{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9999973749767029, "global_step": 190474, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.27, "learning_rate": 1.0000000000000002e-06, "loss": 3.5718, "step": 500 }, { "epoch": 0.54, "learning_rate": 2.0000000000000003e-06, "loss": 3.5525, "step": 1000 }, { "epoch": 0.81, "learning_rate": 3e-06, "loss": 3.5047, "step": 1500 }, { "epoch": 1.08, "learning_rate": 4.000000000000001e-06, "loss": 3.4853, "step": 2000 }, { "epoch": 1.35, "learning_rate": 5e-06, "loss": 3.4635, "step": 2500 }, { "epoch": 1.61, "learning_rate": 6e-06, "loss": 3.4339, "step": 3000 }, { "epoch": 1.88, "learning_rate": 7e-06, "loss": 3.4143, "step": 3500 }, { "epoch": 2.15, "learning_rate": 8.000000000000001e-06, "loss": 3.3797, "step": 4000 }, { "epoch": 2.42, "learning_rate": 9e-06, "loss": 3.368, "step": 4500 }, { "epoch": 2.69, "learning_rate": 1e-05, "loss": 3.3519, "step": 5000 }, { "epoch": 2.96, "learning_rate": 7.944078947368422e-06, "loss": 3.3406, "step": 5500 }, { "epoch": 3.23, "learning_rate": 5.888157894736842e-06, "loss": 3.2885, "step": 6000 }, { "epoch": 3.5, "learning_rate": 3.832236842105263e-06, "loss": 3.262, "step": 6500 }, { "epoch": 3.77, "learning_rate": 1.7763157894736844e-06, "loss": 3.2664, "step": 7000 }, { "epoch": 4.0, "step": 7432, "total_flos": 32244153748534272, "train_runtime": 4035.7935, "train_samples_per_second": 1.842 }, { "epoch": 4.04, "learning_rate": 1.36e-07, "loss": 3.2257, "step": 7500 }, { "epoch": 4.31, "learning_rate": 1.1360000000000002e-06, "loss": 3.2579, "step": 8000 }, { "epoch": 4.57, "learning_rate": 2.1360000000000004e-06, "loss": 3.2497, "step": 8500 }, { "epoch": 4.84, "learning_rate": 3.136e-06, "loss": 3.2399, "step": 9000 }, { "epoch": 5.11, "learning_rate": 4.136000000000001e-06, "loss": 3.2354, "step": 9500 }, { "epoch": 5.38, "learning_rate": 5.136e-06, "loss": 3.2227, "step": 10000 }, { "epoch": 5.65, "learning_rate": 6.136000000000001e-06, "loss": 3.2309, "step": 10500 }, { "epoch": 5.92, "learning_rate": 7.136000000000001e-06, "loss": 3.237, "step": 11000 }, { "epoch": 6.0, "step": 11148, "total_flos": 48368948381409792, "train_runtime": 2016.9377, "train_samples_per_second": 5.527 }, { "epoch": 0.06, "learning_rate": 7.040000000000001e-07, "loss": 3.1385, "step": 11500 }, { "epoch": 0.06, "learning_rate": 1.7040000000000001e-06, "loss": 3.1219, "step": 12000 }, { "epoch": 0.07, "learning_rate": 2.704e-06, "loss": 3.0988, "step": 12500 }, { "epoch": 0.07, "learning_rate": 3.7040000000000005e-06, "loss": 3.0695, "step": 13000 }, { "epoch": 0.07, "learning_rate": 4.704e-06, "loss": 3.0795, "step": 13500 }, { "epoch": 0.07, "learning_rate": 5.704000000000001e-06, "loss": 3.0666, "step": 14000 }, { "epoch": 0.08, "learning_rate": 6.7040000000000005e-06, "loss": 3.0593, "step": 14500 }, { "epoch": 0.08, "learning_rate": 7.704000000000001e-06, "loss": 3.0466, "step": 15000 }, { "epoch": 0.08, "learning_rate": 8.704e-06, "loss": 3.0547, "step": 15500 }, { "epoch": 0.08, "learning_rate": 9.704e-06, "loss": 3.0598, "step": 16000 }, { "epoch": 0.09, "learning_rate": 9.981021598714645e-06, "loss": 3.0721, "step": 16500 }, { "epoch": 0.09, "learning_rate": 9.954063642343403e-06, "loss": 3.0614, "step": 17000 }, { "epoch": 0.09, "learning_rate": 9.927105685972159e-06, "loss": 3.0434, "step": 17500 }, { "epoch": 0.09, "learning_rate": 9.900147729600915e-06, "loss": 3.0653, "step": 18000 }, { "epoch": 0.1, "learning_rate": 9.873189773229673e-06, "loss": 3.0618, "step": 18500 }, { "epoch": 0.1, "learning_rate": 9.846231816858427e-06, "loss": 3.0674, "step": 19000 }, { "epoch": 0.1, "learning_rate": 9.819273860487185e-06, "loss": 3.0515, "step": 19500 }, { "epoch": 0.11, "learning_rate": 9.792315904115941e-06, "loss": 3.0559, "step": 20000 }, { "epoch": 0.11, "learning_rate": 9.765357947744698e-06, "loss": 3.0658, "step": 20500 }, { "epoch": 0.11, "learning_rate": 9.738399991373455e-06, "loss": 3.0525, "step": 21000 }, { "epoch": 0.11, "learning_rate": 9.711442035002212e-06, "loss": 3.0425, "step": 21500 }, { "epoch": 0.12, "learning_rate": 9.684484078630968e-06, "loss": 3.0293, "step": 22000 }, { "epoch": 0.12, "learning_rate": 9.657526122259726e-06, "loss": 3.05, "step": 22500 }, { "epoch": 0.12, "learning_rate": 9.63056816588848e-06, "loss": 3.053, "step": 23000 }, { "epoch": 0.12, "learning_rate": 