{ "best_metric": null, "best_model_checkpoint": null, "epoch": 20.0, "global_step": 269140, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04, "learning_rate": 9.981422308092442e-05, "loss": 6.7888, "step": 500 }, { "epoch": 0.07, "learning_rate": 9.962844616184886e-05, "loss": 6.2621, "step": 1000 }, { "epoch": 0.11, "learning_rate": 9.944266924277327e-05, "loss": 6.2021, "step": 1500 }, { "epoch": 0.15, "learning_rate": 9.92568923236977e-05, "loss": 6.1445, "step": 2000 }, { "epoch": 0.19, "learning_rate": 9.907111540462214e-05, "loss": 6.0937, "step": 2500 }, { "epoch": 0.22, "learning_rate": 9.888533848554656e-05, "loss": 6.0322, "step": 3000 }, { "epoch": 0.26, "learning_rate": 9.869956156647099e-05, "loss": 5.9909, "step": 3500 }, { "epoch": 0.3, "learning_rate": 9.851378464739541e-05, "loss": 5.965, "step": 4000 }, { "epoch": 0.33, "learning_rate": 9.832800772831984e-05, "loss": 5.9108, "step": 4500 }, { "epoch": 0.37, "learning_rate": 9.814223080924426e-05, "loss": 5.877, "step": 5000 }, { "epoch": 0.41, "learning_rate": 9.795645389016869e-05, "loss": 5.8644, "step": 5500 }, { "epoch": 0.45, "learning_rate": 9.777067697109311e-05, "loss": 5.8114, "step": 6000 }, { "epoch": 0.48, "learning_rate": 9.758490005201754e-05, "loss": 5.803, "step": 6500 }, { "epoch": 0.52, "learning_rate": 9.739912313294197e-05, "loss": 5.7799, "step": 7000 }, { "epoch": 0.56, "learning_rate": 9.721334621386639e-05, "loss": 5.7654, "step": 7500 }, { "epoch": 0.59, "learning_rate": 9.702756929479082e-05, "loss": 5.7631, "step": 8000 }, { "epoch": 0.63, "learning_rate": 9.684179237571524e-05, "loss": 5.7225, "step": 8500 }, { "epoch": 0.67, "learning_rate": 9.665601545663968e-05, "loss": 5.7058, "step": 9000 }, { "epoch": 0.71, "learning_rate": 9.64702385375641e-05, "loss": 5.688, "step": 9500 }, { "epoch": 0.74, "learning_rate": 9.628446161848853e-05, "loss": 5.677, "step": 10000 }, { "epoch": 0.78, "learning_rate": 9.609868469941294e-05, "loss": 5.6553, "step": 10500 }, { "epoch": 0.82, "learning_rate": 9.591290778033738e-05, "loss": 5.6418, "step": 11000 }, { "epoch": 0.85, "learning_rate": 9.572713086126181e-05, "loss": 5.6214, "step": 11500 }, { "epoch": 0.89, "learning_rate": 9.554135394218623e-05, "loss": 5.6269, "step": 12000 }, { "epoch": 0.93, "learning_rate": 9.535557702311066e-05, "loss": 5.5986, "step": 12500 }, { "epoch": 0.97, "learning_rate": 9.516980010403508e-05, "loss": 5.5702, "step": 13000 }, { "epoch": 1.0, "learning_rate": 9.49840231849595e-05, "loss": 5.5384, "step": 13500 }, { "epoch": 1.04, "learning_rate": 9.479824626588393e-05, "loss": 5.5147, "step": 14000 }, { "epoch": 1.08, "learning_rate": 9.461246934680835e-05, "loss": 5.4813, "step": 14500 }, { "epoch": 1.11, "learning_rate": 9.44266924277328e-05, "loss": 5.4493, "step": 15000 }, { "epoch": 1.15, "learning_rate": 9.424091550865721e-05, "loss": 5.4311, "step": 15500 }, { "epoch": 1.19, "learning_rate": 9.405513858958163e-05, "loss": 5.384, "step": 16000 }, { "epoch": 1.23, "learning_rate": 9.386936167050606e-05, "loss": 5.3435, "step": 16500 }, { "epoch": 1.26, "learning_rate": 9.368358475143048e-05, "loss": 5.2896, "step": 17000 }, { "epoch": 1.3, "learning_rate": 9.349780783235491e-05, "loss": 5.2532, "step": 17500 }, { "epoch": 1.34, "learning_rate": 9.331203091327933e-05, "loss": 5.1974, "step": 18000 }, { "epoch": 1.37, "learning_rate": 9.312625399420376e-05, "loss": 5.1504, "step": 18500 }, { "epoch": 1.41, "learning_rate": 9.294047707512818e-05, "loss": 5.131, "step": 19000 }, { "epoch": 1.45, "learning_rate": 9.275470015605262e-05, "loss": 5.0999, "step": 19500 }, { "epoch": 1.49, "learning_rate": 9.256892323697705e-05, "loss": 5.0754, "step": 20000 }, { "epoch": 1.52, "learning_rate": 9.238314631790147e-05, "loss": 5.0338, "step": 20500 }, { "epoch": 1.56, "learning_rate": 9.21973693988259e-05, "loss": 5.0154, "step": 21000 }, { "epoch": 1.6, "learning_rate": 9.201159247975032e-05, "loss": 4.966, "step": 21500 }, { "epoch": 1.63, "learning_rate": 9.182581556067475e-05, "loss": 4.9607, "step": 22000 }, { "epoch": 1.67, "learning_rate": 9.164003864159917e-05, "loss": 4.9289, "step": 22500 }, { "epoch": 1.71, "learning_rate": 9.14542617225236e-05, "loss": 4.8969, "step": 23000 }, { "epoch": 1.75, "learning_rate": 9.126848480344803e-05, "loss": 4.8953, "step": 23500 }, { "epoch": 1.78, "learning_rate": 9.108270788437245e-05, "loss": 4.8567, "step": 24000 }, { "epoch": 1.82, "learning_rate": 9.089693096529688e-05, "loss": 4.8592, "step": 24500 }, { "epoch": 1.86, "learning_rate": 9.07111540462213e-05, "loss": 4.8639, "step": 25000 }, { "epoch": 1.89, "learning_rate": 9.052537712714573e-05, "loss": 4.8299, "step": 25500 }, { "epoch": 1.93, "learning_rate": 9.033960020807015e-05, "loss": 4.8168, "step": 26000 }, { "epoch": 1.97, "learning_rate": 9.015382328899457e-05, "loss": 4.7802, "step": 26500 }, { "epoch": 2.01, "learning_rate": 8.9968046369919e-05, "loss": 4.7703, "step": 27000 }, { "epoch": 2.04, "learning_rate": 8.978226945084343e-05, "loss": 4.7495, "step": 27500 }, { "epoch": 2.08, "learning_rate": 8.959649253176787e-05, "loss": 4.742, "step": 28000 }, { "epoch": 2.12, "learning_rate": 8.941071561269229e-05, "loss": 4.7124, "step": 28500 }, { "epoch": 2.16, "learning_rate": 8.92249386936167e-05, "loss": 4.723, "step": 29000 }, { "epoch": 2.19, "learning_rate": 8.903916177454114e-05, "loss": 4.6895, "step": 29500 }, { "epoch": 2.23, "learning_rate": 8.885338485546555e-05, "loss": 4.6883, "step": 30000 }, { "epoch": 2.27, "learning_rate": 8.866760793638999e-05, "loss": 4.6492, "step": 30500 }, { "epoch": 2.3, "learning_rate": 8.84818310173144e-05, "loss": 4.6279, "step": 31000 }, { "epoch": 2.34, "learning_rate": 8.829605409823884e-05, "loss": 4.6412, "step": 31500 }, { "epoch": 2.38, "learning_rate": 8.811027717916327e-05, "loss": 4.609, "step": 32000 }, { "epoch": 2.42, "learning_rate": 