{ "best_metric": 3.952585220336914, "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/binding-case/transformer/1/checkpoints/checkpoint-228960", "epoch": 0.025000606015738065, "eval_steps": 10, "global_step": 228960, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.999998362119627e-05, "loss": 10.8546, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.999161405248948e-05, "loss": 6.8152, "step": 512 }, { "epoch": 0.0, "learning_rate": 4.998322810497896e-05, "loss": 6.1962, "step": 1024 }, { "epoch": 0.0, "learning_rate": 4.997484215746844e-05, "loss": 5.9782, "step": 1536 }, { "epoch": 0.0, "learning_rate": 4.996645620995792e-05, "loss": 5.8176, "step": 2048 }, { "epoch": 0.0, "learning_rate": 4.99580702624474e-05, "loss": 5.7102, "step": 2560 }, { "epoch": 0.0, "learning_rate": 4.994968431493688e-05, "loss": 5.6077, "step": 3072 }, { "epoch": 0.0, "learning_rate": 4.994129836742636e-05, "loss": 5.5352, "step": 3584 }, { "epoch": 0.0, "learning_rate": 4.993291241991584e-05, "loss": 5.4531, "step": 4096 }, { "epoch": 0.0, "learning_rate": 4.992452647240532e-05, "loss": 5.4052, "step": 4608 }, { "epoch": 0.0, "learning_rate": 4.99161405248948e-05, "loss": 5.3446, "step": 5120 }, { "epoch": 0.0, "learning_rate": 4.990775457738428e-05, "loss": 5.3026, "step": 5632 }, { "epoch": 0.0, "learning_rate": 4.989938500867749e-05, "loss": 5.2566, "step": 6144 }, { "epoch": 0.0, "learning_rate": 4.989099906116697e-05, "loss": 5.2091, "step": 6656 }, { "epoch": 0.0, "learning_rate": 4.988261311365645e-05, "loss": 5.1715, "step": 7168 }, { "epoch": 0.0, "learning_rate": 4.987422716614593e-05, "loss": 5.1284, "step": 7680 }, { "epoch": 0.0, "learning_rate": 4.986584121863541e-05, "loss": 5.1004, "step": 8192 }, { "epoch": 0.0, "learning_rate": 4.985745527112489e-05, "loss": 5.0707, "step": 8704 }, { "epoch": 0.0, "learning_rate": 4.984906932361437e-05, "loss": 5.0435, "step": 9216 }, { "epoch": 0.0, "learning_rate": 4.984068337610385e-05, "loss": 5.0123, "step": 9728 }, { "epoch": 0.0, "learning_rate": 4.983229742859333e-05, "loss": 4.9999, "step": 10240 }, { "epoch": 0.0, "learning_rate": 4.982391148108281e-05, "loss": 4.9718, "step": 10752 }, { "epoch": 0.0, "learning_rate": 4.9815541912376026e-05, "loss": 4.9432, "step": 11264 }, { "epoch": 0.0, "learning_rate": 4.9807155964865506e-05, "loss": 4.9305, "step": 11776 }, { "epoch": 0.0, "learning_rate": 4.9798770017354986e-05, "loss": 4.9198, "step": 12288 }, { "epoch": 0.0, "learning_rate": 4.9790384069844466e-05, "loss": 4.8831, "step": 12800 }, { "epoch": 0.0, "learning_rate": 4.9782014501137675e-05, "loss": 4.8646, "step": 13312 }, { "epoch": 0.0, "learning_rate": 4.9773628553627155e-05, "loss": 4.8512, "step": 13824 }, { "epoch": 0.0, "learning_rate": 4.9765242606116635e-05, "loss": 4.837, "step": 14336 }, { "epoch": 0.0, "learning_rate": 4.9756856658606115e-05, "loss": 4.8149, "step": 14848 }, { "epoch": 0.01, "learning_rate": 4.9748487089899324e-05, "loss": 4.7976, "step": 15360 }, { "epoch": 0.01, "learning_rate": 4.9740101142388804e-05, "loss": 4.795, "step": 15872 }, { "epoch": 0.01, "learning_rate": 4.9731715194878284e-05, "loss": 4.779, "step": 16384 }, { "epoch": 0.01, "learning_rate": 4.97233456261715e-05, "loss": 4.7723, "step": 16896 }, { "epoch": 0.01, "learning_rate": 4.971495967866098e-05, "loss": 4.7578, "step": 17408 }, { "epoch": 0.01, "learning_rate": 4.970657373115046e-05, "loss": 4.7399, "step": 17920 }, { "epoch": 0.01, "learning_rate": 4.969818778363994e-05, "loss": 4.7336, "step": 18432 }, { "epoch": 0.01, "learning_rate": 4.968981821493315e-05, "loss": 4.6992, "step": 18944 }, { "epoch": 0.01, "learning_rate": 4.968143226742263e-05, "loss": 4.7062, "step": 19456 }, { "epoch": 0.01, "learning_rate": 4.967304631991211e-05, "loss": 4.6791, "step": 19968 }, { "epoch": 0.01, "learning_rate": 4.966466037240159e-05, "loss": 4.6786, "step": 20480 }, { "epoch": 0.01, "learning_rate": 4.965627442489107e-05, "loss": 4.6663, "step": 20992 }, { "epoch": 0.01, "learning_rate": 4.964788847738054e-05, "loss": 4.669, "step": 21504 }, { "epoch": 0.01, "learning_rate": 4.963950252987002e-05, "loss": 4.6467, "step": 22016 }, { "epoch": 0.01, "learning_rate": 4.96311165823595e-05, "loss": 4.6443, "step": 22528 }, { "epoch": 0.01, "learning_rate": 4.962274701365272e-05, "loss": 4.6357, "step": 23040 }, { "epoch": 0.01, "learning_rate": 4.96143610661422e-05, "loss": 4.6189, "step": 23552 }, { "epoch": 0.01, "learning_rate": 4.960597511863168e-05, "loss": 4.6294, "step": 24064 }, { "epoch": 0.01, "learning_rate": 4.959758917112116e-05, "loss": 4.5942, "step": 24576 }, { "epoch": 0.01, "learning_rate": 4.9589219602414374e-05, "loss": 4.586, "step": 25088 }, { "epoch": 0.01, "learning_rate": 4.958083365490385e-05, "loss": 4.5986, "step": 25600 }, { "epoch": 0.01, "learning_rate": 4.957244770739333e-05, "loss": 4.5931, "step": 26112 }, { "epoch": 0.01, "learning_rate": 4.956406175988281e-05, "loss": 4.5698, "step": 26624 }, { "epoch": 0.01, "learning_rate": 4.9555692191176016e-05, "loss": 4.5621, "step": 27136 }, { "epoch": 0.01, "learning_rate": 4.954732262246923e-05, "loss": 4.5636, "step": 27648 }, { "epoch": 0.01, "learning_rate": 