9.603610209517238e-06, "loss": 3.0306, "step": 23500 }, { "epoch": 0.13, "learning_rate": 9.576652253145994e-06, "loss": 3.0416, "step": 24000 }, { "epoch": 0.13, "learning_rate": 9.54969429677475e-06, "loss": 3.0292, "step": 24500 }, { "epoch": 0.13, "learning_rate": 9.522736340403508e-06, "loss": 3.0431, "step": 25000 }, { "epoch": 0.13, "learning_rate": 9.495778384032264e-06, "loss": 3.0429, "step": 25500 }, { "epoch": 0.14, "learning_rate": 9.46882042766102e-06, "loss": 3.0305, "step": 26000 }, { "epoch": 0.14, "learning_rate": 9.441862471289779e-06, "loss": 3.0355, "step": 26500 }, { "epoch": 0.14, "learning_rate": 9.414904514918533e-06, "loss": 3.0251, "step": 27000 }, { "epoch": 0.14, "learning_rate": 9.387946558547291e-06, "loss": 3.0323, "step": 27500 }, { "epoch": 0.15, "learning_rate": 9.360988602176047e-06, "loss": 3.0118, "step": 28000 }, { "epoch": 0.15, "learning_rate": 9.334030645804803e-06, "loss": 3.0138, "step": 28500 }, { "epoch": 0.15, "learning_rate": 9.307072689433561e-06, "loss": 3.0217, "step": 29000 }, { "epoch": 0.15, "learning_rate": 9.280114733062316e-06, "loss": 3.0138, "step": 29500 }, { "epoch": 0.16, "learning_rate": 9.253156776691074e-06, "loss": 3.0402, "step": 30000 }, { "epoch": 0.16, "learning_rate": 9.22619882031983e-06, "loss": 3.0297, "step": 30500 }, { "epoch": 0.16, "learning_rate": 9.199240863948586e-06, "loss": 3.0147, "step": 31000 }, { "epoch": 0.17, "learning_rate": 9.172282907577344e-06, "loss": 3.0317, "step": 31500 }, { "epoch": 0.17, "learning_rate": 9.1453249512061e-06, "loss": 3.021, "step": 32000 }, { "epoch": 0.17, "learning_rate": 9.118366994834856e-06, "loss": 3.0284, "step": 32500 }, { "epoch": 0.17, "learning_rate": 9.091409038463614e-06, "loss": 3.0274, "step": 33000 }, { "epoch": 0.18, "learning_rate": 9.064451082092369e-06, "loss": 3.0163, "step": 33500 }, { "epoch": 0.18, "learning_rate": 9.037493125721126e-06, "loss": 3.0173, "step": 34000 }, { "epoch": 0.18, "learning_rate": 9.010535169349883e-06, "loss": 3.033, "step": 34500 }, { "epoch": 0.18, "learning_rate": 8.983577212978639e-06, "loss": 3.0174, "step": 35000 }, { "epoch": 0.19, "learning_rate": 8.956619256607397e-06, "loss": 3.0274, "step": 35500 }, { "epoch": 0.19, "learning_rate": 8.929661300236153e-06, "loss": 3.0003, "step": 36000 }, { "epoch": 0.19, "learning_rate": 8.902703343864909e-06, "loss": 3.0088, "step": 36500 }, { "epoch": 0.19, "learning_rate": 8.875745387493667e-06, "loss": 3.0126, "step": 37000 }, { "epoch": 0.2, "learning_rate": 8.848787431122421e-06, "loss": 2.9996, "step": 37500 }, { "epoch": 0.2, "learning_rate": 8.82182947475118e-06, "loss": 3.0292, "step": 38000 }, { "epoch": 0.2, "learning_rate": 8.794871518379935e-06, "loss": 3.008, "step": 38500 }, { "epoch": 0.2, "learning_rate": 8.767913562008692e-06, "loss": 3.0032, "step": 39000 }, { "epoch": 0.21, "learning_rate": 8.74095560563745e-06, "loss": 2.9903, "step": 39500 }, { "epoch": 0.21, "learning_rate": 8.713997649266204e-06, "loss": 3.0021, "step": 40000 }, { "epoch": 0.21, "learning_rate": 8.687039692894962e-06, "loss": 3.0082, "step": 40500 }, { "epoch": 0.22, "learning_rate": 8.660081736523718e-06, "loss": 2.9998, "step": 41000 }, { "epoch": 0.22, "learning_rate": 8.633123780152474e-06, "loss": 2.9956, "step": 41500 }, { "epoch": 0.22, "learning_rate": 8.606165823781232e-06, "loss": 3.0029, "step": 42000 }, { "epoch": 0.22, "learning_rate": 8.579207867409988e-06, "loss": 2.9969, "step": 42500 }, { "epoch": 0.23, "learning_rate": 8.552249911038744e-06, "loss": 2.9917, "step": 43000 }, { "epoch": 0.23, "learning_rate": 8.525291954667502e-06, "loss": 2.9977, "step": 43500 }, { "epoch": 0.23, "learning_rate": 8.498333998296257e-06, "loss": 3.0194, "step": 44000 }, { "epoch": 0.23, "learning_rate": 8.471376041925015e-06, "loss": 2.9922, "step": 44500 }, { "epoch": 0.24, "learning_rate": 8.444418085553771e-06, "loss": 3.0042, "step": 45000 }, { "epoch": 0.24, "learning_rate": 8.417460129182527e-06, "loss": 3.0048, "step": 45500 }, { "epoch": 0.24, "learning_rate": 8.390502172811285e-06, "loss": 2.9955, "step": 46000 }, { "epoch": 0.24, "learning_rate": 8.363544216440041e-06, "loss": 3.0094, "step": 46500 }, { "epoch": 0.25, "learning_rate": 8.336586260068797e-06, "loss": 2.9846, "step": 47000 }, { "epoch": 0.25, "learning_rate": 8.309628303697555e-06, "loss": 