8.792450026008769e-05, "loss": 4.6149, "step": 32500 }, { "epoch": 2.45, "learning_rate": 8.773872334101212e-05, "loss": 4.5923, "step": 33000 }, { "epoch": 2.49, "learning_rate": 8.755294642193654e-05, "loss": 4.5997, "step": 33500 }, { "epoch": 2.53, "learning_rate": 8.736716950286097e-05, "loss": 4.5669, "step": 34000 }, { "epoch": 2.56, "learning_rate": 8.718139258378539e-05, "loss": 4.5359, "step": 34500 }, { "epoch": 2.6, "learning_rate": 8.699561566470982e-05, "loss": 4.5578, "step": 35000 }, { "epoch": 2.64, "learning_rate": 8.680983874563424e-05, "loss": 4.5222, "step": 35500 }, { "epoch": 2.68, "learning_rate": 8.662406182655867e-05, "loss": 4.5189, "step": 36000 }, { "epoch": 2.71, "learning_rate": 8.64382849074831e-05, "loss": 4.5025, "step": 36500 }, { "epoch": 2.75, "learning_rate": 8.625250798840752e-05, "loss": 4.4724, "step": 37000 }, { "epoch": 2.79, "learning_rate": 8.606673106933196e-05, "loss": 4.4692, "step": 37500 }, { "epoch": 2.82, "learning_rate": 8.588095415025637e-05, "loss": 4.4595, "step": 38000 }, { "epoch": 2.86, "learning_rate": 8.569517723118081e-05, "loss": 4.4474, "step": 38500 }, { "epoch": 2.9, "learning_rate": 8.550940031210523e-05, "loss": 4.4585, "step": 39000 }, { "epoch": 2.94, "learning_rate": 8.532362339302964e-05, "loss": 4.4306, "step": 39500 }, { "epoch": 2.97, "learning_rate": 8.513784647395408e-05, "loss": 4.4443, "step": 40000 }, { "epoch": 3.01, "learning_rate": 8.495206955487851e-05, "loss": 4.4032, "step": 40500 }, { "epoch": 3.05, "learning_rate": 8.476629263580294e-05, "loss": 4.4121, "step": 41000 }, { "epoch": 3.08, "learning_rate": 8.458051571672736e-05, "loss": 4.394, "step": 41500 }, { "epoch": 3.12, "learning_rate": 8.439473879765179e-05, "loss": 4.3491, "step": 42000 }, { "epoch": 3.16, "learning_rate": 8.420896187857621e-05, "loss": 4.3639, "step": 42500 }, { "epoch": 3.2, "learning_rate": 8.402318495950063e-05, "loss": 4.3754, "step": 43000 }, { "epoch": 3.23, "learning_rate": 8.383740804042506e-05, "loss": 4.3606, "step": 43500 }, { "epoch": 3.27, "learning_rate": 8.365163112134948e-05, "loss": 4.3412, "step": 44000 }, { "epoch": 3.31, "learning_rate": 8.346585420227392e-05, "loss": 4.3307, "step": 44500 }, { "epoch": 3.34, "learning_rate": 8.328007728319834e-05, "loss": 4.3254, "step": 45000 }, { "epoch": 3.38, "learning_rate": 8.309430036412276e-05, "loss": 4.3204, "step": 45500 }, { "epoch": 3.42, "learning_rate": 8.29085234450472e-05, "loss": 4.318, "step": 46000 }, { "epoch": 3.46, "learning_rate": 8.272274652597161e-05, "loss": 4.3174, "step": 46500 }, { "epoch": 3.49, "learning_rate": 8.253696960689605e-05, "loss": 4.2962, "step": 47000 }, { "epoch": 3.53, "learning_rate": 8.235119268782046e-05, "loss": 4.287, "step": 47500 }, { "epoch": 3.57, "learning_rate": 8.21654157687449e-05, "loss": 4.2903, "step": 48000 }, { "epoch": 3.6, "learning_rate": 8.197963884966931e-05, "loss": 4.2733, "step": 48500 }, { "epoch": 3.64, "learning_rate": 8.179386193059375e-05, "loss": 4.2686, "step": 49000 }, { "epoch": 3.68, "learning_rate": 8.160808501151818e-05, "loss": 4.26, "step": 49500 }, { "epoch": 3.72, "learning_rate": 8.14223080924426e-05, "loss": 4.2583, "step": 50000 }, { "epoch": 3.75, "learning_rate": 8.123653117336703e-05, "loss": 4.2561, "step": 50500 }, { "epoch": 3.79, "learning_rate": 8.105075425429145e-05, "loss": 4.2421, "step": 51000 }, { "epoch": 3.83, "learning_rate": 8.086497733521588e-05, "loss": 4.2306, "step": 51500 }, { "epoch": 3.86, "learning_rate": 8.06792004161403e-05, "loss": 4.2164, "step": 52000 }, { "epoch": 3.9, "learning_rate": 8.049342349706472e-05, "loss": 4.2084, "step": 52500 }, { "epoch": 3.94, "learning_rate": 8.030764657798916e-05, "loss": 4.2099, "step": 53000 }, { "epoch": 3.98, "learning_rate": 8.012186965891358e-05, "loss": 4.2162, "step": 53500 }, { "epoch": 4.01, "learning_rate": 7.993609273983801e-05, "loss": 4.2236, "step": 54000 }, { "epoch": 4.05, "learning_rate": 7.975031582076243e-05, "loss": 4.1909, "step": 54500 }, { "epoch": 4.09, "learning_rate": 7.956453890168686e-05, "loss": 4.1765, "step": 55000 }, { "epoch": 4.12, "learning_rate": 7.937876198261128e-05, "loss": 4.1988, "step": 55500 }, { "epoch": 4.16, "learning_rate": 7.91929850635357e-05, "loss": 4.1815, "step": 56000 }, { "epoch": 4.2, "learning_rate": 7.900720814446013e-05, "loss": 4.1768, "step": 56500 }, { "epoch": 4.24, "learning_rate": 7.882143122538455e-05, "loss": 4.1699, "step": 57000 }, { "epoch": 4.27, "learning_rate": 7.8635654306309e-05, "loss": 4.1473, "step": 57500 }, { "epoch": 4.31, "learning_rate": 7.844987738723342e-05, "loss": 4.1826, "step": 58000 }, { "epoch": 4.35, "learning_rate": 7.826410046815784e-05, "loss": 4.1364, "step": 58500 }, { "epoch": 4.38, "learning_rate": 7.807832354908227e-05, "loss": 4.1521, "step": 59000 }, { "epoch": 4.42, "learning_rate": 7.789254663000669e-05, "loss": 4.1614, "step": 59500 }, { "epoch": 4.46, "learning_rate": 7.770676971093112e-05, "loss": 4.1415, "step": 60000 }, { "epoch": 4.5, "learning_rate": 7.752099279185554e-05, "loss": 4.118, "step": 60500 }, { "epoch": 4.53, "learning_rate": 7.733521587277997e-05, "loss": 4.1446, "step": 61000 }, { "epoch": 4.57, "learning_rate": 7.71494389537044e-05, "loss": 4.1323, "step": 61500 }, { "epoch": 4.61, "learning_rate": 7.696366203462882e-05, "loss": 4.1072, "step": 62000 }, { "epoch": 4.64, "learning_rate": 7.677788511555325e-05, "loss": 4.1396, "step": 62500 }, { "epoch": 4.68, "learning_rate": 7.659210819647767e-05, "loss": 4.0946, "step": 63000 }, { "epoch": 4.72, "learning_rate": 7.64063312774021e-05, "loss": 4.1253, "step": 63500 }, { "epoch": 4.76, "learning_rate": 7.622055435832652e-05, "loss": 4.104, "step": 64000 }, { "epoch": 4.79, "learning_rate": 7.603477743925095e-05, "loss": 4.0819, "step": 64500 }, { "epoch": 4.83, "learning_rate": 7.584900052017537e-05, "loss": 4.0795, "step": 65000 }, { "epoch": 4.87, "learning_rate": 