4.953893667495871e-05, "loss": 4.5446, "step": 28160 }, { "epoch": 0.01, "learning_rate": 4.953055072744819e-05, "loss": 4.5664, "step": 28672 }, { "epoch": 0.01, "learning_rate": 4.952216477993767e-05, "loss": 4.5268, "step": 29184 }, { "epoch": 0.01, "learning_rate": 4.951377883242715e-05, "loss": 4.5372, "step": 29696 }, { "epoch": 0.01, "learning_rate": 4.950539288491663e-05, "loss": 4.5277, "step": 30208 }, { "epoch": 0.01, "learning_rate": 4.949700693740611e-05, "loss": 4.5117, "step": 30720 }, { "epoch": 0.01, "learning_rate": 4.948862098989559e-05, "loss": 4.5193, "step": 31232 }, { "epoch": 0.01, "learning_rate": 4.94802514211888e-05, "loss": 4.5016, "step": 31744 }, { "epoch": 0.01, "learning_rate": 4.947186547367828e-05, "loss": 4.4985, "step": 32256 }, { "epoch": 0.01, "learning_rate": 4.946347952616776e-05, "loss": 4.4896, "step": 32768 }, { "epoch": 0.01, "learning_rate": 4.945509357865724e-05, "loss": 4.5032, "step": 33280 }, { "epoch": 0.01, "learning_rate": 4.944670763114672e-05, "loss": 4.4757, "step": 33792 }, { "epoch": 0.01, "learning_rate": 4.943833806243993e-05, "loss": 4.4807, "step": 34304 }, { "epoch": 0.01, "learning_rate": 4.942995211492941e-05, "loss": 4.4591, "step": 34816 }, { "epoch": 0.01, "learning_rate": 4.942156616741889e-05, "loss": 4.467, "step": 35328 }, { "epoch": 0.01, "learning_rate": 4.941318021990837e-05, "loss": 4.4785, "step": 35840 }, { "epoch": 0.01, "learning_rate": 4.9404810651201585e-05, "loss": 4.4677, "step": 36352 }, { "epoch": 0.01, "learning_rate": 4.9396424703691065e-05, "loss": 4.4509, "step": 36864 }, { "epoch": 0.01, "learning_rate": 4.9388038756180545e-05, "loss": 4.4635, "step": 37376 }, { "epoch": 0.01, "learning_rate": 4.9379652808670025e-05, "loss": 4.465, "step": 37888 }, { "epoch": 0.01, "learning_rate": 4.9371283239963234e-05, "loss": 4.4384, "step": 38400 }, { "epoch": 0.01, "learning_rate": 4.936291367125644e-05, "loss": 4.4448, "step": 38912 }, { "epoch": 0.01, "learning_rate": 4.935452772374592e-05, "loss": 4.4272, "step": 39424 }, { "epoch": 0.01, "learning_rate": 4.93461417762354e-05, "loss": 4.4182, "step": 39936 }, { "epoch": 0.01, "learning_rate": 4.933775582872488e-05, "loss": 4.4163, "step": 40448 }, { "epoch": 0.01, "learning_rate": 4.932936988121436e-05, "loss": 4.416, "step": 40960 }, { "epoch": 0.01, "learning_rate": 4.932098393370384e-05, "loss": 4.4229, "step": 41472 }, { "epoch": 0.01, "learning_rate": 4.931259798619332e-05, "loss": 4.4289, "step": 41984 }, { "epoch": 0.01, "learning_rate": 4.930422841748654e-05, "loss": 4.4166, "step": 42496 }, { "epoch": 0.01, "learning_rate": 4.929584246997602e-05, "loss": 4.3931, "step": 43008 }, { "epoch": 0.01, "learning_rate": 4.92874565224655e-05, "loss": 4.4001, "step": 43520 }, { "epoch": 0.01, "learning_rate": 4.927907057495498e-05, "loss": 4.4018, "step": 44032 }, { "epoch": 0.01, "learning_rate": 4.927070100624819e-05, "loss": 4.3927, "step": 44544 }, { "epoch": 0.01, "learning_rate": 4.926231505873767e-05, "loss": 4.3842, "step": 45056 }, { "epoch": 0.01, "learning_rate": 4.925394549003088e-05, "loss": 4.3814, "step": 45568 }, { "epoch": 0.02, "learning_rate": 4.924555954252036e-05, "loss": 4.3753, "step": 46080 }, { "epoch": 0.02, "learning_rate": 4.923717359500984e-05, "loss": 4.383, "step": 46592 }, { "epoch": 0.02, "learning_rate": 4.9228804026303046e-05, "loss": 4.3712, "step": 47104 }, { "epoch": 0.02, "learning_rate": 4.922041807879253e-05, "loss": 4.3769, "step": 47616 }, { "epoch": 0.02, "learning_rate": 4.921203213128201e-05, "loss": 4.3674, "step": 48128 }, { "epoch": 0.02, "learning_rate": 4.920364618377149e-05, "loss": 4.3648, "step": 48640 }, { "epoch": 0.02, "learning_rate": 4.919526023626097e-05, "loss": 4.3516, "step": 49152 }, { "epoch": 0.02, "learning_rate": 4.918687428875045e-05, "loss": 4.3519, "step": 49664 }, { "epoch": 0.02, "learning_rate": 4.917848834123993e-05, "loss": 4.3505, "step": 50176 }, { "epoch": 0.02, "learning_rate": 4.917010239372941e-05, "loss": 4.3549, "step": 50688 }, { "epoch": 0.02, "learning_rate": 4.916171644621889e-05, "loss": 4.3532, "step": 51200 }, { "epoch": 0.02, "learning_rate": 4.915333049870837e-05, "loss": 4.3338, "step": 51712 }, { "epoch": 0.02, "learning_rate": 4.914494455119785e-05, "loss": 4.3418, "step": 52224 }, { "epoch": 0.02, "learning_rate": 4.9136558603687325e-05, "loss": 4.3331, "step": 52736 }, { "epoch": 0.02, "learning_rate": 4.912818903498054e-05, "loss": 4.3355, "step": 53248 }, { "epoch": 0.02, "learning_rate": 4.911980308747002e-05, "loss": 4.3227, "step": 53760 }, { "epoch": 0.02, "learning_rate": 4.911143351876323e-05, "loss": 4.3201, "step": 54272 }, { "epoch": 0.02, "learning_rate": 4.910304757125272e-05, "loss": 4.327, "step": 54784 }, { "epoch": 0.02, "learning_rate": 4.90946616237422e-05, "loss": 4.3172, "step": 55296 }, { "epoch": 0.02, "learning_rate": 4.908627567623168e-05, "loss": 4.314, "step": 55808 }, { "epoch": 0.02, "learning_rate": 4.907788972872115e-05, "loss": 4.307, "step": 56320 }, { "epoch": 0.02, "learning_rate": 4.906950378121063e-05, "loss": 4.3036, "step": 56832 }, { "epoch": 0.02, "learning_rate": 4.9061134212503846e-05, "loss": 4.3163, "step": 