3.0013, "step": 47500 }, { "epoch": 0.25, "learning_rate": 8.28267034732631e-06, "loss": 2.9834, "step": 48000 }, { "epoch": 0.25, "learning_rate": 8.255712390955068e-06, "loss": 3.0037, "step": 48500 }, { "epoch": 0.26, "learning_rate": 8.228754434583824e-06, "loss": 2.9997, "step": 49000 }, { "epoch": 0.26, "learning_rate": 8.20179647821258e-06, "loss": 2.9993, "step": 49500 }, { "epoch": 0.26, "learning_rate": 8.174838521841338e-06, "loss": 2.979, "step": 50000 }, { "epoch": 0.27, "learning_rate": 8.147880565470094e-06, "loss": 2.9908, "step": 50500 }, { "epoch": 0.27, "learning_rate": 8.12092260909885e-06, "loss": 2.9872, "step": 51000 }, { "epoch": 0.27, "learning_rate": 8.093964652727606e-06, "loss": 2.9869, "step": 51500 }, { "epoch": 0.27, "learning_rate": 8.067006696356363e-06, "loss": 2.9975, "step": 52000 }, { "epoch": 0.28, "learning_rate": 8.04004873998512e-06, "loss": 2.9916, "step": 52500 }, { "epoch": 0.28, "learning_rate": 8.013090783613877e-06, "loss": 2.9964, "step": 53000 }, { "epoch": 0.28, "learning_rate": 7.986132827242633e-06, "loss": 2.9879, "step": 53500 }, { "epoch": 0.28, "learning_rate": 7.95917487087139e-06, "loss": 2.9832, "step": 54000 }, { "epoch": 0.29, "learning_rate": 7.932216914500145e-06, "loss": 2.9927, "step": 54500 }, { "epoch": 0.29, "learning_rate": 7.905258958128903e-06, "loss": 2.981, "step": 55000 }, { "epoch": 0.29, "learning_rate": 7.87830100175766e-06, "loss": 2.9894, "step": 55500 }, { "epoch": 0.29, "learning_rate": 7.851343045386415e-06, "loss": 2.987, "step": 56000 }, { "epoch": 0.3, "learning_rate": 7.824385089015173e-06, "loss": 2.9632, "step": 56500 }, { "epoch": 0.3, "learning_rate": 7.79742713264393e-06, "loss": 2.9863, "step": 57000 }, { "epoch": 0.3, "learning_rate": 7.770469176272686e-06, "loss": 2.9848, "step": 57500 }, { "epoch": 0.3, "learning_rate": 7.743511219901444e-06, "loss": 2.987, "step": 58000 }, { "epoch": 0.31, "learning_rate": 7.716553263530198e-06, "loss": 2.9731, "step": 58500 }, { "epoch": 0.31, "learning_rate": 7.689595307158956e-06, "loss": 2.9886, "step": 59000 }, { "epoch": 0.31, "learning_rate": 7.662637350787712e-06, "loss": 2.9826, "step": 59500 }, { "epoch": 0.32, "learning_rate": 7.635679394416468e-06, "loss": 2.9773, "step": 60000 }, { "epoch": 0.32, "learning_rate": 7.608721438045225e-06, "loss": 2.958, "step": 60500 }, { "epoch": 0.32, "learning_rate": 7.5817634816739815e-06, "loss": 2.9887, "step": 61000 }, { "epoch": 0.32, "learning_rate": 7.5548055253027386e-06, "loss": 2.9685, "step": 61500 }, { "epoch": 0.33, "learning_rate": 7.527847568931496e-06, "loss": 2.9632, "step": 62000 }, { "epoch": 0.33, "learning_rate": 7.500889612560252e-06, "loss": 2.9816, "step": 62500 }, { "epoch": 0.33, "learning_rate": 7.473931656189009e-06, "loss": 2.9726, "step": 63000 }, { "epoch": 0.33, "learning_rate": 7.446973699817764e-06, "loss": 2.9753, "step": 63500 }, { "epoch": 0.34, "learning_rate": 7.420015743446521e-06, "loss": 2.9785, "step": 64000 }, { "epoch": 0.34, "learning_rate": 7.393057787075278e-06, "loss": 2.9749, "step": 64500 }, { "epoch": 0.34, "learning_rate": 7.366099830704034e-06, "loss": 2.9722, "step": 65000 }, { "epoch": 0.34, "learning_rate": 7.3391418743327914e-06, "loss": 2.9636, "step": 65500 }, { "epoch": 0.35, "learning_rate": 7.312183917961548e-06, "loss": 2.9849, "step": 66000 }, { "epoch": 0.35, "learning_rate": 7.285225961590305e-06, "loss": 2.9696, "step": 66500 }, { "epoch": 0.35, "learning_rate": 7.258268005219062e-06, "loss": 2.9667, "step": 67000 }, { "epoch": 0.35, "learning_rate": 7.231310048847817e-06, "loss": 2.9635, "step": 67500 }, { "epoch": 0.36, "learning_rate": 7.204352092476574e-06, "loss": 2.9669, "step": 68000 }, { "epoch": 0.36, "learning_rate": 7.177394136105331e-06, "loss": 2.9778, "step": 68500 }, { "epoch": 0.36, "learning_rate": 7.150436179734087e-06, "loss": 2.9681, "step": 69000 }, { "epoch": 0.36, "learning_rate": 7.123478223362844e-06, "loss": 2.9739, "step": 69500 }, { "epoch": 0.37, "learning_rate": 7.0965202669916e-06, "loss": 2.9737, "step": 70000 }, { "epoch": 0.37, "learning_rate": 7.069562310620357e-06, "loss": 2.9659, "step": 70500 }, { "epoch": 0.37, "learning_rate": 7.042604354249114e-06, "loss": 2.9698, "step": 71000 }, { "epoch": 0.38, "learning_rate": 7.01564639787787e-06, "loss": 2.9675, "step": 71500 }, { "epoch": 0.38, "learning_rate": 