2543, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2528, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2439, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2412, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809654060010626e-05, "loss": 4.2412, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801268112500106e-05, "loss": 4.2439, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2334, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2446, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877614302757601e-05, "loss": 4.2349, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876775708006549e-05, "loss": 4.2371, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875937113255497e-05, "loss": 4.2406, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875098518504445e-05, "loss": 4.2215, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.193474292755127, "eval_runtime": 317.2956, "eval_samples_per_second": 1202.636, "eval_steps_per_second": 37.583, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.874259923753393e-05, "loss": 4.2116, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873421329002341e-05, "loss": 4.21, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872584372131662e-05, "loss": 4.2335, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.87174577738061e-05, "loss": 4.2158, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870907182629558e-05, "loss": 4.2208, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870068587878506e-05, "loss": 4.2133, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869229993127454e-05, "loss": 4.2059, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683913983764027e-05, "loss": 4.1979, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675544415057236e-05, "loss": 4.2071, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667158467546716e-05, "loss": 4.1993, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658772520036196e-05, "loss": 4.2226, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650386572525676e-05, "loss": 4.2066, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642017003818885e-05, "loss": 4.1887, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633631056308365e-05, "loss": 4.188, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625245108797845e-05, "loss": 4.1931, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616859161287324e-05, "loss": 4.1794, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608473213776804e-05, "loss": 4.1918, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860008726626628e-05, "loss": 4.189, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591701318755764e-05, "loss": 4.1751, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583315371245244e-05, "loss": 4.2017, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1808, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.1821, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.855817390751741e-05, "loss": 4.173, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854978796000689e-05, "loss": 4.1918, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1693, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.1707, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.166, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851626054876854e-05, "loss": 4.1657, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850787460125802e-05, "loss": 4.1628, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.84994886537475e-05, "loss": 4.1599, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1631, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1636, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1601, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1662, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.1608, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1597, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.145, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1474, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1394, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841564555744604e-05, "loss": 4.1485, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1392, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1485, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1294, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1491, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.8373732198697167e-05, "loss": 4.1411, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1424, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1374, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1224, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834022116626255e-05, "loss": 4.1235, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833183521875203e-05, "loss": 4.1393, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832344927124151e-05, "loss": 4.1297, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.1247, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830667737622047e-05, "loss": 4.1158, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.8298291428709944e-05, "loss": 4.1274, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.8289905481199424e-05, "loss": 4.1072, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.8281519533688904e-05, "loss": 4.1334, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273133586178384e-05, "loss": 4.103, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.82647640174716e-05, "loss": 4.1229, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.825637806996108e-05, "loss": 4.1192, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.824799212245056e-05, "loss": 4.1066, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823960617494004e-05, "loss": 4.1188, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.823123660623325e-05, "loss": 4.1073, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.822285065872273e-05, "loss": 4.1064, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.821446471121221e-05, "loss": 4.0946, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820607876370169e-05, "loss": 4.1185, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.0927, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818932324748438e-05, "loss": 4.1058, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818093729997386e-05, "loss": 4.0837, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817255135246334e-05, "loss": 4.097, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.1068, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.8155795836246034e-05, "loss": 4.1047, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.8147409888735514e-05, "loss": 4.0996, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.8139023941224994e-05, "loss": 4.1027, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1087, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.0931, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811388247749716e-05, "loss": 4.1021, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810549652998664e-05, "loss": 4.0893, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809712696127985e-05, "loss": 4.0892, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.0848, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808035506625881e-05, "loss": 4.0956, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807196911874829e-05, "loss": 4.0944, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806358317123777e-05, "loss": 4.0999, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805519722372726e-05, "loss": 4.0898, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804682765502047e-05, "loss": 4.0693, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803844170750995e-05, "loss": 4.0746, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803005575999943e-05, "loss": 4.085, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.802166981248891e-05, "loss": 4.0808, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013300243782116e-05, "loss": 4.0758, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004914296271596e-05, "loss": 