{ "best_metric": 3.842529535293579, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-c-command/transformer/3/checkpoints/checkpoint-915840", "epoch": 1.0250006060157382, "eval_steps": 10, "global_step": 915840, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 11.0296, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8182, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1941, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9832, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8117, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.6987, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.597, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5325, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4388, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4063, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3457, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3048, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2634, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.1972, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1771, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1302, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1068, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0772, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0387, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0144, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 4.9993, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.971, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.981552553357229e-05, "loss": 4.9413, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9205, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9122, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8863, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9781998122333946e-05, "loss": 4.8577, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773612174823426e-05, "loss": 4.8489, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.8257, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8134, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748470711095595e-05, "loss": 4.7984, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.974008476358507e-05, "loss": 4.7846, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.7735, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7557, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7519, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7498, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7265, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968980183612942e-05, "loss": 4.6902, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.96814158886189e-05, "loss": 4.696, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967302994110837e-05, "loss": 4.6747, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966464399359785e-05, "loss": 4.6796, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6667, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.6572, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6377, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6469, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6301, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6294, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.618, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5962, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.5964, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5995, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5806, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5695, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.955567581237229e-05, "loss": 4.5615, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.9547306243665496e-05, "loss": 4.5587, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.9538920296154976e-05, "loss": 4.5444, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.9530534348644456e-05, "loss": 4.5637, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.9522148401133936e-05, "loss": 4.5297, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5409, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5325, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5066, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5137, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.948023504238507e-05, "loss": 4.5047, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4899, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4824, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.4991, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4769, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4716, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4594, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.9421582546222625e-05, "loss": 4.4721, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.9413196598712105e-05, "loss": 4.4776, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4624, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4556, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.46, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.4584, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371266861159505e-05, "loss": 4.4476, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.9362897292452714e-05, "loss": 4.4309, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.9354511344942194e-05, "loss": 4.4366, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.9346125397431674e-05, "loss": 4.4265, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.9337739449921154e-05, "loss": 4.4231, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.9329353502410634e-05, "loss": 4.4153, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.9320967554900114e-05, "loss": 4.4188, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.9312581607389594e-05, "loss": 4.4251, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.9304195659879074e-05, "loss": 4.4156, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929582609117229e-05, "loss": 4.3888, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.928744014366177e-05, "loss": 4.3978, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927905419615125e-05, "loss": 4.4012, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927066824864073e-05, "loss": 4.3967, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926229867993394e-05, "loss": 4.3898, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925392911122715e-05, "loss": 4.3854, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924554316371663e-05, "loss": 4.3808, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923715721620611e-05, "loss": 4.3682, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.922877126869559e-05, "loss": 4.3748, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922038532118507e-05, "loss": 4.3748, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921199937367455e-05, "loss": 4.3639, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920361342616403e-05, "loss": 4.3751, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919522747865351e-05, "loss": 4.3548, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918685790994672e-05, "loss": 4.3542, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.91784719624362e-05, "loss": 4.3522, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.9170086014925676e-05, "loss": 4.3498, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.9161700067415156e-05, "loss": 4.3554, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3387, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3365, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3324, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.9128172656176805e-05, "loss": 4.3361, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3192, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3118, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.3214, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3254, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.3186, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.316, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3047, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.906111783370011e-05, "loss": 4.315, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.2984, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3057, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.3052, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.902759042246176e-05, "loss": 4.3076, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.2955, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2931, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.2944, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.2966, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985677063712895e-05, "loss": 4.2837, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977291116202375e-05, "loss": 4.2848, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968905168691855e-05, "loss": 4.2838, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2858, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2682, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2658, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2702, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2729, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2644, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.2776, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2682, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889348077750837e-05, "loss": 4.2546, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888509482999785e-05, "loss": 4.2594, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.887672526129106e-05, "loss": 4.269, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886833931378054e-05, "loss": 4.2613, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885995336627002e-05, "loss": 4.2556, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515674187595e-05, "loss": 4.2464, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2536, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2592, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.246, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2375, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.8809654060010626e-05, "loss": 4.2425, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.8801268112500106e-05, "loss": 4.2373, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879289854379332e-05, "loss": 4.2345, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.87845125962828e-05, "loss": 4.2411, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877612664877228e-05, "loss": 4.2302, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876774070126176e-05, "loss": 4.2319, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875935475375124e-05, "loss": 4.2288, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875096880624072e-05, "loss": 4.2247, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.192929267883301, "eval_runtime": 305.4189, "eval_samples_per_second": 1249.402, "eval_steps_per_second": 39.045, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.87425828587302e-05, "loss": 4.2128, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873419691121968e-05, "loss": 4.2199, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872582734251289e-05, "loss": 4.2278, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871744139500237e-05, "loss": 4.2188, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.2178, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870066949998133e-05, "loss": 4.2125, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869229993127454e-05, "loss": 4.2088, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683913983764027e-05, "loss": 4.1968, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675544415057236e-05, "loss": 4.2223, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667158467546716e-05, "loss": 4.2052, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658772520036196e-05, "loss": 4.2146, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650386572525676e-05, "loss": 4.2112, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642017003818885e-05, "loss": 4.1924, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633631056308365e-05, "loss": 4.1935, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625245108797845e-05, "loss": 4.1902, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616859161287324e-05, "loss": 4.1827, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608473213776804e-05, "loss": 4.1894, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860008726626628e-05, "loss": 4.181, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591701318755764e-05, "loss": 4.1766, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583315371245244e-05, "loss": 4.1999, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.8574929423734724e-05, "loss": 4.1842, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856655985502793e-05, "loss": 4.1758, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.855817390751741e-05, "loss": 4.1736, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854978796000689e-05, "loss": 4.1877, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854140201249637e-05, "loss": 4.1647, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853301606498585e-05, "loss": 4.162, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852463011747533e-05, "loss": 4.1672, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851626054876854e-05, "loss": 4.1657, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850787460125802e-05, "loss": 4.1593, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.84994886537475e-05, "loss": 4.1593, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849110270623698e-05, "loss": 4.1612, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.848271675872646e-05, "loss": 4.1662, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847433081121595e-05, "loss": 4.1494, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846594486370543e-05, "loss": 4.1601, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845757529499864e-05, "loss": 4.165, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844918934748812e-05, "loss": 4.1597, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.84408033999776e-05, "loss": 4.1341, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.843241745246708e-05, "loss": 4.1422, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.842403150495656e-05, "loss": 4.1378, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.841566193624977e-05, "loss": 4.1441, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.840727598873925e-05, "loss": 4.1376, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.839889004122873e-05, "loss": 4.1446, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839050409371821e-05, "loss": 4.1325, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.8382118146207687e-05, "loss": 4.1425, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.83737485775009e-05, "loss": 4.1417, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836536262999038e-05, "loss": 4.1415, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835697668247986e-05, "loss": 4.1395, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.834859073496934e-05, "loss": 4.1199, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834022116626255e-05, "loss": 4.132, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833183521875203e-05, "loss": 4.1371, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832344927124151e-05, "loss": 4.1302, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831506332373099e-05, "loss": 4.1248, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.83066937550242e-05, "loss": 4.116, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829830780751368e-05, "loss": 4.1232, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828992186000316e-05, "loss": 4.1079, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828153591249264e-05, "loss": 4.1355, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.827314996498212e-05, "loss": 4.1133, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264780396275336e-05, "loss": 4.1259, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256394448764816e-05, "loss": 4.125, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248008501254296e-05, "loss": 4.1, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.823962255374377e-05, "loss": 4.1139, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231252985036985e-05, "loss": 4.1082, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222867037526465e-05, "loss": 4.0967, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214481090015945e-05, "loss": 4.0943, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820609514250542e-05, "loss": 4.1128, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.81977091949949e-05, "loss": 4.1018, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.8189339626288114e-05, "loss": 4.098, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.8180953678777594e-05, "loss": 4.0889, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.8172567731267074e-05, "loss": 4.1071, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.8164181783756554e-05, "loss": 4.1095, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.815581221504977e-05, "loss": 4.1051, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814742626753924e-05, "loss": 4.0989, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813904032002872e-05, "loss": 4.109, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.81306543725182e-05, "loss": 4.1058, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812226842500768e-05, "loss": 4.1053, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811389885630089e-05, "loss": 4.0878, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810551290879037e-05, "loss": 4.0983, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809712696127985e-05, "loss": 4.0917, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.808874101376933e-05, "loss": 4.0896, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808037144506255e-05, "loss": 4.0871, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807198549755203e-05, "loss": 4.0908, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806359955004151e-05, "loss": 4.1007, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805521360253099e-05, "loss": 4.095, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.8046844033824197e-05, "loss": 4.0715, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.8038458086313677e-05, "loss": 4.0795, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.8030072138803156e-05, "loss": 4.0846, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.8021686191292636e-05, "loss": 4.0849, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.8013316622585846e-05, "loss": 4.0832, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.8004930675075325e-05, "loss": 4.0799, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.7996544727564805e-05, "loss": 4.0789, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.7988158780054285e-05, "loss": 4.066, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.7979789211347494e-05, "loss": 4.0771, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797140326383698e-05, "loss": 4.0771, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796301731632646e-05, "loss": 4.072, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.795463136881594e-05, "loss": 4.0825, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.794626180010915e-05, "loss": 4.0724, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793787585259863e-05, "loss": 4.0659, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792948990508811e-05, "loss": 4.0696, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792110395757759e-05, "loss": 4.0717, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.79127343888708e-05, "loss": 4.0748, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790434844136028e-05, "loss": 4.0648, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789596249384976e-05, "loss": 