6.988688441506627e-06, "loss": 2.9718, "step": 72000 }, { "epoch": 0.38, "learning_rate": 6.961730485135384e-06, "loss": 2.9665, "step": 72500 }, { "epoch": 0.38, "learning_rate": 6.93477252876414e-06, "loss": 2.9883, "step": 73000 }, { "epoch": 0.39, "learning_rate": 6.907814572392897e-06, "loss": 2.9842, "step": 73500 }, { "epoch": 0.39, "learning_rate": 6.8808566160216525e-06, "loss": 2.9607, "step": 74000 }, { "epoch": 0.39, "learning_rate": 6.8538986596504095e-06, "loss": 2.9776, "step": 74500 }, { "epoch": 0.39, "learning_rate": 6.8269407032791666e-06, "loss": 2.963, "step": 75000 }, { "epoch": 0.4, "learning_rate": 6.799982746907923e-06, "loss": 2.9571, "step": 75500 }, { "epoch": 0.4, "learning_rate": 6.77302479053668e-06, "loss": 2.9495, "step": 76000 }, { "epoch": 0.4, "learning_rate": 6.746066834165436e-06, "loss": 2.9601, "step": 76500 }, { "epoch": 0.4, "learning_rate": 6.719108877794193e-06, "loss": 2.9645, "step": 77000 }, { "epoch": 0.41, "learning_rate": 6.69215092142295e-06, "loss": 2.9559, "step": 77500 }, { "epoch": 0.41, "learning_rate": 6.665192965051705e-06, "loss": 2.9583, "step": 78000 }, { "epoch": 0.41, "learning_rate": 6.638235008680462e-06, "loss": 2.9543, "step": 78500 }, { "epoch": 0.41, "learning_rate": 6.6112770523092194e-06, "loss": 2.9585, "step": 79000 }, { "epoch": 0.42, "learning_rate": 6.584319095937976e-06, "loss": 2.9437, "step": 79500 }, { "epoch": 0.42, "learning_rate": 6.557361139566733e-06, "loss": 2.9573, "step": 80000 }, { "epoch": 0.42, "learning_rate": 6.530403183195488e-06, "loss": 2.9595, "step": 80500 }, { "epoch": 0.43, "learning_rate": 6.503445226824245e-06, "loss": 2.9693, "step": 81000 }, { "epoch": 0.43, "learning_rate": 6.476487270453002e-06, "loss": 2.956, "step": 81500 }, { "epoch": 0.43, "learning_rate": 6.449529314081758e-06, "loss": 2.9568, "step": 82000 }, { "epoch": 0.43, "learning_rate": 6.422571357710515e-06, "loss": 2.9555, "step": 82500 }, { "epoch": 0.44, "learning_rate": 6.395613401339272e-06, "loss": 2.9467, "step": 83000 }, { "epoch": 0.44, "learning_rate": 6.3686554449680285e-06, "loss": 2.9605, "step": 83500 }, { "epoch": 0.44, "learning_rate": 6.3416974885967855e-06, "loss": 2.9549, "step": 84000 }, { "epoch": 0.44, "learning_rate": 6.314739532225541e-06, "loss": 2.9449, "step": 84500 }, { "epoch": 0.45, "learning_rate": 6.287781575854298e-06, "loss": 2.9564, "step": 85000 }, { "epoch": 0.45, "learning_rate": 6.260823619483055e-06, "loss": 2.9448, "step": 85500 }, { "epoch": 0.45, "learning_rate": 6.233865663111811e-06, "loss": 2.9518, "step": 86000 }, { "epoch": 0.45, "learning_rate": 6.206907706740568e-06, "loss": 2.9597, "step": 86500 }, { "epoch": 0.46, "learning_rate": 6.179949750369324e-06, "loss": 2.9664, "step": 87000 }, { "epoch": 0.46, "learning_rate": 6.152991793998081e-06, "loss": 2.9503, "step": 87500 }, { "epoch": 0.46, "learning_rate": 6.126033837626838e-06, "loss": 2.931, "step": 88000 }, { "epoch": 0.46, "learning_rate": 6.099075881255594e-06, "loss": 2.9675, "step": 88500 }, { "epoch": 0.47, "learning_rate": 6.072117924884351e-06, "loss": 2.9647, "step": 89000 }, { "epoch": 0.47, "learning_rate": 6.045159968513108e-06, "loss": 2.9345, "step": 89500 }, { "epoch": 0.47, "learning_rate": 6.018202012141864e-06, "loss": 2.9479, "step": 90000 }, { "epoch": 0.48, "learning_rate": 5.991244055770621e-06, "loss": 2.947, "step": 90500 }, { "epoch": 0.48, "learning_rate": 5.964286099399376e-06, "loss": 2.9549, "step": 91000 }, { "epoch": 0.48, "learning_rate": 5.937328143028133e-06, "loss": 2.9594, "step": 91500 }, { "epoch": 0.48, "learning_rate": 5.91037018665689e-06, "loss": 2.9543, "step": 92000 }, { "epoch": 0.49, "learning_rate": 5.883412230285647e-06, "loss": 2.9481, "step": 92500 }, { "epoch": 0.49, "learning_rate": 5.856454273914404e-06, "loss": 2.9593, "step": 93000 }, { "epoch": 0.49, "learning_rate": 5.829496317543161e-06, "loss": 2.94, "step": 93500 }, { "epoch": 0.49, "learning_rate": 5.802538361171917e-06, "loss": 2.9484, "step": 94000 }, { "epoch": 0.5, "learning_rate": 5.775580404800674e-06, "loss": 2.9431, "step": 94500 }, { "epoch": 0.5, "learning_rate": 5.748622448429429e-06, "loss": 2.9449, "step": 95000 }, { "epoch": 0.5, "learning_rate": 5.721664492058186e-06, "loss": 2.9369, "step": 95500 }, { "epoch": 0.5, "learning_rate": 5.694706535686943e-06, "loss": 2.9542, "step": 