57344 }, { "epoch": 0.02, "learning_rate": 4.9052748264993326e-05, "loss": 4.3036, "step": 57856 }, { "epoch": 0.02, "learning_rate": 4.90443623174828e-05, "loss": 4.3029, "step": 58368 }, { "epoch": 0.02, "learning_rate": 4.903597636997228e-05, "loss": 4.307, "step": 58880 }, { "epoch": 0.02, "learning_rate": 4.9027606801265495e-05, "loss": 4.313, "step": 59392 }, { "epoch": 0.02, "learning_rate": 4.9019220853754975e-05, "loss": 4.2977, "step": 59904 }, { "epoch": 0.02, "learning_rate": 4.9010834906244455e-05, "loss": 4.2856, "step": 60416 }, { "epoch": 0.02, "learning_rate": 4.9002448958733935e-05, "loss": 4.2913, "step": 60928 }, { "epoch": 0.02, "learning_rate": 4.8994063011223415e-05, "loss": 4.2988, "step": 61440 }, { "epoch": 0.02, "learning_rate": 4.8985693442516624e-05, "loss": 4.2832, "step": 61952 }, { "epoch": 0.02, "learning_rate": 4.8977307495006104e-05, "loss": 4.2806, "step": 62464 }, { "epoch": 0.02, "learning_rate": 4.8968921547495584e-05, "loss": 4.2808, "step": 62976 }, { "epoch": 0.02, "learning_rate": 4.8960535599985064e-05, "loss": 4.2822, "step": 63488 }, { "epoch": 0.02, "learning_rate": 4.8952149652474544e-05, "loss": 4.2753, "step": 64000 }, { "epoch": 0.02, "learning_rate": 4.8943763704964024e-05, "loss": 4.2792, "step": 64512 }, { "epoch": 0.02, "learning_rate": 4.8935377757453504e-05, "loss": 4.2714, "step": 65024 }, { "epoch": 0.02, "learning_rate": 4.892700818874671e-05, "loss": 4.2714, "step": 65536 }, { "epoch": 0.02, "learning_rate": 4.891862224123619e-05, "loss": 4.2639, "step": 66048 }, { "epoch": 0.02, "learning_rate": 4.891023629372567e-05, "loss": 4.282, "step": 66560 }, { "epoch": 0.02, "learning_rate": 4.890185034621515e-05, "loss": 4.2663, "step": 67072 }, { "epoch": 0.02, "learning_rate": 4.889346439870464e-05, "loss": 4.2584, "step": 67584 }, { "epoch": 0.02, "learning_rate": 4.888507845119412e-05, "loss": 4.2544, "step": 68096 }, { "epoch": 0.02, "learning_rate": 4.88766925036836e-05, "loss": 4.264, "step": 68608 }, { "epoch": 0.02, "learning_rate": 4.886832293497681e-05, "loss": 4.2577, "step": 69120 }, { "epoch": 0.02, "learning_rate": 4.885995336627002e-05, "loss": 4.2639, "step": 69632 }, { "epoch": 0.02, "learning_rate": 4.88515674187595e-05, "loss": 4.2487, "step": 70144 }, { "epoch": 0.02, "learning_rate": 4.884318147124898e-05, "loss": 4.2566, "step": 70656 }, { "epoch": 0.02, "learning_rate": 4.883479552373846e-05, "loss": 4.2496, "step": 71168 }, { "epoch": 0.02, "learning_rate": 4.882640957622794e-05, "loss": 4.2508, "step": 71680 }, { "epoch": 0.02, "learning_rate": 4.881802362871742e-05, "loss": 4.2409, "step": 72192 }, { "epoch": 0.02, "learning_rate": 4.88096376812069e-05, "loss": 4.2506, "step": 72704 }, { "epoch": 0.02, "learning_rate": 4.880125173369638e-05, "loss": 4.237, "step": 73216 }, { "epoch": 0.02, "learning_rate": 4.879289854379332e-05, "loss": 4.2273, "step": 73728 }, { "epoch": 0.02, "learning_rate": 4.87845125962828e-05, "loss": 4.2476, "step": 74240 }, { "epoch": 0.02, "learning_rate": 4.877612664877228e-05, "loss": 4.2333, "step": 74752 }, { "epoch": 0.02, "learning_rate": 4.876774070126176e-05, "loss": 4.2325, "step": 75264 }, { "epoch": 0.02, "learning_rate": 4.875935475375124e-05, "loss": 4.2383, "step": 75776 }, { "epoch": 0.02, "learning_rate": 4.875096880624072e-05, "loss": 4.2219, "step": 76288 }, { "epoch": 0.03, "eval_loss": 4.19382905960083, "eval_runtime": 350.9337, "eval_samples_per_second": 1087.359, "eval_steps_per_second": 33.981, "step": 76320 }, { "epoch": 1.0, "learning_rate": 4.87425828587302e-05, "loss": 4.2137, "step": 76800 }, { "epoch": 1.0, "learning_rate": 4.873419691121968e-05, "loss": 4.2158, "step": 77312 }, { "epoch": 1.0, "learning_rate": 4.872582734251289e-05, "loss": 4.2212, "step": 77824 }, { "epoch": 1.0, "learning_rate": 4.871744139500237e-05, "loss": 4.2153, "step": 78336 }, { "epoch": 1.0, "learning_rate": 4.870905544749185e-05, "loss": 4.2214, "step": 78848 }, { "epoch": 1.0, "learning_rate": 4.870068587878506e-05, "loss": 4.2092, "step": 79360 }, { "epoch": 1.0, "learning_rate": 4.869229993127454e-05, "loss": 4.2096, "step": 79872 }, { "epoch": 1.0, "learning_rate": 4.8683913983764027e-05, "loss": 4.2015, "step": 80384 }, { "epoch": 1.0, "learning_rate": 4.8675528036253507e-05, "loss": 4.2152, "step": 80896 }, { "epoch": 1.0, "learning_rate": 4.8667142088742986e-05, "loss": 4.1981, "step": 81408 }, { "epoch": 1.0, "learning_rate": 4.8658772520036196e-05, "loss": 4.1967, "step": 81920 }, { "epoch": 1.0, "learning_rate": 4.8650386572525676e-05, "loss": 4.1991, "step": 82432 }, { "epoch": 1.0, "learning_rate": 4.8642017003818885e-05, "loss": 4.1946, "step": 82944 }, { "epoch": 1.0, "learning_rate": 4.8633631056308365e-05, "loss": 4.1878, "step": 83456 }, { "epoch": 1.0, "learning_rate": 4.8625245108797845e-05, "loss": 4.1881, "step": 83968 }, { "epoch": 1.0, "learning_rate": 4.8616859161287324e-05, "loss": 4.1725, "step": 84480 }, { "epoch": 1.0, "learning_rate": 4.8608473213776804e-05, "loss": 4.1837, "step": 84992 }, { "epoch": 1.0, "learning_rate": 4.860008726626628e-05, "loss": 4.1761, "step": 85504 }, { "epoch": 1.0, "learning_rate": 4.8591701318755764e-05, "loss": 