4.0856, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996528348761076e-05, "loss": 4.0698, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988142401250556e-05, "loss": 4.0733, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979772832543765e-05, "loss": 4.0757, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.7971386885033245e-05, "loss": 4.0839, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.7963000937522725e-05, "loss": 4.0795, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795461499001221e-05, "loss": 4.0863, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794624542130542e-05, "loss": 4.0585, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.79378594737949e-05, "loss": 4.0702, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792947352628438e-05, "loss": 4.0669, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792108757877386e-05, "loss": 4.0652, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.791271801006707e-05, "loss": 4.0818, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790433206255655e-05, "loss": 4.0596, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789594611504603e-05, "loss": 4.0654, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788756016753551e-05, "loss": 4.071, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787919059882872e-05, "loss": 4.0669, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.78708046513182e-05, "loss": 4.0507, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.786241870380768e-05, "loss": 4.0646, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854032756297166e-05, "loss": 4.0553, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845663187590375e-05, "loss": 4.0517, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837293618883584e-05, "loss": 4.0508, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828907671373064e-05, "loss": 4.0524, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820521723862544e-05, "loss": 4.0497, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812135776352024e-05, "loss": 4.0614, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803749828841504e-05, "loss": 4.0462, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.7795363881330984e-05, "loss": 4.0537, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.7786977933820464e-05, "loss": 4.0654, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.7778591986309944e-05, "loss": 4.0583, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777022241760315e-05, "loss": 4.0558, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776183647009263e-05, "loss": 4.0505, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775345052258212e-05, "loss": 4.0455, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.77450645750716e-05, "loss": 4.0485, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773669500636481e-05, "loss": 4.0427, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772832543765802e-05, "loss": 4.0414, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.77199394901475e-05, "loss": 4.0433, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771155354263698e-05, "loss": 4.0485, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770316759512646e-05, "loss": 4.0439, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.769478164761594e-05, "loss": 4.0444, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.768639570010542e-05, "loss": 4.045, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.76780097525949e-05, "loss": 4.0345, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766962380508437e-05, "loss": 4.0331, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766123785757386e-05, "loss": 4.0517, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.765286828886707e-05, "loss": 4.0464, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764448234135655e-05, "loss": 4.0413, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.7636096393846026e-05, "loss": 4.0357, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.7627710446335506e-05, "loss": 4.0427, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.7619324498824986e-05, "loss": 4.0382, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.7610954930118195e-05, "loss": 4.0468, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.7602568982607675e-05, "loss": 4.0383, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.7594183035097155e-05, "loss": 4.0336, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.7585797087586635e-05, "loss": 4.0348, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.7577427518879844e-05, "loss": 4.0317, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569041571369324e-05, "loss": 4.0245, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756065562385881e-05, "loss": 4.0304, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.755226967634829e-05, "loss": 4.0347, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.754388372883777e-05, "loss": 4.0212, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.753551416013098e-05, "loss": 4.0394, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.752712821262046e-05, "loss": 4.0288, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.751874226510994e-05, "loss": 4.0277, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.751035631759942e-05, "loss": 4.0313, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.750198674889263e-05, "loss": 4.0184, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.025022029876709, "eval_runtime": 317.0746, "eval_samples_per_second": 1203.474, "eval_steps_per_second": 37.609, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.749360080138211e-05, "loss": 4.0074, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748521485387159e-05, "loss": 4.0086, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.747682890636107e-05, "loss": 4.0333, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746844295885055e-05, "loss": 4.0181, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.746005701134003e-05, "loss": 4.0278, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.745167106382951e-05, "loss": 4.0109, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.744328511631899e-05, "loss": 4.0141, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434899168808475e-05, "loss": 4.0027, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.0138, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0093, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.0274, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.7401371757570124e-05, "loss": 4.0181, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739300218886333e-05, "loss": 3.998, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738461624135281e-05, "loss": 4.0035, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737623029384229e-05, "loss": 4.0092, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736784434633177e-05, "loss": 3.992, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735945839882125e-05, "loss": 4.0043, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735107245131073e-05, "loss": 4.0069, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734268650380021e-05, "loss": 3.9951, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733430055628969e-05, "loss": 4.0229, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732591460877917e-05, "loss": 3.9992, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731752866126865e-05, "loss": 4.0041, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730914271375813e-05, "loss": 3.9967, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730075676624761e-05, "loss": 4.0149, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729238719754082e-05, "loss": 3.989, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.72840012500303e-05, "loss": 3.9962, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727561530251978e-05, "loss": 3.9893, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726722935500926e-05, "loss": 3.9946, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.725885978630247e-05, "loss": 3.9888, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.725047383879195e-05, "loss": 