4.0588, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788757654633924e-05, "loss": 4.0594, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787920697763245e-05, "loss": 4.068, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870821030121935e-05, "loss": 4.052, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862451461415144e-05, "loss": 4.0441, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854065513904624e-05, "loss": 4.059, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845679566394104e-05, "loss": 4.0615, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.7837293618883584e-05, "loss": 4.0531, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.7828907671373064e-05, "loss": 4.056, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.7820521723862544e-05, "loss": 4.0503, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.7812135776352024e-05, "loss": 4.0585, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.7803749828841504e-05, "loss": 4.0453, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779538026013471e-05, "loss": 4.0521, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778699431262419e-05, "loss": 4.0577, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777860836511367e-05, "loss": 4.0586, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777022241760315e-05, "loss": 4.0483, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776185284889637e-05, "loss": 4.0476, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775346690138585e-05, "loss": 4.0514, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774508095387533e-05, "loss": 4.0538, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773669500636481e-05, "loss": 4.0391, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.772832543765802e-05, "loss": 4.0495, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.77199394901475e-05, "loss": 4.0413, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.771155354263698e-05, "loss": 4.0536, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.770316759512646e-05, "loss": 4.0333, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694798026419666e-05, "loss": 4.0332, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686412078909146e-05, "loss": 4.0379, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.7678026131398626e-05, "loss": 4.0394, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.7669640183888106e-05, "loss": 4.0346, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766127061518132e-05, "loss": 4.0518, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528846676708e-05, "loss": 4.04, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764449872016028e-05, "loss": 4.0308, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763611277264976e-05, "loss": 4.0322, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762774320394297e-05, "loss": 4.0478, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761935725643245e-05, "loss": 4.0406, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761097130892193e-05, "loss": 4.0355, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760258536141141e-05, "loss": 4.0295, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759421579270462e-05, "loss": 4.0374, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.75858298451941e-05, "loss": 4.0391, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757744389768358e-05, "loss": 4.0313, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.756905795017306e-05, "loss": 4.0257, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.756067200266254e-05, "loss": 4.0285, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552302433955756e-05, "loss": 4.0255, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543932865248965e-05, "loss": 4.0217, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535546917738445e-05, "loss": 4.0356, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527160970227925e-05, "loss": 4.0233, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518775022717405e-05, "loss": 4.0257, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510389075206885e-05, "loss": 4.0233, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7502003127696365e-05, "loss": 4.0198, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.024447917938232, "eval_runtime": 304.6013, "eval_samples_per_second": 1252.756, "eval_steps_per_second": 39.15, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493617180185845e-05, "loss": 4.007, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748523123267532e-05, "loss": 4.0178, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.74768452851648e-05, "loss": 4.0304, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746845933765428e-05, "loss": 4.0194, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460073390143764e-05, "loss": 4.0233, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451687442633244e-05, "loss": 4.0147, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443301495122724e-05, "loss": 4.0175, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434915547612204e-05, "loss": 4.0007, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.0252, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.021, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.0167, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740138813637385e-05, "loss": 4.0235, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739301856766706e-05, "loss": 4.0023, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738463262015654e-05, "loss": 4.0037, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737624667264602e-05, "loss": 4.0118, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.73678607251355e-05, "loss": 3.9938, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735947477762498e-05, "loss": 4.002, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.735108883011446e-05, "loss": 3.9973, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734270288260394e-05, "loss": 3.9964, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733431693509343e-05, "loss": 4.0225, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732594736638664e-05, "loss": 4.0016, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731756141887612e-05, "loss": 4.0025, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.73091754713656e-05, "loss": 3.9929, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730078952385508e-05, "loss": 4.0105, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.729241995514829e-05, "loss": 3.986, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.728403400763777e-05, "loss": 3.9911, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.727564806012725e-05, "loss": 3.9914, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.726726211261673e-05, "loss": 3.9974, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258892543909936e-05, "loss": 3.9871, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250506596399416e-05, "loss": 3.9876, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7242120648888896e-05, "loss": 3.994, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723375108018211e-05, "loss": 3.9984, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722536513267159e-05, "loss": 3.9792, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721697918516107e-05, "loss": 3.9931, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720859323765055e-05, "loss": 3.9962, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720022366894376e-05, "loss": 3.9908, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719183772143324e-05, "loss": 3.971, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718345177392272e-05, "loss": 3.9812, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.71750658264122e-05, "loss": 3.9687, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716669625770541e-05, "loss": 3.9846, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715831031019489e-05, "loss": 3.9786, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714992436268437e-05, "loss": 3.9845, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714153841517385e-05, "loss": 3.9751, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.7133168846467065e-05, "loss": 3.9805, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.7124782898956545e-05, "loss": 3.9841, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.7116396951446025e-05, "loss": 3.9857, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.7108011003935505e-05, "loss": 3.9827, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.7099641435228714e-05, "loss": 3.961, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091255487718194e-05, "loss": 3.9752, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082869540207674e-05, "loss": 3.9871, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074483592697154e-05, "loss": 3.9704, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706613040279409e-05, "loss": 3.9714, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705774445528357e-05, "loss": 3.9662, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704935850777306e-05, "loss": 3.9702, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.704097256026254e-05, "loss": 3.9575, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703258661275202e-05, "loss": 3.9804, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.70242006652415e-05, "loss": 3.9693, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701581471773098e-05, "loss": 3.9729, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700742877022045e-05, "loss": 3.9813, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.699905920151367e-05, "loss": 3.9517, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699067325400315e-05, "loss": 3.9671, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698228730649263e-05, "loss": 3.9604, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.69739013589821e-05, "loss": 3.9567, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696553179027532e-05, "loss": 3.9495, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.69571458427648e-05, "loss": 3.9643, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694875989525428e-05, "loss": 3.9599, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694037394774376e-05, "loss": 3.9531, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693200437903697e-05, "loss": 3.9441, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692361843152645e-05, "loss": 3.9655, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.6915232484015926e-05, "loss": 3.9702, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.6906846536505406e-05, "loss": 3.9615, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.689847696779862e-05, "loss": 3.9609, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890091020288095e-05, "loss": 3.9685, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881705072777575e-05, "loss": 3.965, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873319125267055e-05, "loss": 3.9673, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.686494955656027e-05, "loss": 3.9455, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.685656360904975e-05, "loss": 3.9623, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.684817766153923e-05, "loss": 3.959, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683979171402871e-05, "loss": 3.9503, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.6831422145321926e-05, "loss": 3.9552, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.68230361978114e-05, "loss": 3.955, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681465025030088e-05, "loss": 3.9674, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680626430279036e-05, "loss": 3.9573, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679789473408357e-05, "loss": 3.9365, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678950878657305e-05, "loss": 3.9435, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678112283906253e-05, "loss": 3.9513, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677273689155201e-05, "loss": 3.9542, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676436732284522e-05, "loss": 3.9514, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.6755981375334704e-05, "loss": 3.9453, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.6747595427824184e-05, "loss": 3.9483, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.6739209480313664e-05, "loss": 3.9371, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673083991160687e-05, "loss": 3.9507, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672245396409635e-05, "loss": 3.9446, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671406801658583e-05, "loss": 3.9454, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.670569844787904e-05, "loss": 3.9563, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.669731250036852e-05, "loss": 3.9483, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688926552858e-05, "loss": 3.9383, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668054060534748e-05, "loss": 3.9435, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667215465783696e-05, "loss": 3.9427, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.666378508913017e-05, "loss": 3.9481, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665539914161966e-05, "loss": 3.9417, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664701319410914e-05, "loss": 3.9358, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663862724659862e-05, "loss": 3.9319, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.66302412990881e-05, "loss": 3.9451, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662185535157758e-05, "loss": 3.9313, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661346940406706e-05, "loss": 3.922, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660509983536027e-05, "loss": 3.9346, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659671388784975e-05, "loss": 3.9394, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658832794033923e-05, "loss": 3.9287, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.6579941992828707e-05, "loss": 3.9402, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.6571556045318187e-05, "loss": 3.9265, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.6563170097807667e-05, "loss": 3.9401, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.6554800529100876e-05, "loss": 3.9256, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.6546414581590356e-05, "loss": 3.9276, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.6538028634079836e-05, "loss": 3.9445, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652964268656932e-05, "loss": 3.9394, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652127311786253e-05, "loss": 3.9305, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651288717035201e-05, "loss": 3.9327, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.650450122284149e-05, "loss": 3.9288, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649611527533097e-05, "loss": 3.9351, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.648772932782045e-05, "loss": 3.9232, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.647934338030993e-05, "loss": 3.9336, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470957432799404e-05, "loss": 3.9257, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462571485288884e-05, "loss": 3.9361, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.64542019165821e-05, "loss": 3.9157, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.644581596907158e-05, "loss": 3.9248, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.643743002156106e-05, "loss": 3.9201, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.642904407405054e-05, "loss": 3.9258, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420674505343756e-05, "loss": 3.9205, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.6412288557833236e-05, "loss": 3.9403, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.6403918989126445e-05, "loss": 3.9279, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.6395533041615925e-05, "loss": 3.9219, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.6387147094105405e-05, "loss": 3.9149, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637876114659488e-05, "loss": 3.9334, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.637037519908436e-05, "loss": 3.9307, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636198925157384e-05, "loss": 3.9272, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635360330406332e-05, "loss": 3.9197, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.63452173565528e-05, "loss": 3.9251, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.6336847787846014e-05, "loss": 3.9278, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.6328461840335494e-05, "loss": 3.9222, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.6320075892824974e-05, "loss": 3.9167, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.6311689945314454e-05, "loss": 3.9214, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.630332037660766e-05, "loss": 3.919, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.629493442909714e-05, "loss": 3.9108, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.628656486039035e-05, "loss": 3.9247, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.627817891287983e-05, "loss": 3.9217, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626979296536931e-05, "loss": 3.9163, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626140701785879e-05, "loss": 3.9134, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.6253037449152e-05, "loss": 3.9092, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.951061248779297, "eval_runtime": 305.5686, "eval_samples_per_second": 1248.79, "eval_steps_per_second": 39.026, "step": 228960 }, { "epoch": 1.0, "learning_rate": 4.624465150164148e-05, "loss": 3.9128, "step": 229376 }, { "epoch": 1.0, "learning_rate": 4.623626555413097e-05, "loss": 3.9105, "step": 229888 }, { "epoch": 1.0, "learning_rate": 4.622787960662045e-05, "loss": 3.9246, "step": 230400 }, { "epoch": 1.0, "learning_rate": 4.621949365910993e-05, "loss": 3.9129, "step": 230912 }, { "epoch": 1.0, "learning_rate": 4.621110771159941e-05, "loss": 3.9219, "step": 231424 }, { "epoch": 1.0, "learning_rate": 4.6202738142892616e-05, "loss": 3.907, "step": 231936 }, { "epoch": 1.0, "learning_rate": 4.6194352195382096e-05, "loss": 3.9142, "step": 232448 }, { "epoch": 1.0, "learning_rate": 4.6185966247871576e-05, "loss": 3.8972, "step": 232960 }, { "epoch": 1.0, "learning_rate": 4.6177580300361056e-05, "loss": 3.9227, "step": 233472 }, { "epoch": 1.0, "learning_rate": 4.6169194352850536e-05, "loss": 3.9164, "step": 233984 }, { "epoch": 1.0, "learning_rate": 4.6160808405340016e-05, "loss": 3.914, "step": 234496 }, { "epoch": 1.0, "learning_rate": 4.6152422457829496e-05, "loss": 3.9201, "step": 235008 }, { "epoch": 1.0, "learning_rate": 4.6144052889122705e-05, "loss": 3.8996, "step": 235520 }, { "epoch": 1.0, "learning_rate": 4.6135666941612185e-05, "loss": 3.9021, "step": 236032 }, { "epoch": 1.0, "learning_rate": 4.6127280994101665e-05, "loss": 3.9112, "step": 236544 }, { "epoch": 1.0, "learning_rate": 4.611889504659115e-05, "loss": 3.8979, "step": 237056 }, { "epoch": 1.0, "learning_rate": 4.611050909908063e-05, "loss": 3.8961, "step": 237568 }, { "epoch": 1.0, "learning_rate": 4.610213953037384e-05, "loss": 3.8965, "step": 238080 }, { "epoch": 1.0, "learning_rate": 4.609375358286332e-05, "loss": 3.898, "step": 238592 }, { "epoch": 1.0, "learning_rate": 4.60853676353528e-05, "loss": 3.9247, "step": 239104 }, { "epoch": 1.0, "learning_rate": 4.607698168784228e-05, "loss": 3.9027, "step": 239616 }, { "epoch": 1.0, "learning_rate": 4.606859574033176e-05, "loss": 3.9021, "step": 240128 }, { "epoch": 1.0, "learning_rate": 4.606020979282124e-05, "loss": 3.8986, "step": 240640 }, { "epoch": 1.0, "learning_rate": 4.6051823845310714e-05, "loss": 3.907, "step": 241152 }, { "epoch": 1.0, "learning_rate": 4.604345427660393e-05, "loss": 3.8917, "step": 241664 }, { "epoch": 1.0, "learning_rate": 4.603506832909341e-05, "loss": 3.8926, "step": 242176 }, { "epoch": 1.0, "learning_rate": 4.602668238158289e-05, "loss": 3.8954, "step": 