4.1701, "step": 86016 }, { "epoch": 1.0, "learning_rate": 4.8583315371245244e-05, "loss": 4.1965, "step": 86528 }, { "epoch": 1.0, "learning_rate": 4.857494580253846e-05, "loss": 4.1733, "step": 87040 }, { "epoch": 1.0, "learning_rate": 4.856655985502793e-05, "loss": 4.1776, "step": 87552 }, { "epoch": 1.0, "learning_rate": 4.855817390751741e-05, "loss": 4.1751, "step": 88064 }, { "epoch": 1.0, "learning_rate": 4.854978796000689e-05, "loss": 4.1891, "step": 88576 }, { "epoch": 1.0, "learning_rate": 4.854141839130011e-05, "loss": 4.1604, "step": 89088 }, { "epoch": 1.0, "learning_rate": 4.853303244378958e-05, "loss": 4.1647, "step": 89600 }, { "epoch": 1.0, "learning_rate": 4.852464649627906e-05, "loss": 4.1694, "step": 90112 }, { "epoch": 1.0, "learning_rate": 4.851626054876854e-05, "loss": 4.1674, "step": 90624 }, { "epoch": 1.0, "learning_rate": 4.850789098006175e-05, "loss": 4.1577, "step": 91136 }, { "epoch": 1.01, "learning_rate": 4.849950503255123e-05, "loss": 4.1559, "step": 91648 }, { "epoch": 1.01, "learning_rate": 4.849111908504072e-05, "loss": 4.1627, "step": 92160 }, { "epoch": 1.01, "learning_rate": 4.84827331375302e-05, "loss": 4.1628, "step": 92672 }, { "epoch": 1.01, "learning_rate": 4.847434719001968e-05, "loss": 4.1662, "step": 93184 }, { "epoch": 1.01, "learning_rate": 4.846597762131289e-05, "loss": 4.1563, "step": 93696 }, { "epoch": 1.01, "learning_rate": 4.845759167380237e-05, "loss": 4.1519, "step": 94208 }, { "epoch": 1.01, "learning_rate": 4.844920572629185e-05, "loss": 4.1597, "step": 94720 }, { "epoch": 1.01, "learning_rate": 4.844081977878133e-05, "loss": 4.1329, "step": 95232 }, { "epoch": 1.01, "learning_rate": 4.8432450210074536e-05, "loss": 4.1532, "step": 95744 }, { "epoch": 1.01, "learning_rate": 4.8424064262564016e-05, "loss": 4.1302, "step": 96256 }, { "epoch": 1.01, "learning_rate": 4.8415678315053496e-05, "loss": 4.1429, "step": 96768 }, { "epoch": 1.01, "learning_rate": 4.8407292367542976e-05, "loss": 4.1369, "step": 97280 }, { "epoch": 1.01, "learning_rate": 4.8398922798836185e-05, "loss": 4.1466, "step": 97792 }, { "epoch": 1.01, "learning_rate": 4.839053685132567e-05, "loss": 4.1406, "step": 98304 }, { "epoch": 1.01, "learning_rate": 4.838215090381515e-05, "loss": 4.1317, "step": 98816 }, { "epoch": 1.01, "learning_rate": 4.837376495630463e-05, "loss": 4.141, "step": 99328 }, { "epoch": 1.01, "learning_rate": 4.836539538759784e-05, "loss": 4.1318, "step": 99840 }, { "epoch": 1.01, "learning_rate": 4.835700944008732e-05, "loss": 4.142, "step": 100352 }, { "epoch": 1.01, "learning_rate": 4.83486234925768e-05, "loss": 4.117, "step": 100864 }, { "epoch": 1.01, "learning_rate": 4.834025392387001e-05, "loss": 4.1176, "step": 101376 }, { "epoch": 1.01, "learning_rate": 4.833186797635949e-05, "loss": 4.1338, "step": 101888 }, { "epoch": 1.01, "learning_rate": 4.832348202884897e-05, "loss": 4.1343, "step": 102400 }, { "epoch": 1.01, "learning_rate": 4.831509608133845e-05, "loss": 4.1175, "step": 102912 }, { "epoch": 1.01, "learning_rate": 4.830671013382793e-05, "loss": 4.1149, "step": 103424 }, { "epoch": 1.01, "learning_rate": 4.829832418631741e-05, "loss": 4.1232, "step": 103936 }, { "epoch": 1.01, "learning_rate": 4.828993823880689e-05, "loss": 4.1059, "step": 104448 }, { "epoch": 1.01, "learning_rate": 4.828155229129637e-05, "loss": 4.1311, "step": 104960 }, { "epoch": 1.01, "learning_rate": 4.8273182722589585e-05, "loss": 4.1108, "step": 105472 }, { "epoch": 1.01, "learning_rate": 4.8264796775079065e-05, "loss": 4.1188, "step": 105984 }, { "epoch": 1.01, "learning_rate": 4.8256410827568545e-05, "loss": 4.1123, "step": 106496 }, { "epoch": 1.01, "learning_rate": 4.8248024880058025e-05, "loss": 4.1021, "step": 107008 }, { "epoch": 1.01, "learning_rate": 4.8239655311351234e-05, "loss": 4.116, "step": 107520 }, { "epoch": 1.01, "learning_rate": 4.8231269363840714e-05, "loss": 4.1023, "step": 108032 }, { "epoch": 1.01, "learning_rate": 4.8222883416330194e-05, "loss": 4.101, "step": 108544 }, { "epoch": 1.01, "learning_rate": 4.8214497468819674e-05, "loss": 4.0972, "step": 109056 }, { "epoch": 1.01, "learning_rate": 4.820612790011288e-05, "loss": 4.1172, "step": 109568 }, { "epoch": 1.01, "learning_rate": 4.819774195260236e-05, "loss": 4.0964, "step": 110080 }, { "epoch": 1.01, "learning_rate": 4.818935600509184e-05, "loss": 4.0988, "step": 110592 }, { "epoch": 1.01, "learning_rate": 4.818097005758132e-05, "loss": 4.0884, "step": 111104 }, { "epoch": 1.01, "learning_rate": 4.817260048887454e-05, "loss": 4.0962, "step": 111616 }, { "epoch": 1.01, "learning_rate": 4.816421454136402e-05, "loss": 4.1103, "step": 112128 }, { "epoch": 1.01, "learning_rate": 4.81558285938535e-05, "loss": 4.1056, "step": 112640 }, { "epoch": 1.01, "learning_rate": 4.814744264634298e-05, "loss": 4.0938, "step": 113152 }, { "epoch": 1.01, "learning_rate": 4.813907307763619e-05, "loss": 4.1045, "step": 113664 }, { "epoch": 1.01, "learning_rate": 4.813068713012567e-05, "loss": 4.1081, "step": 114176 }, { "epoch": 1.01, "learning_rate": 4.812230118261515e-05, "loss": 4.0936, "step": 114688 }, { "epoch": 1.01, "learning_rate": 4.811391523510463e-05, "loss": 4.0982, "step": 115200 }, { "epoch": 1.01, "learning_rate": 4.810554566639784e-05, "loss": 4.0889, "step": 115712 }, { "epoch": 1.01, "learning_rate": 4.809715971888732e-05, "loss": 4.0787, "step": 116224 }, { "epoch": 1.01, "learning_rate": 4.80887737713768e-05, "loss": 4.0819, "step": 116736 }, { "epoch": 1.01, "learning_rate": 4.808038782386628e-05, "loss": 4.0854, "step": 117248 }, { "epoch": 1.01, "learning_rate": 4.807201825515949e-05, "loss": 4.09, "step": 117760 }, { "epoch": 1.01, "learning_rate": 4.806363230764897e-05, "loss": 4.1036, "step": 118272 }, { "epoch": 1.01, "learning_rate": 4.805524636013845e-05, "loss": 4.0916, "step": 118784 }, { "epoch": 1.01, "learning_rate": 4.804686041262793e-05, "loss": 4.0693, "step": 119296 }, { "epoch": 1.01, "learning_rate": 4.803849084392114e-05, "loss": 4.0814, "step": 119808 }, { "epoch": 1.01, "learning_rate": 4.803010489641062e-05, "loss": 4.0845, "step": 120320 }, { "epoch": 1.01, "learning_rate": 4.80217189489001e-05, "loss": 4.0808, "step": 120832 }, { "epoch": 1.01, "learning_rate": 4.801333300138958e-05, "loss": 4.0733, "step": 121344 }, { "epoch": 1.01, "learning_rate": 4.800496343268279e-05, "loss": 4.0742, "step": 121856 }, { "epoch": 1.02, "learning_rate": 4.799657748517227e-05, "loss": 4.0728, "step": 122368 }, { "epoch": 1.02, "learning_rate": 4.798819153766175e-05, "loss": 4.0756, "step": 122880 }, { "epoch": 1.02, "learning_rate": 4.797980559015123e-05, "loss": 4.07, "step": 123392 }, { "epoch": 1.02, "learning_rate": 4.797141964264071e-05, "loss": 4.0765, "step": 123904 }, { "epoch": 1.02, "learning_rate": 4.796303369513019e-05, "loss": 4.0719, "step": 124416 }, { "epoch": 1.02, "learning_rate": 4.7954664126423406e-05, "loss": 4.0758, "step": 124928 }, { "epoch": 1.02, "learning_rate": 4.7946278178912886e-05, "loss": 4.0591, "step": 125440 }, { "epoch": 1.02, "learning_rate": 4.793789223140236e-05, "loss": 4.0698, "step": 125952 }, { "epoch": 1.02, "learning_rate": 4.792950628389184e-05, "loss": 4.0661, "step": 126464 }, { "epoch": 1.02, "learning_rate": 4.792112033638132e-05, "loss": 4.0693, "step": 126976 }, { "epoch": 1.02, "learning_rate": 4.79127343888708e-05, "loss": 4.0709, "step": 127488 }, { "epoch": 1.02, "learning_rate": 4.790434844136028e-05, "loss": 4.0593, "step": 128000 }, { "epoch": 1.02, "learning_rate": 4.789597887265349e-05, "loss": 4.0607, "step": 128512 }, { "epoch": 1.02, "learning_rate": 4.788759292514297e-05, "loss": 4.0603, "step": 129024 }, { "epoch": 1.02, "learning_rate": 4.787920697763245e-05, "loss": 4.0641, "step": 129536 }, { "epoch": 1.02, "learning_rate": 4.7870821030121935e-05, "loss": 4.0493, "step": 130048 }, { "epoch": 1.02, "learning_rate": 4.7862451461415144e-05, "loss": 4.0517, "step": 130560 }, { "epoch": 1.02, "learning_rate": 4.7854065513904624e-05, "loss": 4.0618, "step": 131072 }, { "epoch": 1.02, "learning_rate": 4.7845679566394104e-05, "loss": 4.0504, "step": 131584 }, { "epoch": 1.02, "learning_rate": 4.783730999768731e-05, "loss": 4.0511, "step": 132096 }, { "epoch": 1.02, "learning_rate": 4.782892405017679e-05, "loss": 4.0465, "step": 132608 }, { "epoch": 1.02, "learning_rate": 4.782053810266627e-05, "loss": 4.0417, "step": 133120 }, { "epoch": 1.02, "learning_rate": 4.781215215515575e-05, "loss": 4.0648, "step": 133632 }, { "epoch": 1.02, "learning_rate": 4.780376620764523e-05, "loss": 4.045, "step": 134144 }, { "epoch": 1.02, "learning_rate": 4.779538026013471e-05, "loss": 4.0533, "step": 134656 }, { "epoch": 1.02, "learning_rate": 4.778699431262419e-05, "loss": 4.0499, "step": 135168 }, { "epoch": 1.02, "learning_rate": 4.777860836511367e-05, "loss": 4.0656, "step": 135680 }, { "epoch": 1.02, "learning_rate": 4.777023879640689e-05, "loss": 4.051, "step": 136192 }, { "epoch": 1.02, "learning_rate": 4.776185284889637e-05, "loss": 4.0368, "step": 136704 }, { "epoch": 1.02, "learning_rate": 4.775346690138585e-05, "loss": 4.0452, "step": 137216 }, { "epoch": 1.02, "learning_rate": 4.774508095387533e-05, "loss": 4.052, "step": 137728 }, { "epoch": 1.02, "learning_rate": 4.773671138516854e-05, "loss": 4.036, "step": 138240 }, { "epoch": 1.02, "learning_rate": 4.7728341816461747e-05, "loss": 4.0426, "step": 138752 }, { "epoch": 1.02, "learning_rate": 4.7719955868951227e-05, "loss": 4.0367, "step": 139264 }, { "epoch": 1.02, "learning_rate": 4.7711569921440707e-05, "loss": 4.0478, "step": 139776 }, { "epoch": 1.02, "learning_rate": 4.7703183973930186e-05, "loss": 4.036, "step": 140288 }, { "epoch": 1.02, "learning_rate": 4.7694798026419666e-05, "loss": 4.0447, "step": 140800 }, { "epoch": 1.02, "learning_rate": 4.7686412078909146e-05, "loss": 4.0387, "step": 141312 }, { "epoch": 1.02, "learning_rate": 4.7678026131398626e-05, "loss": 4.0405, "step": 141824 }, { "epoch": 1.02, "learning_rate": 4.766965656269184e-05, "loss": 4.0317, "step": 142336 }, { "epoch": 1.02, "learning_rate": 4.766127061518132e-05, "loss": 4.0538, "step": 142848 }, { "epoch": 1.02, "learning_rate": 4.76528846676708e-05, "loss": 4.0419, "step": 143360 }, { "epoch": 1.02, "learning_rate": 4.764449872016028e-05, "loss": 4.0269, "step": 143872 }, { "epoch": 1.02, "learning_rate": 4.763612915145349e-05, "loss": 4.0294, "step": 