3.9873, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.724210427008517e-05, "loss": 3.9952, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.7233718322574647e-05, "loss": 3.996, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225332375064127e-05, "loss": 3.988, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216946427553606e-05, "loss": 4.0014, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208560480043086e-05, "loss": 3.9881, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200174532532566e-05, "loss": 3.9944, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191788585022046e-05, "loss": 3.9806, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183402637511526e-05, "loss": 3.9846, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175033068804735e-05, "loss": 3.9719, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.7166647121294215e-05, "loss": 3.9875, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158261173783695e-05, "loss": 3.9756, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149875226273175e-05, "loss": 3.9883, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.7141505657566384e-05, "loss": 3.9731, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133119710055864e-05, "loss": 3.9851, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712473376254535e-05, "loss": 3.9894, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711634781503483e-05, "loss": 3.9813, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710797824632804e-05, "loss": 3.984, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709959229881752e-05, "loss": 3.9663, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709122273011073e-05, "loss": 3.9671, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708283678260021e-05, "loss": 3.9843, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707445083508969e-05, "loss": 3.9758, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706606488757917e-05, "loss": 3.974, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705767894006865e-05, "loss": 3.9616, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704929299255813e-05, "loss": 3.9752, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704090704504761e-05, "loss": 3.9527, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703252109753709e-05, "loss": 3.986, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024151528830305e-05, "loss": 3.9538, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015765581319785e-05, "loss": 3.9739, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007379633809265e-05, "loss": 3.9729, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6998993686298745e-05, "loss": 3.9587, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990624117591954e-05, "loss": 3.9746, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982238170081434e-05, "loss": 3.9588, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973852222570914e-05, "loss": 3.9598, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.6965466275060394e-05, "loss": 3.9478, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.69570967063536e-05, "loss": 3.9715, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694871075884308e-05, "loss": 3.9525, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694032481133256e-05, "loss": 3.9603, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693193886382204e-05, "loss": 3.9448, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692356929511526e-05, "loss": 3.9528, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691518334760474e-05, "loss": 3.9644, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690679740009422e-05, "loss": 3.9676, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689841145258369e-05, "loss": 3.9551, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689004188387691e-05, "loss": 3.9669, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688165593636639e-05, "loss": 3.9676, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687326998885587e-05, "loss": 3.9573, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686488404134534e-05, "loss": 3.958, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856514472638556e-05, "loss": 3.9583, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848128525128036e-05, "loss": 3.9522, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683974257761751e-05, "loss": 3.9499, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831356630106996e-05, "loss": 3.959, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822987061400205e-05, "loss": 3.9605, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681460111388969e-05, "loss": 3.9668, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806215166379165e-05, "loss": 3.952, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797829218868645e-05, "loss": 3.9326, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678945965016186e-05, "loss": 3.9416, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678107370265134e-05, "loss": 3.9539, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772687755140814e-05, "loss": 3.948, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764301807630294e-05, "loss": 3.9429, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675593223892351e-05, "loss": 3.9503, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674754629141298e-05, "loss": 3.9454, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.673916034390246e-05, "loss": 3.9373, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673077439639194e-05, "loss": 3.945, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672240482768516e-05, "loss": 3.9548, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671401888017464e-05, "loss": 3.9505, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670563293266412e-05, "loss": 3.9554, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.66972469851536e-05, "loss": 3.9388, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688877416446815e-05, "loss": 3.9423, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668049146893629e-05, "loss": 3.9405, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667210552142577e-05, "loss": 3.9429, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666371957391525e-05, "loss": 3.9524, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665535000520846e-05, "loss": 3.937, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664696405769794e-05, "loss": 3.9386, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663857811018742e-05, "loss": 3.9455, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66301921626769e-05, "loss": 3.9468, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662182259397011e-05, "loss": 3.9272, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661343664645959e-05, "loss": 3.9357, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660505069894907e-05, "loss": 3.9376, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659668113024229e-05, "loss": 3.9292, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.65883115615355e-05, "loss": 3.9297, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657992561402498e-05, "loss": 3.9309, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657153966651446e-05, "loss": 3.933, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656315371900393e-05, "loss": 3.9375, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655476777149341e-05, "loss": 3.9263, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654638182398289e-05, "loss": 3.9327, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653799587647237e-05, "loss": 3.9452, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652960992896185e-05, "loss": 3.9463, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.6521240360255066e-05, "loss": 3.9346, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.6512854412744546e-05, "loss": 3.9348, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.6504468465234026e-05, "loss": 3.9303, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.6496082517723506e-05, "loss": 3.9311, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.6487712949016715e-05, "loss": 3.9221, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647934338030993e-05, "loss": 