242688 }, { "epoch": 1.0, "learning_rate": 4.601829643407237e-05, "loss": 3.903, "step": 243200 }, { "epoch": 1.0, "learning_rate": 4.600991048656185e-05, "loss": 3.8862, "step": 243712 }, { "epoch": 1.01, "learning_rate": 4.6001540917855065e-05, "loss": 3.8938, "step": 244224 }, { "epoch": 1.01, "learning_rate": 4.599315497034454e-05, "loss": 3.8938, "step": 244736 }, { "epoch": 1.01, "learning_rate": 4.598476902283402e-05, "loss": 3.9016, "step": 245248 }, { "epoch": 1.01, "learning_rate": 4.59763830753235e-05, "loss": 3.8896, "step": 245760 }, { "epoch": 1.01, "learning_rate": 4.596799712781298e-05, "loss": 3.8945, "step": 246272 }, { "epoch": 1.01, "learning_rate": 4.595962755910619e-05, "loss": 3.8971, "step": 246784 }, { "epoch": 1.01, "learning_rate": 4.595124161159567e-05, "loss": 3.8972, "step": 247296 }, { "epoch": 1.01, "learning_rate": 4.594285566408515e-05, "loss": 3.8785, "step": 247808 }, { "epoch": 1.01, "learning_rate": 4.593446971657463e-05, "loss": 3.8895, "step": 248320 }, { "epoch": 1.01, "learning_rate": 4.592608376906411e-05, "loss": 3.874, "step": 248832 }, { "epoch": 1.01, "learning_rate": 4.591769782155359e-05, "loss": 3.8921, "step": 249344 }, { "epoch": 1.01, "learning_rate": 4.590931187404307e-05, "loss": 3.8816, "step": 249856 }, { "epoch": 1.01, "learning_rate": 4.5900925926532554e-05, "loss": 3.8941, "step": 250368 }, { "epoch": 1.01, "learning_rate": 4.589255635782576e-05, "loss": 3.8861, "step": 250880 }, { "epoch": 1.01, "learning_rate": 4.588417041031524e-05, "loss": 3.8849, "step": 251392 }, { "epoch": 1.01, "learning_rate": 4.587578446280472e-05, "loss": 3.8939, "step": 251904 }, { "epoch": 1.01, "learning_rate": 4.58673985152942e-05, "loss": 3.8916, "step": 252416 }, { "epoch": 1.01, "learning_rate": 4.585902894658741e-05, "loss": 3.889, "step": 252928 }, { "epoch": 1.01, "learning_rate": 4.585065937788062e-05, "loss": 3.8755, "step": 253440 }, { "epoch": 1.01, "learning_rate": 4.58422734303701e-05, "loss": 3.8785, "step": 253952 }, { "epoch": 1.01, "learning_rate": 4.583388748285958e-05, "loss": 3.8957, "step": 254464 }, { "epoch": 1.01, "learning_rate": 4.582550153534906e-05, "loss": 3.8818, "step": 254976 }, { "epoch": 1.01, "learning_rate": 4.581713196664228e-05, "loss": 3.8781, "step": 255488 }, { "epoch": 1.01, "learning_rate": 4.580874601913176e-05, "loss": 3.8776, "step": 256000 }, { "epoch": 1.01, "learning_rate": 4.580036007162124e-05, "loss": 3.8826, "step": 256512 }, { "epoch": 1.01, "learning_rate": 4.579197412411072e-05, "loss": 3.8667, "step": 257024 }, { "epoch": 1.01, "learning_rate": 4.57835881766002e-05, "loss": 3.8877, "step": 257536 }, { "epoch": 1.01, "learning_rate": 4.577520222908968e-05, "loss": 3.8806, "step": 258048 }, { "epoch": 1.01, "learning_rate": 4.576681628157916e-05, "loss": 3.8848, "step": 258560 }, { "epoch": 1.01, "learning_rate": 4.5758430334068637e-05, "loss": 3.889, "step": 259072 }, { "epoch": 1.01, "learning_rate": 4.5750060765361846e-05, "loss": 3.8678, "step": 259584 }, { "epoch": 1.01, "learning_rate": 4.5741674817851326e-05, "loss": 3.8721, "step": 260096 }, { "epoch": 1.01, "learning_rate": 4.5733305249144535e-05, "loss": 3.8783, "step": 260608 }, { "epoch": 1.01, "learning_rate": 4.5724919301634015e-05, "loss": 3.8672, "step": 261120 }, { "epoch": 1.01, "learning_rate": 4.5716533354123495e-05, "loss": 3.8634, "step": 261632 }, { "epoch": 1.01, "learning_rate": 4.5708147406612975e-05, "loss": 3.8745, "step": 262144 }, { "epoch": 1.01, "learning_rate": 4.569976145910246e-05, "loss": 3.8755, "step": 262656 }, { "epoch": 1.01, "learning_rate": 4.569137551159194e-05, "loss": 3.8664, "step": 263168 }, { "epoch": 1.01, "learning_rate": 4.568300594288515e-05, "loss": 3.8585, "step": 263680 }, { "epoch": 1.01, "learning_rate": 4.567461999537463e-05, "loss": 3.875, "step": 264192 }, { "epoch": 1.01, "learning_rate": 4.566623404786411e-05, "loss": 3.8819, "step": 264704 }, { "epoch": 1.01, "learning_rate": 4.565784810035359e-05, "loss": 3.8721, "step": 265216 }, { "epoch": 1.01, "learning_rate": 4.564946215284307e-05, "loss": 3.8788, "step": 265728 }, { "epoch": 1.01, "learning_rate": 4.564107620533255e-05, "loss": 3.8831, "step": 266240 }, { "epoch": 1.01, "learning_rate": 4.563270663662576e-05, "loss": 3.8815, "step": 266752 }, { "epoch": 1.01, "learning_rate": 4.562432068911524e-05, "loss": 3.8858, "step": 267264 }, { "epoch": 1.01, "learning_rate": 4.561593474160472e-05, "loss": 3.8606, "step": 267776 }, { "epoch": 1.01, "learning_rate": 4.56075487940942e-05, "loss": 3.8767, "step": 268288 }, { "epoch": 1.01, "learning_rate": 4.5599179225387415e-05, "loss": 3.8771, "step": 268800 }, { "epoch": 1.01, "learning_rate": 4.5590793277876895e-05, "loss": 3.8643, "step": 269312 }, { "epoch": 1.01, "learning_rate": 4.5582407330366375e-05, "loss": 3.8773, "step": 269824 }, { "epoch": 1.01, "learning_rate": 4.557402138285585e-05, "loss": 3.8696, "step": 270336 }, { "epoch": 1.01, "learning_rate": 4.556563543534533e-05, "loss": 3.882, "step": 270848 }, { "epoch": 1.01, "learning_rate": 4.555724948783481e-05, "loss": 3.8751, "step": 271360 }, { "epoch": 1.01, "learning_rate": 4.554886354032429e-05, "loss": 3.8537, "step": 271872 }, { "epoch": 1.01, "learning_rate": 4.55404939716175e-05, "loss": 3.8627, "step": 272384 }, { "epoch": 1.01, "learning_rate": 4.553210802410698e-05, "loss": 3.8659, "step": 272896 }, { "epoch": 1.01, "learning_rate": 4.552372207659646e-05, "loss": 3.8691, "step": 273408 }, { "epoch": 1.01, "learning_rate": 4.551533612908594e-05, "loss": 3.8712, "step": 273920 }, { "epoch": 1.01, "learning_rate": 4.550696656037915e-05, "loss": 3.8599, "step": 274432 }, { "epoch": 1.02, "learning_rate": 4.549858061286863e-05, "loss": 3.8672, "step": 274944 }, { "epoch": 1.02, "learning_rate": 4.549019466535811e-05, "loss": 3.8575, "step": 275456 }, { "epoch": 1.02, "learning_rate": 4.548180871784759e-05, "loss": 3.8674, "step": 275968 }, { "epoch": 1.02, "learning_rate": 4.547342277033707e-05, "loss": 3.8593, "step": 276480 }, { "epoch": 1.02, "learning_rate": 4.546503682282655e-05, "loss": 3.8662, "step": 276992 }, { "epoch": 1.02, "learning_rate": 4.545666725411976e-05, "loss": 3.8771, "step": 277504 }, { "epoch": 1.02, "learning_rate": 4.544828130660924e-05, "loss": 3.8666, "step": 278016 }, { "epoch": 1.02, "learning_rate": 4.543989535909872e-05, "loss": 3.8578, "step": 278528 }, { "epoch": 1.02, "learning_rate": 4.54315094115882e-05, "loss": 3.8637, "step": 279040 }, { "epoch": 1.02, "learning_rate": 4.542312346407768e-05, "loss": 3.8622, "step": 279552 }, { "epoch": 1.02, "learning_rate": 4.541475389537089e-05, "loss": 3.8691, "step": 280064 }, { "epoch": 1.02, "learning_rate": 4.540636794786037e-05, "loss": 3.8618, "step": 280576 }, { "epoch": 1.02, "learning_rate": 4.539798200034985e-05, "loss": 3.8573, "step": 281088 }, { "epoch": 1.02, "learning_rate": 4.538959605283933e-05, "loss": 3.8502, "step": 281600 }, { "epoch": 1.02, "learning_rate": 4.538121010532882e-05, "loss": 3.8693, "step": 282112 }, { "epoch": 1.02, "learning_rate": 4.53728241578183e-05, "loss": 3.8484, "step": 282624 }, { "epoch": 1.02, "learning_rate": 4.5364454589111506e-05, "loss": 3.8464, "step": 283136 }, { "epoch": 1.02, "learning_rate": 4.5356068641600986e-05, "loss": 3.8544, "step": 283648 }, { "epoch": 1.02, "learning_rate": 4.5347682694090466e-05, "loss": 3.8586, "step": 284160 }, { "epoch": 1.02, "learning_rate": 4.5339296746579946e-05, "loss": 3.8511, "step": 284672 }, { "epoch": 1.02, "learning_rate": 4.5330910799069426e-05, "loss": 3.8668, "step": 285184 }, { "epoch": 1.02, "learning_rate": 4.5322541230362635e-05, "loss": 3.8505, "step": 285696 }, { "epoch": 1.02, "learning_rate": 4.5314155282852115e-05, "loss": 3.8554, "step": 286208 }, { "epoch": 1.02, "learning_rate": 4.5305769335341595e-05, "loss": 3.8543, "step": 286720 }, { "epoch": 1.02, "learning_rate": 4.5297383387831075e-05, "loss": 3.8466, "step": 287232 }, { "epoch": 1.02, "learning_rate": 4.5288997440320555e-05, "loss": 3.8708, "step": 287744 }, { "epoch": 1.02, "learning_rate": 4.5280611492810035e-05, "loss": 3.8625, "step": 288256 }, { "epoch": 1.02, "learning_rate": 4.527224192410325e-05, "loss": 3.8572, "step": 288768 }, { "epoch": 1.02, "learning_rate": 4.526385597659273e-05, "loss": 3.8563, "step": 289280 }, { "epoch": 1.02, "learning_rate": 4.525547002908221e-05, "loss": 3.8482, "step": 289792 }, { "epoch": 1.02, "learning_rate": 4.5247084081571684e-05, "loss": 3.8605, "step": 290304 }, { "epoch": 1.02, "learning_rate": 4.5238698134061164e-05, "loss": 3.8478, "step": 290816 }, { "epoch": 1.02, "learning_rate": 4.5230312186550644e-05, "loss": 3.8628, "step": 291328 }, { "epoch": 1.02, "learning_rate": 4.5221926239040124e-05, "loss": 3.846, "step": 291840 }, { "epoch": 1.02, "learning_rate": 4.5213540291529604e-05, "loss": 3.856, "step": 292352 }, { "epoch": 1.02, "learning_rate": 4.520517072282281e-05, "loss": 3.846, "step": 292864 }, { "epoch": 1.02, "learning_rate": 4.519678477531229e-05, "loss": 3.8487, "step": 293376 }, { "epoch": 1.02, "learning_rate": 4.518839882780177e-05, "loss": 3.844, "step": 293888 }, { "epoch": 1.02, "learning_rate": 4.518001288029125e-05, "loss": 3.8516, "step": 294400 }, { "epoch": 1.02, "learning_rate": 4.517164331158447e-05, "loss": 3.8462, "step": 294912 }, { "epoch": 1.02, "learning_rate": 4.516325736407395e-05, "loss": 3.865, "step": 295424 }, { "epoch": 1.02, "learning_rate": 4.515487141656343e-05, "loss": 3.8543, "step": 295936 }, { "epoch": 1.02, "learning_rate": 4.514648546905291e-05, "loss": 3.8492, "step": 296448 }, { "epoch": 1.02, "learning_rate": 4.513809952154239e-05, "loss": 3.8368, "step": 296960 }, { "epoch": 1.02, "learning_rate": 4.512971357403187e-05, "loss": 3.8588, "step": 297472 }, { "epoch": 1.02, "learning_rate": 4.512134400532508e-05, "loss": 3.8542, "step": 297984 }, { "epoch": 1.02, "learning_rate": 4.511295805781456e-05, "loss": 3.8573, "step": 298496 }, { "epoch": 1.02, "learning_rate": 4.510457211030404e-05, "loss": 3.8462, "step": 299008 }, { "epoch": 1.02, "learning_rate": 4.509618616279352e-05, "loss": 3.8484, "step": 299520 }, { "epoch": 1.02, "learning_rate": 4.5087816594086726e-05, "loss": 3.8548, "step": 300032 }, { "epoch": 1.02, "learning_rate": 4.5079430646576206e-05, "loss": 3.8532, "step": 300544 }, { "epoch": 1.02, "learning_rate": 4.507104469906569e-05, "loss": 3.8422, "step": 301056 }, { "epoch": 1.02, "learning_rate": 4.506265875155517e-05, "loss": 3.8488, "step": 301568 }, { "epoch": 1.02, "learning_rate": 4.505427280404465e-05, "loss": 3.8441, "step": 302080 }, { "epoch": 1.02, "learning_rate": 4.504588685653413e-05, "loss": 3.8383, "step": 302592 }, { "epoch": 1.02, "learning_rate": 4.503751728782734e-05, "loss": 3.8518, "step": 303104 }, { "epoch": 1.02, "learning_rate": 4.502913134031682e-05, "loss": 3.8538, "step": 303616 }, { "epoch": 1.02, "learning_rate": 4.50207453928063e-05, "loss": 3.8418, "step": 304128 }, { "epoch": 1.02, "learning_rate": 4.501235944529578e-05, "loss": 3.8379, "step": 304640 }, { "epoch": 1.02, "learning_rate": 4.500398987658899e-05, "loss": 3.8454, "step": 305152 }, { "epoch": 1.03, "eval_loss": 3.909972906112671, "eval_runtime": 308.3464, "eval_samples_per_second": 1237.54, "eval_steps_per_second": 38.674, "step": 305280 }, { "epoch": 0.0, "learning_rate": 4.499560392907847e-05, "loss": 3.8346, "step": 305664 }, { "epoch": 0.0, "learning_rate": 4.498721798156795e-05, "loss": 3.8397, "step": 306176 }, { "epoch": 0.0, "learning_rate": 4.497883203405743e-05, "loss": 3.8516, "step": 306688 }, { "epoch": 0.0, "learning_rate": 4.497044608654691e-05, "loss": 3.8413, "step": 307200 }, { "epoch": 0.0, "learning_rate": 4.496206013903639e-05, "loss": 3.8541, "step": 307712 }, { "epoch": 0.0, "learning_rate": 4.495367419152587e-05, "loss": 3.8364, "step": 308224 }, { "epoch": 0.0, "learning_rate": 4.494528824401535e-05, "loss": 3.8422, "step": 308736 }, { "epoch": 0.0, "learning_rate": 4.493690229650483e-05, "loss": 3.8292, "step": 309248 }, { "epoch": 0.0, "learning_rate": 4.4928532727798047e-05, "loss": 3.8548, "step": 309760 }, { "epoch": 0.0, "learning_rate": 4.492014678028752e-05, "loss": 3.8439, "step": 310272 }, { "epoch": 0.0, "learning_rate": 4.4911760832777e-05, "loss": 3.8403, "step": 310784 }, { "epoch": 0.0, "learning_rate": 4.490337488526648e-05, "loss": 3.8531, "step": 311296 }, { "epoch": 0.0, "learning_rate": 4.4895021695363425e-05, "loss": 3.8283, "step": 311808 }, { "epoch": 0.0, "learning_rate": 4.4886635747852905e-05, "loss": 3.8377, "step": 312320 }, { "epoch": 0.0, "learning_rate": 4.4878249800342385e-05, "loss": 3.8405, "step": 312832 }, { "epoch": 0.0, "learning_rate": 4.4869863852831864e-05, "loss": 3.8296, "step": 313344 }, { "epoch": 0.0, "learning_rate": 4.4861477905321344e-05, "loss": 3.8291, "step": 313856 }, { "epoch": 0.0, "learning_rate": 4.4853091957810824e-05, "loss": 3.8281, "step": 314368 }, { "epoch": 0.0, "learning_rate": 4.4844706010300304e-05, "loss": 3.8332, "step": 314880 }, { "epoch": 0.0, "learning_rate": 4.4836320062789784e-05, "loss": 3.8511, "step": 315392 }, { "epoch": 0.0, "learning_rate": 4.4827934115279264e-05, "loss": 3.8347, "step": 315904 }, { "epoch": 0.0, "learning_rate": 4.481956454657247e-05, "loss": 3.8327, "step": 316416 }, { "epoch": 0.0, "learning_rate": 4.481117859906195e-05, "loss": 3.8322, "step": 316928 }, { "epoch": 0.0, "learning_rate": 4.480279265155143e-05, "loss": 3.8396, "step": 317440 }, { "epoch": 0.0, "learning_rate": 4.479440670404091e-05, "loss": 3.8245, "step": 317952 }, { "epoch": 0.0, "learning_rate": 4.478602075653039e-05, "loss": 3.8253, "step": 318464 }, { "epoch": 0.0, "learning_rate": 4.477763480901987e-05, "loss": 3.826, "step": 318976 }, { "epoch": 0.0, "learning_rate": 4.476926524031308e-05, "loss": 3.836, "step": 319488 }, { "epoch": 0.0, "learning_rate": 4.476087929280256e-05, "loss": 3.8196, "step": 320000 }, { "epoch": 0.0, "learning_rate": 4.475249334529205e-05, "loss": 3.8294, "step": 320512 }, { "epoch": 0.01, "learning_rate": 4.474410739778153e-05, "loss": 3.8291, "step": 321024 }, { "epoch": 0.01, "learning_rate": 4.473573782907474e-05, "loss": 3.8346, "step": 321536 }, { "epoch": 0.01, "learning_rate": 4.472735188156422e-05, "loss": 3.824, "step": 322048 }, { "epoch": 0.01, "learning_rate": 4.47189659340537e-05, "loss": 3.8303, "step": 322560 }, { "epoch": 0.01, "learning_rate": 4.471057998654318e-05, "loss": 3.8305, "step": 323072 }, { "epoch": 0.01, "learning_rate": 4.470219403903266e-05, "loss": 3.8312, "step": 323584 }, { "epoch": 0.01, "learning_rate": 4.469380809152214e-05, "loss": 3.8174, "step": 324096 }, { "epoch": 0.01, "learning_rate": 4.468543852281535e-05, "loss": 3.8192, "step": 324608 }, { "epoch": 0.01, "learning_rate": 4.467705257530483e-05, "loss": 3.8104, "step": 325120 }, { "epoch": 0.01, "learning_rate": 4.466866662779431e-05, "loss": 3.825, "step": 325632 }, { "epoch": 0.01, "learning_rate": 4.466028068028379e-05, "loss": 3.8169, "step": 326144 }, { "epoch": 0.01, "learning_rate": 4.4651911111577e-05, "loss": 3.8282, "step": 326656 }, { "epoch": 0.01, "learning_rate": 4.464352516406648e-05, "loss": 3.8214, "step": 327168 }, { "epoch": 0.01, "learning_rate": 4.463513921655596e-05, "loss": 3.8226, "step": 327680 }, { "epoch": 0.01, "learning_rate": 4.462675326904544e-05, "loss": 3.8267, "step": 328192 }, { "epoch": 0.01, "learning_rate": 4.461836732153492e-05, "loss": 3.8259, "step": 328704 }, { "epoch": 0.01, "learning_rate": 4.46099813740244e-05, "loss": 3.828, "step": 329216 }, { "epoch": 0.01, "learning_rate": 4.460161180531761e-05, "loss": 3.8143, "step": 329728 }, { "epoch": 0.01, "learning_rate": 4.459322585780709e-05, "loss": 3.8089, "step": 330240 }, { "epoch": 0.01, "learning_rate": 4.458483991029657e-05, "loss": 3.8329, "step": 330752 }, { "epoch": 0.01, "learning_rate": 4.457645396278605e-05, "loss": 3.8176, "step": 331264 }, { "epoch": 0.01, "learning_rate": 4.456808439407926e-05, "loss": 3.8144, "step": 331776 }, { "epoch": 0.01, "learning_rate": 4.455969844656874e-05, "loss": 3.8134, "step": 332288 }, { "epoch": 0.01, "learning_rate": 4.455131249905822e-05, "loss": 3.8203, "step": 332800 }, { "epoch": 0.01, "learning_rate": 4.45429265515477e-05, "loss": 3.8013, "step": 333312 }, { "epoch": 0.01, "learning_rate": 4.4534556982840916e-05, "loss": 3.8244, "step": 333824 }, { "epoch": 0.01, "learning_rate": 4.4526171035330396e-05, "loss": 3.8177, "step": 334336 }, { "epoch": 0.01, "learning_rate": 4.4517785087819876e-05, "loss": 3.8201, "step": 334848 }, { "epoch": 0.01, "learning_rate": 4.4509399140309356e-05, "loss": 3.8276, "step": 335360 }, { "epoch": 0.01, "learning_rate": 4.450101319279883e-05, "loss": 3.8109, "step": 335872 }, { "epoch": 0.01, "learning_rate": 4.4492643624092045e-05, "loss": 3.8075, "step": 336384 }, { "epoch": 0.01, "learning_rate": 4.4484257676581525e-05, "loss": 3.8217, "step": 336896 }, { "epoch": 0.01, "learning_rate": 4.4475871729071e-05, "loss": 3.7994, "step": 337408 }, { "epoch": 0.01, "learning_rate": 4.446748578156048e-05, "loss": 3.8021, "step": 337920 }, { "epoch": 0.01, "learning_rate": 4.445909983404996e-05, "loss": 3.8141, "step": 338432 }, { "epoch": 0.01, "learning_rate": 4.445071388653944e-05, "loss": 3.8142, "step": 338944 }, { "epoch": 0.01, "learning_rate": 4.4442344317832654e-05, "loss": 3.8028, "step": 339456 }, { "epoch": 0.01, "learning_rate": 4.4433958370322134e-05, "loss": 3.8005, "step": 339968 }, { "epoch": 0.01, "learning_rate": 4.4425572422811614e-05, "loss": 3.8128, "step": 340480 }, { "epoch": 0.01, "learning_rate": 4.4417186475301094e-05, "loss": 3.8185, "step": 340992 }, { "epoch": 0.01, "learning_rate": 4.44088169065943e-05, "loss": 3.8153, "step": 341504 }, { "epoch": 0.01, "learning_rate": 4.440043095908378e-05, "loss": 3.814, "step": 342016 }, { "epoch": 0.01, "learning_rate": 4.439204501157326e-05, "loss": 3.8231, "step": 342528 }, { "epoch": 0.01, "learning_rate": 4.438365906406274e-05, "loss": 3.8171, "step": 343040 }, { "epoch": 0.01, "learning_rate": 4.437527311655222e-05, "loss": 3.8271, "step": 343552 }, { "epoch": 0.01, "learning_rate": 4.436690354784543e-05, "loss": 3.8004, "step": 344064 }, { "epoch": 0.01, "learning_rate": 4.435851760033491e-05, "loss": 3.8169, "step": 344576 }, { "epoch": 0.01, "learning_rate": 4.435013165282439e-05, "loss": 3.8145, "step": 345088 }, { "epoch": 0.01, "learning_rate": 4.434174570531388e-05, "loss": 3.8021, "step": 345600 }, { "epoch": 0.01, "learning_rate": 4.433335975780336e-05, "loss": 3.8198, "step": 346112 }, { "epoch": 0.01, "learning_rate": 4.432499018909657e-05, "loss": 3.8088, "step": 346624 }, { "epoch": 0.01, "learning_rate": 4.431660424158605e-05, "loss": 3.818, "step": 347136 }, { "epoch": 0.01, "learning_rate": 4.430821829407553e-05, "loss": 3.8185, "step": 347648 }, { "epoch": 0.01, "learning_rate": 4.429983234656501e-05, "loss": 3.7945, "step": 348160 }, { "epoch": 0.01, "learning_rate": 4.4291462777858217e-05, "loss": 3.8048, "step": 348672 }, { "epoch": 0.01, "learning_rate": 4.4283076830347696e-05, "loss": 3.8025, "step": 349184 }, { "epoch": 0.01, "learning_rate": 4.4274690882837176e-05, "loss": 3.8117, "step": 349696 }, { "epoch": 0.01, "learning_rate": 4.4266304935326656e-05, "loss": 3.81, "step": 350208 }, { "epoch": 0.01, "learning_rate": 4.4257935366619865e-05, "loss": 3.8023, "step": 350720 }, { "epoch": 0.02, "learning_rate": 4.4249549419109345e-05, "loss": 3.8096, "step": 351232 }, { "epoch": 0.02, "learning_rate": 4.424116347159883e-05, "loss": 3.7998, "step": 351744 }, { "epoch": 0.02, "learning_rate": 4.423277752408831e-05, "loss": 3.8028, "step": 352256 }, { "epoch": 0.02, "learning_rate": 4.422440795538152e-05, "loss": 3.8012, "step": 352768 }, { "epoch": 0.02, "learning_rate": 4.4216022007871e-05, "loss": 3.81, "step": 353280 }, { "epoch": 0.02, "learning_rate": 4.420763606036048e-05, "loss": 3.8172, "step": 353792 }, { "epoch": 0.02, "learning_rate": 4.419925011284996e-05, "loss": 3.8086, "step": 354304 }, { "epoch": 0.02, "learning_rate": 4.419088054414317e-05, "loss": 3.7995, "step": 354816 }, { "epoch": 0.02, "learning_rate": 4.418249459663265e-05, "loss": 3.8038, "step": 355328 }, { "epoch": 