{ "best_metric": 3.951106309890747, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/1/checkpoints/checkpoint-228960", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 228960, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.9232, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8136, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1808, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.976, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8215, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.713, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.61, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5443, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4534, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4147, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3633, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3228, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2592, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2219, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1884, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1394, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1226, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.089, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0496, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0283, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 5.0114, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.9823927859886547e-05, "loss": 4.981, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9633, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9298, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9221, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790400448648195e-05, "loss": 4.9022, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8784, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.857, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8314, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756873037409844e-05, "loss": 4.824, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.8069, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.8009, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7843, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7694, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7615, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7503, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.739, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 4.7088, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 4.707, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 4.6818, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 4.6879, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6677, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6699, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.649, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6457, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6376, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6291, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6187, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5937, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.6004, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.601, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5946, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5739, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5624, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5642, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.55, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5649, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5261, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5434, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5326, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5126, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5224, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5079, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4979, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4943, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5034, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944672400995045e-05, "loss": 4.4827, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4789, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.471, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.4655, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4722, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.940482703000532e-05, "loss": 4.477, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396441082494794e-05, "loss": 4.4526, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388055134984274e-05, "loss": 4.4636, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379669187473754e-05, "loss": 4.4666, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4495, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4365, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4387, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4364, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4224, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.4195, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4287, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4282, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930421203868281e-05, "loss": 4.4123, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3904, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4031, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4074, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927068462744446e-05, "loss": 4.3974, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.3991, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3821, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.3804, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.3754, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922878764749932e-05, "loss": 4.3731, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.92204016999888e-05, "loss": 4.3787, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921201575247828e-05, "loss": 4.3669, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3841, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.3662, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3504, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.352, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3593, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.351, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3494, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3473, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.913657498249106e-05, "loss": 4.337, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3398, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3189, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.91114171399595e-05, "loss": 4.3246, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3298, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3238, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3181, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.3261, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3007, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.3122, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.3079, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3116, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3183, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3073, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019237232558704e-05, "loss": 4.2984, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010851285048184e-05, "loss": 4.2929, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.900246533753767e-05, "loss": 4.3001, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.899407939002715e-05, "loss": 4.2944, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985693442516624e-05, "loss": 4.2926, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977307495006104e-05, "loss": 4.2851, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968921547495584e-05, "loss": 4.2819, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2825, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2709, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2795, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2758, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2697, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2613, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2795, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2796, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2674, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2552, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887670888248733e-05, "loss": 4.2636, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2639, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885993698746629e-05, "loss": 4.2627, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.885155103995577e-05, "loss": 