3.9235, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470957432799404e-05, "loss": 3.9275, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462571485288884e-05, "loss": 3.9355, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454185537778364e-05, "loss": 3.9269, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445799590267844e-05, "loss": 3.9308, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437413642757324e-05, "loss": 3.9288, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429027695246804e-05, "loss": 3.9202, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642064174773629e-05, "loss": 3.9177, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.64122721790295e-05, "loss": 3.9377, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640388623151898e-05, "loss": 3.9347, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639550028400846e-05, "loss": 3.9259, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638713071530167e-05, "loss": 3.9231, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637874476779115e-05, "loss": 3.9261, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637035882028063e-05, "loss": 3.9294, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636197287277011e-05, "loss": 3.9395, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635360330406332e-05, "loss": 3.9267, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.63452173565528e-05, "loss": 3.9211, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633683140904228e-05, "loss": 3.9246, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632844546153176e-05, "loss": 3.9214, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320059514021244e-05, "loss": 3.9185, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311673566510724e-05, "loss": 3.9207, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303287619000204e-05, "loss": 3.925, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.6294901671489684e-05, "loss": 3.9151, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628654848158662e-05, "loss": 3.928, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.62781625340761e-05, "loss": 3.9243, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626977658656558e-05, "loss": 3.9191, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626139063905506e-05, "loss": 3.9233, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625300469154454e-05, "loss": 3.9089, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.9513087272644043, "eval_runtime": 301.973, "eval_samples_per_second": 1263.659, "eval_steps_per_second": 39.49, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624461874403402e-05, "loss": 3.9125, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.62362327965235e-05, "loss": 3.9009, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622786322781671e-05, "loss": 3.9276, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.62194772803062e-05, "loss": 3.9126, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621109133279568e-05, "loss": 3.9262, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.620270538528516e-05, "loss": 3.9052, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.619431943777464e-05, "loss": 3.9158, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.618593349026412e-05, "loss": 3.8953, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.617756392155733e-05, "loss": 3.9142, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.616917797404681e-05, "loss": 3.9035, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.616079202653629e-05, "loss": 3.9261, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.615240607902577e-05, "loss": 3.9134, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6144036510318976e-05, "loss": 3.8943, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135650562808456e-05, "loss": 3.901, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127264615297936e-05, "loss": 3.909, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.6118878667787416e-05, "loss": 3.8948, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.6110492720276896e-05, "loss": 3.9025, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.6102106772766376e-05, "loss": 3.9059, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.6093720825255856e-05, "loss": 3.8965, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.6085334877745336e-05, "loss": 3.9278, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.6076948930234816e-05, "loss": 3.8983, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.6068562982724296e-05, "loss": 3.9022, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.6060177035213776e-05, "loss": 3.9017, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051807466506985e-05, "loss": 3.9094, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.6043421518996465e-05, "loss": 3.8932, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.6035035571485945e-05, "loss": 3.8994, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.6026649623975425e-05, "loss": 3.8938, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.6018280055268634e-05, "loss": 3.8967, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.6009894107758114e-05, "loss": 3.8913, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.60015081602476e-05, "loss": 3.8909, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599312221273708e-05, "loss": 3.895, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598473626522656e-05, "loss": 3.9013, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.597635031771604e-05, "loss": 3.8996, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596796437020552e-05, "loss": 3.9016, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595959480149873e-05, "loss": 3.8928, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595120885398821e-05, "loss": 3.8981, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594282290647769e-05, "loss": 3.8839, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593443695896717e-05, "loss": 3.8972, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592605101145665e-05, "loss": 3.8781, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591768144274986e-05, "loss": 3.8905, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590929549523934e-05, "loss": 3.8828, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.590090954772882e-05, "loss": 3.898, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.58925236002183e-05, "loss": 3.8818, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.5884137652707785e-05, "loss": 3.8869, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587575170519726e-05, "loss": 3.8972, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.586736575768674e-05, "loss": 3.8911, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585897981017622e-05, "loss": 3.8929, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585061024146943e-05, "loss": 3.877, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.584224067276264e-05, "loss": 3.8754, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583385472525212e-05, "loss": 3.8892, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.58254687777416e-05, "loss": 3.8863, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.5817082830231076e-05, "loss": 3.8807, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.5808696882720556e-05, "loss": 3.8751, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580032731401377e-05, "loss": 3.8864, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579194136650325e-05, "loss": 3.8654, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.578355541899273e-05, "loss": 3.8862, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577516947148221e-05, "loss": 3.8675, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576678352397169e-05, "loss": 3.8814, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.57584139552649e-05, "loss": 3.8863, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.575002800775438e-05, "loss": 3.8715, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.574164206024386e-05, "loss": 3.8817, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.573325611273334e-05, "loss": 