96000 }, { "epoch": 0.51, "learning_rate": 5.6677485793156994e-06, "loss": 2.9468, "step": 96500 }, { "epoch": 0.51, "learning_rate": 5.6407906229444565e-06, "loss": 2.9551, "step": 97000 }, { "epoch": 0.51, "learning_rate": 5.613832666573213e-06, "loss": 2.9282, "step": 97500 }, { "epoch": 0.51, "learning_rate": 5.58687471020197e-06, "loss": 2.9475, "step": 98000 }, { "epoch": 0.52, "learning_rate": 5.559916753830727e-06, "loss": 2.9546, "step": 98500 }, { "epoch": 0.52, "learning_rate": 5.532958797459482e-06, "loss": 2.9335, "step": 99000 }, { "epoch": 0.52, "learning_rate": 5.506000841088239e-06, "loss": 2.9486, "step": 99500 }, { "epoch": 0.53, "learning_rate": 5.479042884716996e-06, "loss": 2.9595, "step": 100000 }, { "epoch": 0.53, "learning_rate": 5.452084928345752e-06, "loss": 2.9223, "step": 100500 }, { "epoch": 0.53, "learning_rate": 5.425126971974509e-06, "loss": 2.9461, "step": 101000 }, { "epoch": 0.53, "learning_rate": 5.3981690156032655e-06, "loss": 2.9471, "step": 101500 }, { "epoch": 0.54, "learning_rate": 5.371211059232022e-06, "loss": 2.9323, "step": 102000 }, { "epoch": 0.54, "learning_rate": 5.344253102860779e-06, "loss": 2.9288, "step": 102500 }, { "epoch": 0.54, "learning_rate": 5.317295146489535e-06, "loss": 2.9378, "step": 103000 }, { "epoch": 0.54, "learning_rate": 5.290337190118292e-06, "loss": 2.9221, "step": 103500 }, { "epoch": 0.55, "learning_rate": 5.263379233747049e-06, "loss": 2.9339, "step": 104000 }, { "epoch": 0.55, "learning_rate": 5.236421277375805e-06, "loss": 2.9353, "step": 104500 }, { "epoch": 0.55, "learning_rate": 5.209463321004562e-06, "loss": 2.9405, "step": 105000 }, { "epoch": 0.55, "learning_rate": 5.1825053646333175e-06, "loss": 2.9514, "step": 105500 }, { "epoch": 0.56, "learning_rate": 5.155547408262075e-06, "loss": 2.9346, "step": 106000 }, { "epoch": 0.56, "learning_rate": 5.128589451890832e-06, "loss": 2.9421, "step": 106500 }, { "epoch": 0.56, "learning_rate": 5.101631495519588e-06, "loss": 2.9353, "step": 107000 }, { "epoch": 0.56, "learning_rate": 5.074673539148345e-06, "loss": 2.933, "step": 107500 }, { "epoch": 0.57, "learning_rate": 5.047715582777101e-06, "loss": 2.9221, "step": 108000 }, { "epoch": 0.57, "learning_rate": 5.020757626405858e-06, "loss": 2.9621, "step": 108500 }, { "epoch": 0.57, "learning_rate": 4.993799670034614e-06, "loss": 2.9304, "step": 109000 }, { "epoch": 0.57, "learning_rate": 4.966841713663371e-06, "loss": 2.9428, "step": 109500 }, { "epoch": 0.58, "learning_rate": 4.9398837572921274e-06, "loss": 2.9215, "step": 110000 }, { "epoch": 0.58, "learning_rate": 4.9129258009208845e-06, "loss": 2.948, "step": 110500 }, { "epoch": 0.58, "learning_rate": 4.885967844549641e-06, "loss": 2.9427, "step": 111000 }, { "epoch": 0.59, "learning_rate": 4.859009888178398e-06, "loss": 2.9462, "step": 111500 }, { "epoch": 0.59, "learning_rate": 4.832051931807154e-06, "loss": 2.9374, "step": 112000 }, { "epoch": 0.59, "learning_rate": 4.805093975435911e-06, "loss": 2.9145, "step": 112500 }, { "epoch": 0.59, "learning_rate": 4.778136019064667e-06, "loss": 2.9384, "step": 113000 }, { "epoch": 0.6, "learning_rate": 4.751178062693424e-06, "loss": 2.9349, "step": 113500 }, { "epoch": 0.6, "learning_rate": 4.72422010632218e-06, "loss": 2.9303, "step": 114000 }, { "epoch": 0.6, "learning_rate": 4.6972621499509365e-06, "loss": 2.9306, "step": 114500 }, { "epoch": 0.6, "learning_rate": 4.6703041935796935e-06, "loss": 2.921, "step": 115000 }, { "epoch": 0.61, "learning_rate": 4.6433462372084506e-06, "loss": 2.928, "step": 115500 }, { "epoch": 0.61, "learning_rate": 4.616388280837207e-06, "loss": 2.9289, "step": 116000 }, { "epoch": 0.61, "learning_rate": 4.589430324465963e-06, "loss": 2.9219, "step": 116500 }, { "epoch": 0.61, "learning_rate": 4.56247236809472e-06, "loss": 2.914, "step": 117000 }, { "epoch": 0.62, "learning_rate": 4.535514411723476e-06, "loss": 2.9339, "step": 117500 }, { "epoch": 0.62, "learning_rate": 4.508556455352233e-06, "loss": 2.9264, "step": 118000 }, { "epoch": 0.62, "learning_rate": 4.481598498980989e-06, "loss": 2.9312, "step": 118500 }, { "epoch": 0.62, "learning_rate": 4.454640542609746e-06, "loss": 2.9132, "step": 119000 }, { "epoch": 0.63, "learning_rate": 4.427682586238503e-06, "loss": 2.9201, "step": 119500 }, { "epoch": 0.63, "learning_rate": 4.40072462986726e-06, "loss": 