7.566322360109979e-05, "loss": 4.0805, "step": 65500 }, { "epoch": 4.9, "learning_rate": 7.547744668202424e-05, "loss": 4.0792, "step": 66000 }, { "epoch": 4.94, "learning_rate": 7.529166976294866e-05, "loss": 4.0704, "step": 66500 }, { "epoch": 4.98, "learning_rate": 7.510589284387309e-05, "loss": 4.0694, "step": 67000 }, { "epoch": 5.02, "learning_rate": 7.49201159247975e-05, "loss": 4.0499, "step": 67500 }, { "epoch": 5.05, "learning_rate": 7.473433900572194e-05, "loss": 4.0686, "step": 68000 }, { "epoch": 5.09, "learning_rate": 7.454856208664636e-05, "loss": 4.0632, "step": 68500 }, { "epoch": 5.13, "learning_rate": 7.436278516757078e-05, "loss": 4.0458, "step": 69000 }, { "epoch": 5.16, "learning_rate": 7.417700824849521e-05, "loss": 4.03, "step": 69500 }, { "epoch": 5.2, "learning_rate": 7.399123132941964e-05, "loss": 4.0443, "step": 70000 }, { "epoch": 5.24, "learning_rate": 7.380545441034407e-05, "loss": 4.0303, "step": 70500 }, { "epoch": 5.28, "learning_rate": 7.361967749126849e-05, "loss": 4.0296, "step": 71000 }, { "epoch": 5.31, "learning_rate": 7.343390057219291e-05, "loss": 4.0206, "step": 71500 }, { "epoch": 5.35, "learning_rate": 7.324812365311734e-05, "loss": 4.0245, "step": 72000 }, { "epoch": 5.39, "learning_rate": 7.306234673404176e-05, "loss": 4.0397, "step": 72500 }, { "epoch": 5.42, "learning_rate": 7.287656981496619e-05, "loss": 4.0174, "step": 73000 }, { "epoch": 5.46, "learning_rate": 7.269079289589061e-05, "loss": 4.0038, "step": 73500 }, { "epoch": 5.5, "learning_rate": 7.250501597681504e-05, "loss": 4.0074, "step": 74000 }, { "epoch": 5.54, "learning_rate": 7.231923905773948e-05, "loss": 4.0191, "step": 74500 }, { "epoch": 5.57, "learning_rate": 7.21334621386639e-05, "loss": 4.0251, "step": 75000 }, { "epoch": 5.61, "learning_rate": 7.194768521958833e-05, "loss": 3.9988, "step": 75500 }, { "epoch": 5.65, "learning_rate": 7.176190830051274e-05, "loss": 4.0091, "step": 76000 }, { "epoch": 5.68, "learning_rate": 7.157613138143718e-05, "loss": 4.0174, "step": 76500 }, { "epoch": 5.72, "learning_rate": 7.13903544623616e-05, "loss": 4.0052, "step": 77000 }, { "epoch": 5.76, "learning_rate": 7.120457754328603e-05, "loss": 3.9793, "step": 77500 }, { "epoch": 5.8, "learning_rate": 7.101880062421045e-05, "loss": 4.0016, "step": 78000 }, { "epoch": 5.83, "learning_rate": 7.083302370513488e-05, "loss": 3.997, "step": 78500 }, { "epoch": 5.87, "learning_rate": 7.064724678605931e-05, "loss": 3.9835, "step": 79000 }, { "epoch": 5.91, "learning_rate": 7.046146986698373e-05, "loss": 3.985, "step": 79500 }, { "epoch": 5.94, "learning_rate": 7.027569294790816e-05, "loss": 3.9706, "step": 80000 }, { "epoch": 5.98, "learning_rate": 7.008991602883258e-05, "loss": 3.9823, "step": 80500 }, { "epoch": 6.02, "learning_rate": 6.990413910975701e-05, "loss": 3.9795, "step": 81000 }, { "epoch": 6.06, "learning_rate": 6.971836219068143e-05, "loss": 3.9638, "step": 81500 }, { "epoch": 6.09, "learning_rate": 6.953258527160585e-05, "loss": 3.9441, "step": 82000 }, { "epoch": 6.13, "learning_rate": 6.93468083525303e-05, "loss": 3.9639, "step": 82500 }, { "epoch": 6.17, "learning_rate": 6.916103143345471e-05, "loss": 3.9706, "step": 83000 }, { "epoch": 6.2, "learning_rate": 6.897525451437915e-05, "loss": 3.9546, "step": 83500 }, { "epoch": 6.24, "learning_rate": 6.878947759530356e-05, "loss": 3.9641, "step": 84000 }, { "epoch": 6.28, "learning_rate": 6.860370067622798e-05, "loss": 3.957, "step": 84500 }, { "epoch": 6.32, "learning_rate": 6.841792375715241e-05, "loss": 3.9565, "step": 85000 }, { "epoch": 6.35, "learning_rate": 6.823214683807683e-05, "loss": 3.9318, "step": 85500 }, { "epoch": 6.39, "learning_rate": 6.804636991900127e-05, "loss": 3.9241, "step": 86000 }, { "epoch": 6.43, "learning_rate": 6.786059299992568e-05, "loss": 3.946, "step": 86500 }, { "epoch": 6.47, "learning_rate": 6.767481608085012e-05, "loss": 3.9291, "step": 87000 }, { "epoch": 6.5, "learning_rate": 6.748903916177455e-05, "loss": 3.9367, "step": 87500 }, { "epoch": 6.54, "learning_rate": 6.730326224269897e-05, "loss": 3.9206, "step": 88000 }, { "epoch": 6.58, "learning_rate": 6.71174853236234e-05, "loss": 3.9244, "step": 88500 }, { "epoch": 6.61, "learning_rate": 6.693170840454782e-05, "loss": 3.9265, "step": 89000 }, { "epoch": 6.65, "learning_rate": 6.674593148547225e-05, "loss": 3.9047, "step": 89500 }, { "epoch": 6.69, "learning_rate": 6.656015456639667e-05, "loss": 3.9176, "step": 90000 }, { "epoch": 6.73, "learning_rate": 6.63743776473211e-05, "loss": 3.9342, "step": 90500 }, { "epoch": 6.76, "learning_rate": 6.618860072824553e-05, "loss": 3.9144, "step": 91000 }, { "epoch": 6.8, "learning_rate": 6.600282380916995e-05, "loss": 3.9232, "step": 91500 }, { "epoch": 6.84, "learning_rate": 6.581704689009438e-05, "loss": 3.9213, "step": 92000 }, { "epoch": 6.87, "learning_rate": 6.56312699710188e-05, "loss": 3.8885, "step": 92500 }, { "epoch": 6.91, "learning_rate": 6.544549305194323e-05, "loss": 3.8859, "step": 93000 }, { "epoch": 6.95, "learning_rate": 6.525971613286765e-05, "loss": 3.9033, "step": 93500 }, { "epoch": 6.99, "learning_rate": 6.507393921379209e-05, "loss": 3.9087, "step": 94000 }, { "epoch": 7.02, "learning_rate": 6.48881622947165e-05, "loss": 3.9058, "step": 94500 }, { "epoch": 7.06, "learning_rate": 6.470238537564092e-05, "loss": 3.8973, "step": 95000 }, { "epoch": 7.1, "learning_rate": 6.451660845656537e-05, "loss": 3.89, "step": 95500 }, { "epoch": 7.13, "learning_rate": 6.433083153748979e-05, "loss": 3.8861, "step": 96000 }, { "epoch": 7.17, "learning_rate": 6.414505461841422e-05, "loss": 3.9072, "step": 96500 }, { "epoch": 7.21, "learning_rate": 6.395927769933864e-05, "loss": 3.8848, "step": 97000 }, { "epoch": 7.25, "learning_rate": 6.377350078026306e-05, "loss": 3.8844, "step": 97500 }, { "epoch": 7.28, "learning_rate": 6.358772386118749e-05, "loss": 3.8934, "step": 98000 }, { "epoch": 7.32, "learning_rate": 6.340194694211191e-05, "loss": 3.8635, "step": 98500 }, { "epoch": 7.36, "learning_rate": 6.321617002303634e-05, "loss": 3.8807, "step": 99000 }, { "epoch": 7.39, "learning_rate": 6.303039310396077e-05, "loss": 3.8656, "step": 99500 }, { "epoch": 7.43, "learning_rate": 6.284461618488519e-05, "loss": 3.8823, "step": 100000 }, { "epoch": 7.47, "learning_rate": 6.265883926580962e-05, "loss": 3.8634, "step": 100500 }, { "epoch": 7.51, "learning_rate": 6.247306234673404e-05, "loss": 3.8661, "step": 101000 }, { "epoch": 7.54, "learning_rate": 6.228728542765847e-05, "loss": 3.8707, "step": 101500 }, { "epoch": 7.58, "learning_rate": 6.210150850858289e-05, "loss": 3.8768, "step": 102000 }, { "epoch": 7.62, "learning_rate": 6.191573158950732e-05, "loss": 3.8466, "step": 102500 }, { "epoch": 7.65, "learning_rate": 6.172995467043174e-05, "loss": 3.8705, "step": 103000 }, { "epoch": 7.69, "learning_rate": 6.154417775135617e-05, "loss": 3.8378, "step": 103500 }, { "epoch": 7.73, "learning_rate": 6.13584008322806e-05, "loss": 3.8644, "step": 104000 }, { "epoch": 7.77, "learning_rate": 6.117262391320503e-05, "loss": 3.8536, "step": 104500 }, { "epoch": 7.8, "learning_rate": 6.098684699412946e-05, "loss": 3.8729, "step": 105000 }, { "epoch": 7.84, "learning_rate": 6.0801070075053876e-05, "loss": 3.8516, "step": 105500 }, { "epoch": 7.88, "learning_rate": 6.06152931559783e-05, "loss": 3.8524, "step": 106000 }, { "epoch": 7.91, "learning_rate": 6.042951623690273e-05, "loss": 3.8463, "step": 106500 }, { "epoch": 7.95, "learning_rate": 6.024373931782715e-05, "loss": 3.8415, "step": 107000 }, { "epoch": 7.99, "learning_rate": 6.005796239875158e-05, "loss": 3.8421, "step": 107500 }, { "epoch": 8.03, "learning_rate": 5.987218547967601e-05, "loss": 3.8555, "step": 108000 }, { "epoch": 8.06, "learning_rate": 5.9686408560600435e-05, "loss": 3.8433, "step": 108500 }, { "epoch": 8.1, "learning_rate": 5.950063164152486e-05, "loss": 3.859, "step": 109000 }, { "epoch": 8.14, "learning_rate": 5.9314854722449286e-05, "loss": 3.8425, "step": 109500 }, { "epoch": 8.17, "learning_rate": 5.912907780337371e-05, "loss": 3.8299, "step": 110000 }, { "epoch": 8.21, "learning_rate": 5.894330088429814e-05, "loss": 3.8344, "step": 110500 }, { "epoch": 8.25, "learning_rate": 5.875752396522256e-05, "loss": 3.8103, "step": 111000 }, { "epoch": 8.29, "learning_rate": 5.857174704614699e-05, "loss": 3.8241, "step": 111500 }, { "epoch": 8.32, "learning_rate": 5.838597012707141e-05, "loss": 3.8318, "step": 112000 }, { "epoch": 8.36, "learning_rate": 5.8200193207995845e-05, "loss": 3.83, "step": 112500 }, { "epoch": 8.4, "learning_rate": 5.801441628892027e-05, "loss": 3.8282, "step": 113000 }, { "epoch": 8.43, "learning_rate": 5.7828639369844696e-05, "loss": 3.8268, "step": 113500 }, { "epoch": 8.47, "learning_rate": 5.764286245076912e-05, "loss": 3.8282, "step": 114000 }, { "epoch": 8.51, "learning_rate": 5.7457085531693546e-05, "loss": 3.8148, "step": 114500 }, { "epoch": 8.55, "learning_rate": 5.727130861261797e-05, "loss": 3.8032, "step": 115000 }, { "epoch": 8.58, "learning_rate": 5.708553169354239e-05, "loss": 3.8169, "step": 115500 }, { "epoch": 8.62, "learning_rate": 5.6899754774466816e-05, "loss": 3.7967, "step": 116000 }, { "epoch": 8.66, "learning_rate": 5.6713977855391255e-05, "loss": 3.8234, "step": 116500 }, { "epoch": 8.69, "learning_rate": 5.652820093631568e-05, "loss": 3.802, "step": 117000 }, { "epoch": 8.73, "learning_rate": 5.6342424017240106e-05, "loss": 3.7919, "step": 117500 }, { "epoch": 8.77, "learning_rate": 5.615664709816453e-05, "loss": 3.7957, "step": 118000 }, { "epoch": 8.81, "learning_rate": 5.597087017908895e-05, "loss": 3.79, "step": 118500 }, { "epoch": 8.84, "learning_rate": 5.5785093260013375e-05, "loss": 3.7996, "step": 119000 }, { "epoch": 8.88, "learning_rate": 5.55993163409378e-05, "loss": 3.8089, "step": 119500 }, { "epoch": 8.92, "learning_rate": 5.5413539421862226e-05, "loss": 3.8031, "step": 120000 }, { "epoch": 8.95, "learning_rate": 5.5227762502786665e-05, "loss": 3.7984, "step": 120500 }, { "epoch": 8.99, "learning_rate": 5.504198558371108e-05, "loss": 3.7881, "step": 121000 }, { "epoch": 9.03, "learning_rate": 5.485620866463551e-05, "loss": 3.8057, "step": 121500 }, { "epoch": 9.07, "learning_rate": 5.4670431745559934e-05, "loss": 3.7843, "step": 122000 }, { "epoch": 9.1, "learning_rate": 5.448465482648436e-05, "loss": 3.7845, "step": 122500 }, { "epoch": 9.14, "learning_rate": 5.4298877907408785e-05, "loss": 3.8025, "step": 123000 }, { "epoch": 9.18, "learning_rate": 5.411310098833321e-05, "loss": 3.7746, "step": 123500 }, { "epoch": 9.21, "learning_rate": 5.3927324069257636e-05, "loss": 3.7869, "step": 124000 }, { "epoch": 9.25, "learning_rate": 5.374154715018206e-05, "loss": 3.7852, "step": 124500 }, { "epoch": 9.29, "learning_rate": 5.355577023110649e-05, "loss": 3.7819, "step": 125000 }, { "epoch": 9.33, "learning_rate": 5.336999331203092e-05, "loss": 3.8059, "step": 125500 }, { "epoch": 9.36, "learning_rate": 5.3184216392955344e-05, "loss": 3.7748, "step": 126000 }, { "epoch": 9.4, "learning_rate": 5.299843947387977e-05, "loss": 3.7689, "step": 126500 }, { "epoch": 9.44, "learning_rate": 5.2812662554804195e-05, "loss": 3.7766, "step": 127000 }, { "epoch": 9.47, "learning_rate": 5.262688563572862e-05, "loss": 3.7697, "step": 127500 }, { "epoch": 9.51, "learning_rate": 5.2441108716653045e-05, "loss": 3.7897, "step": 128000 }, { "epoch": 9.55, "learning_rate": 5.2255331797577464e-05, "loss": 3.7679, "step": 128500 }, { "epoch": 9.59, "learning_rate": 5.20695548785019e-05, "loss": 3.7808, "step": 129000 }, { "epoch": 9.62, "learning_rate": 5.188377795942633e-05, "loss": 3.7562, "step": 129500 }, { "epoch": 9.66, "learning_rate": 5.1698001040350754e-05, "loss": 3.7502, "step": 130000 }, { "epoch": 9.7, "learning_rate": 5.151222412127518e-05, "loss": 