144384 }, { "epoch": 1.02, "learning_rate": 4.762774320394297e-05, "loss": 4.0358, "step": 144896 }, { "epoch": 1.02, "learning_rate": 4.761935725643245e-05, "loss": 4.037, "step": 145408 }, { "epoch": 1.02, "learning_rate": 4.761097130892193e-05, "loss": 4.0468, "step": 145920 }, { "epoch": 1.02, "learning_rate": 4.760260174021514e-05, "loss": 4.0271, "step": 146432 }, { "epoch": 1.02, "learning_rate": 4.759421579270462e-05, "loss": 4.0368, "step": 146944 }, { "epoch": 1.02, "learning_rate": 4.75858298451941e-05, "loss": 4.0306, "step": 147456 }, { "epoch": 1.02, "learning_rate": 4.757744389768358e-05, "loss": 4.0367, "step": 147968 }, { "epoch": 1.02, "learning_rate": 4.7569074328976796e-05, "loss": 4.0284, "step": 148480 }, { "epoch": 1.02, "learning_rate": 4.7560688381466276e-05, "loss": 4.0341, "step": 148992 }, { "epoch": 1.02, "learning_rate": 4.7552302433955756e-05, "loss": 4.0237, "step": 149504 }, { "epoch": 1.02, "learning_rate": 4.7543916486445236e-05, "loss": 4.0192, "step": 150016 }, { "epoch": 1.02, "learning_rate": 4.7535546917738445e-05, "loss": 4.0375, "step": 150528 }, { "epoch": 1.02, "learning_rate": 4.7527160970227925e-05, "loss": 4.0256, "step": 151040 }, { "epoch": 1.02, "learning_rate": 4.7518775022717405e-05, "loss": 4.0242, "step": 151552 }, { "epoch": 1.02, "learning_rate": 4.7510389075206885e-05, "loss": 4.027, "step": 152064 }, { "epoch": 1.02, "learning_rate": 4.7502003127696365e-05, "loss": 4.0179, "step": 152576 }, { "epoch": 1.03, "eval_loss": 4.026176452636719, "eval_runtime": 347.0521, "eval_samples_per_second": 1099.521, "eval_steps_per_second": 34.361, "step": 152640 }, { "epoch": 0.0, "learning_rate": 4.7493617180185845e-05, "loss": 4.0104, "step": 153088 }, { "epoch": 0.0, "learning_rate": 4.748523123267532e-05, "loss": 4.0104, "step": 153600 }, { "epoch": 0.0, "learning_rate": 4.74768452851648e-05, "loss": 4.0234, "step": 154112 }, { "epoch": 0.0, "learning_rate": 4.746845933765428e-05, "loss": 4.0124, "step": 154624 }, { "epoch": 0.0, "learning_rate": 4.7460073390143764e-05, "loss": 4.027, "step": 155136 }, { "epoch": 0.0, "learning_rate": 4.7451687442633244e-05, "loss": 4.0102, "step": 155648 }, { "epoch": 0.0, "learning_rate": 4.7443301495122724e-05, "loss": 4.0131, "step": 156160 }, { "epoch": 0.0, "learning_rate": 4.7434915547612204e-05, "loss": 4.0062, "step": 156672 }, { "epoch": 0.0, "learning_rate": 4.7426529600101684e-05, "loss": 4.023, "step": 157184 }, { "epoch": 0.0, "learning_rate": 4.7418143652591164e-05, "loss": 4.0077, "step": 157696 }, { "epoch": 0.0, "learning_rate": 4.7409757705080644e-05, "loss": 4.005, "step": 158208 }, { "epoch": 0.0, "learning_rate": 4.740138813637385e-05, "loss": 4.0056, "step": 158720 }, { "epoch": 0.0, "learning_rate": 4.739303494647079e-05, "loss": 4.0061, "step": 159232 }, { "epoch": 0.0, "learning_rate": 4.738464899896027e-05, "loss": 3.9997, "step": 159744 }, { "epoch": 0.0, "learning_rate": 4.737626305144975e-05, "loss": 4.0025, "step": 160256 }, { "epoch": 0.0, "learning_rate": 4.736787710393923e-05, "loss": 3.9911, "step": 160768 }, { "epoch": 0.0, "learning_rate": 4.735949115642871e-05, "loss": 3.9964, "step": 161280 }, { "epoch": 0.0, "learning_rate": 4.73511052089182e-05, "loss": 3.9906, "step": 161792 }, { "epoch": 0.0, "learning_rate": 4.734271926140768e-05, "loss": 3.9877, "step": 162304 }, { "epoch": 0.0, "learning_rate": 4.733433331389716e-05, "loss": 4.0202, "step": 162816 }, { "epoch": 0.0, "learning_rate": 4.732594736638664e-05, "loss": 3.9942, "step": 163328 }, { "epoch": 0.0, "learning_rate": 4.731756141887612e-05, "loss": 3.9924, "step": 163840 }, { "epoch": 0.0, "learning_rate": 4.73091754713656e-05, "loss": 4.0001, "step": 164352 }, { "epoch": 0.0, "learning_rate": 4.730080590265881e-05, "loss": 4.0074, "step": 164864 }, { "epoch": 0.0, "learning_rate": 4.7292436333952016e-05, "loss": 3.9851, "step": 165376 }, { "epoch": 0.0, "learning_rate": 4.7284050386441496e-05, "loss": 3.9918, "step": 165888 }, { "epoch": 0.0, "learning_rate": 4.7275664438930976e-05, "loss": 3.9908, "step": 166400 }, { "epoch": 0.0, "learning_rate": 4.7267278491420456e-05, "loss": 3.9955, "step": 166912 }, { "epoch": 0.0, "learning_rate": 4.7258892543909936e-05, "loss": 3.981, "step": 167424 }, { "epoch": 0.01, "learning_rate": 4.7250506596399416e-05, "loss": 3.9856, "step": 167936 }, { "epoch": 0.01, "learning_rate": 4.7242120648888896e-05, "loss": 3.9876, "step": 168448 }, { "epoch": 0.01, "learning_rate": 4.723373470137838e-05, "loss": 3.994, "step": 168960 }, { "epoch": 0.01, "learning_rate": 4.722536513267159e-05, "loss": 4.0011, "step": 169472 }, { "epoch": 0.01, "learning_rate": 4.721697918516107e-05, "loss": 3.9884, "step": 169984 }, { "epoch": 0.01, "learning_rate": 4.720859323765055e-05, "loss": 3.9814, "step": 170496 }, { "epoch": 0.01, "learning_rate": 4.720020729014003e-05, "loss": 3.9918, "step": 171008 }, { "epoch": 0.01, "learning_rate": 4.719183772143324e-05, "loss": 3.9722, "step": 171520 }, { "epoch": 0.01, "learning_rate": 4.718345177392272e-05, "loss": 3.9857, "step": 172032 }, { "epoch": 0.01, "learning_rate": 4.71750658264122e-05, "loss": 3.9676, "step": 172544 }, { "epoch": 