4.2588, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2586, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2527, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2502, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2447, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.2488, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.2398, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.8792882164989586e-05, "loss": 4.2344, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.878449621747907e-05, "loss": 4.2476, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877611026996855e-05, "loss": 4.2317, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876772432245803e-05, "loss": 4.2424, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875933837494751e-05, "loss": 4.2295, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875096880624072e-05, "loss": 4.224, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.19596529006958, "eval_runtime": 307.6211, "eval_samples_per_second": 1240.458, "eval_steps_per_second": 38.765, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.87425828587302e-05, "loss": 4.2161, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873419691121968e-05, "loss": 4.2145, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872581096370916e-05, "loss": 4.2271, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.8717425016198635e-05, "loss": 4.2185, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.8709039068688115e-05, "loss": 4.2223, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2098, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869228355247081e-05, "loss": 4.2089, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.868389760496029e-05, "loss": 4.1976, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.867551165744977e-05, "loss": 4.2139, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.866712570993925e-05, "loss": 4.2054, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.865875614123246e-05, "loss": 4.2174, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.865037019372194e-05, "loss": 4.199, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642000625015155e-05, "loss": 4.1959, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633614677504635e-05, "loss": 4.1895, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.862522872999411e-05, "loss": 4.1857, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.861684278248359e-05, "loss": 4.1848, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.860845683497307e-05, "loss": 4.1926, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860007088746255e-05, "loss": 4.181, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.859168493995203e-05, "loss": 4.1791, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.858329899244151e-05, "loss": 4.1997, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1842, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.8566543476224204e-05, "loss": 4.1846, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.8558157528713684e-05, "loss": 4.1733, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.8549771581203164e-05, "loss": 4.186, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1715, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.1731, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.1706, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851624416996481e-05, "loss": 4.1629, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850787460125802e-05, "loss": 4.159, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.84994886537475e-05, "loss": 4.158, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1673, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1656, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847434719001968e-05, "loss": 4.1599, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846596124250916e-05, "loss": 4.1656, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.1609, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1605, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844081977878133e-05, "loss": 4.1478, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843243383127081e-05, "loss": 4.1481, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842404788376029e-05, "loss": 4.1373, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841566193624977e-05, "loss": 4.15, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1347, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398906420032456e-05, "loss": 4.1489, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.8390520472521936e-05, "loss": 4.1351, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382134525011416e-05, "loss": 4.1394, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83737485775009e-05, "loss": 4.1396, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836537900879411e-05, "loss": 4.1371, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835699306128359e-05, "loss": 4.1348, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834860711377307e-05, "loss": 4.1203, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834022116626255e-05, "loss": 4.1246, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833185159755576e-05, "loss": 4.1364, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832346565004524e-05, "loss": 4.1332, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831507970253472e-05, "loss": 4.1238, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.83066937550242e-05, "loss": 4.1138, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829832418631741e-05, "loss": 4.1229, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828993823880689e-05, "loss": 4.11, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828155229129637e-05, "loss": 4.1329, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273166343785856e-05, "loss": 4.1041, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264796775079065e-05, "loss": 4.1261, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256410827568545e-05, "loss": 4.1179, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248024880058025e-05, "loss": 4.1028, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.8239638932547505e-05, "loss": 4.1151, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231269363840714e-05, "loss": 4.1112, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222883416330194e-05, "loss": 4.0991, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214497468819674e-05, "loss": 4.1038, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.8206111521309154e-05, "loss": 4.1144, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819774195260236e-05, "loss": 4.1019, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818935600509184e-05, "loss": 4.1004, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818097005758132e-05, "loss": 4.0964, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817258411007081e-05, "loss": 4.0942, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816421454136402e-05, "loss": 4.1035, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.81558285938535e-05, "loss": 4.1158, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814744264634298e-05, "loss": 4.0961, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813905669883246e-05, "loss": 4.1094, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813068713012567e-05, "loss": 4.1096, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812230118261515e-05, "loss": 4.0974, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811391523510463e-05, "loss": 4.089, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810552928759411e-05, "loss": 4.0998, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809715971888732e-05, "loss": 4.0974, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.80887737713768e-05, "loss": 4.088, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808038782386628e-05, "loss": 4.0883, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807200187635576e-05, "loss": 4.0946, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806363230764897e-05, "loss": 4.1017, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805524636013845e-05, "loss": 4.0884, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804686041262793e-05, "loss": 4.0768, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803847446511741e-05, "loss": 4.082, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803010489641062e-05, "loss": 4.0887, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.80217189489001e-05, "loss": 4.0863, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801333300138958e-05, "loss": 4.0892, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800496343268279e-05, "loss": 4.0766, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799657748517227e-05, "loss": 4.0722, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798819153766175e-05, "loss": 4.0715, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797980559015123e-05, "loss": 4.0741, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797141964264071e-05, "loss": 4.0767, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796303369513019e-05, "loss": 4.0739, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795464774761967e-05, "loss": 4.094, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794626180010915e-05, "loss": 4.0777, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793789223140236e-05, "loss": 