3.7809, "step": 130500 }, { "epoch": 9.73, "learning_rate": 5.1326447202199604e-05, "loss": 3.7752, "step": 131000 }, { "epoch": 9.77, "learning_rate": 5.114067028312402e-05, "loss": 3.7532, "step": 131500 }, { "epoch": 9.81, "learning_rate": 5.095489336404845e-05, "loss": 3.7683, "step": 132000 }, { "epoch": 9.85, "learning_rate": 5.0769116444972874e-05, "loss": 3.7538, "step": 132500 }, { "epoch": 9.88, "learning_rate": 5.05833395258973e-05, "loss": 3.7633, "step": 133000 }, { "epoch": 9.92, "learning_rate": 5.039756260682174e-05, "loss": 3.7457, "step": 133500 }, { "epoch": 9.96, "learning_rate": 5.021178568774616e-05, "loss": 3.7745, "step": 134000 }, { "epoch": 9.99, "learning_rate": 5.002600876867058e-05, "loss": 3.7592, "step": 134500 }, { "epoch": 10.03, "learning_rate": 4.984023184959501e-05, "loss": 3.7506, "step": 135000 }, { "epoch": 10.07, "learning_rate": 4.965445493051943e-05, "loss": 3.7601, "step": 135500 }, { "epoch": 10.11, "learning_rate": 4.946867801144386e-05, "loss": 3.7622, "step": 136000 }, { "epoch": 10.14, "learning_rate": 4.928290109236829e-05, "loss": 3.7059, "step": 136500 }, { "epoch": 10.18, "learning_rate": 4.9097124173292716e-05, "loss": 3.7491, "step": 137000 }, { "epoch": 10.22, "learning_rate": 4.891134725421714e-05, "loss": 3.7145, "step": 137500 }, { "epoch": 10.25, "learning_rate": 4.872557033514156e-05, "loss": 3.7217, "step": 138000 }, { "epoch": 10.29, "learning_rate": 4.853979341606599e-05, "loss": 3.7461, "step": 138500 }, { "epoch": 10.33, "learning_rate": 4.835401649699042e-05, "loss": 3.7317, "step": 139000 }, { "epoch": 10.37, "learning_rate": 4.816823957791484e-05, "loss": 3.7605, "step": 139500 }, { "epoch": 10.4, "learning_rate": 4.798246265883927e-05, "loss": 3.7422, "step": 140000 }, { "epoch": 10.44, "learning_rate": 4.7796685739763694e-05, "loss": 3.738, "step": 140500 }, { "epoch": 10.48, "learning_rate": 4.761090882068812e-05, "loss": 3.7314, "step": 141000 }, { "epoch": 10.51, "learning_rate": 4.7425131901612544e-05, "loss": 3.7486, "step": 141500 }, { "epoch": 10.55, "learning_rate": 4.723935498253697e-05, "loss": 3.7335, "step": 142000 }, { "epoch": 10.59, "learning_rate": 4.7053578063461395e-05, "loss": 3.7377, "step": 142500 }, { "epoch": 10.63, "learning_rate": 4.686780114438583e-05, "loss": 3.7252, "step": 143000 }, { "epoch": 10.66, "learning_rate": 4.668202422531025e-05, "loss": 3.7199, "step": 143500 }, { "epoch": 10.7, "learning_rate": 4.649624730623468e-05, "loss": 3.7202, "step": 144000 }, { "epoch": 10.74, "learning_rate": 4.63104703871591e-05, "loss": 3.7152, "step": 144500 }, { "epoch": 10.78, "learning_rate": 4.612469346808353e-05, "loss": 3.6946, "step": 145000 }, { "epoch": 10.81, "learning_rate": 4.5938916549007954e-05, "loss": 3.7183, "step": 145500 }, { "epoch": 10.85, "learning_rate": 4.575313962993238e-05, "loss": 3.7272, "step": 146000 }, { "epoch": 10.89, "learning_rate": 4.5567362710856805e-05, "loss": 3.7211, "step": 146500 }, { "epoch": 10.92, "learning_rate": 4.538158579178124e-05, "loss": 3.7328, "step": 147000 }, { "epoch": 10.96, "learning_rate": 4.5195808872705656e-05, "loss": 3.7167, "step": 147500 }, { "epoch": 11.0, "learning_rate": 4.501003195363008e-05, "loss": 3.7314, "step": 148000 }, { "epoch": 11.04, "learning_rate": 4.4824255034554506e-05, "loss": 3.707, "step": 148500 }, { "epoch": 11.07, "learning_rate": 4.463847811547894e-05, "loss": 3.7117, "step": 149000 }, { "epoch": 11.11, "learning_rate": 4.4452701196403364e-05, "loss": 3.698, "step": 149500 }, { "epoch": 11.15, "learning_rate": 4.426692427732779e-05, "loss": 3.7057, "step": 150000 }, { "epoch": 11.18, "learning_rate": 4.4081147358252215e-05, "loss": 3.7069, "step": 150500 }, { "epoch": 11.22, "learning_rate": 4.3895370439176633e-05, "loss": 3.7068, "step": 151000 }, { "epoch": 11.26, "learning_rate": 4.3709593520101066e-05, "loss": 3.7025, "step": 151500 }, { "epoch": 11.3, "learning_rate": 4.352381660102549e-05, "loss": 3.6943, "step": 152000 }, { "epoch": 11.33, "learning_rate": 4.3338039681949916e-05, "loss": 3.712, "step": 152500 }, { "epoch": 11.37, "learning_rate": 4.315226276287434e-05, "loss": 3.6925, "step": 153000 }, { "epoch": 11.41, "learning_rate": 4.2966485843798774e-05, "loss": 3.6832, "step": 153500 }, { "epoch": 11.44, "learning_rate": 4.278070892472319e-05, "loss": 3.6895, "step": 154000 }, { "epoch": 11.48, "learning_rate": 4.259493200564762e-05, "loss": 3.6915, "step": 154500 }, { "epoch": 11.52, "learning_rate": 4.240915508657204e-05, "loss": 3.6923, "step": 155000 }, { "epoch": 11.56, "learning_rate": 4.2223378167496475e-05, "loss": 3.6957, "step": 155500 }, { "epoch": 11.59, "learning_rate": 4.20376012484209e-05, "loss": 3.7213, "step": 156000 }, { "epoch": 11.63, "learning_rate": 4.1851824329345326e-05, "loss": 3.6744, "step": 156500 }, { "epoch": 11.67, "learning_rate": 4.166604741026975e-05, "loss": 3.6872, "step": 157000 }, { "epoch": 11.7, "learning_rate": 4.148027049119418e-05, "loss": 3.695, "step": 157500 }, { "epoch": 11.74, "learning_rate": 4.12944935721186e-05, "loss": 3.6935, "step": 158000 }, { "epoch": 11.78, "learning_rate": 4.110871665304303e-05, "loss": 3.684, "step": 158500 }, { "epoch": 11.82, "learning_rate": 4.092293973396745e-05, "loss": 3.6791, "step": 159000 }, { "epoch": 11.85, "learning_rate": 4.073716281489188e-05, "loss": 3.6711, "step": 159500 }, { "epoch": 11.89, "learning_rate": 4.055138589581631e-05, "loss": 3.6809, "step": 160000 }, { "epoch": 11.93, "learning_rate": 4.036560897674073e-05, "loss": 3.6661, "step": 160500 }, { "epoch": 11.96, "learning_rate": 4.0179832057665155e-05, "loss": 3.6764, "step": 161000 }, { "epoch": 12.0, "learning_rate": 3.999405513858958e-05, "loss": 3.6734, "step": 161500 }, { "epoch": 12.04, "learning_rate": 3.980827821951401e-05, "loss": 3.6866, "step": 162000 }, { "epoch": 12.08, "learning_rate": 3.962250130043844e-05, "loss": 3.6503, "step": 