2.9214, "step": 120000 }, { "epoch": 0.63, "learning_rate": 4.373766673496016e-06, "loss": 2.9197, "step": 120500 }, { "epoch": 0.64, "learning_rate": 4.346808717124773e-06, "loss": 2.9238, "step": 121000 }, { "epoch": 0.64, "learning_rate": 4.319850760753529e-06, "loss": 2.9114, "step": 121500 }, { "epoch": 0.64, "learning_rate": 4.292892804382286e-06, "loss": 2.9142, "step": 122000 }, { "epoch": 0.64, "learning_rate": 4.265934848011042e-06, "loss": 2.9223, "step": 122500 }, { "epoch": 0.65, "learning_rate": 4.238976891639799e-06, "loss": 2.9169, "step": 123000 }, { "epoch": 0.65, "learning_rate": 4.2120189352685554e-06, "loss": 2.9305, "step": 123500 }, { "epoch": 0.65, "learning_rate": 4.1850609788973125e-06, "loss": 2.9298, "step": 124000 }, { "epoch": 0.65, "learning_rate": 4.158103022526069e-06, "loss": 2.9412, "step": 124500 }, { "epoch": 0.66, "learning_rate": 4.131145066154825e-06, "loss": 2.9149, "step": 125000 }, { "epoch": 0.66, "learning_rate": 4.104187109783582e-06, "loss": 2.9191, "step": 125500 }, { "epoch": 0.66, "learning_rate": 4.077229153412339e-06, "loss": 2.9188, "step": 126000 }, { "epoch": 0.66, "learning_rate": 4.050271197041095e-06, "loss": 2.9163, "step": 126500 }, { "epoch": 0.67, "learning_rate": 4.023313240669851e-06, "loss": 2.9082, "step": 127000 }, { "epoch": 0.67, "learning_rate": 3.996355284298608e-06, "loss": 2.9169, "step": 127500 }, { "epoch": 0.67, "learning_rate": 3.9693973279273645e-06, "loss": 2.9091, "step": 128000 }, { "epoch": 0.67, "learning_rate": 3.9424393715561215e-06, "loss": 2.9196, "step": 128500 }, { "epoch": 0.68, "learning_rate": 3.915481415184878e-06, "loss": 2.9287, "step": 129000 }, { "epoch": 0.68, "learning_rate": 3.888523458813635e-06, "loss": 2.8979, "step": 129500 }, { "epoch": 0.68, "learning_rate": 3.861565502442391e-06, "loss": 2.9169, "step": 130000 }, { "epoch": 0.69, "learning_rate": 3.834607546071148e-06, "loss": 2.9144, "step": 130500 }, { "epoch": 0.69, "learning_rate": 3.8076495896999046e-06, "loss": 2.9094, "step": 131000 }, { "epoch": 0.69, "learning_rate": 3.7806916333286608e-06, "loss": 2.9113, "step": 131500 }, { "epoch": 0.69, "learning_rate": 3.7537336769574174e-06, "loss": 2.9179, "step": 132000 }, { "epoch": 0.7, "learning_rate": 3.7267757205861744e-06, "loss": 2.9321, "step": 132500 }, { "epoch": 0.7, "learning_rate": 3.6998177642149306e-06, "loss": 2.9284, "step": 133000 }, { "epoch": 0.7, "learning_rate": 3.672859807843687e-06, "loss": 2.9231, "step": 133500 }, { "epoch": 0.7, "learning_rate": 3.645901851472444e-06, "loss": 2.9114, "step": 134000 }, { "epoch": 0.71, "learning_rate": 3.618943895101201e-06, "loss": 2.9173, "step": 134500 }, { "epoch": 0.71, "learning_rate": 3.591985938729957e-06, "loss": 2.9145, "step": 135000 }, { "epoch": 0.71, "learning_rate": 3.5650279823587136e-06, "loss": 2.9127, "step": 135500 }, { "epoch": 0.71, "learning_rate": 3.5380700259874702e-06, "loss": 2.9149, "step": 136000 }, { "epoch": 0.72, "learning_rate": 3.5111120696162273e-06, "loss": 2.926, "step": 136500 }, { "epoch": 0.72, "learning_rate": 3.4841541132449834e-06, "loss": 2.9061, "step": 137000 }, { "epoch": 0.72, "learning_rate": 3.45719615687374e-06, "loss": 2.9266, "step": 137500 }, { "epoch": 0.72, "learning_rate": 3.4302382005024967e-06, "loss": 2.9092, "step": 138000 }, { "epoch": 0.73, "learning_rate": 3.403280244131253e-06, "loss": 2.9268, "step": 138500 }, { "epoch": 0.73, "learning_rate": 3.37632228776001e-06, "loss": 2.9088, "step": 139000 }, { "epoch": 0.73, "learning_rate": 3.3493643313887665e-06, "loss": 2.8918, "step": 139500 }, { "epoch": 0.74, "learning_rate": 3.3224063750175227e-06, "loss": 2.9174, "step": 140000 }, { "epoch": 0.74, "learning_rate": 3.2954484186462793e-06, "loss": 2.9104, "step": 140500 }, { "epoch": 0.74, "learning_rate": 3.2684904622750363e-06, "loss": 2.9042, "step": 141000 }, { "epoch": 0.74, "learning_rate": 3.241532505903793e-06, "loss": 2.9035, "step": 141500 }, { "epoch": 0.75, "learning_rate": 3.214574549532549e-06, "loss": 2.8953, "step": 142000 }, { "epoch": 0.75, "learning_rate": 3.1876165931613057e-06, "loss": 2.9143, "step": 142500 }, { "epoch": 0.75, "learning_rate": 3.1606586367900627e-06, "loss": 2.9151, "step": 143000 }, { "epoch": 0.75, "learning_rate": 3.1337006804188193e-06, "loss": 2.9104, "step": 143500 }, { "epoch": 0.76, "learning_rate": 