4.061, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792950628389184e-05, "loss": 4.0699, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792112033638132e-05, "loss": 4.0729, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.79127343888708e-05, "loss": 4.0726, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790436482016401e-05, "loss": 4.0715, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789597887265349e-05, "loss": 4.068, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788759292514297e-05, "loss": 4.0614, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787920697763245e-05, "loss": 4.0714, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870837408925664e-05, "loss": 4.0442, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862451461415144e-05, "loss": 4.0587, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.785408189270836e-05, "loss": 4.0595, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.784569594519783e-05, "loss": 4.0604, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783730999768731e-05, "loss": 4.051, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782892405017679e-05, "loss": 4.0618, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782053810266627e-05, "loss": 4.0482, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781215215515575e-05, "loss": 4.052, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780376620764523e-05, "loss": 4.0537, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779539663893844e-05, "loss": 4.054, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778701069142792e-05, "loss": 4.0698, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.77786247439174e-05, "loss": 4.0596, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777025517521062e-05, "loss": 4.0532, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.77618692277001e-05, "loss": 4.048, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775348328018958e-05, "loss": 4.0512, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774509733267906e-05, "loss": 4.0502, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773671138516854e-05, "loss": 4.0467, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772832543765802e-05, "loss": 4.046, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.77199394901475e-05, "loss": 4.0423, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771155354263698e-05, "loss": 4.0469, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703183973930186e-05, "loss": 4.035, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694798026419666e-05, "loss": 4.0426, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686412078909146e-05, "loss": 4.0393, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.7678042510202355e-05, "loss": 4.0414, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766965656269184e-05, "loss": 4.0281, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766127061518132e-05, "loss": 4.0519, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528846676708e-05, "loss": 4.0558, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764451509896401e-05, "loss": 4.0378, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763612915145349e-05, "loss": 4.0316, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762774320394297e-05, "loss": 4.0392, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761935725643245e-05, "loss": 4.0414, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761098768772566e-05, "loss": 4.042, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760260174021514e-05, "loss": 4.038, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759421579270462e-05, "loss": 4.0379, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.758584622399783e-05, "loss": 4.0331, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757746027648731e-05, "loss": 4.0389, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569074328976796e-05, "loss": 4.0273, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560688381466276e-05, "loss": 4.0357, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552302433955756e-05, "loss": 4.0321, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543932865248965e-05, "loss": 4.0209, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535546917738445e-05, "loss": 4.0379, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527160970227925e-05, "loss": 4.0249, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518775022717405e-05, "loss": 4.0343, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510389075206885e-05, "loss": 4.0203, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7502003127696365e-05, "loss": 4.021, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.025944232940674, "eval_runtime": 312.8015, "eval_samples_per_second": 1219.914, "eval_steps_per_second": 38.123, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493617180185845e-05, "loss": 4.0152, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748523123267532e-05, "loss": 4.0082, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.74768452851648e-05, "loss": 4.0288, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746845933765428e-05, "loss": 4.0195, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460073390143764e-05, "loss": 4.0285, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451687442633244e-05, "loss": 4.0096, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443301495122724e-05, "loss": 4.0167, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434915547612204e-05, "loss": 4.0008, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.0183, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0191, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.0196, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740138813637385e-05, "loss": 4.0122, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739301856766706e-05, "loss": 4.004, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738463262015654e-05, "loss": 4.0029, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737624667264602e-05, "loss": 3.9995, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.73678607251355e-05, "loss": 4.0008, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735947477762498e-05, "loss": 4.0031, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735108883011446e-05, "loss": 3.9981, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734270288260394e-05, "loss": 3.9991, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733433331389716e-05, "loss": 4.0189, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732594736638664e-05, "loss": 4.0015, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731756141887612e-05, "loss": 4.0076, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.730919185016933e-05, "loss": 3.9948, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730080590265881e-05, "loss": 4.0107, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729241995514829e-05, "loss": 3.9874, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728403400763777e-05, "loss": 3.9989, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727564806012725e-05, "loss": 3.9967, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726726211261673e-05, "loss": 3.9934, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258892543909936e-05, "loss": 3.9809, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250506596399416e-05, "loss": 3.9872, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7242120648888896e-05, "loss": 3.9963, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723373470137838e-05, "loss": 3.9972, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.7225348753867856e-05, "loss": 3.9931, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.7216962806357336e-05, "loss": 3.9947, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.7208576858846816e-05, "loss": 3.9912, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.7200190911336296e-05, "loss": 3.9972, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.7191821342629505e-05, "loss": 3.9815, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.7183435395118985e-05, "loss": 3.9819, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.7175049447608465e-05, "loss": 3.9722, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716667987890168e-05, "loss": 3.9896, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.7158293931391154e-05, "loss": 3.9758, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.7149907983880634e-05, "loss": 3.9858, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714152203637012e-05, "loss": 3.9783, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.71331360888596e-05, "loss": 3.9749, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712476652015281e-05, "loss": 3.9874, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711638057264229e-05, "loss": 3.9756, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710799462513177e-05, "loss": 3.9774, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709960867762125e-05, "loss": 3.9596, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.709122273011073e-05, "loss": 3.9712, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.708283678260021e-05, "loss": 