0.02, "learning_rate": 4.417410864912213e-05, "loss": 3.807, "step": 355840 }, { "epoch": 0.02, "learning_rate": 4.416572270161161e-05, "loss": 3.8127, "step": 356352 }, { "epoch": 0.02, "learning_rate": 4.415733675410109e-05, "loss": 3.8064, "step": 356864 }, { "epoch": 0.02, "learning_rate": 4.41489671853943e-05, "loss": 3.7999, "step": 357376 }, { "epoch": 0.02, "learning_rate": 4.414058123788378e-05, "loss": 3.7951, "step": 357888 }, { "epoch": 0.02, "learning_rate": 4.4132195290373266e-05, "loss": 3.8078, "step": 358400 }, { "epoch": 0.02, "learning_rate": 4.4123809342862746e-05, "loss": 3.792, "step": 358912 }, { "epoch": 0.02, "learning_rate": 4.4115439774155955e-05, "loss": 3.7935, "step": 359424 }, { "epoch": 0.02, "learning_rate": 4.4107053826645435e-05, "loss": 3.7903, "step": 359936 }, { "epoch": 0.02, "learning_rate": 4.4098667879134915e-05, "loss": 3.8042, "step": 360448 }, { "epoch": 0.02, "learning_rate": 4.4090298310428124e-05, "loss": 3.79, "step": 360960 }, { "epoch": 0.02, "learning_rate": 4.4081912362917604e-05, "loss": 3.8144, "step": 361472 }, { "epoch": 0.02, "learning_rate": 4.4073526415407084e-05, "loss": 3.7902, "step": 361984 }, { "epoch": 0.02, "learning_rate": 4.4065140467896564e-05, "loss": 3.8035, "step": 362496 }, { "epoch": 0.02, "learning_rate": 4.4056754520386044e-05, "loss": 3.799, "step": 363008 }, { "epoch": 0.02, "learning_rate": 4.4048368572875524e-05, "loss": 3.7896, "step": 363520 }, { "epoch": 0.02, "learning_rate": 4.4039982625365004e-05, "loss": 3.8141, "step": 364032 }, { "epoch": 0.02, "learning_rate": 4.4031596677854484e-05, "loss": 3.8061, "step": 364544 }, { "epoch": 0.02, "learning_rate": 4.40232271091477e-05, "loss": 3.7995, "step": 365056 }, { "epoch": 0.02, "learning_rate": 4.401484116163718e-05, "loss": 3.7992, "step": 365568 }, { "epoch": 0.02, "learning_rate": 4.400645521412666e-05, "loss": 3.7921, "step": 366080 }, { "epoch": 0.02, "learning_rate": 4.399806926661613e-05, "loss": 3.803, "step": 366592 }, { "epoch": 0.02, "learning_rate": 4.398969969790935e-05, "loss": 3.7853, "step": 367104 }, { "epoch": 0.02, "learning_rate": 4.398131375039883e-05, "loss": 3.8079, "step": 367616 }, { "epoch": 0.02, "learning_rate": 4.397292780288831e-05, "loss": 3.7951, "step": 368128 }, { "epoch": 0.02, "learning_rate": 4.396454185537778e-05, "loss": 3.7972, "step": 368640 }, { "epoch": 0.02, "learning_rate": 4.3956172286671e-05, "loss": 3.7924, "step": 369152 }, { "epoch": 0.02, "learning_rate": 4.394778633916048e-05, "loss": 3.7943, "step": 369664 }, { "epoch": 0.02, "learning_rate": 4.393940039164996e-05, "loss": 3.7857, "step": 370176 }, { "epoch": 0.02, "learning_rate": 4.393101444413944e-05, "loss": 3.7976, "step": 370688 }, { "epoch": 0.02, "learning_rate": 4.392264487543265e-05, "loss": 3.7893, "step": 371200 }, { "epoch": 0.02, "learning_rate": 4.391425892792213e-05, "loss": 3.8064, "step": 371712 }, { "epoch": 0.02, "learning_rate": 4.3905872980411606e-05, "loss": 3.7999, "step": 372224 }, { "epoch": 0.02, "learning_rate": 4.3897487032901086e-05, "loss": 3.7964, "step": 372736 }, { "epoch": 0.02, "learning_rate": 4.3889101085390566e-05, "loss": 3.7818, "step": 373248 }, { "epoch": 0.02, "learning_rate": 4.3880715137880046e-05, "loss": 3.8023, "step": 373760 }, { "epoch": 0.02, "learning_rate": 4.3872345569173255e-05, "loss": 3.798, "step": 374272 }, { "epoch": 0.02, "learning_rate": 4.3863959621662735e-05, "loss": 3.8015, "step": 374784 }, { "epoch": 0.02, "learning_rate": 4.3855573674152215e-05, "loss": 3.7914, "step": 375296 }, { "epoch": 0.02, "learning_rate": 4.3847187726641695e-05, "loss": 3.7945, "step": 375808 }, { "epoch": 0.02, "learning_rate": 4.383881815793491e-05, "loss": 3.7985, "step": 376320 }, { "epoch": 0.02, "learning_rate": 4.383043221042439e-05, "loss": 3.8038, "step": 376832 }, { "epoch": 0.02, "learning_rate": 4.382204626291387e-05, "loss": 3.7874, "step": 377344 }, { "epoch": 0.02, "learning_rate": 4.381366031540335e-05, "loss": 3.7973, "step": 377856 }, { "epoch": 0.02, "learning_rate": 4.380529074669656e-05, "loss": 3.7877, "step": 378368 }, { "epoch": 0.02, "learning_rate": 4.379690479918604e-05, "loss": 3.7855, "step": 378880 }, { "epoch": 0.02, "learning_rate": 4.3788535230479256e-05, "loss": 3.8027, "step": 379392 }, { "epoch": 0.02, "learning_rate": 4.378014928296873e-05, "loss": 3.7917, "step": 379904 }, { "epoch": 0.02, "learning_rate": 4.377176333545821e-05, "loss": 3.7913, "step": 380416 }, { "epoch": 0.02, "learning_rate": 4.376337738794769e-05, "loss": 3.7842, "step": 380928 }, { "epoch": 0.02, "learning_rate": 4.375499144043717e-05, "loss": 3.7914, "step": 381440 }, { "epoch": 0.03, "eval_loss": 3.88553786277771, "eval_runtime": 320.7264, "eval_samples_per_second": 1189.771, "eval_steps_per_second": 37.181, "step": 381600 }, { "epoch": 1.0, "learning_rate": 4.374660549292665e-05, "loss": 3.7885, "step": 381952 }, { "epoch": 1.0, "learning_rate": 4.373821954541613e-05, "loss": 3.7854, "step": 382464 }, { "epoch": 1.0, "learning_rate": 4.372983359790561e-05, "loss": 3.8006, "step": 382976 }, { "epoch": 1.0, "learning_rate": 4.3721464029198824e-05, "loss": 3.7913, "step": 383488 }, { "epoch": 1.0, "learning_rate": 4.3713078081688304e-05, "loss": 3.7962, "step": 384000 }, { "epoch": 1.0, "learning_rate": 4.3704692134177784e-05, "loss": 3.7883, "step": 384512 }, { "epoch": 1.0, "learning_rate": 4.3696306186667264e-05, "loss": 3.7855, "step": 385024 }, { "epoch": 1.0, "learning_rate": 4.3687936617960473e-05, "loss": 3.7771, "step": 385536 }, { "epoch": 1.0, "learning_rate": 4.3679550670449953e-05, "loss": 3.7962, "step": 386048 }, { "epoch": 1.0, "learning_rate": 4.367116472293943e-05, "loss": 3.7976, "step": 386560 }, { "epoch": 1.0, "learning_rate": 4.366277877542891e-05, "loss": 3.789, "step": 387072 }, { "epoch": 1.0, "learning_rate": 4.365440920672212e-05, "loss": 3.798, "step": 387584 }, { "epoch": 1.0, "learning_rate": 4.364603963801533e-05, "loss": 3.7768, "step": 388096 }, { "epoch": 1.0, "learning_rate": 4.363765369050482e-05, "loss": 3.7846, "step": 388608 }, { "epoch": 1.0, "learning_rate": 4.36292677429943e-05, "loss": 3.7905, "step": 389120 }, { "epoch": 1.0, "learning_rate": 4.362088179548378e-05, "loss": 3.7767, "step": 389632 }, { "epoch": 1.0, "learning_rate": 4.361249584797326e-05, "loss": 3.7767, "step": 390144 }, { "epoch": 1.0, "learning_rate": 4.360410990046274e-05, "loss": 3.7782, "step": 390656 }, { "epoch": 1.0, "learning_rate": 4.359572395295222e-05, "loss": 3.7809, "step": 391168 }, { "epoch": 1.0, "learning_rate": 4.35873380054417e-05, "loss": 3.7973, "step": 391680 }, { "epoch": 1.0, "learning_rate": 4.357896843673491e-05, "loss": 3.7862, "step": 392192 }, { "epoch": 1.0, "learning_rate": 4.357058248922439e-05, "loss": 3.7848, "step": 392704 }, { "epoch": 1.0, "learning_rate": 4.356219654171387e-05, "loss": 3.7772, "step": 393216 }, { "epoch": 1.0, "learning_rate": 4.355381059420335e-05, "loss": 3.7886, "step": 393728 }, { "epoch": 1.0, "learning_rate": 4.3545441025496556e-05, "loss": 3.7724, "step": 394240 }, { "epoch": 1.0, "learning_rate": 4.3537055077986036e-05, "loss": 3.7737, "step": 394752 }, { "epoch": 1.0, "learning_rate": 4.3528669130475516e-05, "loss": 3.7779, "step": 395264 }, { "epoch": 1.0, "learning_rate": 4.3520283182964996e-05, "loss": 3.7829, "step": 395776 }, { "epoch": 1.0, "learning_rate": 4.351191361425821e-05, "loss": 3.7689, "step": 396288 }, { "epoch": 1.0, "learning_rate": 4.350352766674769e-05, "loss": 3.7781, "step": 396800 }, { "epoch": 1.01, "learning_rate": 4.349514171923717e-05, "loss": 3.781, "step": 397312 }, { "epoch": 1.01, "learning_rate": 4.348675577172665e-05, "loss": 3.7832, "step": 397824 }, { "epoch": 1.01, "learning_rate": 4.347838620301986e-05, "loss": 3.7773, "step": 398336 }, { "epoch": 1.01, "learning_rate": 4.347000025550934e-05, "loss": 3.7762, "step": 398848 }, { "epoch": 1.01, "learning_rate": 4.346161430799882e-05, "loss": 3.78, "step": 399360 }, { "epoch": 1.01, "learning_rate": 4.34532283604883e-05, "loss": 3.7776, "step": 399872 }, { "epoch": 1.01, "learning_rate": 4.344484241297778e-05, "loss": 3.7711, "step": 400384 }, { "epoch": 1.01, "learning_rate": 4.343647284427099e-05, "loss": 3.7695, "step": 400896 }, { "epoch": 1.01, "learning_rate": 4.342808689676047e-05, "loss": 3.7615, "step": 401408 }, { "epoch": 1.01, "learning_rate": 4.341970094924995e-05, "loss": 3.7735, "step": 401920 }, { "epoch": 1.01, "learning_rate": 4.3411331380543165e-05, "loss": 3.77, "step": 402432 }, { "epoch": 1.01, "learning_rate": 4.3402945433032645e-05, "loss": 3.7788, "step": 402944 }, { "epoch": 1.01, "learning_rate": 4.3394559485522125e-05, "loss": 3.7709, "step": 403456 }, { "epoch": 1.01, "learning_rate": 4.3386173538011605e-05, "loss": 3.77, "step": 403968 }, { "epoch": 1.01, "learning_rate": 4.3377803969304814e-05, "loss": 3.7802, "step": 404480 }, { "epoch": 1.01, "learning_rate": 4.3369418021794294e-05, "loss": 3.7751, "step": 404992 }, { "epoch": 1.01, "learning_rate": 4.3361032074283774e-05, "loss": 3.7788, "step": 405504 }, { "epoch": 1.01, "learning_rate": 4.3352646126773254e-05, "loss": 3.7627, "step": 406016 }, { "epoch": 1.01, "learning_rate": 4.334427655806646e-05, "loss": 3.7602, "step": 406528 }, { "epoch": 1.01, "learning_rate": 4.333589061055594e-05, "loss": 3.7856, "step": 407040 }, { "epoch": 1.01, "learning_rate": 4.332750466304542e-05, "loss": 3.7684, "step": 407552 }, { "epoch": 1.01, "learning_rate": 4.33191187155349e-05, "loss": 3.7661, "step": 408064 }, { "epoch": 1.01, "learning_rate": 4.331074914682812e-05, "loss": 3.7647, "step": 408576 }, { "epoch": 1.01, "learning_rate": 4.33023631993176e-05, "loss": 3.7712, "step": 409088 }, { "epoch": 1.01, "learning_rate": 4.329397725180708e-05, "loss": 3.753, "step": 409600 }, { "epoch": 1.01, "learning_rate": 4.328559130429656e-05, "loss": 3.7752, "step": 410112 }, { "epoch": 1.01, "learning_rate": 4.327722173558977e-05, "loss": 3.7703, "step": 410624 }, { "epoch": 1.01, "learning_rate": 4.326883578807925e-05, "loss": 3.7667, "step": 411136 }, { "epoch": 1.01, "learning_rate": 4.326044984056873e-05, "loss": 3.7841, "step": 411648 }, { "epoch": 1.01, "learning_rate": 4.325206389305821e-05, "loss": 3.7591, "step": 412160 }, { "epoch": 1.01, "learning_rate": 4.324369432435142e-05, "loss": 3.7613, "step": 412672 }, { "epoch": 1.01, "learning_rate": 4.32353083768409e-05, "loss": 3.7752, "step": 413184 }, { "epoch": 1.01, "learning_rate": 4.322692242933038e-05, "loss": 3.7553, "step": 413696 }, { "epoch": 1.01, "learning_rate": 4.321853648181986e-05, "loss": 3.7549, "step": 414208 }, { "epoch": 1.01, "learning_rate": 4.321016691311307e-05, "loss": 3.765, "step": 414720 }, { "epoch": 1.01, "learning_rate": 4.320178096560255e-05, "loss": 3.7657, "step": 415232 }, { "epoch": 1.01, "learning_rate": 4.319339501809203e-05, "loss": 3.7581, "step": 415744 }, { "epoch": 1.01, "learning_rate": 4.3185009070581506e-05, "loss": 3.7532, "step": 416256 }, { "epoch": 1.01, "learning_rate": 4.317663950187472e-05, "loss": 3.7598, "step": 416768 }, { "epoch": 1.01, "learning_rate": 4.31682535543642e-05, "loss": 3.7683, "step": 417280 }, { "epoch": 1.01, "learning_rate": 4.315986760685368e-05, "loss": 3.7668, "step": 417792 }, { "epoch": 1.01, "learning_rate": 4.3151481659343155e-05, "loss": 3.7698, "step": 418304 }, { "epoch": 1.01, "learning_rate": 4.314311209063637e-05, "loss": 3.7729, "step": 418816 }, { "epoch": 1.01, "learning_rate": 4.313472614312585e-05, "loss": 3.7713, "step": 419328 }, { "epoch": 1.01, "learning_rate": 4.312634019561533e-05, "loss": 3.7818, "step": 419840 }, { "epoch": 1.01, "learning_rate": 4.311795424810481e-05, "loss": 3.7504, "step": 420352 }, { "epoch": 1.01, "learning_rate": 4.310956830059429e-05, "loss": 3.775, "step": 420864 }, { "epoch": 1.01, "learning_rate": 4.3101198731887506e-05, "loss": 3.769, "step": 421376 }, { "epoch": 1.01, "learning_rate": 4.309281278437698e-05, "loss": 3.7491, "step": 421888 }, { "epoch": 1.01, "learning_rate": 4.308442683686646e-05, "loss": 3.7765, "step": 422400 }, { "epoch": 1.01, "learning_rate": 4.307604088935594e-05, "loss": 3.7613, "step": 422912 }, { "epoch": 1.01, "learning_rate": 4.3067671320649155e-05, "loss": 3.7718, "step": 423424 }, { "epoch": 1.01, "learning_rate": 4.305928537313863e-05, "loss": 3.7719, "step": 423936 }, { "epoch": 1.01, "learning_rate": 4.305089942562811e-05, "loss": 3.7505, "step": 424448 }, { "epoch": 1.01, "learning_rate": 4.3042529856921324e-05, "loss": 3.7547, "step": 424960 }, { "epoch": 1.01, "learning_rate": 4.3034143909410804e-05, "loss": 3.7566, "step": 425472 }, { "epoch": 1.01, "learning_rate": 4.3025757961900284e-05, "loss": 3.7665, "step": 425984 }, { "epoch": 1.01, "learning_rate": 4.3017372014389764e-05, "loss": 3.7614, "step": 426496 }, { "epoch": 1.01, "learning_rate": 4.300900244568298e-05, "loss": 3.7593, "step": 427008 }, { "epoch": 1.02, "learning_rate": 4.300061649817245e-05, "loss": 3.7583, "step": 427520 }, { "epoch": 1.02, "learning_rate": 4.299223055066193e-05, "loss": 3.7566, "step": 428032 }, { "epoch": 1.02, "learning_rate": 4.298384460315141e-05, "loss": 3.7584, "step": 428544 }, { "epoch": 1.02, "learning_rate": 4.297547503444463e-05, "loss": 3.7533, "step": 429056 }, { "epoch": 1.02, "learning_rate": 4.29670890869341e-05, "loss": 3.7666, "step": 429568 }, { "epoch": 1.02, "learning_rate": 4.295870313942358e-05, "loss": 3.769, "step": 430080 }, { "epoch": 1.02, "learning_rate": 4.295031719191306e-05, "loss": 3.7687, "step": 430592 }, { "epoch": 1.02, "learning_rate": 4.294194762320628e-05, "loss": 3.7508, "step": 431104 }, { "epoch": 1.02, "learning_rate": 4.293356167569576e-05, "loss": 3.7593, "step": 431616 }, { "epoch": 1.02, "learning_rate": 4.292517572818524e-05, "loss": 3.7573, "step": 432128 }, { "epoch": 1.02, "learning_rate": 4.291678978067472e-05, "loss": 3.7634, "step": 432640 }, { "epoch": 1.02, "learning_rate": 4.290842021196793e-05, "loss": 3.7627, "step": 433152 }, { "epoch": 1.02, "learning_rate": 4.290003426445741e-05, "loss": 3.757, "step": 433664 }, { "epoch": 1.02, "learning_rate": 4.289164831694689e-05, "loss": 3.7487, "step": 434176 }, { "epoch": 1.02, "learning_rate": 4.288326236943637e-05, "loss": 3.7612, "step": 434688 }, { "epoch": 1.02, "learning_rate": 4.2874892800729576e-05, "loss": 3.751, "step": 435200 }, { "epoch": 1.02, "learning_rate": 4.2866506853219056e-05, "loss": 3.7472, "step": 435712 }, { "epoch": 1.02, "learning_rate": 4.2858120905708536e-05, "loss": 3.7408, "step": 436224 }, { "epoch": 1.02, "learning_rate": 4.2849734958198016e-05, "loss": 3.759, "step": 436736 }, { "epoch": 1.02, "learning_rate": 4.284138176829496e-05, "loss": 3.75, "step": 437248 }, { "epoch": 1.02, "learning_rate": 4.283299582078444e-05, "loss": 3.7652, "step": 437760 }, { "epoch": 1.02, "learning_rate": 4.282460987327393e-05, "loss": 3.749, "step": 438272 }, { "epoch": 1.02, "learning_rate": 4.28162239257634e-05, "loss": 3.7559, "step": 438784 }, { "epoch": 1.02, "learning_rate": 4.280783797825288e-05, "loss": 3.7563, "step": 439296 }, { "epoch": 1.02, "learning_rate": 4.279945203074236e-05, "loss": 3.7451, "step": 439808 }, { "epoch": 1.02, "learning_rate": 4.279106608323184e-05, "loss": 3.7684, "step": 440320 }, { "epoch": 1.02, "learning_rate": 4.278268013572132e-05, "loss": 3.7609, "step": 440832 }, { "epoch": 1.02, "learning_rate": 4.277431056701453e-05, "loss": 3.7538, "step": 441344 }, { "epoch": 1.02, "learning_rate": 4.276592461950401e-05, "loss": 3.7545, "step": 441856 }, { "epoch": 1.02, "learning_rate": 4.275753867199349e-05, "loss": 3.7513, "step": 442368 }, { "epoch": 1.02, "learning_rate": 4.274915272448297e-05, "loss": 3.7603, "step": 442880 }, { "epoch": 1.02, "learning_rate": 4.274078315577618e-05, "loss": 3.7388, "step": 443392 }, { "epoch": 1.02, "learning_rate": 4.2732397208265665e-05, "loss": 3.7636, "step": 443904 }, { "epoch": 1.02, "learning_rate": 4.2724011260755145e-05, "loss": 3.7468, "step": 444416 }, { "epoch": 1.02, "learning_rate": 4.2715625313244625e-05, "loss": 3.7523, "step": 444928 }, { "epoch": 1.02, "learning_rate": 4.2707255744537834e-05, "loss": 3.7519, "step": 445440 }, { "epoch": 1.02, "learning_rate": 4.2698869797027314e-05, "loss": 3.7478, "step": 445952 }, { "epoch": 1.02, "learning_rate": 4.2690483849516794e-05, "loss": 3.7477, "step": 446464 }, { "epoch": 1.02, "learning_rate": 4.2682097902006274e-05, "loss": 3.7496, "step": 446976 }, { "epoch": 1.02, "learning_rate": 4.267372833329948e-05, "loss": 3.7501, "step": 447488 }, { "epoch": 1.02, "learning_rate": 4.266534238578896e-05, "loss": 3.7609, "step": 448000 }, { "epoch": 1.02, "learning_rate": 4.265695643827844e-05, "loss": 3.7524, "step": 448512 }, { "epoch": 1.02, "learning_rate": 4.264857049076792e-05, "loss": 3.7546, "step": 449024 }, { "epoch": 1.02, "learning_rate": 4.264020092206113e-05, "loss": 3.7364, "step": 449536 }, { "epoch": 1.02, "learning_rate": 4.263181497455062e-05, "loss": 3.7617, "step": 450048 }, { "epoch": 1.02, "learning_rate": 4.26234290270401e-05, "loss": 3.7517, "step": 450560 }, { "epoch": 1.02, "learning_rate": 4.261504307952958e-05, "loss": 3.7558, "step": 451072 }, { "epoch": 1.02, "learning_rate": 4.260667351082279e-05, "loss": 3.7492, "step": 451584 }, { "epoch": 1.02, "learning_rate": 4.259828756331227e-05, "loss": 3.7473, "step": 452096 }, { "epoch": 1.02, "learning_rate": 4.258990161580175e-05, "loss": 3.7575, "step": 452608 }, { "epoch": 1.02, "learning_rate": 4.258151566829123e-05, "loss": 3.7602, "step": 453120 }, { "epoch": 1.02, "learning_rate": 4.257314609958444e-05, "loss": 3.7435, "step": 453632 }, { "epoch": 1.02, "learning_rate": 4.256476015207392e-05, "loss": 3.7518, "step": 454144 }, { "epoch": 1.02, "learning_rate": 4.25563742045634e-05, "loss": 3.7475, "step": 454656 }, { "epoch": 1.02, "learning_rate": 4.254798825705288e-05, "loss": 3.7422, "step": 455168 }, { "epoch": 1.02, "learning_rate": 4.2539618688346086e-05, "loss": 3.7587, "step": 455680 }, { "epoch": 1.02, "learning_rate": 4.253123274083557e-05, "loss": 3.7473, "step": 456192 }, { "epoch": 1.02, "learning_rate": 4.252284679332505e-05, "loss": 3.7537, "step": 456704 }, { "epoch": 1.02, "learning_rate": 4.251446084581453e-05, "loss": 3.7367, "step": 457216 }, { "epoch": 1.02, "learning_rate": 4.250607489830401e-05, "loss": 3.7515, "step": 457728 }, { "epoch": 1.03, "eval_loss": 3.8704419136047363, "eval_runtime": 359.2798, "eval_samples_per_second": 1062.1, "eval_steps_per_second": 33.191, "step": 457920 }, { "epoch": 0.0, "learning_rate": 4.249768895079349e-05, "loss": 3.7448, "step": 458240 }, { "epoch": 0.0, "learning_rate": 4.248930300328297e-05, "loss": 3.74, "step": 458752 }, { "epoch": 0.0, "learning_rate": 4.248091705577245e-05, "loss": 3.7577, "step": 459264 }, { "epoch": 0.0, "learning_rate": 4.247253110826193e-05, "loss": 3.7505, "step": 459776 }, { "epoch": 0.0, "learning_rate": 4.246414516075141e-05, "loss": 3.7526, "step": 460288 }, { "epoch": 0.0, "learning_rate": 4.2455759213240885e-05, "loss": 3.7464, "step": 460800 }, { "epoch": 0.0, "learning_rate": 4.2447373265730365e-05, "loss": 3.7385, "step": 461312 }, { "epoch": 0.0, "learning_rate": 4.2438987318219845e-05, "loss": 3.7418, "step": 461824 }, { "epoch": 0.0, "learning_rate": 4.2430617749513054e-05, "loss": 3.7494, "step": 462336 }, { "epoch": 0.0, "learning_rate": 4.2422231802002534e-05, "loss": 3.7574, "step": 462848 }, { "epoch": 0.0, "learning_rate": 4.241384585449202e-05, "loss": 3.7464, "step": 463360 }, { "epoch": 0.0, "learning_rate": 4.24054599069815e-05, "loss": 3.7573, "step": 463872 }, { "epoch": 0.0, "learning_rate": 4.2397106717078446e-05, "loss": 3.7403, "step": 464384 }, { "epoch": 0.0, "learning_rate": 4.2388720769567926e-05, "loss": 3.7388, "step": 464896 }, { "epoch": 0.0, "learning_rate": 4.2380334822057406e-05, "loss": 3.7495, "step": 465408 }, { "epoch": 0.0, "learning_rate": 4.2371948874546886e-05, "loss": 3.7347, "step": 465920 }, { "epoch": 0.0, "learning_rate": 4.236356292703636e-05, "loss": 3.735, "step": 466432 }, { "epoch": 0.0, "learning_rate": 4.235517697952584e-05, "loss": 3.734, "step": 466944 }, { "epoch": 0.0, "learning_rate": 4.234679103201532e-05, "loss": 