162500 }, { "epoch": 12.11, "learning_rate": 3.943672438136286e-05, "loss": 3.6859, "step": 163000 }, { "epoch": 12.15, "learning_rate": 3.925094746228729e-05, "loss": 3.6527, "step": 163500 }, { "epoch": 12.19, "learning_rate": 3.9065170543211714e-05, "loss": 3.6639, "step": 164000 }, { "epoch": 12.22, "learning_rate": 3.887939362413614e-05, "loss": 3.6663, "step": 164500 }, { "epoch": 12.26, "learning_rate": 3.8693616705060564e-05, "loss": 3.6774, "step": 165000 }, { "epoch": 12.3, "learning_rate": 3.850783978598499e-05, "loss": 3.6705, "step": 165500 }, { "epoch": 12.34, "learning_rate": 3.832206286690942e-05, "loss": 3.6783, "step": 166000 }, { "epoch": 12.37, "learning_rate": 3.813628594783385e-05, "loss": 3.6554, "step": 166500 }, { "epoch": 12.41, "learning_rate": 3.7950509028758266e-05, "loss": 3.6564, "step": 167000 }, { "epoch": 12.45, "learning_rate": 3.776473210968269e-05, "loss": 3.6713, "step": 167500 }, { "epoch": 12.48, "learning_rate": 3.757895519060712e-05, "loss": 3.6641, "step": 168000 }, { "epoch": 12.52, "learning_rate": 3.739317827153155e-05, "loss": 3.6747, "step": 168500 }, { "epoch": 12.56, "learning_rate": 3.7207401352455974e-05, "loss": 3.6826, "step": 169000 }, { "epoch": 12.6, "learning_rate": 3.70216244333804e-05, "loss": 3.663, "step": 169500 }, { "epoch": 12.63, "learning_rate": 3.6835847514304825e-05, "loss": 3.6661, "step": 170000 }, { "epoch": 12.67, "learning_rate": 3.665007059522925e-05, "loss": 3.6552, "step": 170500 }, { "epoch": 12.71, "learning_rate": 3.6464293676153676e-05, "loss": 3.666, "step": 171000 }, { "epoch": 12.74, "learning_rate": 3.62785167570781e-05, "loss": 3.6531, "step": 171500 }, { "epoch": 12.78, "learning_rate": 3.609273983800253e-05, "loss": 3.6543, "step": 172000 }, { "epoch": 12.82, "learning_rate": 3.590696291892696e-05, "loss": 3.6503, "step": 172500 }, { "epoch": 12.86, "learning_rate": 3.5721185999851384e-05, "loss": 3.6605, "step": 173000 }, { "epoch": 12.89, "learning_rate": 3.55354090807758e-05, "loss": 3.6355, "step": 173500 }, { "epoch": 12.93, "learning_rate": 3.534963216170023e-05, "loss": 3.6543, "step": 174000 }, { "epoch": 12.97, "learning_rate": 3.516385524262466e-05, "loss": 3.6494, "step": 174500 }, { "epoch": 13.0, "learning_rate": 3.4978078323549086e-05, "loss": 3.625, "step": 175000 }, { "epoch": 13.04, "learning_rate": 3.479230140447351e-05, "loss": 3.6604, "step": 175500 }, { "epoch": 13.08, "learning_rate": 3.4606524485397936e-05, "loss": 3.6587, "step": 176000 }, { "epoch": 13.12, "learning_rate": 3.442074756632236e-05, "loss": 3.6422, "step": 176500 }, { "epoch": 13.15, "learning_rate": 3.423497064724679e-05, "loss": 3.6392, "step": 177000 }, { "epoch": 13.19, "learning_rate": 3.404919372817121e-05, "loss": 3.6254, "step": 177500 }, { "epoch": 13.23, "learning_rate": 3.386341680909564e-05, "loss": 3.6426, "step": 178000 }, { "epoch": 13.26, "learning_rate": 3.3677639890020063e-05, "loss": 3.6778, "step": 178500 }, { "epoch": 13.3, "learning_rate": 3.3491862970944496e-05, "loss": 3.6645, "step": 179000 }, { "epoch": 13.34, "learning_rate": 3.330608605186892e-05, "loss": 3.6433, "step": 179500 }, { "epoch": 13.38, "learning_rate": 3.312030913279334e-05, "loss": 3.6614, "step": 180000 }, { "epoch": 13.41, "learning_rate": 3.2934532213717765e-05, "loss": 3.6654, "step": 180500 }, { "epoch": 13.45, "learning_rate": 3.27487552946422e-05, "loss": 3.6309, "step": 181000 }, { "epoch": 13.49, "learning_rate": 3.256297837556662e-05, "loss": 3.629, "step": 181500 }, { "epoch": 13.52, "learning_rate": 3.237720145649105e-05, "loss": 3.6235, "step": 182000 }, { "epoch": 13.56, "learning_rate": 3.219142453741547e-05, "loss": 3.6386, "step": 182500 }, { "epoch": 13.6, "learning_rate": 3.20056476183399e-05, "loss": 3.6491, "step": 183000 }, { "epoch": 13.64, "learning_rate": 3.1819870699264324e-05, "loss": 3.632, "step": 183500 }, { "epoch": 13.67, "learning_rate": 3.163409378018875e-05, "loss": 3.6363, "step": 184000 }, { "epoch": 13.71, "learning_rate": 3.1448316861113175e-05, "loss": 3.6232, "step": 184500 }, { "epoch": 13.75, "learning_rate": 3.126253994203761e-05, "loss": 3.6226, "step": 185000 }, { "epoch": 13.78, "learning_rate": 3.107676302296203e-05, "loss": 3.6455, "step": 185500 }, { "epoch": 13.82, "learning_rate": 3.089098610388646e-05, "loss": 3.6386, "step": 186000 }, { "epoch": 13.86, "learning_rate": 3.0705209184810876e-05, "loss": 3.6171, "step": 186500 }, { "epoch": 13.9, "learning_rate": 3.05194322657353e-05, "loss": 3.6286, "step": 187000 }, { "epoch": 13.93, "learning_rate": 3.0333655346659734e-05, "loss": 3.6253, "step": 187500 }, { "epoch": 13.97, "learning_rate": 3.014787842758416e-05, "loss": 3.6207, "step": 188000 }, { "epoch": 14.01, "learning_rate": 2.9962101508508585e-05, "loss": 3.6429, "step": 188500 }, { "epoch": 14.04, "learning_rate": 2.9776324589433007e-05, "loss": 3.6227, "step": 189000 }, { "epoch": 14.08, "learning_rate": 2.959054767035744e-05, "loss": 3.6268, "step": 189500 }, { "epoch": 14.12, "learning_rate": 2.9404770751281864e-05, "loss": 3.6449, "step": 190000 }, { "epoch": 14.16, "learning_rate": 2.9218993832206286e-05, "loss": 3.6343, "step": 190500 }, { "epoch": 14.19, "learning_rate": 2.903321691313071e-05, "loss": 3.6216, "step": 191000 }, { "epoch": 14.23, "learning_rate": 2.8847439994055144e-05, "loss": 3.6226, "step": 191500 }, { "epoch": 14.27, "learning_rate": 2.8661663074979566e-05, "loss": 3.6349, "step": 192000 }, { "epoch": 14.3, "learning_rate": 2.847588615590399e-05, "loss": 3.6263, "step": 192500 }, { "epoch": 14.34, "learning_rate": 2.8290109236828416e-05, "loss": 3.6124, "step": 193000 }, { "epoch": 14.38, "learning_rate": 2.8104332317752845e-05, "loss": 3.6135, "step": 193500 }, { "epoch": 14.42, "learning_rate": 2.791855539867727e-05, "loss": 3.6049, "step": 194000 }, { "epoch": 14.45, "learning_rate": 2.7732778479601696e-05, "loss": 3.6161, "step": 