3.9803, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.707445083508969e-05, "loss": 3.9751, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.70660812663829e-05, "loss": 3.9738, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705769531887238e-05, "loss": 3.9593, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704930937136186e-05, "loss": 3.9722, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704092342385134e-05, "loss": 3.9577, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703253747634082e-05, "loss": 3.9814, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.7024151528830305e-05, "loss": 3.955, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.7015781960123514e-05, "loss": 3.9744, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.7007396012612994e-05, "loss": 3.972, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.6999010065102474e-05, "loss": 3.953, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.6990624117591954e-05, "loss": 3.963, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.6982238170081434e-05, "loss": 3.9669, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.6973852222570914e-05, "loss": 3.953, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696548265386412e-05, "loss": 3.9589, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.69570967063536e-05, "loss": 3.9676, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694871075884308e-05, "loss": 3.964, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694032481133256e-05, "loss": 3.9518, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693193886382204e-05, "loss": 3.9563, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692355291631152e-05, "loss": 3.9486, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915166968801e-05, "loss": 3.9609, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.690678102129048e-05, "loss": 3.9739, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689842783138743e-05, "loss": 3.9575, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.689004188387691e-05, "loss": 3.9697, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.688165593636639e-05, "loss": 3.968, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.687326998885587e-05, "loss": 3.9614, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686488404134534e-05, "loss": 3.9488, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856514472638556e-05, "loss": 3.9646, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848128525128036e-05, "loss": 3.9557, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683974257761751e-05, "loss": 3.9564, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831356630106996e-05, "loss": 3.9518, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.6822970682596476e-05, "loss": 3.9574, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681460111388969e-05, "loss": 3.9695, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.6806215166379165e-05, "loss": 3.9526, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.6797829218868645e-05, "loss": 3.9405, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.6789443271358125e-05, "loss": 3.9459, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.6781057323847605e-05, "loss": 3.9561, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.6772671376337085e-05, "loss": 3.9559, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.6764285428826565e-05, "loss": 3.9581, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755915860119774e-05, "loss": 3.9426, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747529912609254e-05, "loss": 3.9461, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739143965098734e-05, "loss": 3.9371, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.6730758017588214e-05, "loss": 3.943, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672238844888143e-05, "loss": 3.9485, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671400250137091e-05, "loss": 3.9487, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670561655386039e-05, "loss": 3.9659, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669723060634987e-05, "loss": 3.9461, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.668884465883935e-05, "loss": 3.9381, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668045871132883e-05, "loss": 3.9426, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667207276381831e-05, "loss": 3.9435, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666370319511152e-05, "loss": 3.9499, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.6655317247601e-05, "loss": 3.9459, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664693130009048e-05, "loss": 3.9419, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663854535257996e-05, "loss": 3.9377, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663015940506944e-05, "loss": 3.9463, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662177345755892e-05, "loss": 3.9211, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661340388885213e-05, "loss": 3.9387, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.6605017941341614e-05, "loss": 3.9345, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.6596631993831094e-05, "loss": 3.9378, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.6588246046320574e-05, "loss": 3.9303, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657987647761378e-05, "loss": 3.9396, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657149053010326e-05, "loss": 3.925, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.656310458259274e-05, "loss": 3.931, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655471863508222e-05, "loss": 3.9383, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.65463326875717e-05, "loss": 3.9313, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653796311886491e-05, "loss": 3.9512, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652957717135439e-05, "loss": 3.9432, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652119122384387e-05, "loss": 3.9377, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651280527633335e-05, "loss": 3.9264, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650443570762657e-05, "loss": 3.9306, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649604976011605e-05, "loss": 3.9343, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648766381260553e-05, "loss": 3.931, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.6479277865095e-05, "loss": 3.9295, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.647090829638822e-05, "loss": 3.9216, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.64625223488777e-05, "loss": 3.9317, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.645413640136718e-05, "loss": 3.9188, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644575045385665e-05, "loss": 3.9276, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643736450634613e-05, "loss": 3.9241, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6428994937639346e-05, "loss": 3.9254, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.642060899012882e-05, "loss": 3.9145, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412223042618306e-05, "loss": 3.9399, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403837095107786e-05, "loss": 3.9408, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395467526401e-05, "loss": 3.9287, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387081578890475e-05, "loss": 3.9144, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.6378695631379955e-05, "loss": 3.9268, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.6370309683869435e-05, "loss": 3.9281, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.6361923736358915e-05, "loss": 3.9319, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.6353554167652124e-05, "loss": 3.9251, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.6345168220141604e-05, "loss": 3.9242, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336782272631084e-05, "loss": 3.9244, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328396325120564e-05, "loss": 3.9314, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320010377610043e-05, "loss": 3.9206, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631164080890326e-05, "loss": 3.9259, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630325486139274e-05, "loss": 3.9222, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629486891388222e-05, "loss": 3.914, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.62864829663717e-05, "loss": 3.9269, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627811339766491e-05, "loss": 3.9242, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626972745015439e-05, "loss": 3.9223, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626134150264387e-05, "loss": 3.9137, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625295555513335e-05, "loss": 3.9128, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.951106309890747, "eval_runtime": 307.338, "eval_samples_per_second": 1241.6, "eval_steps_per_second": 38.801, "step": 228960 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.5966083050864128e+17, "trial_name": null, "trial_params": null }