3.8735, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.572487016522282e-05, "loss": 3.8714, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.571650059651603e-05, "loss": 3.8657, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.570811464900551e-05, "loss": 3.8805, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569972870149499e-05, "loss": 3.8672, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.5691342753984476e-05, "loss": 3.8752, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.5682956806473956e-05, "loss": 3.8592, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.5674587237767165e-05, "loss": 3.8654, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.5666201290256645e-05, "loss": 3.8766, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.5657815342746125e-05, "loss": 3.8832, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.5649429395235605e-05, "loss": 3.869, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.5641043447725085e-05, "loss": 3.883, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.5632657500214565e-05, "loss": 3.8808, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.5624271552704045e-05, "loss": 3.8709, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.5615885605193525e-05, "loss": 3.8756, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.5607516036486734e-05, "loss": 3.8727, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599130088976214e-05, "loss": 3.8685, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590744141465694e-05, "loss": 3.8669, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.5582358193955174e-05, "loss": 3.8741, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557398862524839e-05, "loss": 3.8781, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556560267773787e-05, "loss": 3.8743, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555721673022735e-05, "loss": 3.8724, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554883078271683e-05, "loss": 3.853, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.554044483520631e-05, "loss": 3.8575, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553207526649952e-05, "loss": 3.8682, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.5523689318989e-05, "loss": 3.8678, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551530337147848e-05, "loss": 3.8623, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550691742396796e-05, "loss": 3.8668, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549854785526117e-05, "loss": 3.8631, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549016190775065e-05, "loss": 3.8563, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548177596024013e-05, "loss": 3.8641, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547339001272961e-05, "loss": 3.8712, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546500406521909e-05, "loss": 3.8682, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545661811770857e-05, "loss": 3.8783, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544823217019805e-05, "loss": 3.8612, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543984622268753e-05, "loss": 3.859, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.543149303278447e-05, "loss": 3.8615, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542310708527395e-05, "loss": 3.8634, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541472113776343e-05, "loss": 3.8735, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540633519025291e-05, "loss": 3.8565, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539796562154612e-05, "loss": 3.86, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.53895796740356e-05, "loss": 3.864, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538119372652508e-05, "loss": 3.8692, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.537280777901456e-05, "loss": 3.8491, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.536442183150404e-05, "loss": 3.8591, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.535605226279726e-05, "loss": 3.8593, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.534766631528674e-05, "loss": 3.8511, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.533928036777621e-05, "loss": 3.8475, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.533089442026569e-05, "loss": 3.8569, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.532250847275517e-05, "loss": 3.8564, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.531412252524465e-05, "loss": 3.8581, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.530575295653786e-05, "loss": 3.8508, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.529736700902734e-05, "loss": 3.851, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.528898106151682e-05, "loss": 3.8702, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.52805951140063e-05, "loss": 3.8668, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.5272209166495786e-05, "loss": 3.8609, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.5263839597788995e-05, "loss": 3.8579, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.5255453650278475e-05, "loss": 3.855, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5247067702767955e-05, "loss": 3.8528, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238681755257435e-05, "loss": 3.8471, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.5230312186550644e-05, "loss": 3.847, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.5221926239040124e-05, "loss": 3.8507, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213540291529604e-05, "loss": 3.8596, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.5205154344019084e-05, "loss": 3.8497, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519678477531229e-05, "loss": 3.8584, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518839882780177e-05, "loss": 3.8505, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.518001288029125e-05, "loss": 3.8466, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517162693278074e-05, "loss": 3.843, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516325736407395e-05, "loss": 3.8639, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515487141656343e-05, "loss": 3.8618, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514648546905291e-05, "loss": 3.8516, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513809952154239e-05, "loss": 3.8481, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512971357403187e-05, "loss": 3.8549, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512134400532508e-05, "loss": 3.8514, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511295805781456e-05, "loss": 3.8633, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510457211030404e-05, "loss": 3.8484, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509618616279352e-05, "loss": 3.8522, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087816594086726e-05, "loss": 3.8489, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079430646576206e-05, "loss": 3.8544, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507104469906569e-05, "loss": 3.8425, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506265875155517e-05, "loss": 3.8469, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505428918284838e-05, "loss": 3.8517, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504590323533786e-05, "loss": 3.844, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503751728782734e-05, "loss": 3.8518, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502913134031682e-05, "loss": 3.8557, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.502076177161003e-05, "loss": 3.8473, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501237582409951e-05, "loss": 3.8488, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500398987658899e-05, "loss": 3.8437, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.9104487895965576, "eval_runtime": 302.9202, "eval_samples_per_second": 1259.708, "eval_steps_per_second": 39.367, "step": 305280 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 2.1246717110453453e+17, "trial_name": null, "trial_params": null }