0.01, "learning_rate": 4.716669625770541e-05, "loss": 3.9759, "step": 173056 }, { "epoch": 0.01, "learning_rate": 4.715831031019489e-05, "loss": 3.9779, "step": 173568 }, { "epoch": 0.01, "learning_rate": 4.714992436268437e-05, "loss": 3.9877, "step": 174080 }, { "epoch": 0.01, "learning_rate": 4.714153841517385e-05, "loss": 3.9805, "step": 174592 }, { "epoch": 0.01, "learning_rate": 4.713315246766333e-05, "loss": 3.9737, "step": 175104 }, { "epoch": 0.01, "learning_rate": 4.712476652015281e-05, "loss": 3.9787, "step": 175616 }, { "epoch": 0.01, "learning_rate": 4.711638057264229e-05, "loss": 3.9753, "step": 176128 }, { "epoch": 0.01, "learning_rate": 4.710799462513177e-05, "loss": 3.9828, "step": 176640 }, { "epoch": 0.01, "learning_rate": 4.709962505642498e-05, "loss": 3.962, "step": 177152 }, { "epoch": 0.01, "learning_rate": 4.7091255487718194e-05, "loss": 3.9604, "step": 177664 }, { "epoch": 0.01, "learning_rate": 4.7082869540207674e-05, "loss": 3.9801, "step": 178176 }, { "epoch": 0.01, "learning_rate": 4.7074483592697154e-05, "loss": 3.9756, "step": 178688 }, { "epoch": 0.01, "learning_rate": 4.706609764518663e-05, "loss": 3.9642, "step": 179200 }, { "epoch": 0.01, "learning_rate": 4.705772807647984e-05, "loss": 3.9645, "step": 179712 }, { "epoch": 0.01, "learning_rate": 4.704934212896932e-05, "loss": 3.9684, "step": 180224 }, { "epoch": 0.01, "learning_rate": 4.70409561814588e-05, "loss": 3.9535, "step": 180736 }, { "epoch": 0.01, "learning_rate": 4.703257023394828e-05, "loss": 3.9767, "step": 181248 }, { "epoch": 0.01, "learning_rate": 4.702418428643776e-05, "loss": 3.963, "step": 181760 }, { "epoch": 0.01, "learning_rate": 4.701579833892724e-05, "loss": 3.9681, "step": 182272 }, { "epoch": 0.01, "learning_rate": 4.700741239141672e-05, "loss": 3.9616, "step": 182784 }, { "epoch": 0.01, "learning_rate": 4.69990264439062e-05, "loss": 3.9598, "step": 183296 }, { "epoch": 0.01, "learning_rate": 4.699065687519941e-05, "loss": 3.9616, "step": 183808 }, { "epoch": 0.01, "learning_rate": 4.698227092768889e-05, "loss": 3.9593, "step": 184320 }, { "epoch": 0.01, "learning_rate": 4.697388498017837e-05, "loss": 3.9532, "step": 184832 }, { "epoch": 0.01, "learning_rate": 4.696549903266785e-05, "loss": 3.9515, "step": 185344 }, { "epoch": 0.01, "learning_rate": 4.695712946396106e-05, "loss": 3.9704, "step": 185856 }, { "epoch": 0.01, "learning_rate": 4.694874351645054e-05, "loss": 3.9534, "step": 186368 }, { "epoch": 0.01, "learning_rate": 4.694035756894003e-05, "loss": 3.9543, "step": 186880 }, { "epoch": 0.01, "learning_rate": 4.693197162142951e-05, "loss": 3.9463, "step": 187392 }, { "epoch": 0.01, "learning_rate": 4.692358567391899e-05, "loss": 3.9538, "step": 187904 }, { "epoch": 0.01, "learning_rate": 4.691519972640847e-05, "loss": 3.9699, "step": 188416 }, { "epoch": 0.01, "learning_rate": 4.6906830157701677e-05, "loss": 3.9646, "step": 188928 }, { "epoch": 0.01, "learning_rate": 4.6898444210191157e-05, "loss": 3.9563, "step": 189440 }, { "epoch": 0.01, "learning_rate": 4.6890058262680636e-05, "loss": 3.9637, "step": 189952 }, { "epoch": 0.01, "learning_rate": 4.6881672315170116e-05, "loss": 3.9676, "step": 190464 }, { "epoch": 0.01, "learning_rate": 4.6873286367659596e-05, "loss": 3.951, "step": 190976 }, { "epoch": 0.01, "learning_rate": 4.6864900420149076e-05, "loss": 3.9603, "step": 191488 }, { "epoch": 0.01, "learning_rate": 4.6856514472638556e-05, "loss": 3.9525, "step": 192000 }, { "epoch": 0.01, "learning_rate": 4.6848144903931765e-05, "loss": 3.9434, "step": 192512 }, { "epoch": 0.01, "learning_rate": 4.683977533522498e-05, "loss": 3.9507, "step": 193024 }, { "epoch": 0.01, "learning_rate": 4.683138938771446e-05, "loss": 3.9461, "step": 193536 }, { "epoch": 0.01, "learning_rate": 4.682300344020394e-05, "loss": 3.9553, "step": 194048 }, { "epoch": 0.01, "learning_rate": 4.681461749269342e-05, "loss": 3.9636, "step": 194560 }, { "epoch": 0.01, "learning_rate": 4.680624792398663e-05, "loss": 3.9592, "step": 195072 }, { "epoch": 0.01, "learning_rate": 4.679786197647611e-05, "loss": 3.9332, "step": 195584 }, { "epoch": 0.01, "learning_rate": 4.678947602896559e-05, "loss": 3.9493, "step": 196096 }, { "epoch": 0.01, "learning_rate": 4.678109008145507e-05, "loss": 3.9493, "step": 196608 }, { "epoch": 0.01, "learning_rate": 4.677270413394455e-05, "loss": 3.9496, "step": 197120 }, { "epoch": 0.01, "learning_rate": 4.676431818643403e-05, "loss": 3.9436, "step": 197632 }, { "epoch": 0.01, "learning_rate": 4.675593223892351e-05, "loss": 3.9373, "step": 198144 }, { "epoch": 0.02, "learning_rate": 4.674756267021672e-05, "loss": 3.9492, "step": 198656 }, { "epoch": 0.02, "learning_rate": 4.67391767227062e-05, "loss": 3.9407, "step": 199168 }, { "epoch": 0.02, "learning_rate": 4.673079077519568e-05, "loss": 3.9401, "step": 199680 }, { "epoch": 0.02, "learning_rate": 4.672240482768516e-05, "loss": 3.9466, "step": 200192 }, { "epoch": 0.02, "learning_rate": 4.671401888017464e-05, "loss": 3.9419, "step": 200704 }, { "epoch": 0.02, "learning_rate": 4.6705649311467855e-05, "loss": 3.9496, "step": 201216 }, { "epoch": 0.02, "learning_rate": 4.6697263363957335e-05, "loss": 3.9349, "step": 201728 }, { "epoch": 0.02, "learning_rate": 4.6688877416446815e-05, "loss": 3.9382, "step": 202240 }, { "epoch": 0.02, "learning_rate": 4.668049146893629e-05, "loss": 3.9386, "step": 202752 }, { "epoch": 0.02, "learning_rate": 4.667210552142577e-05, "loss": 3.9465, "step": 203264 }, { "epoch": 0.02, "learning_rate": 4.6663735952718984e-05, "loss": 3.9444, "step": 203776 }, { "epoch": 0.02, "learning_rate": 4.665535000520846e-05, "loss": 3.9345, "step": 204288 }, { "epoch": 0.02, "learning_rate": 4.664696405769794e-05, "loss": 3.9358, "step": 204800 }, { "epoch": 0.02, "learning_rate": 4.663857811018742e-05, "loss": 3.9356, "step": 205312 }, { "epoch": 0.02, "learning_rate": 4.663020854148063e-05, "loss": 3.9395, "step": 205824 }, { "epoch": 0.02, "learning_rate": 4.662182259397011e-05, "loss": 3.9231, "step": 206336 }, { "epoch": 0.02, "learning_rate": 4.661343664645959e-05, "loss": 3.9274, "step": 206848 }, { "epoch": 0.02, "learning_rate": 4.660505069894907e-05, "loss": 3.943, "step": 207360 }, { "epoch": 0.02, "learning_rate": 4.659666475143855e-05, "loss": 3.9329, "step": 207872 }, { "epoch": 0.02, "learning_rate": 4.658829518273176e-05, "loss": 3.9269, "step": 208384 }, { "epoch": 0.02, "learning_rate": 4.657990923522124e-05, "loss": 3.9252, "step": 208896 }, { "epoch": 0.02, "learning_rate": 4.657152328771072e-05, "loss": 3.9241, "step": 209408 }, { "epoch": 0.02, "learning_rate": 4.65631373402002e-05, "loss": 3.9406, "step": 209920 }, { "epoch": 0.02, "learning_rate": 4.655475139268968e-05, "loss": 3.9297, "step": 210432 }, { "epoch": 0.02, "learning_rate": 4.654636544517916e-05, "loss": 3.9292, "step": 210944 }, { "epoch": 0.02, "learning_rate": 4.653799587647237e-05, "loss": 3.9327, "step": 211456 }, { "epoch": 0.02, "learning_rate": 4.652960992896185e-05, "loss": 3.9469, "step": 211968 }, { "epoch": 0.02, "learning_rate": 4.652122398145134e-05, "loss": 3.9334, "step": 212480 }, { "epoch": 0.02, "learning_rate": 4.651283803394082e-05, "loss": 3.9207, "step": 212992 }, { "epoch": 0.02, "learning_rate": 4.65044520864303e-05, "loss": 3.9294, "step": 213504 }, { "epoch": 0.02, "learning_rate": 4.649606613891978e-05, "loss": 3.9308, "step": 214016 }, { "epoch": 0.02, "learning_rate": 4.6487696570212986e-05, "loss": 3.9212, "step": 214528 }, { "epoch": 0.02, "learning_rate": 4.6479310622702466e-05, "loss": 3.9237, "step": 215040 }, { "epoch": 0.02, "learning_rate": 4.6470924675191946e-05, "loss": 3.92, "step": 215552 }, { "epoch": 0.02, "learning_rate": 4.6462538727681426e-05, "loss": 3.9329, "step": 216064 }, { "epoch": 0.02, "learning_rate": 4.6454152780170906e-05, "loss": 3.9175, "step": 216576 }, { "epoch": 0.02, "learning_rate": 4.6445783211464115e-05, "loss": 3.9331, "step": 217088 }, { "epoch": 0.02, "learning_rate": 4.6437397263953595e-05, "loss": 3.916, "step": 217600 }, { "epoch": 0.02, "learning_rate": 4.6429011316443075e-05, "loss": 3.9277, "step": 218112 }, { "epoch": 0.02, "learning_rate": 4.6420625368932555e-05, "loss": 3.9156, "step": 218624 }, { "epoch": 0.02, "learning_rate": 4.641225580022577e-05, "loss": 3.9374, "step": 219136 }, { "epoch": 0.02, "learning_rate": 4.640386985271525e-05, "loss": 3.9298, "step": 219648 }, { "epoch": 0.02, "learning_rate": 4.639548390520473e-05, "loss": 3.9207, "step": 220160 }, { "epoch": 0.02, "learning_rate": 4.638709795769421e-05, "loss": 3.912, "step": 220672 }, { "epoch": 0.02, "learning_rate": 4.637871201018369e-05, "loss": 3.9251, "step": 221184 }, { "epoch": 0.02, "learning_rate": 4.63703424414769e-05, "loss": 3.9218, "step": 221696 }, { "epoch": 0.02, "learning_rate": 4.636195649396638e-05, "loss": 3.9344, "step": 222208 }, { "epoch": 0.02, "learning_rate": 4.635357054645586e-05, "loss": 3.9146, "step": 222720 }, { "epoch": 0.02, "learning_rate": 4.634518459894534e-05, "loss": 3.9282, "step": 223232 }, { "epoch": 0.02, "learning_rate": 4.633679865143482e-05, "loss": 3.9202, "step": 223744 }, { "epoch": 0.02, "learning_rate": 4.632841270392429e-05, "loss": 3.9311, "step": 224256 }, { "epoch": 0.02, "learning_rate": 4.632002675641377e-05, "loss": 3.9145, "step": 224768 }, { "epoch": 0.02, "learning_rate": 4.631165718770699e-05, "loss": 3.923, "step": 225280 }, { "epoch": 0.02, "learning_rate": 4.6303287619000204e-05, "loss": 3.9164, "step": 225792 }, { "epoch": 0.02, "learning_rate": 4.6294901671489684e-05, "loss": 3.9095, "step": 226304 }, { "epoch": 0.02, "learning_rate": 4.6286515723979164e-05, "loss": 3.9293, "step": 226816 }, { "epoch": 0.02, "learning_rate": 4.6278129776468644e-05, "loss": 3.9225, "step": 227328 }, { "epoch": 0.02, "learning_rate": 4.626974382895812e-05, "loss": 3.9099, "step": 227840 }, { "epoch": 0.02, "learning_rate": 4.626137426025133e-05, "loss": 3.9197, "step": 228352 }, { "epoch": 0.02, "learning_rate": 4.625298831274081e-05, "loss": 3.9092, "step": 228864 }, { "epoch": 0.03, "eval_loss": 3.952585220336914, "eval_runtime": 319.2814, "eval_samples_per_second": 1195.156, "eval_steps_per_second": 37.349, "step": 228960 } ], "logging_steps": 512, "max_steps": 3052726, "num_train_epochs": 9223372036854775807, "save_steps": 10, "total_flos": 1.5824830797219226e+17, "trial_name": null, "trial_params": null }