3.1067427240475755e-06, "loss": 2.9164, "step": 144000 }, { "epoch": 0.76, "learning_rate": 3.079784767676332e-06, "loss": 2.9027, "step": 144500 }, { "epoch": 0.76, "learning_rate": 3.052826811305089e-06, "loss": 2.9007, "step": 145000 }, { "epoch": 0.76, "learning_rate": 3.0258688549338454e-06, "loss": 2.9028, "step": 145500 }, { "epoch": 0.77, "learning_rate": 2.998910898562602e-06, "loss": 2.9095, "step": 146000 }, { "epoch": 0.77, "learning_rate": 2.9719529421913586e-06, "loss": 2.8995, "step": 146500 }, { "epoch": 0.77, "learning_rate": 2.9449949858201156e-06, "loss": 2.9016, "step": 147000 }, { "epoch": 0.77, "learning_rate": 2.9180370294488718e-06, "loss": 2.9078, "step": 147500 }, { "epoch": 0.78, "learning_rate": 2.8910790730776284e-06, "loss": 2.9225, "step": 148000 }, { "epoch": 0.78, "learning_rate": 2.864121116706385e-06, "loss": 2.8951, "step": 148500 }, { "epoch": 0.78, "learning_rate": 2.837163160335141e-06, "loss": 2.8937, "step": 149000 }, { "epoch": 0.78, "learning_rate": 2.8102052039638982e-06, "loss": 2.9105, "step": 149500 }, { "epoch": 0.79, "learning_rate": 2.783247247592655e-06, "loss": 2.9172, "step": 150000 }, { "epoch": 0.79, "learning_rate": 2.756289291221411e-06, "loss": 2.8935, "step": 150500 }, { "epoch": 0.79, "learning_rate": 2.7293313348501676e-06, "loss": 2.8989, "step": 151000 }, { "epoch": 0.8, "learning_rate": 2.7023733784789247e-06, "loss": 2.9197, "step": 151500 }, { "epoch": 0.8, "learning_rate": 2.6754154221076813e-06, "loss": 2.9014, "step": 152000 }, { "epoch": 0.8, "learning_rate": 2.6484574657364374e-06, "loss": 2.917, "step": 152500 }, { "epoch": 0.8, "learning_rate": 2.621499509365194e-06, "loss": 2.9114, "step": 153000 }, { "epoch": 0.81, "learning_rate": 2.594541552993951e-06, "loss": 2.8914, "step": 153500 }, { "epoch": 0.81, "learning_rate": 2.5675835966227077e-06, "loss": 2.8933, "step": 154000 }, { "epoch": 0.81, "learning_rate": 2.540625640251464e-06, "loss": 2.9082, "step": 154500 }, { "epoch": 0.81, "learning_rate": 2.5136676838802205e-06, "loss": 2.9024, "step": 155000 }, { "epoch": 0.82, "learning_rate": 2.486709727508977e-06, "loss": 2.8803, "step": 155500 }, { "epoch": 0.82, "learning_rate": 2.4597517711377337e-06, "loss": 2.9039, "step": 156000 }, { "epoch": 0.82, "learning_rate": 2.4327938147664903e-06, "loss": 2.9101, "step": 156500 }, { "epoch": 0.82, "learning_rate": 2.405835858395247e-06, "loss": 2.8997, "step": 157000 }, { "epoch": 0.83, "learning_rate": 2.3788779020240035e-06, "loss": 2.9082, "step": 157500 }, { "epoch": 0.83, "learning_rate": 2.35191994565276e-06, "loss": 2.8857, "step": 158000 }, { "epoch": 0.83, "learning_rate": 2.3249619892815167e-06, "loss": 2.9077, "step": 158500 }, { "epoch": 0.83, "learning_rate": 2.2980040329102734e-06, "loss": 2.8974, "step": 159000 }, { "epoch": 0.84, "learning_rate": 2.27104607653903e-06, "loss": 2.8819, "step": 159500 }, { "epoch": 0.84, "learning_rate": 2.2440881201677866e-06, "loss": 2.9061, "step": 160000 }, { "epoch": 0.84, "learning_rate": 2.217130163796543e-06, "loss": 2.9103, "step": 160500 }, { "epoch": 0.85, "learning_rate": 2.1901722074252994e-06, "loss": 2.9046, "step": 161000 }, { "epoch": 0.85, "learning_rate": 2.1632142510540564e-06, "loss": 2.8976, "step": 161500 }, { "epoch": 0.85, "learning_rate": 2.1362562946828126e-06, "loss": 2.8751, "step": 162000 }, { "epoch": 0.85, "learning_rate": 2.1092983383115696e-06, "loss": 2.9034, "step": 162500 }, { "epoch": 0.86, "learning_rate": 2.082340381940326e-06, "loss": 2.9018, "step": 163000 }, { "epoch": 0.86, "learning_rate": 2.055382425569083e-06, "loss": 2.8938, "step": 163500 }, { "epoch": 0.86, "learning_rate": 2.028424469197839e-06, "loss": 2.9216, "step": 164000 }, { "epoch": 0.86, "learning_rate": 2.001466512826596e-06, "loss": 2.8841, "step": 164500 }, { "epoch": 0.87, "learning_rate": 1.9745085564553522e-06, "loss": 2.893, "step": 165000 }, { "epoch": 0.87, "learning_rate": 1.9475506000841093e-06, "loss": 2.9049, "step": 165500 }, { "epoch": 0.87, "learning_rate": 1.9205926437128654e-06, "loss": 2.8978, "step": 166000 }, { "epoch": 0.87, "learning_rate": 1.8936346873416223e-06, "loss": 2.8871, "step": 166500 }, { "epoch": 0.88, "learning_rate": 1.8666767309703787e-06, "loss": 2.8934, "step": 167000 }, { "epoch": 0.88, "learning_rate": 1.8397187745991355e-06, "loss": 2.9071, "step": 167500 }, { "epoch": 