194500 }, { "epoch": 14.49, "learning_rate": 2.754700156052612e-05, "loss": 3.6112, "step": 195000 }, { "epoch": 14.53, "learning_rate": 2.736122464145055e-05, "loss": 3.6308, "step": 195500 }, { "epoch": 14.56, "learning_rate": 2.7175447722374976e-05, "loss": 3.6182, "step": 196000 }, { "epoch": 14.6, "learning_rate": 2.69896708032994e-05, "loss": 3.6005, "step": 196500 }, { "epoch": 14.64, "learning_rate": 2.6803893884223823e-05, "loss": 3.6148, "step": 197000 }, { "epoch": 14.68, "learning_rate": 2.661811696514825e-05, "loss": 3.6142, "step": 197500 }, { "epoch": 14.71, "learning_rate": 2.643234004607268e-05, "loss": 3.6146, "step": 198000 }, { "epoch": 14.75, "learning_rate": 2.6246563126997102e-05, "loss": 3.6134, "step": 198500 }, { "epoch": 14.79, "learning_rate": 2.6060786207921528e-05, "loss": 3.6265, "step": 199000 }, { "epoch": 14.82, "learning_rate": 2.5875009288845953e-05, "loss": 3.5949, "step": 199500 }, { "epoch": 14.86, "learning_rate": 2.5689232369770382e-05, "loss": 3.6383, "step": 200000 }, { "epoch": 14.9, "learning_rate": 2.5503455450694807e-05, "loss": 3.5996, "step": 200500 }, { "epoch": 14.94, "learning_rate": 2.5317678531619233e-05, "loss": 3.6005, "step": 201000 }, { "epoch": 14.97, "learning_rate": 2.5131901612543658e-05, "loss": 3.6066, "step": 201500 }, { "epoch": 15.01, "learning_rate": 2.4946124693468084e-05, "loss": 3.5974, "step": 202000 }, { "epoch": 15.05, "learning_rate": 2.4760347774392512e-05, "loss": 3.5954, "step": 202500 }, { "epoch": 15.09, "learning_rate": 2.4574570855316938e-05, "loss": 3.6086, "step": 203000 }, { "epoch": 15.12, "learning_rate": 2.4388793936241363e-05, "loss": 3.5961, "step": 203500 }, { "epoch": 15.16, "learning_rate": 2.420301701716579e-05, "loss": 3.6197, "step": 204000 }, { "epoch": 15.2, "learning_rate": 2.4017240098090217e-05, "loss": 3.6059, "step": 204500 }, { "epoch": 15.23, "learning_rate": 2.383146317901464e-05, "loss": 3.5814, "step": 205000 }, { "epoch": 15.27, "learning_rate": 2.3645686259939065e-05, "loss": 3.6082, "step": 205500 }, { "epoch": 15.31, "learning_rate": 2.3459909340863493e-05, "loss": 3.6141, "step": 206000 }, { "epoch": 15.35, "learning_rate": 2.3274132421787915e-05, "loss": 3.6143, "step": 206500 }, { "epoch": 15.38, "learning_rate": 2.3088355502712344e-05, "loss": 3.6195, "step": 207000 }, { "epoch": 15.42, "learning_rate": 2.290257858363677e-05, "loss": 3.6097, "step": 207500 }, { "epoch": 15.46, "learning_rate": 2.2716801664561195e-05, "loss": 3.6006, "step": 208000 }, { "epoch": 15.49, "learning_rate": 2.253102474548562e-05, "loss": 3.5869, "step": 208500 }, { "epoch": 15.53, "learning_rate": 2.234524782641005e-05, "loss": 3.6097, "step": 209000 }, { "epoch": 15.57, "learning_rate": 2.2159470907334474e-05, "loss": 3.6082, "step": 209500 }, { "epoch": 15.61, "learning_rate": 2.19736939882589e-05, "loss": 3.598, "step": 210000 }, { "epoch": 15.64, "learning_rate": 2.1787917069183325e-05, "loss": 3.5982, "step": 210500 }, { "epoch": 15.68, "learning_rate": 2.1602140150107754e-05, "loss": 3.6078, "step": 211000 }, { "epoch": 15.72, "learning_rate": 2.1416363231032176e-05, "loss": 3.5942, "step": 211500 }, { "epoch": 15.75, "learning_rate": 2.1230586311956605e-05, "loss": 3.6247, "step": 212000 }, { "epoch": 15.79, "learning_rate": 2.104480939288103e-05, "loss": 3.5861, "step": 212500 }, { "epoch": 15.83, "learning_rate": 2.0859032473805456e-05, "loss": 3.614, "step": 213000 }, { "epoch": 15.87, "learning_rate": 2.067325555472988e-05, "loss": 3.6239, "step": 213500 }, { "epoch": 15.9, "learning_rate": 2.048747863565431e-05, "loss": 3.596, "step": 214000 }, { "epoch": 15.94, "learning_rate": 2.0301701716578732e-05, "loss": 3.6064, "step": 214500 }, { "epoch": 15.98, "learning_rate": 2.0115924797503157e-05, "loss": 3.5961, "step": 215000 }, { "epoch": 16.01, "learning_rate": 1.9930147878427586e-05, "loss": 3.5828, "step": 215500 }, { "epoch": 16.05, "learning_rate": 1.974437095935201e-05, "loss": 3.5974, "step": 216000 }, { "epoch": 16.09, "learning_rate": 1.9558594040276437e-05, "loss": 3.6004, "step": 216500 }, { "epoch": 16.13, "learning_rate": 1.9372817121200862e-05, "loss": 3.5748, "step": 217000 }, { "epoch": 16.16, "learning_rate": 1.918704020212529e-05, "loss": 3.6198, "step": 217500 }, { "epoch": 16.2, "learning_rate": 1.9001263283049713e-05, "loss": 3.5917, "step": 218000 }, { "epoch": 16.24, "learning_rate": 1.881548636397414e-05, "loss": 3.5839, "step": 218500 }, { "epoch": 16.27, "learning_rate": 1.8629709444898567e-05, "loss": 3.6037, "step": 219000 }, { "epoch": 16.31, "learning_rate": 1.8443932525822992e-05, "loss": 3.5726, "step": 219500 }, { "epoch": 16.35, "learning_rate": 1.8258155606747418e-05, "loss": 3.6034, "step": 220000 }, { "epoch": 16.39, "learning_rate": 1.8072378687671846e-05, "loss": 3.5972, "step": 220500 }, { "epoch": 16.42, "learning_rate": 1.788660176859627e-05, "loss": 3.5918, "step": 221000 }, { "epoch": 16.46, "learning_rate": 1.7700824849520697e-05, "loss": 3.6055, "step": 221500 }, { "epoch": 16.5, "learning_rate": 1.7515047930445123e-05, "loss": 3.6021, "step": 222000 }, { "epoch": 16.53, "learning_rate": 1.7329271011369548e-05, "loss": 3.5969, "step": 222500 }, { "epoch": 16.57, "learning_rate": 1.7143494092293973e-05, "loss": 3.6042, "step": 223000 }, { "epoch": 16.61, "learning_rate": 1.6957717173218402e-05, "loss": 3.5999, "step": 223500 }, { "epoch": 16.65, "learning_rate": 1.6771940254142828e-05, "loss": 3.6069, "step": 224000 }, { "epoch": 16.68, "learning_rate": 1.658616333506725e-05, "loss": 3.5965, "step": 224500 }, { "epoch": 16.72, "learning_rate": 1.640038641599168e-05, "loss": 3.5873, "step": 225000 }, { "epoch": 16.76, "learning_rate": 1.6214609496916104e-05, "loss": 3.5832, "step": 225500 }, { "epoch": 16.79, "learning_rate": 1.602883257784053e-05, "loss": 3.5859, "step": 226000 }, { "epoch": 16.83, "learning_rate": 