3.7407, "step": 467456 }, { "epoch": 0.0, "learning_rate": 4.23384050845048e-05, "loss": 3.7513, "step": 467968 }, { "epoch": 0.0, "learning_rate": 4.233003551579801e-05, "loss": 3.746, "step": 468480 }, { "epoch": 0.0, "learning_rate": 4.232164956828749e-05, "loss": 3.7445, "step": 468992 }, { "epoch": 0.0, "learning_rate": 4.2313263620776975e-05, "loss": 3.7336, "step": 469504 }, { "epoch": 0.0, "learning_rate": 4.2304877673266455e-05, "loss": 3.7475, "step": 470016 }, { "epoch": 0.0, "learning_rate": 4.2296508104559664e-05, "loss": 3.7351, "step": 470528 }, { "epoch": 0.0, "learning_rate": 4.2288122157049144e-05, "loss": 3.7352, "step": 471040 }, { "epoch": 0.0, "learning_rate": 4.2279736209538624e-05, "loss": 3.7319, "step": 471552 }, { "epoch": 0.0, "learning_rate": 4.2271350262028104e-05, "loss": 3.74, "step": 472064 }, { "epoch": 0.0, "learning_rate": 4.226298069332131e-05, "loss": 3.7351, "step": 472576 }, { "epoch": 0.0, "learning_rate": 4.225459474581079e-05, "loss": 3.7326, "step": 473088 }, { "epoch": 0.01, "learning_rate": 4.224620879830027e-05, "loss": 3.7409, "step": 473600 }, { "epoch": 0.01, "learning_rate": 4.223782285078975e-05, "loss": 3.7412, "step": 474112 }, { "epoch": 0.01, "learning_rate": 4.222945328208296e-05, "loss": 3.7365, "step": 474624 }, { "epoch": 0.01, "learning_rate": 4.222106733457244e-05, "loss": 3.7403, "step": 475136 }, { "epoch": 0.01, "learning_rate": 4.221268138706193e-05, "loss": 3.737, "step": 475648 }, { "epoch": 0.01, "learning_rate": 4.220429543955141e-05, "loss": 3.7363, "step": 476160 }, { "epoch": 0.01, "learning_rate": 4.219592587084462e-05, "loss": 3.7347, "step": 476672 }, { "epoch": 0.01, "learning_rate": 4.21875399233341e-05, "loss": 3.7232, "step": 477184 }, { "epoch": 0.01, "learning_rate": 4.217915397582358e-05, "loss": 3.7197, "step": 477696 }, { "epoch": 0.01, "learning_rate": 4.217076802831306e-05, "loss": 3.7321, "step": 478208 }, { "epoch": 0.01, "learning_rate": 4.2162398459606267e-05, "loss": 3.7323, "step": 478720 }, { "epoch": 0.01, "learning_rate": 4.2154012512095746e-05, "loss": 3.7354, "step": 479232 }, { "epoch": 0.01, "learning_rate": 4.2145626564585226e-05, "loss": 3.733, "step": 479744 }, { "epoch": 0.01, "learning_rate": 4.2137240617074706e-05, "loss": 3.7314, "step": 480256 }, { "epoch": 0.01, "learning_rate": 4.2128871048367915e-05, "loss": 3.7409, "step": 480768 }, { "epoch": 0.01, "learning_rate": 4.2120485100857395e-05, "loss": 3.7339, "step": 481280 }, { "epoch": 0.01, "learning_rate": 4.211209915334688e-05, "loss": 3.7407, "step": 481792 }, { "epoch": 0.01, "learning_rate": 4.210371320583636e-05, "loss": 3.7224, "step": 482304 }, { "epoch": 0.01, "learning_rate": 4.209534363712957e-05, "loss": 3.7161, "step": 482816 }, { "epoch": 0.01, "learning_rate": 4.208695768961905e-05, "loss": 3.7474, "step": 483328 }, { "epoch": 0.01, "learning_rate": 4.207857174210853e-05, "loss": 3.7332, "step": 483840 }, { "epoch": 0.01, "learning_rate": 4.207018579459801e-05, "loss": 3.7231, "step": 484352 }, { "epoch": 0.01, "learning_rate": 4.206181622589122e-05, "loss": 3.7269, "step": 484864 }, { "epoch": 0.01, "learning_rate": 4.20534302783807e-05, "loss": 3.7291, "step": 485376 }, { "epoch": 0.01, "learning_rate": 4.204504433087018e-05, "loss": 3.7172, "step": 485888 }, { "epoch": 0.01, "learning_rate": 4.203665838335966e-05, "loss": 3.7307, "step": 486400 }, { "epoch": 0.01, "learning_rate": 4.202828881465287e-05, "loss": 3.7325, "step": 486912 }, { "epoch": 0.01, "learning_rate": 4.201990286714235e-05, "loss": 3.7318, "step": 487424 }, { "epoch": 0.01, "learning_rate": 4.2011516919631836e-05, "loss": 3.7427, "step": 487936 }, { "epoch": 0.01, "learning_rate": 4.2003130972121316e-05, "loss": 3.718, "step": 488448 }, { "epoch": 0.01, "learning_rate": 4.1994761403414525e-05, "loss": 3.723, "step": 488960 }, { "epoch": 0.01, "learning_rate": 4.1986375455904005e-05, "loss": 3.7387, "step": 489472 }, { "epoch": 0.01, "learning_rate": 4.1977989508393485e-05, "loss": 3.7154, "step": 489984 }, { "epoch": 0.01, "learning_rate": 4.1969603560882965e-05, "loss": 3.7131, "step": 490496 }, { "epoch": 0.01, "learning_rate": 4.1961233992176174e-05, "loss": 3.7259, "step": 491008 }, { "epoch": 0.01, "learning_rate": 4.1952848044665654e-05, "loss": 3.725, "step": 491520 }, { "epoch": 0.01, "learning_rate": 4.1944462097155134e-05, "loss": 3.7177, "step": 492032 }, { "epoch": 0.01, "learning_rate": 4.1936076149644614e-05, "loss": 3.7184, "step": 492544 }, { "epoch": 0.01, "learning_rate": 4.192770658093782e-05, "loss": 3.7158, "step": 493056 }, { "epoch": 0.01, "learning_rate": 4.19193206334273e-05, "loss": 3.7347, "step": 493568 }, { "epoch": 0.01, "learning_rate": 4.191093468591679e-05, "loss": 3.7286, "step": 494080 }, { "epoch": 0.01, "learning_rate": 4.190254873840627e-05, "loss": 3.7293, "step": 494592 }, { "epoch": 0.01, "learning_rate": 4.189417916969948e-05, "loss": 3.7322, "step": 495104 }, { "epoch": 0.01, "learning_rate": 4.188579322218896e-05, "loss": 3.7307, "step": 495616 }, { "epoch": 0.01, "learning_rate": 4.187740727467844e-05, "loss": 3.7441, "step": 496128 }, { "epoch": 0.01, "learning_rate": 4.186902132716792e-05, "loss": 3.7149, "step": 496640 }, { "epoch": 0.01, "learning_rate": 4.186065175846113e-05, "loss": 3.7357, "step": 497152 }, { "epoch": 0.01, "learning_rate": 4.185226581095061e-05, "loss": 3.7306, "step": 497664 }, { "epoch": 0.01, "learning_rate": 4.184387986344009e-05, "loss": 3.7141, "step": 498176 }, { "epoch": 0.01, "learning_rate": 4.183549391592957e-05, "loss": 3.7349, "step": 498688 }, { "epoch": 0.01, "learning_rate": 4.1827124347222776e-05, "loss": 3.7243, "step": 499200 }, { "epoch": 0.01, "learning_rate": 4.1818738399712256e-05, "loss": 3.732, "step": 499712 }, { "epoch": 0.01, "learning_rate": 4.181035245220174e-05, "loss": 3.7341, "step": 500224 }, { "epoch": 0.01, "learning_rate": 4.180198288349495e-05, "loss": 3.7163, "step": 500736 }, { "epoch": 0.01, "learning_rate": 4.179359693598443e-05, "loss": 3.7114, "step": 501248 }, { "epoch": 0.01, "learning_rate": 4.178521098847391e-05, "loss": 3.7186, "step": 501760 }, { "epoch": 0.01, "learning_rate": 4.177682504096339e-05, "loss": 3.7307, "step": 502272 }, { "epoch": 0.01, "learning_rate": 4.17684554722566e-05, "loss": 3.7215, "step": 502784 }, { "epoch": 0.01, "learning_rate": 4.176006952474608e-05, "loss": 3.7223, "step": 503296 }, { "epoch": 0.02, "learning_rate": 4.175168357723556e-05, "loss": 3.7222, "step": 503808 }, { "epoch": 0.02, "learning_rate": 4.174329762972504e-05, "loss": 3.7177, "step": 504320 }, { "epoch": 0.02, "learning_rate": 4.173492806101825e-05, "loss": 3.7225, "step": 504832 }, { "epoch": 0.02, "learning_rate": 4.172654211350773e-05, "loss": 3.7164, "step": 505344 }, { "epoch": 0.02, "learning_rate": 4.171815616599721e-05, "loss": 3.729, "step": 505856 }, { "epoch": 0.02, "learning_rate": 4.170977021848669e-05, "loss": 3.7304, "step": 506368 }, { "epoch": 0.02, "learning_rate": 4.1701400649779906e-05, "loss": 3.7304, "step": 506880 }, { "epoch": 0.02, "learning_rate": 4.1693014702269386e-05, "loss": 3.7129, "step": 507392 }, { "epoch": 0.02, "learning_rate": 4.1684628754758866e-05, "loss": 3.7232, "step": 507904 }, { "epoch": 0.02, "learning_rate": 4.1676242807248346e-05, "loss": 3.7235, "step": 508416 }, { "epoch": 0.02, "learning_rate": 4.1667889617345284e-05, "loss": 3.7266, "step": 508928 }, { "epoch": 0.02, "learning_rate": 4.1659503669834764e-05, "loss": 3.7248, "step": 509440 }, { "epoch": 0.02, "learning_rate": 4.1651117722324244e-05, "loss": 3.7159, "step": 509952 }, { "epoch": 0.02, "learning_rate": 4.1642731774813724e-05, "loss": 3.7168, "step": 510464 }, { "epoch": 0.02, "learning_rate": 4.1634345827303204e-05, "loss": 3.7216, "step": 510976 }, { "epoch": 0.02, "learning_rate": 4.1625959879792684e-05, "loss": 3.7125, "step": 511488 }, { "epoch": 0.02, "learning_rate": 4.1617573932282164e-05, "loss": 3.7173, "step": 512000 }, { "epoch": 0.02, "learning_rate": 4.1609187984771644e-05, "loss": 3.6983, "step": 512512 }, { "epoch": 0.02, "learning_rate": 4.160081841606486e-05, "loss": 3.724, "step": 513024 }, { "epoch": 0.02, "learning_rate": 4.159244884735807e-05, "loss": 3.7148, "step": 513536 }, { "epoch": 0.02, "learning_rate": 4.158406289984755e-05, "loss": 3.7247, "step": 514048 }, { "epoch": 0.02, "learning_rate": 4.157567695233703e-05, "loss": 3.7136, "step": 514560 }, { "epoch": 0.02, "learning_rate": 4.156729100482651e-05, "loss": 3.7206, "step": 515072 }, { "epoch": 0.02, "learning_rate": 4.155890505731599e-05, "loss": 3.7204, "step": 515584 }, { "epoch": 0.02, "learning_rate": 4.155051910980547e-05, "loss": 3.7054, "step": 516096 }, { "epoch": 0.02, "learning_rate": 4.154213316229495e-05, "loss": 3.7333, "step": 516608 }, { "epoch": 0.02, "learning_rate": 4.153374721478443e-05, "loss": 3.7226, "step": 517120 }, { "epoch": 0.02, "learning_rate": 4.152537764607764e-05, "loss": 3.7187, "step": 517632 }, { "epoch": 0.02, "learning_rate": 4.151699169856712e-05, "loss": 3.7228, "step": 518144 }, { "epoch": 0.02, "learning_rate": 4.15086057510566e-05, "loss": 3.706, "step": 518656 }, { "epoch": 0.02, "learning_rate": 4.1500219803546084e-05, "loss": 3.7263, "step": 519168 }, { "epoch": 0.02, "learning_rate": 4.149185023483929e-05, "loss": 3.7077, "step": 519680 }, { "epoch": 0.02, "learning_rate": 4.148346428732877e-05, "loss": 3.7245, "step": 520192 }, { "epoch": 0.02, "learning_rate": 4.147507833981825e-05, "loss": 3.7085, "step": 520704 }, { "epoch": 0.02, "learning_rate": 4.146669239230773e-05, "loss": 3.7175, "step": 521216 }, { "epoch": 0.02, "learning_rate": 4.145832282360094e-05, "loss": 3.7131, "step": 521728 }, { "epoch": 0.02, "learning_rate": 4.144993687609042e-05, "loss": 3.7143, "step": 522240 }, { "epoch": 0.02, "learning_rate": 4.14415509285799e-05, "loss": 3.7136, "step": 522752 }, { "epoch": 0.02, "learning_rate": 4.143316498106938e-05, "loss": 3.7089, "step": 523264 }, { "epoch": 0.02, "learning_rate": 4.142479541236259e-05, "loss": 3.716, "step": 523776 }, { "epoch": 0.02, "learning_rate": 4.141640946485207e-05, "loss": 3.7243, "step": 524288 }, { "epoch": 0.02, "learning_rate": 4.140802351734155e-05, "loss": 3.7134, "step": 524800 }, { "epoch": 0.02, "learning_rate": 4.139963756983103e-05, "loss": 3.7228, "step": 525312 }, { "epoch": 0.02, "learning_rate": 4.139126800112425e-05, "loss": 3.7009, "step": 525824 }, { "epoch": 0.02, "learning_rate": 4.138288205361373e-05, "loss": 3.7241, "step": 526336 }, { "epoch": 0.02, "learning_rate": 4.137449610610321e-05, "loss": 3.7213, "step": 526848 }, { "epoch": 0.02, "learning_rate": 4.136611015859268e-05, "loss": 3.7173, "step": 527360 }, { "epoch": 0.02, "learning_rate": 4.1357740589885896e-05, "loss": 3.7125, "step": 527872 }, { "epoch": 0.02, "learning_rate": 4.1349354642375376e-05, "loss": 3.7145, "step": 528384 }, { "epoch": 0.02, "learning_rate": 4.1340968694864856e-05, "loss": 3.7168, "step": 528896 }, { "epoch": 0.02, "learning_rate": 4.133258274735433e-05, "loss": 3.7277, "step": 529408 }, { "epoch": 0.02, "learning_rate": 4.1324213178647545e-05, "loss": 3.7046, "step": 529920 }, { "epoch": 0.02, "learning_rate": 4.1315827231137025e-05, "loss": 3.7177, "step": 530432 }, { "epoch": 0.02, "learning_rate": 4.1307441283626505e-05, "loss": 3.7116, "step": 530944 }, { "epoch": 0.02, "learning_rate": 4.1299055336115985e-05, "loss": 3.7067, "step": 531456 }, { "epoch": 0.02, "learning_rate": 4.12906857674092e-05, "loss": 3.7192, "step": 531968 }, { "epoch": 0.02, "learning_rate": 4.128229981989868e-05, "loss": 3.712, "step": 532480 }, { "epoch": 0.02, "learning_rate": 4.1273913872388154e-05, "loss": 3.7166, "step": 532992 }, { "epoch": 0.02, "learning_rate": 4.1265527924877634e-05, "loss": 3.7029, "step": 533504 }, { "epoch": 0.02, "learning_rate": 4.1257141977367114e-05, "loss": 3.7206, "step": 534016 }, { "epoch": 0.03, "eval_loss": 3.859236240386963, "eval_runtime": 307.2076, "eval_samples_per_second": 1242.128, "eval_steps_per_second": 38.817, "step": 534240 }, { "epoch": 1.0, "learning_rate": 4.1248756029856594e-05, "loss": 3.7075, "step": 534528 }, { "epoch": 1.0, "learning_rate": 4.1240370082346074e-05, "loss": 3.706, "step": 535040 }, { "epoch": 1.0, "learning_rate": 4.1231984134835553e-05, "loss": 3.7192, "step": 535552 }, { "epoch": 1.0, "learning_rate": 4.122361456612876e-05, "loss": 3.7148, "step": 536064 }, { "epoch": 1.0, "learning_rate": 4.121522861861824e-05, "loss": 3.7162, "step": 536576 }, { "epoch": 1.0, "learning_rate": 4.120684267110773e-05, "loss": 3.7127, "step": 537088 }, { "epoch": 1.0, "learning_rate": 4.119845672359721e-05, "loss": 3.7048, "step": 537600 }, { "epoch": 1.0, "learning_rate": 4.119008715489042e-05, "loss": 3.7052, "step": 538112 }, { "epoch": 1.0, "learning_rate": 4.11817012073799e-05, "loss": 3.7164, "step": 538624 }, { "epoch": 1.0, "learning_rate": 4.117331525986938e-05, "loss": 3.7184, "step": 539136 }, { "epoch": 1.0, "learning_rate": 4.116492931235886e-05, "loss": 3.7116, "step": 539648 }, { "epoch": 1.0, "learning_rate": 4.115655974365207e-05, "loss": 3.7194, "step": 540160 }, { "epoch": 1.0, "learning_rate": 4.1148190174945276e-05, "loss": 3.7089, "step": 540672 }, { "epoch": 1.0, "learning_rate": 4.1139804227434756e-05, "loss": 3.7027, "step": 541184 }, { "epoch": 1.0, "learning_rate": 4.1131418279924236e-05, "loss": 3.7121, "step": 541696 }, { "epoch": 1.0, "learning_rate": 4.1123032332413716e-05, "loss": 3.6979, "step": 542208 }, { "epoch": 1.0, "learning_rate": 4.1114646384903196e-05, "loss": 3.7023, "step": 542720 }, { "epoch": 1.0, "learning_rate": 4.110626043739268e-05, "loss": 3.7004, "step": 543232 }, { "epoch": 1.0, "learning_rate": 4.109787448988216e-05, "loss": 3.7081, "step": 543744 }, { "epoch": 1.0, "learning_rate": 4.108948854237164e-05, "loss": 3.7136, "step": 544256 }, { "epoch": 1.0, "learning_rate": 4.108111897366485e-05, "loss": 3.7172, "step": 544768 }, { "epoch": 1.0, "learning_rate": 4.107273302615433e-05, "loss": 3.7067, "step": 545280 }, { "epoch": 1.0, "learning_rate": 4.106434707864381e-05, "loss": 3.6995, "step": 545792 }, { "epoch": 1.0, "learning_rate": 4.105596113113329e-05, "loss": 3.7116, "step": 546304 }, { "epoch": 1.0, "learning_rate": 4.10475915624265e-05, "loss": 3.6968, "step": 546816 }, { "epoch": 1.0, "learning_rate": 4.103920561491598e-05, "loss": 3.7038, "step": 547328 }, { "epoch": 1.0, "learning_rate": 4.103081966740546e-05, "loss": 3.6973, "step": 547840 }, { "epoch": 1.0, "learning_rate": 4.102243371989494e-05, "loss": 3.7076, "step": 548352 }, { "epoch": 1.0, "learning_rate": 4.101406415118815e-05, "loss": 3.6979, "step": 548864 }, { "epoch": 1.0, "learning_rate": 4.1005678203677637e-05, "loss": 3.702, "step": 549376 }, { "epoch": 1.01, "learning_rate": 4.0997292256167117e-05, "loss": 3.7028, "step": 549888 }, { "epoch": 1.01, "learning_rate": 4.0988906308656597e-05, "loss": 3.7108, "step": 550400 }, { "epoch": 1.01, "learning_rate": 4.0980536739949806e-05, "loss": 3.7036, "step": 550912 }, { "epoch": 1.01, "learning_rate": 4.0972150792439286e-05, "loss": 3.7012, "step": 551424 }, { "epoch": 1.01, "learning_rate": 4.0963764844928766e-05, "loss": 3.7044, "step": 551936 }, { "epoch": 1.01, "learning_rate": 4.0955395276221975e-05, "loss": 3.7002, "step": 552448 }, { "epoch": 1.01, "learning_rate": 4.0947009328711455e-05, "loss": 3.7039, "step": 552960 }, { "epoch": 1.01, "learning_rate": 4.0938623381200935e-05, "loss": 3.6856, "step": 553472 }, { "epoch": 1.01, "learning_rate": 4.0930237433690414e-05, "loss": 3.6886, "step": 553984 }, { "epoch": 1.01, "learning_rate": 4.0921867864983624e-05, "loss": 3.6969, "step": 554496 }, { "epoch": 1.01, "learning_rate": 4.0913481917473104e-05, "loss": 3.7017, "step": 555008 }, { "epoch": 1.01, "learning_rate": 4.0905095969962583e-05, "loss": 3.7013, "step": 555520 }, { "epoch": 1.01, "learning_rate": 4.089671002245207e-05, "loss": 3.6992, "step": 556032 }, { "epoch": 1.01, "learning_rate": 4.088834045374528e-05, "loss": 3.6947, "step": 556544 }, { "epoch": 1.01, "learning_rate": 4.087995450623476e-05, "loss": 3.7082, "step": 557056 }, { "epoch": 1.01, "learning_rate": 4.087156855872424e-05, "loss": 3.6973, "step": 557568 }, { "epoch": 1.01, "learning_rate": 4.086318261121372e-05, "loss": 3.7155, "step": 558080 }, { "epoch": 1.01, "learning_rate": 4.085481304250693e-05, "loss": 3.6873, "step": 558592 }, { "epoch": 1.01, "learning_rate": 4.084642709499641e-05, "loss": 3.6774, "step": 559104 }, { "epoch": 1.01, "learning_rate": 4.083804114748589e-05, "loss": 3.717, "step": 559616 }, { "epoch": 1.01, "learning_rate": 4.082965519997537e-05, "loss": 3.6964, "step": 560128 }, { "epoch": 1.01, "learning_rate": 4.082128563126858e-05, "loss": 3.696, "step": 560640 }, { "epoch": 1.01, "learning_rate": 4.081289968375806e-05, "loss": 3.6962, "step": 561152 }, { "epoch": 1.01, "learning_rate": 4.080451373624754e-05, "loss": 3.6921, "step": 561664 }, { "epoch": 1.01, "learning_rate": 4.079614416754075e-05, "loss": 3.6858, "step": 562176 }, { "epoch": 1.01, "learning_rate": 4.078775822003023e-05, "loss": 3.6967, "step": 562688 }, { "epoch": 1.01, "learning_rate": 4.077937227251971e-05, "loss": 3.6992, "step": 563200 }, { "epoch": 1.01, "learning_rate": 4.077098632500919e-05, "loss": 3.6981, "step": 563712 }, { "epoch": 1.01, "learning_rate": 4.076260037749867e-05, "loss": 3.7123, "step": 564224 }, { "epoch": 1.01, "learning_rate": 4.075421442998815e-05, "loss": 3.687, "step": 564736 }, { "epoch": 1.01, "learning_rate": 4.074582848247763e-05, "loss": 3.688, "step": 565248 }, { "epoch": 1.01, "learning_rate": 4.073745891377084e-05, "loss": 3.7074, "step": 565760 }, { "epoch": 1.01, "learning_rate": 4.072907296626032e-05, "loss": 3.6825, "step": 566272 }, { "epoch": 1.01, "learning_rate": 4.07206870187498e-05, "loss": 3.6819, "step": 566784 }, { "epoch": 1.01, "learning_rate": 4.071230107123928e-05, "loss": 3.6916, "step": 567296 }, { "epoch": 1.01, "learning_rate": 4.070393150253249e-05, "loss": 3.6942, "step": 567808 }, { "epoch": 1.01, "learning_rate": 4.069554555502198e-05, "loss": 3.682, "step": 568320 }, { "epoch": 1.01, "learning_rate": 4.068715960751146e-05, "loss": 3.6908, "step": 568832 }, { "epoch": 1.01, "learning_rate": 4.067877366000094e-05, "loss": 3.6833, "step": 569344 }, { "epoch": 1.01, "learning_rate": 4.0670404091294147e-05, "loss": 3.6968, "step": 569856 }, { "epoch": 1.01, "learning_rate": 4.0662018143783627e-05, "loss": 3.7002, "step": 570368 }, { "epoch": 1.01, "learning_rate": 4.0653632196273106e-05, "loss": 3.6927, "step": 570880 }, { "epoch": 1.01, "learning_rate": 4.064524624876258e-05, "loss": 3.7006, "step": 571392 }, { "epoch": 1.01, "learning_rate": 4.0636876680055796e-05, "loss": 3.6996, "step": 571904 }, { "epoch": 1.01, "learning_rate": 4.0628490732545275e-05, "loss": 3.7118, "step": 572416 }, { "epoch": 1.01, "learning_rate": 4.0620104785034755e-05, "loss": 3.6804, "step": 572928 }, { "epoch": 1.01, "learning_rate": 4.061171883752423e-05, "loss": 3.7058, "step": 573440 }, { "epoch": 1.01, "learning_rate": 4.0603349268817444e-05, "loss": 3.6942, "step": 573952 }, { "epoch": 1.01, "learning_rate": 4.059496332130693e-05, "loss": 3.6834, "step": 574464 }, { "epoch": 1.01, "learning_rate": 4.0586577373796404e-05, "loss": 3.7011, "step": 574976 }, { "epoch": 1.01, "learning_rate": 4.0578191426285884e-05, "loss": 3.6954, "step": 575488 }, { "epoch": 1.01, "learning_rate": 4.05698218575791e-05, "loss": 3.6973, "step": 576000 }, { "epoch": 1.01, "learning_rate": 4.056143591006858e-05, "loss": 3.7051, "step": 576512 }, { "epoch": 1.01, "learning_rate": 4.055304996255805e-05, "loss": 3.6817, "step": 577024 }, { "epoch": 1.01, "learning_rate": 4.054466401504753e-05, "loss": 3.6774, "step": 577536 }, { "epoch": 1.01, "learning_rate": 4.053629444634075e-05, "loss": 3.6876, "step": 578048 }, { "epoch": 1.01, "learning_rate": 4.052790849883023e-05, "loss": 3.6992, "step": 578560 }, { "epoch": 1.01, "learning_rate": 4.05195225513197e-05, "loss": 3.6921, "step": 579072 }, { "epoch": 1.01, "learning_rate": 4.051113660380918e-05, "loss": 3.6875, "step": 579584 }, { "epoch": 1.02, "learning_rate": 4.05027670351024e-05, "loss": 