0.88, "learning_rate": 1.8127608182278919e-06, "loss": 2.8993, "step": 168000 }, { "epoch": 0.88, "learning_rate": 1.7858028618566487e-06, "loss": 2.8957, "step": 168500 }, { "epoch": 0.89, "learning_rate": 1.758844905485405e-06, "loss": 2.9015, "step": 169000 }, { "epoch": 0.89, "learning_rate": 1.731886949114162e-06, "loss": 2.8916, "step": 169500 }, { "epoch": 0.89, "learning_rate": 1.7049289927429183e-06, "loss": 2.9013, "step": 170000 }, { "epoch": 0.9, "learning_rate": 1.6779710363716747e-06, "loss": 2.8928, "step": 170500 }, { "epoch": 0.9, "learning_rate": 1.6510130800004315e-06, "loss": 2.8813, "step": 171000 }, { "epoch": 0.9, "learning_rate": 1.624055123629188e-06, "loss": 2.8782, "step": 171500 }, { "epoch": 0.9, "learning_rate": 1.5970971672579447e-06, "loss": 2.8838, "step": 172000 }, { "epoch": 0.91, "learning_rate": 1.5701392108867011e-06, "loss": 2.8859, "step": 172500 }, { "epoch": 0.91, "learning_rate": 1.543181254515458e-06, "loss": 2.8822, "step": 173000 }, { "epoch": 0.91, "learning_rate": 1.5162232981442144e-06, "loss": 2.8794, "step": 173500 }, { "epoch": 0.91, "learning_rate": 1.489265341772971e-06, "loss": 2.894, "step": 174000 }, { "epoch": 0.92, "learning_rate": 1.4623073854017276e-06, "loss": 2.8849, "step": 174500 }, { "epoch": 0.92, "learning_rate": 1.4353494290304842e-06, "loss": 2.9072, "step": 175000 }, { "epoch": 0.92, "learning_rate": 1.4083914726592408e-06, "loss": 2.8869, "step": 175500 }, { "epoch": 0.92, "learning_rate": 1.3814335162879974e-06, "loss": 2.8873, "step": 176000 }, { "epoch": 0.93, "learning_rate": 1.3544755599167538e-06, "loss": 2.9072, "step": 176500 }, { "epoch": 0.93, "learning_rate": 1.3275176035455106e-06, "loss": 2.889, "step": 177000 }, { "epoch": 0.93, "learning_rate": 1.300559647174267e-06, "loss": 2.8639, "step": 177500 }, { "epoch": 0.93, "learning_rate": 1.2736016908030238e-06, "loss": 2.8928, "step": 178000 }, { "epoch": 0.94, "learning_rate": 1.2466437344317802e-06, "loss": 2.8948, "step": 178500 }, { "epoch": 0.94, "learning_rate": 1.2196857780605368e-06, "loss": 2.8877, "step": 179000 }, { "epoch": 0.94, "learning_rate": 1.1927278216892934e-06, "loss": 2.8897, "step": 179500 }, { "epoch": 0.95, "learning_rate": 1.16576986531805e-06, "loss": 2.8959, "step": 180000 }, { "epoch": 0.95, "learning_rate": 1.1388119089468067e-06, "loss": 2.8988, "step": 180500 }, { "epoch": 0.95, "learning_rate": 1.1118539525755633e-06, "loss": 2.8774, "step": 181000 }, { "epoch": 0.95, "learning_rate": 1.0848959962043199e-06, "loss": 2.8977, "step": 181500 }, { "epoch": 0.96, "learning_rate": 1.0579380398330765e-06, "loss": 2.8776, "step": 182000 }, { "epoch": 0.96, "learning_rate": 1.030980083461833e-06, "loss": 2.889, "step": 182500 }, { "epoch": 0.96, "learning_rate": 1.0040221270905897e-06, "loss": 2.8759, "step": 183000 }, { "epoch": 0.96, "learning_rate": 9.770641707193463e-07, "loss": 2.8768, "step": 183500 }, { "epoch": 0.97, "learning_rate": 9.501062143481028e-07, "loss": 2.8877, "step": 184000 }, { "epoch": 0.97, "learning_rate": 9.231482579768594e-07, "loss": 2.8839, "step": 184500 }, { "epoch": 0.97, "learning_rate": 8.96190301605616e-07, "loss": 2.8889, "step": 185000 }, { "epoch": 0.97, "learning_rate": 8.692323452343726e-07, "loss": 2.8838, "step": 185500 }, { "epoch": 0.98, "learning_rate": 8.42274388863129e-07, "loss": 2.8698, "step": 186000 }, { "epoch": 0.98, "learning_rate": 8.153164324918856e-07, "loss": 2.8761, "step": 186500 }, { "epoch": 0.98, "learning_rate": 7.883584761206422e-07, "loss": 2.8769, "step": 187000 }, { "epoch": 0.98, "learning_rate": 7.614005197493989e-07, "loss": 2.8713, "step": 187500 }, { "epoch": 0.99, "learning_rate": 7.344425633781555e-07, "loss": 2.8764, "step": 188000 }, { "epoch": 0.99, "learning_rate": 7.074846070069121e-07, "loss": 2.8854, "step": 188500 }, { "epoch": 0.99, "learning_rate": 6.805266506356687e-07, "loss": 2.8777, "step": 189000 }, { "epoch": 0.99, "learning_rate": 6.535686942644253e-07, "loss": 2.8941, "step": 189500 }, { "epoch": 1.0, "learning_rate": 6.266107378931818e-07, "loss": 2.8917, "step": 190000 }, { "epoch": 1.0, "step": 190474, "total_flos": 812201236873720320, "train_runtime": 31399.0337, "train_samples_per_second": 6.066 } ], "max_steps": 190474, "num_train_epochs": 1, "total_flos": 812201236873720320, "trial_name": null, "trial_params": null }