3.6854, "step": 580096 }, { "epoch": 1.02, "learning_rate": 4.049438108759188e-05, "loss": 3.6878, "step": 580608 }, { "epoch": 1.02, "learning_rate": 4.048599514008136e-05, "loss": 3.689, "step": 581120 }, { "epoch": 1.02, "learning_rate": 4.047760919257084e-05, "loss": 3.6861, "step": 581632 }, { "epoch": 1.02, "learning_rate": 4.0469239623864054e-05, "loss": 3.6951, "step": 582144 }, { "epoch": 1.02, "learning_rate": 4.046085367635353e-05, "loss": 3.7001, "step": 582656 }, { "epoch": 1.02, "learning_rate": 4.045246772884301e-05, "loss": 3.6963, "step": 583168 }, { "epoch": 1.02, "learning_rate": 4.044408178133249e-05, "loss": 3.6838, "step": 583680 }, { "epoch": 1.02, "learning_rate": 4.04357122126257e-05, "loss": 3.6931, "step": 584192 }, { "epoch": 1.02, "learning_rate": 4.0427326265115176e-05, "loss": 3.6854, "step": 584704 }, { "epoch": 1.02, "learning_rate": 4.041895669640839e-05, "loss": 3.6946, "step": 585216 }, { "epoch": 1.02, "learning_rate": 4.041057074889787e-05, "loss": 3.6942, "step": 585728 }, { "epoch": 1.02, "learning_rate": 4.040218480138735e-05, "loss": 3.6887, "step": 586240 }, { "epoch": 1.02, "learning_rate": 4.039379885387683e-05, "loss": 3.6809, "step": 586752 }, { "epoch": 1.02, "learning_rate": 4.038541290636631e-05, "loss": 3.6857, "step": 587264 }, { "epoch": 1.02, "learning_rate": 4.037702695885579e-05, "loss": 3.6853, "step": 587776 }, { "epoch": 1.02, "learning_rate": 4.036864101134527e-05, "loss": 3.6837, "step": 588288 }, { "epoch": 1.02, "learning_rate": 4.036025506383475e-05, "loss": 3.6708, "step": 588800 }, { "epoch": 1.02, "learning_rate": 4.035188549512796e-05, "loss": 3.6926, "step": 589312 }, { "epoch": 1.02, "learning_rate": 4.0343515926421177e-05, "loss": 3.6872, "step": 589824 }, { "epoch": 1.02, "learning_rate": 4.033512997891065e-05, "loss": 3.6872, "step": 590336 }, { "epoch": 1.02, "learning_rate": 4.032674403140013e-05, "loss": 3.6792, "step": 590848 }, { "epoch": 1.02, "learning_rate": 4.031835808388961e-05, "loss": 3.6955, "step": 591360 }, { "epoch": 1.02, "learning_rate": 4.030997213637909e-05, "loss": 3.6859, "step": 591872 }, { "epoch": 1.02, "learning_rate": 4.0301586188868576e-05, "loss": 3.676, "step": 592384 }, { "epoch": 1.02, "learning_rate": 4.0293200241358056e-05, "loss": 3.6995, "step": 592896 }, { "epoch": 1.02, "learning_rate": 4.0284814293847536e-05, "loss": 3.692, "step": 593408 }, { "epoch": 1.02, "learning_rate": 4.0276444725140745e-05, "loss": 3.686, "step": 593920 }, { "epoch": 1.02, "learning_rate": 4.0268058777630225e-05, "loss": 3.6934, "step": 594432 }, { "epoch": 1.02, "learning_rate": 4.0259672830119705e-05, "loss": 3.6767, "step": 594944 }, { "epoch": 1.02, "learning_rate": 4.0251286882609185e-05, "loss": 3.695, "step": 595456 }, { "epoch": 1.02, "learning_rate": 4.0242917313902394e-05, "loss": 3.6788, "step": 595968 }, { "epoch": 1.02, "learning_rate": 4.0234531366391874e-05, "loss": 3.6907, "step": 596480 }, { "epoch": 1.02, "learning_rate": 4.0226145418881354e-05, "loss": 3.6783, "step": 596992 }, { "epoch": 1.02, "learning_rate": 4.0217759471370834e-05, "loss": 3.6866, "step": 597504 }, { "epoch": 1.02, "learning_rate": 4.020938990266404e-05, "loss": 3.6827, "step": 598016 }, { "epoch": 1.02, "learning_rate": 4.020100395515353e-05, "loss": 3.6821, "step": 598528 }, { "epoch": 1.02, "learning_rate": 4.019261800764301e-05, "loss": 3.6799, "step": 599040 }, { "epoch": 1.02, "learning_rate": 4.018423206013249e-05, "loss": 3.6797, "step": 599552 }, { "epoch": 1.02, "learning_rate": 4.01758624914257e-05, "loss": 3.6865, "step": 600064 }, { "epoch": 1.02, "learning_rate": 4.016747654391518e-05, "loss": 3.692, "step": 600576 }, { "epoch": 1.02, "learning_rate": 4.015909059640466e-05, "loss": 3.6791, "step": 601088 }, { "epoch": 1.02, "learning_rate": 4.015070464889414e-05, "loss": 3.6952, "step": 601600 }, { "epoch": 1.02, "learning_rate": 4.014233508018735e-05, "loss": 3.6679, "step": 602112 }, { "epoch": 1.02, "learning_rate": 4.013394913267683e-05, "loss": 3.6947, "step": 602624 }, { "epoch": 1.02, "learning_rate": 4.012556318516631e-05, "loss": 3.6896, "step": 603136 }, { "epoch": 1.02, "learning_rate": 4.011717723765579e-05, "loss": 3.6874, "step": 603648 }, { "epoch": 1.02, "learning_rate": 4.0108807668949e-05, "loss": 3.6812, "step": 604160 }, { "epoch": 1.02, "learning_rate": 4.0100421721438484e-05, "loss": 3.6855, "step": 604672 }, { "epoch": 1.02, "learning_rate": 4.0092035773927964e-05, "loss": 3.6873, "step": 605184 }, { "epoch": 1.02, "learning_rate": 4.0083649826417444e-05, "loss": 3.6985, "step": 605696 }, { "epoch": 1.02, "learning_rate": 4.007528025771065e-05, "loss": 3.6739, "step": 606208 }, { "epoch": 1.02, "learning_rate": 4.006689431020013e-05, "loss": 3.6861, "step": 606720 }, { "epoch": 1.02, "learning_rate": 4.005850836268961e-05, "loss": 3.6795, "step": 607232 }, { "epoch": 1.02, "learning_rate": 4.005012241517909e-05, "loss": 3.6834, "step": 607744 }, { "epoch": 1.02, "learning_rate": 4.004176922527603e-05, "loss": 3.6821, "step": 608256 }, { "epoch": 1.02, "learning_rate": 4.003338327776551e-05, "loss": 3.6819, "step": 608768 }, { "epoch": 1.02, "learning_rate": 4.002499733025499e-05, "loss": 3.6899, "step": 609280 }, { "epoch": 1.02, "learning_rate": 4.001661138274447e-05, "loss": 3.6711, "step": 609792 }, { "epoch": 1.02, "learning_rate": 4.000822543523395e-05, "loss": 3.6904, "step": 610304 }, { "epoch": 1.03, "eval_loss": 3.85294246673584, "eval_runtime": 307.3127, "eval_samples_per_second": 1241.703, "eval_steps_per_second": 38.804, "step": 610560 }, { "epoch": 0.0, "learning_rate": 3.999983948772343e-05, "loss": 3.6776, "step": 610816 }, { "epoch": 0.0, "learning_rate": 3.999145354021292e-05, "loss": 3.6786, "step": 611328 }, { "epoch": 0.0, "learning_rate": 3.99830675927024e-05, "loss": 3.6858, "step": 611840 }, { "epoch": 0.0, "learning_rate": 3.997468164519188e-05, "loss": 3.6837, "step": 612352 }, { "epoch": 0.0, "learning_rate": 3.996629569768136e-05, "loss": 3.6904, "step": 612864 }, { "epoch": 0.0, "learning_rate": 3.995790975017084e-05, "loss": 3.6792, "step": 613376 }, { "epoch": 0.0, "learning_rate": 3.994952380266031e-05, "loss": 3.6769, "step": 613888 }, { "epoch": 0.0, "learning_rate": 3.9941154233953526e-05, "loss": 3.6781, "step": 614400 }, { "epoch": 0.0, "learning_rate": 3.9932768286443006e-05, "loss": 3.682, "step": 614912 }, { "epoch": 0.0, "learning_rate": 3.992438233893248e-05, "loss": 3.6912, "step": 615424 }, { "epoch": 0.0, "learning_rate": 3.991599639142196e-05, "loss": 3.6836, "step": 615936 }, { "epoch": 0.0, "learning_rate": 3.990761044391144e-05, "loss": 3.6883, "step": 616448 }, { "epoch": 0.0, "learning_rate": 3.9899240875204655e-05, "loss": 3.6765, "step": 616960 }, { "epoch": 0.0, "learning_rate": 3.9890854927694135e-05, "loss": 3.6766, "step": 617472 }, { "epoch": 0.0, "learning_rate": 3.9882468980183615e-05, "loss": 3.6833, "step": 617984 }, { "epoch": 0.0, "learning_rate": 3.9874083032673095e-05, "loss": 3.668, "step": 618496 }, { "epoch": 0.0, "learning_rate": 3.9865697085162575e-05, "loss": 3.6709, "step": 619008 }, { "epoch": 0.0, "learning_rate": 3.9857311137652055e-05, "loss": 3.6701, "step": 619520 }, { "epoch": 0.0, "learning_rate": 3.9848925190141535e-05, "loss": 3.678, "step": 620032 }, { "epoch": 0.0, "learning_rate": 3.9840539242631015e-05, "loss": 3.6817, "step": 620544 }, { "epoch": 0.0, "learning_rate": 3.9832169673924224e-05, "loss": 3.6883, "step": 621056 }, { "epoch": 0.0, "learning_rate": 3.9823783726413704e-05, "loss": 3.6786, "step": 621568 }, { "epoch": 0.0, "learning_rate": 3.9815397778903184e-05, "loss": 3.6702, "step": 622080 }, { "epoch": 0.0, "learning_rate": 3.9807011831392664e-05, "loss": 3.6785, "step": 622592 }, { "epoch": 0.0, "learning_rate": 3.979864226268587e-05, "loss": 3.6714, "step": 623104 }, { "epoch": 0.0, "learning_rate": 3.979025631517535e-05, "loss": 3.675, "step": 623616 }, { "epoch": 0.0, "learning_rate": 3.978187036766484e-05, "loss": 3.6651, "step": 624128 }, { "epoch": 0.0, "learning_rate": 3.977348442015432e-05, "loss": 3.6786, "step": 624640 }, { "epoch": 0.0, "learning_rate": 3.976511485144753e-05, "loss": 3.6733, "step": 625152 }, { "epoch": 0.0, "learning_rate": 3.975672890393701e-05, "loss": 3.6703, "step": 625664 }, { "epoch": 0.01, "learning_rate": 3.974835933523022e-05, "loss": 3.6724, "step": 626176 }, { "epoch": 0.01, "learning_rate": 3.97399733877197e-05, "loss": 3.6837, "step": 626688 }, { "epoch": 0.01, "learning_rate": 3.973158744020918e-05, "loss": 3.6727, "step": 627200 }, { "epoch": 0.01, "learning_rate": 3.972320149269866e-05, "loss": 3.6701, "step": 627712 }, { "epoch": 0.01, "learning_rate": 3.971481554518814e-05, "loss": 3.6732, "step": 628224 }, { "epoch": 0.01, "learning_rate": 3.970642959767762e-05, "loss": 3.677, "step": 628736 }, { "epoch": 0.01, "learning_rate": 3.96980436501671e-05, "loss": 3.6716, "step": 629248 }, { "epoch": 0.01, "learning_rate": 3.968965770265658e-05, "loss": 3.6581, "step": 629760 }, { "epoch": 0.01, "learning_rate": 3.968128813394979e-05, "loss": 3.6617, "step": 630272 }, { "epoch": 0.01, "learning_rate": 3.967290218643927e-05, "loss": 3.6663, "step": 630784 }, { "epoch": 0.01, "learning_rate": 3.966451623892875e-05, "loss": 3.6713, "step": 631296 }, { "epoch": 0.01, "learning_rate": 3.965613029141823e-05, "loss": 3.6723, "step": 631808 }, { "epoch": 0.01, "learning_rate": 3.964776072271144e-05, "loss": 3.6707, "step": 632320 }, { "epoch": 0.01, "learning_rate": 3.963937477520092e-05, "loss": 3.6683, "step": 632832 }, { "epoch": 0.01, "learning_rate": 3.96309888276904e-05, "loss": 3.6751, "step": 633344 }, { "epoch": 0.01, "learning_rate": 3.962260288017988e-05, "loss": 3.6674, "step": 633856 }, { "epoch": 0.01, "learning_rate": 3.961423331147309e-05, "loss": 3.6827, "step": 634368 }, { "epoch": 0.01, "learning_rate": 3.960584736396257e-05, "loss": 3.6635, "step": 634880 }, { "epoch": 0.01, "learning_rate": 3.959746141645205e-05, "loss": 3.6463, "step": 635392 }, { "epoch": 0.01, "learning_rate": 3.958907546894153e-05, "loss": 3.6884, "step": 635904 }, { "epoch": 0.01, "learning_rate": 3.958070590023475e-05, "loss": 3.6682, "step": 636416 }, { "epoch": 0.01, "learning_rate": 3.957231995272423e-05, "loss": 3.6695, "step": 636928 }, { "epoch": 0.01, "learning_rate": 3.956393400521371e-05, "loss": 3.667, "step": 637440 }, { "epoch": 0.01, "learning_rate": 3.955554805770319e-05, "loss": 3.6629, "step": 637952 }, { "epoch": 0.01, "learning_rate": 3.9547178488996396e-05, "loss": 3.6566, "step": 638464 }, { "epoch": 0.01, "learning_rate": 3.9538792541485876e-05, "loss": 3.6657, "step": 638976 }, { "epoch": 0.01, "learning_rate": 3.9530406593975356e-05, "loss": 3.6737, "step": 639488 }, { "epoch": 0.01, "learning_rate": 3.9522020646464836e-05, "loss": 3.6713, "step": 640000 }, { "epoch": 0.01, "learning_rate": 3.9513634698954316e-05, "loss": 3.6834, "step": 640512 }, { "epoch": 0.01, "learning_rate": 3.950524875144379e-05, "loss": 3.6581, "step": 641024 }, { "epoch": 0.01, "learning_rate": 3.949686280393327e-05, "loss": 3.6576, "step": 641536 }, { "epoch": 0.01, "learning_rate": 3.948847685642275e-05, "loss": 3.6811, "step": 642048 }, { "epoch": 0.01, "learning_rate": 3.9480107287715965e-05, "loss": 3.6498, "step": 642560 }, { "epoch": 0.01, "learning_rate": 3.9471721340205445e-05, "loss": 3.6526, "step": 643072 }, { "epoch": 0.01, "learning_rate": 3.9463335392694925e-05, "loss": 3.6633, "step": 643584 }, { "epoch": 0.01, "learning_rate": 3.945496582398814e-05, "loss": 3.6654, "step": 644096 }, { "epoch": 0.01, "learning_rate": 3.944657987647762e-05, "loss": 3.6555, "step": 644608 }, { "epoch": 0.01, "learning_rate": 3.9438193928967094e-05, "loss": 3.6606, "step": 645120 }, { "epoch": 0.01, "learning_rate": 3.9429807981456573e-05, "loss": 3.6555, "step": 645632 }, { "epoch": 0.01, "learning_rate": 3.942143841274979e-05, "loss": 3.6713, "step": 646144 }, { "epoch": 0.01, "learning_rate": 3.941305246523926e-05, "loss": 3.6683, "step": 646656 }, { "epoch": 0.01, "learning_rate": 3.940466651772874e-05, "loss": 3.667, "step": 647168 }, { "epoch": 0.01, "learning_rate": 3.939628057021822e-05, "loss": 3.6719, "step": 647680 }, { "epoch": 0.01, "learning_rate": 3.938791100151144e-05, "loss": 3.6718, "step": 648192 }, { "epoch": 0.01, "learning_rate": 3.937954143280465e-05, "loss": 3.6815, "step": 648704 }, { "epoch": 0.01, "learning_rate": 3.9371155485294134e-05, "loss": 3.6542, "step": 649216 }, { "epoch": 0.01, "learning_rate": 3.9362769537783614e-05, "loss": 3.6796, "step": 649728 }, { "epoch": 0.01, "learning_rate": 3.935438359027309e-05, "loss": 3.6612, "step": 650240 }, { "epoch": 0.01, "learning_rate": 3.934599764276257e-05, "loss": 3.6559, "step": 650752 }, { "epoch": 0.01, "learning_rate": 3.933761169525205e-05, "loss": 3.6732, "step": 651264 }, { "epoch": 0.01, "learning_rate": 3.932922574774153e-05, "loss": 3.668, "step": 651776 }, { "epoch": 0.01, "learning_rate": 3.932083980023101e-05, "loss": 3.6701, "step": 652288 }, { "epoch": 0.01, "learning_rate": 3.9312470231524216e-05, "loss": 3.676, "step": 652800 }, { "epoch": 0.01, "learning_rate": 3.9304084284013696e-05, "loss": 3.6538, "step": 653312 }, { "epoch": 0.01, "learning_rate": 3.9295698336503176e-05, "loss": 3.6476, "step": 653824 }, { "epoch": 0.01, "learning_rate": 3.9287312388992656e-05, "loss": 3.6606, "step": 654336 }, { "epoch": 0.01, "learning_rate": 3.927894282028587e-05, "loss": 3.6703, "step": 654848 }, { "epoch": 0.01, "learning_rate": 3.927055687277535e-05, "loss": 3.6651, "step": 655360 }, { "epoch": 0.01, "learning_rate": 3.926217092526483e-05, "loss": 3.6615, "step": 655872 }, { "epoch": 0.02, "learning_rate": 3.925378497775431e-05, "loss": 3.6571, "step": 656384 }, { "epoch": 0.02, "learning_rate": 3.924539903024379e-05, "loss": 3.658, "step": 656896 }, { "epoch": 0.02, "learning_rate": 3.923701308273327e-05, "loss": 3.6627, "step": 657408 }, { "epoch": 0.02, "learning_rate": 3.922862713522275e-05, "loss": 3.6572, "step": 657920 }, { "epoch": 0.02, "learning_rate": 3.922024118771223e-05, "loss": 3.6663, "step": 658432 }, { "epoch": 0.02, "learning_rate": 3.921187161900544e-05, "loss": 3.671, "step": 658944 }, { "epoch": 0.02, "learning_rate": 3.920350205029865e-05, "loss": 3.6696, "step": 659456 }, { "epoch": 0.02, "learning_rate": 3.919511610278813e-05, "loss": 3.6584, "step": 659968 }, { "epoch": 0.02, "learning_rate": 3.918673015527761e-05, "loss": 3.663, "step": 660480 }, { "epoch": 0.02, "learning_rate": 3.917834420776709e-05, "loss": 3.6588, "step": 660992 }, { "epoch": 0.02, "learning_rate": 3.9169974639060306e-05, "loss": 3.6659, "step": 661504 }, { "epoch": 0.02, "learning_rate": 3.9161588691549786e-05, "loss": 3.6668, "step": 662016 }, { "epoch": 0.02, "learning_rate": 3.9153202744039265e-05, "loss": 3.6626, "step": 662528 }, { "epoch": 0.02, "learning_rate": 3.9144816796528745e-05, "loss": 3.6589, "step": 663040 }, { "epoch": 0.02, "learning_rate": 3.9136447227821955e-05, "loss": 3.6512, "step": 663552 }, { "epoch": 0.02, "learning_rate": 3.9128061280311434e-05, "loss": 3.6606, "step": 664064 }, { "epoch": 0.02, "learning_rate": 3.9119675332800914e-05, "loss": 3.6555, "step": 664576 }, { "epoch": 0.02, "learning_rate": 3.9111289385290394e-05, "loss": 3.6414, "step": 665088 }, { "epoch": 0.02, "learning_rate": 3.9102903437779874e-05, "loss": 3.6682, "step": 665600 }, { "epoch": 0.02, "learning_rate": 3.9094533869073083e-05, "loss": 3.6595, "step": 666112 }, { "epoch": 0.02, "learning_rate": 3.9086147921562563e-05, "loss": 3.6614, "step": 666624 }, { "epoch": 0.02, "learning_rate": 3.907776197405204e-05, "loss": 3.6497, "step": 667136 }, { "epoch": 0.02, "learning_rate": 3.906937602654152e-05, "loss": 3.6658, "step": 667648 }, { "epoch": 0.02, "learning_rate": 3.906099007903101e-05, "loss": 3.6616, "step": 668160 }, { "epoch": 0.02, "learning_rate": 3.905260413152049e-05, "loss": 3.6494, "step": 668672 }, { "epoch": 0.02, "learning_rate": 3.904421818400997e-05, "loss": 3.6733, "step": 669184 }, { "epoch": 0.02, "learning_rate": 3.903583223649945e-05, "loss": 3.6669, "step": 669696 }, { "epoch": 0.02, "learning_rate": 3.902746266779266e-05, "loss": 3.6591, "step": 670208 }, { "epoch": 0.02, "learning_rate": 3.901907672028214e-05, "loss": 3.6644, "step": 670720 }, { "epoch": 0.02, "learning_rate": 3.901069077277162e-05, "loss": 3.6474, "step": 671232 }, { "epoch": 0.02, "learning_rate": 3.90023048252611e-05, "loss": 3.6662, "step": 671744 }, { "epoch": 0.02, "learning_rate": 3.899395163535804e-05, "loss": 3.6554, "step": 672256 }, { "epoch": 0.02, "learning_rate": 3.898556568784752e-05, "loss": 3.6594, "step": 672768 }, { "epoch": 0.02, "learning_rate": 3.8977179740337e-05, "loss": 3.6521, "step": 673280 }, { "epoch": 0.02, "learning_rate": 3.896879379282648e-05, "loss": 3.6632, "step": 673792 }, { "epoch": 0.02, "learning_rate": 3.8960407845315964e-05, "loss": 3.6564, "step": 674304 }, { "epoch": 0.02, "learning_rate": 3.8952021897805444e-05, "loss": 3.653, "step": 674816 }, { "epoch": 0.02, "learning_rate": 3.8943635950294924e-05, "loss": 3.6529, "step": 675328 }, { "epoch": 0.02, "learning_rate": 3.89352500027844e-05, "loss": 3.6574, "step": 675840 }, { "epoch": 0.02, "learning_rate": 3.892688043407761e-05, "loss": 3.6553, "step": 676352 }, { "epoch": 0.02, "learning_rate": 3.891849448656709e-05, "loss": 3.6645, "step": 676864 }, { "epoch": 0.02, "learning_rate": 3.891010853905657e-05, "loss": 3.6538, "step": 677376 }, { "epoch": 0.02, "learning_rate": 3.8901722591546046e-05, "loss": 3.6709, "step": 677888 }, { "epoch": 0.02, "learning_rate": 3.889335302283926e-05, "loss": 3.6407, "step": 678400 }, { "epoch": 0.02, "learning_rate": 3.888496707532874e-05, "loss": 3.6665, "step": 678912 }, { "epoch": 0.02, "learning_rate": 3.887658112781822e-05, "loss": 3.6649, "step": 679424 }, { "epoch": 0.02, "learning_rate": 3.88681951803077e-05, "loss": 3.6634, "step": 679936 }, { "epoch": 0.02, "learning_rate": 3.885982561160092e-05, "loss": 3.6532, "step": 680448 }, { "epoch": 0.02, "learning_rate": 3.88514396640904e-05, "loss": 3.6565, "step": 680960 }, { "epoch": 0.02, "learning_rate": 3.884305371657987e-05, "loss": 3.6568, "step": 681472 }, { "epoch": 0.02, "learning_rate": 3.883466776906935e-05, "loss": 3.6767, "step": 681984 }, { "epoch": 0.02, "learning_rate": 3.8826298200362566e-05, "loss": 3.6469, "step": 682496 }, { "epoch": 0.02, "learning_rate": 3.8817912252852046e-05, "loss": 3.6574, "step": 683008 }, { "epoch": 0.02, "learning_rate": 3.880952630534152e-05, "loss": 3.6526, "step": 683520 }, { "epoch": 0.02, "learning_rate": 3.8801140357831e-05, "loss": 3.6602, "step": 684032 }, { "epoch": 0.02, "learning_rate": 3.8792787167927944e-05, "loss": 3.6519, "step": 684544 }, { "epoch": 0.02, "learning_rate": 3.8784401220417424e-05, "loss": 3.6587, "step": 685056 }, { "epoch": 0.02, "learning_rate": 3.8776015272906904e-05, "loss": 3.6599, "step": 685568 }, { "epoch": 0.02, "learning_rate": 3.8767629325396384e-05, "loss": 3.6525, "step": 686080 }, { "epoch": 0.02, "learning_rate": 3.875924337788587e-05, "loss": 3.6599, "step": 686592 }, { "epoch": 0.03, "eval_loss": 3.848494052886963, "eval_runtime": 317.0125, "eval_samples_per_second": 1203.71, "eval_steps_per_second": 37.617, "step": 686880 }, { "epoch": 1.0, "learning_rate": 3.875087380917908e-05, "loss": 3.6479, "step": 687104 }, { "epoch": 1.0, "learning_rate": 3.874248786166856e-05, "loss": 3.6495, "step": 687616 }, { "epoch": 1.0, "learning_rate": 3.873410191415804e-05, "loss": 3.6616, "step": 688128 }, { "epoch": 1.0, "learning_rate": 3.872571596664752e-05, "loss": 3.6583, "step": 688640 }, { "epoch": 1.0, "learning_rate": 3.871733001913699e-05, "loss": 3.6626, "step": 689152 }, { "epoch": 1.0, "learning_rate": 3.870896045043021e-05, "loss": 3.6529, "step": 689664 }, { "epoch": 1.0, "learning_rate": 3.870057450291969e-05, "loss": 3.65, "step": 690176 }, { "epoch": 1.0, "learning_rate": 3.869218855540916e-05, "loss": 3.6543, "step": 690688 }, { "epoch": 1.0, "learning_rate": 3.868380260789864e-05, "loss": 3.6534, "step": 691200 }, { "epoch": 1.0, "learning_rate": 3.867541666038812e-05, "loss": 3.6644, "step": 691712 }, { "epoch": 1.0, "learning_rate": 3.866703071287761e-05, "loss": 3.6574, "step": 692224 }, { "epoch": 1.0, "learning_rate": 3.865864476536709e-05, "loss": 3.6583, "step": 692736 }, { "epoch": 1.0, "learning_rate": 3.86502751966603e-05, "loss": 3.6598, "step": 693248 }, { "epoch": 1.0, "learning_rate": 3.864188924914978e-05, "loss": 3.6421, "step": 693760 }, { "epoch": 1.0, "learning_rate": 3.863350330163926e-05, "loss": 3.6576, "step": 694272 }, { "epoch": 1.0, "learning_rate": 3.862511735412874e-05, "loss": 3.6432, "step": 694784 }, { "epoch": 1.0, "learning_rate": 3.861673140661822e-05, "loss": 3.6435, "step": 695296 }, { "epoch": 1.0, "learning_rate": 3.86083454591077e-05, "loss": 3.6465, "step": 695808 }, { "epoch": 1.0, "learning_rate": 3.859995951159718e-05, "loss": 3.6481, "step": 696320 }, { "epoch": 1.0, "learning_rate": 3.859157356408666e-05, "loss": 3.6555, "step": 696832 }, { "epoch": 1.0, "learning_rate": 3.858320399537987e-05, "loss": 3.6653, "step": 697344 }, { "epoch": 1.0, "learning_rate": 3.857481804786935e-05, "loss": 3.6576, "step": 697856 }, { "epoch": 1.0, "learning_rate": 3.8566432100358827e-05, "loss": 3.6446, "step": 698368 }, { "epoch": 1.0, "learning_rate": 3.8558046152848307e-05, "loss": 3.6501, "step": 698880 }, { "epoch": 1.0, "learning_rate": 3.854967658414152e-05, "loss": 3.6448, "step": 699392 }, { "epoch": 1.0, "learning_rate": 3.8541290636631e-05, "loss": 3.6475, "step": 699904 }, { "epoch": 1.0, "learning_rate": 3.853290468912048e-05, "loss": 3.6414, "step": 700416 }, { "epoch": 1.0, "learning_rate": 3.852451874160996e-05, "loss": 3.6563, "step": 700928 }, { "epoch": 1.0, "learning_rate": 3.851614917290317e-05, "loss": 3.6424, "step": 701440 }, { "epoch": 1.0, "learning_rate": 3.850776322539265e-05, "loss": 3.6451, "step": 701952 }, { "epoch": 1.01, "learning_rate": 3.849939365668586e-05, "loss": 3.6424, "step": 702464 }, { "epoch": 1.01, "learning_rate": 3.849100770917534e-05, "loss": 3.6573, "step": 702976 }, { "epoch": 1.01, "learning_rate": 3.848262176166482e-05, "loss": 3.6488, "step": 703488 }, { "epoch": 1.01, "learning_rate": 3.84742358141543e-05, "loss": 3.6458, "step": 704000 }, { "epoch": 1.01, "learning_rate": 3.846584986664378e-05, "loss": 3.6478, "step": 704512 }, { "epoch": 1.01, "learning_rate": 3.845746391913326e-05, "loss": 3.6472, "step": 705024 }, { "epoch": 1.01, "learning_rate": 3.844907797162274e-05, "loss": 3.6501, "step": 705536 }, { "epoch": 1.01, "learning_rate": 3.844069202411223e-05, "loss": 3.635, "step": 706048 }, { "epoch": 1.01, "learning_rate": 3.8432322455405436e-05, "loss": 3.6353, "step": 706560 }, { "epoch": 1.01, "learning_rate": 3.8423952886698645e-05, "loss": 3.6397, "step": 707072 }, { "epoch": 1.01, "learning_rate": 3.8415566939188125e-05, "loss": 3.6426, "step": 707584 }, { "epoch": 1.01, "learning_rate": 3.8407180991677605e-05, "loss": 3.6457, "step": 708096 }, { "epoch": 1.01, "learning_rate": 3.8398795044167085e-05, "loss": 3.6452, "step": 708608 }, { "epoch": 1.01, "learning_rate": 3.8390409096656565e-05, "loss": 3.6479, "step": 709120 }, { "epoch": 1.01, "learning_rate": 3.8382023149146045e-05, "loss": 3.6439, "step": 709632 }, { "epoch": 1.01, "learning_rate": 3.8373637201635525e-05, "loss": 3.6468, "step": 710144 }, { "epoch": 1.01, "learning_rate": 3.8365251254125e-05, "loss": 3.6553, "step": 710656 }, { "epoch": 1.01, "learning_rate": 3.8356881685418214e-05, "loss": 3.6399, "step": 711168 }, { "epoch": 1.01, "learning_rate": 3.8348495737907694e-05, "loss": 3.6215, "step": 711680 }, { "epoch": 1.01, "learning_rate": 3.834010979039718e-05, "loss": 3.6594, "step": 712192 }, { "epoch": 1.01, "learning_rate": 3.8331723842886654e-05, "loss": 3.6421, "step": 712704 }, { "epoch": 1.01, "learning_rate": 3.832335427417987e-05, "loss": 3.6447, "step": 713216 }, { "epoch": 1.01, "learning_rate": 3.831496832666935e-05, "loss": 3.6455, "step": 713728 }, { "epoch": 1.01, "learning_rate": 3.830658237915883e-05, "loss": 3.6364, "step": 714240 }, { "epoch": 1.01, "learning_rate": 3.829821281045204e-05, "loss": 3.6315, "step": 714752 }, { "epoch": 1.01, "learning_rate": 3.828982686294152e-05, "loss": 3.6385, "step": 715264 }, { "epoch": 1.01, "learning_rate": 3.8281440915431e-05, "loss": 3.6507, "step": 715776 }, { "epoch": 1.01, "learning_rate": 3.827305496792047e-05, "loss": 3.6419, "step": 716288 }, { "epoch": 1.01, "learning_rate": 3.826466902040995e-05, "loss": 3.6562, "step": 716800 }, { "epoch": 1.01, "learning_rate": 3.825628307289943e-05, "loss": 3.6357, "step": 717312 }, { "epoch": 1.01, "learning_rate": 3.824789712538892e-05, "loss": 3.629, "step": 717824 }, { "epoch": 1.01, "learning_rate": 3.82395111778784e-05, "loss": 3.6545, "step": 718336 }, { "epoch": 1.01, "learning_rate": 3.823114160917161e-05, "loss": 3.6298, "step": 718848 }, { "epoch": 1.01, "learning_rate": 3.822275566166109e-05, "loss": 3.6267, "step": 719360 }, { "epoch": 1.01, "learning_rate": 3.821436971415057e-05, "loss": 3.6401, "step": 719872 }, { "epoch": 1.01, "learning_rate": 3.8206000145443776e-05, "loss": 3.6377, "step": 720384 }, { "epoch": 1.01, "learning_rate": 3.8197614197933256e-05, "loss": 3.6317, "step": 720896 }, { "epoch": 1.01, "learning_rate": 3.8189228250422736e-05, "loss": 3.6351, "step": 721408 }, { "epoch": 1.01, "learning_rate": 3.8180842302912216e-05, "loss": 3.6303, "step": 721920 }, { "epoch": 1.01, "learning_rate": 3.8172472734205425e-05, "loss": 3.6438, "step": 722432 }, { "epoch": 1.01, "learning_rate": 3.8164086786694905e-05, "loss": 3.6451, "step": 722944 }, { "epoch": 1.01, "learning_rate": 3.8155700839184385e-05, "loss": 3.6419, "step": 723456 }, { "epoch": 1.01, "learning_rate": 3.814731489167387e-05, "loss": 3.6458, "step": 723968 }, { "epoch": 1.01, "learning_rate": 3.813894532296708e-05, "loss": 3.6451, "step": 724480 }, { "epoch": 1.01, "learning_rate": 3.81305757542603e-05, "loss": 3.655, "step": 724992 }, { "epoch": 1.01, "learning_rate": 3.812218980674977e-05, "loss": 3.6325, "step": 725504 }, { "epoch": 1.01, "learning_rate": 3.811380385923925e-05, "loss": 3.6546, "step": 726016 }, { "epoch": 1.01, "learning_rate": 3.810541791172873e-05, "loss": 3.6342, "step": 726528 }, { "epoch": 1.01, "learning_rate": 3.809703196421821e-05, "loss": 3.635, "step": 727040 }, { "epoch": 1.01, "learning_rate": 3.808864601670769e-05, "loss": 3.643, "step": 727552 }, { "epoch": 1.01, "learning_rate": 3.808026006919717e-05, "loss": 3.6447, "step": 728064 }, { "epoch": 1.01, "learning_rate": 3.807187412168665e-05, "loss": 3.6464, "step": 728576 }, { "epoch": 1.01, "learning_rate": 3.806350455297986e-05, "loss": 3.6504, "step": 729088 }, { "epoch": 1.01, "learning_rate": 3.805511860546934e-05, "loss": 3.6281, "step": 729600 }, { "epoch": 1.01, "learning_rate": 3.8046732657958826e-05, "loss": 3.6262, "step": 730112 }, { "epoch": 1.01, "learning_rate": 3.8038363089252035e-05, "loss": 3.6359, "step": 730624 }, { "epoch": 1.01, "learning_rate": 3.8029977141741515e-05, "loss": 3.6471, "step": 731136 }, { "epoch": 1.01, "learning_rate": 3.8021591194230995e-05, "loss": 3.6363, "step": 731648 }, { "epoch": 1.01, "learning_rate": 3.8013205246720475e-05, "loss": 3.6371, "step": 732160 }, { "epoch": 1.02, "learning_rate": 3.8004819299209955e-05, "loss": 3.6374, "step": 732672 }, { "epoch": 1.02, "learning_rate": 3.7996449730503164e-05, "loss": 3.635, "step": 733184 }, { "epoch": 1.02, "learning_rate": 3.7988063782992644e-05, "loss": 3.6347, "step": 733696 }, { "epoch": 1.02, "learning_rate": 3.7979677835482124e-05, "loss": 3.6336, "step": 734208 }, { "epoch": 1.02, "learning_rate": 3.7971291887971604e-05, "loss": 3.6417, "step": 734720 }, { "epoch": 1.02, "learning_rate": 3.7962905940461084e-05, "loss": 3.6458, "step": 735232 }, { "epoch": 1.02, "learning_rate": 3.795453637175429e-05, "loss": 3.6486, "step": 735744 }, { "epoch": 1.02, "learning_rate": 3.794615042424377e-05, "loss": 3.6337, "step": 736256 }, { "epoch": 1.02, "learning_rate": 3.793776447673326e-05, "loss": 3.6355, "step": 736768 }, { "epoch": 1.02, "learning_rate": 3.792937852922274e-05, "loss": 3.6376, "step": 737280 }, { "epoch": 1.02, "learning_rate": 3.792099258171222e-05, "loss": 3.64, "step": 737792 }, { "epoch": 1.02, "learning_rate": 3.791262301300543e-05, "loss": 3.6424, "step": 738304 }, { "epoch": 1.02, "learning_rate": 3.790423706549491e-05, "loss": 3.6395, "step": 738816 }, { "epoch": 1.02, "learning_rate": 3.789585111798439e-05, "loss": 3.6331, "step": 739328 }, { "epoch": 1.02, "learning_rate": 3.788746517047387e-05, "loss": 3.6263, "step": 739840 }, { "epoch": 1.02, "learning_rate": 3.787907922296335e-05, "loss": 3.6394, "step": 740352 }, { "epoch": 1.02, "learning_rate": 3.787069327545283e-05, "loss": 3.6302, "step": 740864 }, { "epoch": 1.02, "learning_rate": 3.786230732794231e-05, "loss": 3.6149, "step": 741376 }, { "epoch": 1.02, "learning_rate": 3.785393775923552e-05, "loss": 3.6373, "step": 741888 }, { "epoch": 1.02, "learning_rate": 3.7845568190528726e-05, "loss": 3.6439, "step": 742400 }, { "epoch": 1.02, "learning_rate": 3.783718224301821e-05, "loss": 3.6334, "step": 742912 }, { "epoch": 1.02, "learning_rate": 3.782879629550769e-05, "loss": 3.6272, "step": 743424 }, { "epoch": 1.02, "learning_rate": 3.782041034799717e-05, "loss": 3.637, "step": 743936 }, { "epoch": 1.02, "learning_rate": 3.781202440048665e-05, "loss": 3.6369, "step": 744448 }, { "epoch": 1.02, "learning_rate": 3.780363845297613e-05, "loss": 3.6264, "step": 744960 }, { "epoch": 1.02, "learning_rate": 3.7795252505465606e-05, "loss": 3.6499, "step": 745472 }, { "epoch": 1.02, "learning_rate": 3.778688293675882e-05, "loss": 3.6438, "step": 745984 }, { "epoch": 1.02, "learning_rate": 3.77784969892483e-05, "loss": 3.6324, "step": 746496 }, { "epoch": 1.02, "learning_rate": 3.777011104173778e-05, "loss": 3.638, "step": 747008 }, { "epoch": 1.02, "learning_rate": 3.7761725094227255e-05, "loss": 3.6271, "step": 747520 }, { "epoch": 1.02, "learning_rate": 3.7753339146716735e-05, "loss": 3.6397, "step": 748032 }, { "epoch": 1.02, "learning_rate": 3.774496957800995e-05, "loss": 3.632, "step": 748544 }, { "epoch": 1.02, "learning_rate": 3.773658363049943e-05, "loss": 3.6342, "step": 749056 }, { "epoch": 1.02, "learning_rate": 3.772819768298891e-05, "loss": 3.6286, "step": 749568 }, { "epoch": 1.02, "learning_rate": 3.771981173547839e-05, "loss": 3.6391, "step": 750080 }, { "epoch": 1.02, "learning_rate": 3.771142578796787e-05, "loss": 3.6342, "step": 750592 }, { "epoch": 1.02, "learning_rate": 3.770303984045735e-05, "loss": 3.6306, "step": 751104 }, { "epoch": 1.02, "learning_rate": 3.769465389294683e-05, "loss": 3.6277, "step": 751616 }, { "epoch": 1.02, "learning_rate": 3.768626794543631e-05, "loss": 3.6339, "step": 752128 }, { "epoch": 1.02, "learning_rate": 3.767789837672952e-05, "loss": 3.63, "step": 752640 }, { "epoch": 1.02, "learning_rate": 3.766952880802273e-05, "loss": 3.6409, "step": 753152 }, { "epoch": 1.02, "learning_rate": 3.766114286051221e-05, "loss": 3.6329, "step": 753664 }, { "epoch": 1.02, "learning_rate": 3.765275691300169e-05, "loss": 3.6442, "step": 754176 }, { "epoch": 1.02, "learning_rate": 3.764437096549117e-05, "loss": 3.6174, "step": 754688 }, { "epoch": 1.02, "learning_rate": 3.763598501798065e-05, "loss": 3.6453, "step": 755200 }, { "epoch": 1.02, "learning_rate": 3.7627599070470135e-05, "loss": 3.6379, "step": 755712 }, { "epoch": 1.02, "learning_rate": 3.7619213122959615e-05, "loss": 3.6379, "step": 756224 }, { "epoch": 1.02, "learning_rate": 3.7610827175449095e-05, "loss": 3.6318, "step": 756736 }, { "epoch": 1.02, "learning_rate": 3.7602457606742304e-05, "loss": 3.6311, "step": 757248 }, { "epoch": 1.02, "learning_rate": 3.7594071659231784e-05, "loss": 3.6339, "step": 757760 }, { "epoch": 1.02, "learning_rate": 3.7585685711721264e-05, "loss": 3.655, "step": 758272 }, { "epoch": 1.02, "learning_rate": 3.7577299764210744e-05, "loss": 3.621, "step": 758784 }, { "epoch": 1.02, "learning_rate": 3.756893019550395e-05, "loss": 3.6364, "step": 759296 }, { "epoch": 1.02, "learning_rate": 3.756054424799343e-05, "loss": 3.6297, "step": 759808 }, { "epoch": 1.02, "learning_rate": 3.755215830048291e-05, "loss": 3.634, "step": 760320 }, { "epoch": 1.02, "learning_rate": 3.754378873177612e-05, "loss": 3.629, "step": 760832 }, { "epoch": 1.02, "learning_rate": 3.75354027842656e-05, "loss": 3.636, "step": 761344 }, { "epoch": 1.02, "learning_rate": 3.752701683675509e-05, "loss": 3.6347, "step": 761856 }, { "epoch": 1.02, "learning_rate": 3.751863088924457e-05, "loss": 3.6328, "step": 762368 }, { "epoch": 1.02, "learning_rate": 3.751024494173405e-05, "loss": 3.6327, "step": 762880 }, { "epoch": 1.03, "eval_loss": 3.8461601734161377, "eval_runtime": 314.3363, "eval_samples_per_second": 1213.958, "eval_steps_per_second": 37.937, "step": 763200 }, { "epoch": 0.0, "learning_rate": 3.750185899422353e-05, "loss": 3.6247, "step": 763392 }, { "epoch": 0.0, "learning_rate": 3.749347304671301e-05, "loss": 3.6254, "step": 763904 }, { "epoch": 0.0, "learning_rate": 3.748508709920249e-05, "loss": 3.636, "step": 764416 }, { "epoch": 0.0, "learning_rate": 3.747670115169197e-05, "loss": 3.6393, "step": 764928 }, { "epoch": 0.0, "learning_rate": 3.746831520418144e-05, "loss": 3.6389, "step": 765440 }, { "epoch": 0.0, "learning_rate": 3.745992925667092e-05, "loss": 3.6306, "step": 765952 }, { "epoch": 0.0, "learning_rate": 3.745155968796414e-05, "loss": 3.6272, "step": 766464 }, { "epoch": 0.0, "learning_rate": 3.744317374045362e-05, "loss": 3.6274, "step": 766976 }, { "epoch": 0.0, "learning_rate": 3.743478779294309e-05, "loss": 3.6305, "step": 767488 }, { "epoch": 0.0, "learning_rate": 3.742640184543257e-05, "loss": 3.6406, "step": 768000 }, { "epoch": 0.0, "learning_rate": 3.741801589792206e-05, "loss": 3.6333, "step": 768512 }, { "epoch": 0.0, "learning_rate": 3.740962995041154e-05, "loss": 3.6363, "step": 769024 }, { "epoch": 0.0, "learning_rate": 3.7401260381704747e-05, "loss": 3.6393, "step": 769536 }, { "epoch": 0.0, "learning_rate": 3.7392874434194226e-05, "loss": 3.6162, "step": 770048 }, { "epoch": 0.0, "learning_rate": 3.7384488486683706e-05, "loss": 3.6378, "step": 770560 }, { "epoch": 0.0, "learning_rate": 3.7376102539173186e-05, "loss": 3.6155, "step": 771072 }, { "epoch": 0.0, "learning_rate": 3.7367732970466395e-05, "loss": 3.6215, "step": 771584 }, { "epoch": 0.0, "learning_rate": 3.7359347022955875e-05, "loss": 3.6229, "step": 772096 }, { "epoch": 0.0, "learning_rate": 3.7350961075445355e-05, "loss": 3.6242, "step": 772608 }, { "epoch": 0.0, "learning_rate": 3.7342575127934835e-05, "loss": 3.6325, "step": 773120 }, { "epoch": 0.0, "learning_rate": 3.7334189180424315e-05, "loss": 3.6395, "step": 773632 }, { "epoch": 0.0, "learning_rate": 3.7325803232913795e-05, "loss": 3.6342, "step": 774144 }, { "epoch": 0.0, "learning_rate": 3.7317417285403275e-05, "loss": 3.6227, "step": 774656 }, { "epoch": 0.0, "learning_rate": 3.7309031337892755e-05, "loss": 3.6219, "step": 775168 }, { "epoch": 0.0, "learning_rate": 3.730066176918597e-05, "loss": 3.6294, "step": 775680 }, { "epoch": 0.0, "learning_rate": 3.729227582167545e-05, "loss": 3.6228, "step": 776192 }, { "epoch": 0.0, "learning_rate": 3.728388987416493e-05, "loss": 3.6193, "step": 776704 }, { "epoch": 0.0, "learning_rate": 3.727552030545814e-05, "loss": 3.6335, "step": 777216 }, { "epoch": 0.0, "learning_rate": 3.726713435794762e-05, "loss": 3.6154, "step": 777728 }, { "epoch": 0.0, "learning_rate": 3.72587484104371e-05, "loss": 3.6267, "step": 778240 }, { "epoch": 0.01, "learning_rate": 3.725036246292658e-05, "loss": 3.6185, "step": 778752 }, { "epoch": 0.01, "learning_rate": 3.724197651541606e-05, "loss": 3.6318, "step": 779264 }, { "epoch": 0.01, "learning_rate": 3.723359056790554e-05, "loss": 3.6302, "step": 779776 }, { "epoch": 0.01, "learning_rate": 3.722520462039502e-05, "loss": 3.6206, "step": 780288 }, { "epoch": 0.01, "learning_rate": 3.72168186728845e-05, "loss": 3.6269, "step": 780800 }, { "epoch": 0.01, "learning_rate": 3.720844910417771e-05, "loss": 3.619, "step": 781312 }, { "epoch": 0.01, "learning_rate": 3.720006315666719e-05, "loss": 3.6286, "step": 781824 }, { "epoch": 0.01, "learning_rate": 3.7191677209156676e-05, "loss": 3.6173, "step": 782336 }, { "epoch": 0.01, "learning_rate": 3.7183291261646155e-05, "loss": 3.61, "step": 782848 }, { "epoch": 0.01, "learning_rate": 3.7174938071743094e-05, "loss": 3.6161, "step": 783360 }, { "epoch": 0.01, "learning_rate": 3.7166552124232574e-05, "loss": 3.6237, "step": 783872 }, { "epoch": 0.01, "learning_rate": 3.7158166176722054e-05, "loss": 3.6194, "step": 784384 }, { "epoch": 0.01, "learning_rate": 3.7149780229211534e-05, "loss": 3.6194, "step": 784896 }, { "epoch": 0.01, "learning_rate": 3.7141394281701014e-05, "loss": 3.6238, "step": 785408 }, { "epoch": 0.01, "learning_rate": 3.7133008334190493e-05, "loss": 3.6226, "step": 785920 }, { "epoch": 0.01, "learning_rate": 3.7124622386679973e-05, "loss": 3.6253, "step": 786432 }, { "epoch": 0.01, "learning_rate": 3.7116236439169453e-05, "loss": 3.6364, "step": 786944 }, { "epoch": 0.01, "learning_rate": 3.710786687046266e-05, "loss": 3.6175, "step": 787456 }, { "epoch": 0.01, "learning_rate": 3.709948092295214e-05, "loss": 3.5965, "step": 787968 }, { "epoch": 0.01, "learning_rate": 3.709109497544163e-05, "loss": 3.6374, "step": 788480 }, { "epoch": 0.01, "learning_rate": 3.70827090279311e-05, "loss": 3.6188, "step": 788992 }, { "epoch": 0.01, "learning_rate": 3.707433945922432e-05, "loss": 3.6239, "step": 789504 }, { "epoch": 0.01, "learning_rate": 3.706596989051753e-05, "loss": 3.6207, "step": 790016 }, { "epoch": 0.01, "learning_rate": 3.705758394300701e-05, "loss": 3.6155, "step": 790528 }, { "epoch": 0.01, "learning_rate": 3.704919799549649e-05, "loss": 3.6077, "step": 791040 }, { "epoch": 0.01, "learning_rate": 3.704081204798597e-05, "loss": 3.6127, "step": 791552 }, { "epoch": 0.01, "learning_rate": 3.7032442479279176e-05, "loss": 3.6321, "step": 792064 }, { "epoch": 0.01, "learning_rate": 3.7024056531768656e-05, "loss": 3.617, "step": 792576 }, { "epoch": 0.01, "learning_rate": 3.7015670584258136e-05, "loss": 3.6343, "step": 793088 }, { "epoch": 0.01, "learning_rate": 3.7007284636747616e-05, "loss": 3.6152, "step": 793600 }, { "epoch": 0.01, "learning_rate": 3.6998898689237096e-05, "loss": 3.6041, "step": 794112 }, { "epoch": 0.01, "learning_rate": 3.6990512741726576e-05, "loss": 3.6301, "step": 794624 }, { "epoch": 0.01, "learning_rate": 3.6982126794216056e-05, "loss": 3.6151, "step": 795136 }, { "epoch": 0.01, "learning_rate": 3.6973740846705536e-05, "loss": 3.6009, "step": 795648 }, { "epoch": 0.01, "learning_rate": 3.696537127799875e-05, "loss": 3.6185, "step": 796160 }, { "epoch": 0.01, "learning_rate": 3.6956985330488225e-05, "loss": 3.6163, "step": 796672 }, { "epoch": 0.01, "learning_rate": 3.6948599382977705e-05, "loss": 3.6102, "step": 797184 }, { "epoch": 0.01, "learning_rate": 3.6940213435467185e-05, "loss": 3.6126, "step": 797696 }, { "epoch": 0.01, "learning_rate": 3.69318438667604e-05, "loss": 3.6084, "step": 798208 }, { "epoch": 0.01, "learning_rate": 3.6923457919249874e-05, "loss": 3.6226, "step": 798720 }, { "epoch": 0.01, "learning_rate": 3.6915071971739354e-05, "loss": 3.6259, "step": 799232 }, { "epoch": 0.01, "learning_rate": 3.6906686024228834e-05, "loss": 3.6157, "step": 799744 }, { "epoch": 0.01, "learning_rate": 3.689830007671832e-05, "loss": 3.6253, "step": 800256 }, { "epoch": 0.01, "learning_rate": 3.68899141292078e-05, "loss": 3.6221, "step": 800768 }, { "epoch": 0.01, "learning_rate": 3.688152818169728e-05, "loss": 3.6343, "step": 801280 }, { "epoch": 0.01, "learning_rate": 3.687315861299049e-05, "loss": 3.6124, "step": 801792 }, { "epoch": 0.01, "learning_rate": 3.686477266547997e-05, "loss": 3.634, "step": 802304 }, { "epoch": 0.01, "learning_rate": 3.685638671796945e-05, "loss": 3.6123, "step": 802816 }, { "epoch": 0.01, "learning_rate": 3.684800077045893e-05, "loss": 3.6105, "step": 803328 }, { "epoch": 0.01, "learning_rate": 3.683961482294841e-05, "loss": 3.6266, "step": 803840 }, { "epoch": 0.01, "learning_rate": 3.683122887543789e-05, "loss": 3.6179, "step": 804352 }, { "epoch": 0.01, "learning_rate": 3.682284292792737e-05, "loss": 3.6262, "step": 804864 }, { "epoch": 0.01, "learning_rate": 3.681447335922058e-05, "loss": 3.6288, "step": 805376 }, { "epoch": 0.01, "learning_rate": 3.680608741171006e-05, "loss": 3.6078, "step": 805888 }, { "epoch": 0.01, "learning_rate": 3.679770146419954e-05, "loss": 3.6033, "step": 806400 }, { "epoch": 0.01, "learning_rate": 3.678931551668902e-05, "loss": 3.6118, "step": 806912 }, { "epoch": 0.01, "learning_rate": 3.6780945947982234e-05, "loss": 3.6282, "step": 807424 }, { "epoch": 0.01, "learning_rate": 3.6772560000471714e-05, "loss": 3.6113, "step": 807936 }, { "epoch": 0.01, "learning_rate": 3.6764174052961194e-05, "loss": 3.6165, "step": 808448 }, { "epoch": 0.01, "learning_rate": 3.6755788105450674e-05, "loss": 3.6189, "step": 808960 }, { "epoch": 0.02, "learning_rate": 3.6747402157940154e-05, "loss": 3.6064, "step": 809472 }, { "epoch": 0.02, "learning_rate": 3.6739016210429634e-05, "loss": 3.6171, "step": 809984 }, { "epoch": 0.02, "learning_rate": 3.6730630262919114e-05, "loss": 3.611, "step": 810496 }, { "epoch": 0.02, "learning_rate": 3.672224431540859e-05, "loss": 3.6206, "step": 811008 }, { "epoch": 0.02, "learning_rate": 3.67138747467018e-05, "loss": 3.6218, "step": 811520 }, { "epoch": 0.02, "learning_rate": 3.670550517799501e-05, "loss": 3.6286, "step": 812032 }, { "epoch": 0.02, "learning_rate": 3.669711923048449e-05, "loss": 3.6109, "step": 812544 }, { "epoch": 0.02, "learning_rate": 3.668873328297397e-05, "loss": 3.6179, "step": 813056 }, { "epoch": 0.02, "learning_rate": 3.668034733546345e-05, "loss": 3.6126, "step": 813568 }, { "epoch": 0.02, "learning_rate": 3.667196138795294e-05, "loss": 3.6195, "step": 814080 }, { "epoch": 0.02, "learning_rate": 3.666359181924615e-05, "loss": 3.623, "step": 814592 }, { "epoch": 0.02, "learning_rate": 3.665520587173563e-05, "loss": 3.6144, "step": 815104 }, { "epoch": 0.02, "learning_rate": 3.664681992422511e-05, "loss": 3.6142, "step": 815616 }, { "epoch": 0.02, "learning_rate": 3.663843397671459e-05, "loss": 3.6059, "step": 816128 }, { "epoch": 0.02, "learning_rate": 3.663004802920406e-05, "loss": 3.6145, "step": 816640 }, { "epoch": 0.02, "learning_rate": 3.662167846049728e-05, "loss": 3.6097, "step": 817152 }, { "epoch": 0.02, "learning_rate": 3.661329251298676e-05, "loss": 3.5943, "step": 817664 }, { "epoch": 0.02, "learning_rate": 3.660490656547623e-05, "loss": 3.6169, "step": 818176 }, { "epoch": 0.02, "learning_rate": 3.659652061796571e-05, "loss": 3.6188, "step": 818688 }, { "epoch": 0.02, "learning_rate": 3.658813467045519e-05, "loss": 3.612, "step": 819200 }, { "epoch": 0.02, "learning_rate": 3.6579748722944676e-05, "loss": 3.6075, "step": 819712 }, { "epoch": 0.02, "learning_rate": 3.6571362775434156e-05, "loss": 3.6147, "step": 820224 }, { "epoch": 0.02, "learning_rate": 3.6562976827923636e-05, "loss": 3.6153, "step": 820736 }, { "epoch": 0.02, "learning_rate": 3.6554607259216845e-05, "loss": 3.6019, "step": 821248 }, { "epoch": 0.02, "learning_rate": 3.654623769051006e-05, "loss": 3.6303, "step": 821760 }, { "epoch": 0.02, "learning_rate": 3.6537851742999535e-05, "loss": 3.6194, "step": 822272 }, { "epoch": 0.02, "learning_rate": 3.6529465795489015e-05, "loss": 3.6116, "step": 822784 }, { "epoch": 0.02, "learning_rate": 3.6521079847978494e-05, "loss": 3.6194, "step": 823296 }, { "epoch": 0.02, "learning_rate": 3.6512693900467974e-05, "loss": 3.6056, "step": 823808 }, { "epoch": 0.02, "learning_rate": 3.6504324331761184e-05, "loss": 3.6191, "step": 824320 }, { "epoch": 0.02, "learning_rate": 3.6495938384250663e-05, "loss": 3.6127, "step": 824832 }, { "epoch": 0.02, "learning_rate": 3.6487552436740143e-05, "loss": 3.6084, "step": 825344 }, { "epoch": 0.02, "learning_rate": 3.647916648922963e-05, "loss": 3.6103, "step": 825856 }, { "epoch": 0.02, "learning_rate": 3.647078054171911e-05, "loss": 3.6146, "step": 826368 }, { "epoch": 0.02, "learning_rate": 3.646239459420859e-05, "loss": 3.6147, "step": 826880 }, { "epoch": 0.02, "learning_rate": 3.645400864669807e-05, "loss": 3.6065, "step": 827392 }, { "epoch": 0.02, "learning_rate": 3.644562269918755e-05, "loss": 3.6099, "step": 827904 }, { "epoch": 0.02, "learning_rate": 3.643725313048076e-05, "loss": 3.6077, "step": 828416 }, { "epoch": 0.02, "learning_rate": 3.642886718297024e-05, "loss": 3.6078, "step": 828928 }, { "epoch": 0.02, "learning_rate": 3.642049761426345e-05, "loss": 3.6237, "step": 829440 }, { "epoch": 0.02, "learning_rate": 3.641211166675293e-05, "loss": 3.6116, "step": 829952 }, { "epoch": 0.02, "learning_rate": 3.640372571924241e-05, "loss": 3.621, "step": 830464 }, { "epoch": 0.02, "learning_rate": 3.639533977173189e-05, "loss": 3.5929, "step": 830976 }, { "epoch": 0.02, "learning_rate": 3.638695382422137e-05, "loss": 3.627, "step": 831488 }, { "epoch": 0.02, "learning_rate": 3.637856787671085e-05, "loss": 3.616, "step": 832000 }, { "epoch": 0.02, "learning_rate": 3.637018192920033e-05, "loss": 3.6164, "step": 832512 }, { "epoch": 0.02, "learning_rate": 3.6361795981689815e-05, "loss": 3.6119, "step": 833024 }, { "epoch": 0.02, "learning_rate": 3.6353426412983024e-05, "loss": 3.6064, "step": 833536 }, { "epoch": 0.02, "learning_rate": 3.6345040465472504e-05, "loss": 3.6148, "step": 834048 }, { "epoch": 0.02, "learning_rate": 3.6336654517961984e-05, "loss": 3.6319, "step": 834560 }, { "epoch": 0.02, "learning_rate": 3.6328268570451464e-05, "loss": 3.6021, "step": 835072 }, { "epoch": 0.02, "learning_rate": 3.6319882622940944e-05, "loss": 3.6154, "step": 835584 }, { "epoch": 0.02, "learning_rate": 3.631149667543042e-05, "loss": 3.606, "step": 836096 }, { "epoch": 0.02, "learning_rate": 3.63031107279199e-05, "loss": 3.6118, "step": 836608 }, { "epoch": 0.02, "learning_rate": 3.629474115921311e-05, "loss": 3.61, "step": 837120 }, { "epoch": 0.02, "learning_rate": 3.628635521170259e-05, "loss": 3.614, "step": 837632 }, { "epoch": 0.02, "learning_rate": 3.6277969264192066e-05, "loss": 3.6136, "step": 838144 }, { "epoch": 0.02, "learning_rate": 3.626958331668155e-05, "loss": 3.6157, "step": 838656 }, { "epoch": 0.02, "learning_rate": 3.626119736917103e-05, "loss": 3.6099, "step": 839168 }, { "epoch": 0.03, "eval_loss": 3.844151020050049, "eval_runtime": 303.9418, "eval_samples_per_second": 1255.474, "eval_steps_per_second": 39.234, "step": 839520 }, { "epoch": 1.0, "learning_rate": 3.625282780046425e-05, "loss": 3.6039, "step": 839680 }, { "epoch": 1.0, "learning_rate": 3.624444185295372e-05, "loss": 3.6042, "step": 840192 }, { "epoch": 1.0, "learning_rate": 3.62360559054432e-05, "loss": 3.6166, "step": 840704 }, { "epoch": 1.0, "learning_rate": 3.622766995793268e-05, "loss": 3.6133, "step": 841216 }, { "epoch": 1.0, "learning_rate": 3.621930038922589e-05, "loss": 3.6191, "step": 841728 }, { "epoch": 1.0, "learning_rate": 3.621091444171537e-05, "loss": 3.6087, "step": 842240 }, { "epoch": 1.0, "learning_rate": 3.620252849420485e-05, "loss": 3.6054, "step": 842752 }, { "epoch": 1.0, "learning_rate": 3.619414254669433e-05, "loss": 3.6109, "step": 843264 }, { "epoch": 1.0, "learning_rate": 3.618575659918381e-05, "loss": 3.6053, "step": 843776 }, { "epoch": 1.0, "learning_rate": 3.617737065167329e-05, "loss": 3.6145, "step": 844288 }, { "epoch": 1.0, "learning_rate": 3.6169001082966506e-05, "loss": 3.615, "step": 844800 }, { "epoch": 1.0, "learning_rate": 3.6160615135455986e-05, "loss": 3.6186, "step": 845312 }, { "epoch": 1.0, "learning_rate": 3.6152245566749195e-05, "loss": 3.6175, "step": 845824 }, { "epoch": 1.0, "learning_rate": 3.6143859619238675e-05, "loss": 3.5957, "step": 846336 }, { "epoch": 1.0, "learning_rate": 3.6135473671728155e-05, "loss": 3.6149, "step": 846848 }, { "epoch": 1.0, "learning_rate": 3.6127087724217635e-05, "loss": 3.594, "step": 847360 }, { "epoch": 1.0, "learning_rate": 3.6118701776707115e-05, "loss": 3.6017, "step": 847872 }, { "epoch": 1.0, "learning_rate": 3.6110315829196595e-05, "loss": 3.6039, "step": 848384 }, { "epoch": 1.0, "learning_rate": 3.6101929881686075e-05, "loss": 3.6014, "step": 848896 }, { "epoch": 1.0, "learning_rate": 3.6093543934175555e-05, "loss": 3.6089, "step": 849408 }, { "epoch": 1.0, "learning_rate": 3.6085157986665035e-05, "loss": 3.6207, "step": 849920 }, { "epoch": 1.0, "learning_rate": 3.6076772039154515e-05, "loss": 3.6106, "step": 850432 }, { "epoch": 1.0, "learning_rate": 3.6068402470447724e-05, "loss": 3.606, "step": 850944 }, { "epoch": 1.0, "learning_rate": 3.6060016522937204e-05, "loss": 3.6037, "step": 851456 }, { "epoch": 1.0, "learning_rate": 3.6051630575426684e-05, "loss": 3.6057, "step": 851968 }, { "epoch": 1.0, "learning_rate": 3.604324462791617e-05, "loss": 3.6002, "step": 852480 }, { "epoch": 1.0, "learning_rate": 3.603485868040565e-05, "loss": 3.5973, "step": 852992 }, { "epoch": 1.0, "learning_rate": 3.602647273289513e-05, "loss": 3.6139, "step": 853504 }, { "epoch": 1.0, "learning_rate": 3.601810316418834e-05, "loss": 3.599, "step": 854016 }, { "epoch": 1.0, "learning_rate": 3.600971721667782e-05, "loss": 3.6038, "step": 854528 }, { "epoch": 1.01, "learning_rate": 3.60013312691673e-05, "loss": 3.5991, "step": 855040 }, { "epoch": 1.01, "learning_rate": 3.599296170046051e-05, "loss": 3.6121, "step": 855552 }, { "epoch": 1.01, "learning_rate": 3.598457575294999e-05, "loss": 3.6024, "step": 856064 }, { "epoch": 1.01, "learning_rate": 3.597618980543947e-05, "loss": 3.6046, "step": 856576 }, { "epoch": 1.01, "learning_rate": 3.596780385792895e-05, "loss": 3.606, "step": 857088 }, { "epoch": 1.01, "learning_rate": 3.595941791041843e-05, "loss": 3.6002, "step": 857600 }, { "epoch": 1.01, "learning_rate": 3.595103196290791e-05, "loss": 3.6108, "step": 858112 }, { "epoch": 1.01, "learning_rate": 3.594264601539739e-05, "loss": 3.5918, "step": 858624 }, { "epoch": 1.01, "learning_rate": 3.593426006788687e-05, "loss": 3.5917, "step": 859136 }, { "epoch": 1.01, "learning_rate": 3.5925890499180084e-05, "loss": 3.5951, "step": 859648 }, { "epoch": 1.01, "learning_rate": 3.591750455166956e-05, "loss": 3.6037, "step": 860160 }, { "epoch": 1.01, "learning_rate": 3.590911860415904e-05, "loss": 3.5995, "step": 860672 }, { "epoch": 1.01, "learning_rate": 3.590073265664852e-05, "loss": 3.6011, "step": 861184 }, { "epoch": 1.01, "learning_rate": 3.5892346709138e-05, "loss": 3.6031, "step": 861696 }, { "epoch": 1.01, "learning_rate": 3.588396076162748e-05, "loss": 3.6024, "step": 862208 }, { "epoch": 1.01, "learning_rate": 3.587557481411696e-05, "loss": 3.6036, "step": 862720 }, { "epoch": 1.01, "learning_rate": 3.586718886660644e-05, "loss": 3.6116, "step": 863232 }, { "epoch": 1.01, "learning_rate": 3.5858819297899646e-05, "loss": 3.5998, "step": 863744 }, { "epoch": 1.01, "learning_rate": 3.5850433350389126e-05, "loss": 3.5794, "step": 864256 }, { "epoch": 1.01, "learning_rate": 3.5842047402878606e-05, "loss": 3.6158, "step": 864768 }, { "epoch": 1.01, "learning_rate": 3.583366145536809e-05, "loss": 3.6001, "step": 865280 }, { "epoch": 1.01, "learning_rate": 3.58252918866613e-05, "loss": 3.6004, "step": 865792 }, { "epoch": 1.01, "learning_rate": 3.581692231795451e-05, "loss": 3.5994, "step": 866304 }, { "epoch": 1.01, "learning_rate": 3.580853637044399e-05, "loss": 3.5956, "step": 866816 }, { "epoch": 1.01, "learning_rate": 3.580015042293347e-05, "loss": 3.5874, "step": 867328 }, { "epoch": 1.01, "learning_rate": 3.579176447542295e-05, "loss": 3.5927, "step": 867840 }, { "epoch": 1.01, "learning_rate": 3.578339490671616e-05, "loss": 3.6152, "step": 868352 }, { "epoch": 1.01, "learning_rate": 3.577500895920564e-05, "loss": 3.5974, "step": 868864 }, { "epoch": 1.01, "learning_rate": 3.576662301169512e-05, "loss": 3.614, "step": 869376 }, { "epoch": 1.01, "learning_rate": 3.57582370641846e-05, "loss": 3.5967, "step": 869888 }, { "epoch": 1.01, "learning_rate": 3.574985111667408e-05, "loss": 3.5815, "step": 870400 }, { "epoch": 1.01, "learning_rate": 3.5741481547967296e-05, "loss": 3.6108, "step": 870912 }, { "epoch": 1.01, "learning_rate": 3.5733095600456775e-05, "loss": 3.5945, "step": 871424 }, { "epoch": 1.01, "learning_rate": 3.5724709652946255e-05, "loss": 3.5823, "step": 871936 }, { "epoch": 1.01, "learning_rate": 3.5716323705435735e-05, "loss": 3.5968, "step": 872448 }, { "epoch": 1.01, "learning_rate": 3.5707937757925215e-05, "loss": 3.5939, "step": 872960 }, { "epoch": 1.01, "learning_rate": 3.5699551810414695e-05, "loss": 3.5895, "step": 873472 }, { "epoch": 1.01, "learning_rate": 3.5691165862904175e-05, "loss": 3.5952, "step": 873984 }, { "epoch": 1.01, "learning_rate": 3.5682796294197384e-05, "loss": 3.5897, "step": 874496 }, { "epoch": 1.01, "learning_rate": 3.5674410346686864e-05, "loss": 3.5975, "step": 875008 }, { "epoch": 1.01, "learning_rate": 3.5666024399176344e-05, "loss": 3.6046, "step": 875520 }, { "epoch": 1.01, "learning_rate": 3.5657638451665824e-05, "loss": 3.5968, "step": 876032 }, { "epoch": 1.01, "learning_rate": 3.5649252504155304e-05, "loss": 3.6038, "step": 876544 }, { "epoch": 1.01, "learning_rate": 3.5640866556644784e-05, "loss": 3.6024, "step": 877056 }, { "epoch": 1.01, "learning_rate": 3.5632480609134264e-05, "loss": 3.6152, "step": 877568 }, { "epoch": 1.01, "learning_rate": 3.5624094661623744e-05, "loss": 3.5927, "step": 878080 }, { "epoch": 1.01, "learning_rate": 3.561574147172069e-05, "loss": 3.6128, "step": 878592 }, { "epoch": 1.01, "learning_rate": 3.560735552421017e-05, "loss": 3.5921, "step": 879104 }, { "epoch": 1.01, "learning_rate": 3.559896957669965e-05, "loss": 3.5913, "step": 879616 }, { "epoch": 1.01, "learning_rate": 3.559058362918913e-05, "loss": 3.6019, "step": 880128 }, { "epoch": 1.01, "learning_rate": 3.558219768167861e-05, "loss": 3.5986, "step": 880640 }, { "epoch": 1.01, "learning_rate": 3.557381173416809e-05, "loss": 3.6048, "step": 881152 }, { "epoch": 1.01, "learning_rate": 3.556542578665756e-05, "loss": 3.6097, "step": 881664 }, { "epoch": 1.01, "learning_rate": 3.555703983914704e-05, "loss": 3.5915, "step": 882176 }, { "epoch": 1.01, "learning_rate": 3.554868664924399e-05, "loss": 3.5826, "step": 882688 }, { "epoch": 1.01, "learning_rate": 3.554030070173347e-05, "loss": 3.5901, "step": 883200 }, { "epoch": 1.01, "learning_rate": 3.553191475422295e-05, "loss": 3.6094, "step": 883712 }, { "epoch": 1.01, "learning_rate": 3.5523528806712434e-05, "loss": 3.5896, "step": 884224 }, { "epoch": 1.01, "learning_rate": 3.5515142859201914e-05, "loss": 3.5996, "step": 884736 }, { "epoch": 1.01, "learning_rate": 3.550677329049512e-05, "loss": 3.5988, "step": 885248 }, { "epoch": 1.02, "learning_rate": 3.54983873429846e-05, "loss": 3.5852, "step": 885760 }, { "epoch": 1.02, "learning_rate": 3.549000139547408e-05, "loss": 3.5956, "step": 886272 }, { "epoch": 1.02, "learning_rate": 3.548161544796356e-05, "loss": 3.5927, "step": 886784 }, { "epoch": 1.02, "learning_rate": 3.5473229500453036e-05, "loss": 3.5981, "step": 887296 }, { "epoch": 1.02, "learning_rate": 3.546485993174625e-05, "loss": 3.6065, "step": 887808 }, { "epoch": 1.02, "learning_rate": 3.545647398423573e-05, "loss": 3.6074, "step": 888320 }, { "epoch": 1.02, "learning_rate": 3.544808803672521e-05, "loss": 3.5925, "step": 888832 }, { "epoch": 1.02, "learning_rate": 3.5439702089214685e-05, "loss": 3.5958, "step": 889344 }, { "epoch": 1.02, "learning_rate": 3.543131614170417e-05, "loss": 3.5912, "step": 889856 }, { "epoch": 1.02, "learning_rate": 3.542293019419365e-05, "loss": 3.6001, "step": 890368 }, { "epoch": 1.02, "learning_rate": 3.541456062548686e-05, "loss": 3.5996, "step": 890880 }, { "epoch": 1.02, "learning_rate": 3.540617467797634e-05, "loss": 3.5934, "step": 891392 }, { "epoch": 1.02, "learning_rate": 3.539778873046582e-05, "loss": 3.5947, "step": 891904 }, { "epoch": 1.02, "learning_rate": 3.53894027829553e-05, "loss": 3.5854, "step": 892416 }, { "epoch": 1.02, "learning_rate": 3.538103321424851e-05, "loss": 3.5965, "step": 892928 }, { "epoch": 1.02, "learning_rate": 3.537264726673799e-05, "loss": 3.5908, "step": 893440 }, { "epoch": 1.02, "learning_rate": 3.536426131922747e-05, "loss": 3.5764, "step": 893952 }, { "epoch": 1.02, "learning_rate": 3.535587537171695e-05, "loss": 3.5978, "step": 894464 }, { "epoch": 1.02, "learning_rate": 3.534750580301016e-05, "loss": 3.5971, "step": 894976 }, { "epoch": 1.02, "learning_rate": 3.533911985549964e-05, "loss": 3.5923, "step": 895488 }, { "epoch": 1.02, "learning_rate": 3.5330733907989125e-05, "loss": 3.5878, "step": 896000 }, { "epoch": 1.02, "learning_rate": 3.5322347960478605e-05, "loss": 3.5961, "step": 896512 }, { "epoch": 1.02, "learning_rate": 3.5313978391771814e-05, "loss": 3.5955, "step": 897024 }, { "epoch": 1.02, "learning_rate": 3.5305592444261294e-05, "loss": 3.5831, "step": 897536 }, { "epoch": 1.02, "learning_rate": 3.5297206496750774e-05, "loss": 3.6064, "step": 898048 }, { "epoch": 1.02, "learning_rate": 3.5288820549240254e-05, "loss": 3.5986, "step": 898560 }, { "epoch": 1.02, "learning_rate": 3.5280434601729734e-05, "loss": 3.5934, "step": 899072 }, { "epoch": 1.02, "learning_rate": 3.527206503302294e-05, "loss": 3.5998, "step": 899584 }, { "epoch": 1.02, "learning_rate": 3.526367908551242e-05, "loss": 3.5882, "step": 900096 }, { "epoch": 1.02, "learning_rate": 3.52552931380019e-05, "loss": 3.5973, "step": 900608 }, { "epoch": 1.02, "learning_rate": 3.524692356929511e-05, "loss": 3.5963, "step": 901120 }, { "epoch": 1.02, "learning_rate": 3.523853762178459e-05, "loss": 3.5902, "step": 901632 }, { "epoch": 1.02, "learning_rate": 3.523015167427408e-05, "loss": 3.5903, "step": 902144 }, { "epoch": 1.02, "learning_rate": 3.522176572676356e-05, "loss": 3.595, "step": 902656 }, { "epoch": 1.02, "learning_rate": 3.521337977925304e-05, "loss": 3.5952, "step": 903168 }, { "epoch": 1.02, "learning_rate": 3.520499383174252e-05, "loss": 3.5861, "step": 903680 }, { "epoch": 1.02, "learning_rate": 3.5196607884232e-05, "loss": 3.5878, "step": 904192 }, { "epoch": 1.02, "learning_rate": 3.518823831552521e-05, "loss": 3.5908, "step": 904704 }, { "epoch": 1.02, "learning_rate": 3.517985236801469e-05, "loss": 3.5863, "step": 905216 }, { "epoch": 1.02, "learning_rate": 3.517146642050417e-05, "loss": 3.6055, "step": 905728 }, { "epoch": 1.02, "learning_rate": 3.516308047299365e-05, "loss": 3.5922, "step": 906240 }, { "epoch": 1.02, "learning_rate": 3.515469452548313e-05, "loss": 3.6047, "step": 906752 }, { "epoch": 1.02, "learning_rate": 3.514630857797261e-05, "loss": 3.5713, "step": 907264 }, { "epoch": 1.02, "learning_rate": 3.513792263046209e-05, "loss": 3.6065, "step": 907776 }, { "epoch": 1.02, "learning_rate": 3.512953668295157e-05, "loss": 3.5913, "step": 908288 }, { "epoch": 1.02, "learning_rate": 3.5121167114244776e-05, "loss": 3.6021, "step": 908800 }, { "epoch": 1.02, "learning_rate": 3.511278116673426e-05, "loss": 3.5934, "step": 909312 }, { "epoch": 1.02, "learning_rate": 3.510439521922374e-05, "loss": 3.5822, "step": 909824 }, { "epoch": 1.02, "learning_rate": 3.509600927171322e-05, "loss": 3.5974, "step": 910336 }, { "epoch": 1.02, "learning_rate": 3.508763970300643e-05, "loss": 3.6157, "step": 910848 }, { "epoch": 1.02, "learning_rate": 3.507925375549591e-05, "loss": 3.5787, "step": 911360 }, { "epoch": 1.02, "learning_rate": 3.507086780798539e-05, "loss": 3.5957, "step": 911872 }, { "epoch": 1.02, "learning_rate": 3.506248186047487e-05, "loss": 3.5891, "step": 912384 }, { "epoch": 1.02, "learning_rate": 3.505411229176808e-05, "loss": 3.5909, "step": 912896 }, { "epoch": 1.02, "learning_rate": 3.504574272306129e-05, "loss": 3.5902, "step": 913408 }, { "epoch": 1.02, "learning_rate": 3.503735677555077e-05, "loss": 3.5946, "step": 913920 }, { "epoch": 1.02, "learning_rate": 3.502897082804025e-05, "loss": 3.5883, "step": 914432 }, { "epoch": 1.02, "learning_rate": 3.502058488052973e-05, "loss": 3.5954, "step": 914944 }, { "epoch": 1.02, "learning_rate": 3.501219893301922e-05, "loss": 3.5921, "step": 915456 }, { "epoch": 1.03, "eval_loss": 3.842529535293579, "eval_runtime": 305.9765, "eval_samples_per_second": 1247.125, "eval_steps_per_second": 38.974, "step": 915840 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 6.400789530703626e+17, "trial_name": null, "trial_params": null }