1.5843055658764954e-05, "loss": 3.586, "step": 226500 }, { "epoch": 16.87, "learning_rate": 1.5657278739689383e-05, "loss": 3.5837, "step": 227000 }, { "epoch": 16.91, "learning_rate": 1.5471501820613805e-05, "loss": 3.5757, "step": 227500 }, { "epoch": 16.94, "learning_rate": 1.5285724901538234e-05, "loss": 3.5858, "step": 228000 }, { "epoch": 16.98, "learning_rate": 1.509994798246266e-05, "loss": 3.5886, "step": 228500 }, { "epoch": 17.02, "learning_rate": 1.4914171063387086e-05, "loss": 3.5836, "step": 229000 }, { "epoch": 17.05, "learning_rate": 1.472839414431151e-05, "loss": 3.6144, "step": 229500 }, { "epoch": 17.09, "learning_rate": 1.4542617225235939e-05, "loss": 3.5952, "step": 230000 }, { "epoch": 17.13, "learning_rate": 1.4356840306160363e-05, "loss": 3.6013, "step": 230500 }, { "epoch": 17.17, "learning_rate": 1.417106338708479e-05, "loss": 3.5861, "step": 231000 }, { "epoch": 17.2, "learning_rate": 1.3985286468009215e-05, "loss": 3.583, "step": 231500 }, { "epoch": 17.24, "learning_rate": 1.3799509548933642e-05, "loss": 3.5808, "step": 232000 }, { "epoch": 17.28, "learning_rate": 1.3613732629858068e-05, "loss": 3.5968, "step": 232500 }, { "epoch": 17.31, "learning_rate": 1.3427955710782495e-05, "loss": 3.6015, "step": 233000 }, { "epoch": 17.35, "learning_rate": 1.3242178791706918e-05, "loss": 3.5969, "step": 233500 }, { "epoch": 17.39, "learning_rate": 1.3056401872631344e-05, "loss": 3.5887, "step": 234000 }, { "epoch": 17.43, "learning_rate": 1.287062495355577e-05, "loss": 3.582, "step": 234500 }, { "epoch": 17.46, "learning_rate": 1.2684848034480196e-05, "loss": 3.5699, "step": 235000 }, { "epoch": 17.5, "learning_rate": 1.2499071115404623e-05, "loss": 3.5769, "step": 235500 }, { "epoch": 17.54, "learning_rate": 1.2313294196329049e-05, "loss": 3.5844, "step": 236000 }, { "epoch": 17.57, "learning_rate": 1.2127517277253476e-05, "loss": 3.5819, "step": 236500 }, { "epoch": 17.61, "learning_rate": 1.1941740358177901e-05, "loss": 3.5774, "step": 237000 }, { "epoch": 17.65, "learning_rate": 1.1755963439102326e-05, "loss": 3.5811, "step": 237500 }, { "epoch": 17.69, "learning_rate": 1.1570186520026752e-05, "loss": 3.5779, "step": 238000 }, { "epoch": 17.72, "learning_rate": 1.1384409600951177e-05, "loss": 3.6015, "step": 238500 }, { "epoch": 17.76, "learning_rate": 1.1198632681875604e-05, "loss": 3.5761, "step": 239000 }, { "epoch": 17.8, "learning_rate": 1.101285576280003e-05, "loss": 3.5738, "step": 239500 }, { "epoch": 17.83, "learning_rate": 1.0827078843724455e-05, "loss": 3.5726, "step": 240000 }, { "epoch": 17.87, "learning_rate": 1.0641301924648882e-05, "loss": 3.5745, "step": 240500 }, { "epoch": 17.91, "learning_rate": 1.0455525005573308e-05, "loss": 3.5656, "step": 241000 }, { "epoch": 17.95, "learning_rate": 1.0269748086497735e-05, "loss": 3.5615, "step": 241500 }, { "epoch": 17.98, "learning_rate": 1.008397116742216e-05, "loss": 3.6016, "step": 242000 }, { "epoch": 18.02, "learning_rate": 9.898194248346585e-06, "loss": 3.5701, "step": 242500 }, { "epoch": 18.06, "learning_rate": 9.712417329271012e-06, "loss": 3.5849, "step": 243000 }, { "epoch": 18.09, "learning_rate": 9.526640410195438e-06, "loss": 3.588, "step": 243500 }, { "epoch": 18.13, "learning_rate": 9.340863491119863e-06, "loss": 3.5743, "step": 244000 }, { "epoch": 18.17, "learning_rate": 9.15508657204429e-06, "loss": 3.569, "step": 244500 }, { "epoch": 18.21, "learning_rate": 8.969309652968716e-06, "loss": 3.587, "step": 245000 }, { "epoch": 18.24, "learning_rate": 8.783532733893143e-06, "loss": 3.569, "step": 245500 }, { "epoch": 18.28, "learning_rate": 8.597755814817568e-06, "loss": 3.5792, "step": 246000 }, { "epoch": 18.32, "learning_rate": 8.411978895741994e-06, "loss": 3.5709, "step": 246500 }, { "epoch": 18.35, "learning_rate": 8.22620197666642e-06, "loss": 3.5869, "step": 247000 }, { "epoch": 18.39, "learning_rate": 8.040425057590844e-06, "loss": 3.5759, "step": 247500 }, { "epoch": 18.43, "learning_rate": 7.854648138515271e-06, "loss": 3.5717, "step": 248000 }, { "epoch": 18.47, "learning_rate": 7.668871219439697e-06, "loss": 3.5706, "step": 248500 }, { "epoch": 18.5, "learning_rate": 7.483094300364123e-06, "loss": 3.5902, "step": 249000 }, { "epoch": 18.54, "learning_rate": 7.297317381288548e-06, "loss": 3.5644, "step": 249500 }, { "epoch": 18.58, "learning_rate": 7.111540462212975e-06, "loss": 3.5794, "step": 250000 }, { "epoch": 18.61, "learning_rate": 6.925763543137401e-06, "loss": 3.5598, "step": 250500 }, { "epoch": 18.65, "learning_rate": 6.739986624061827e-06, "loss": 3.5712, "step": 251000 }, { "epoch": 18.69, "learning_rate": 6.5542097049862525e-06, "loss": 3.5658, "step": 251500 }, { "epoch": 18.73, "learning_rate": 6.368432785910679e-06, "loss": 3.583, "step": 252000 }, { "epoch": 18.76, "learning_rate": 6.182655866835105e-06, "loss": 3.5836, "step": 252500 }, { "epoch": 18.8, "learning_rate": 5.996878947759531e-06, "loss": 3.5804, "step": 253000 }, { "epoch": 18.84, "learning_rate": 5.8111020286839565e-06, "loss": 3.5619, "step": 253500 }, { "epoch": 18.87, "learning_rate": 5.625325109608383e-06, "loss": 3.5812, "step": 254000 }, { "epoch": 18.91, "learning_rate": 5.439548190532808e-06, "loss": 3.5444, "step": 254500 }, { "epoch": 18.95, "learning_rate": 5.253771271457234e-06, "loss": 3.5842, "step": 255000 }, { "epoch": 18.99, "learning_rate": 5.06799435238166e-06, "loss": 3.5781, "step": 255500 }, { "epoch": 19.02, "learning_rate": 4.882217433306086e-06, "loss": 3.5553, "step": 256000 }, { "epoch": 19.06, "learning_rate": 4.696440514230512e-06, "loss": 3.5715, "step": 256500 }, { "epoch": 19.1, "learning_rate": 4.5106635951549385e-06, "loss": 3.5596, "step": 257000 }, { "epoch": 19.14, "learning_rate": 4.324886676079364e-06, "loss": 3.5656, "step": 257500 }, { "epoch": 19.17, "learning_rate": 4.13910975700379e-06, "loss": 3.5672, "step": 258000 }, { "epoch": 19.21, "learning_rate": 3.953332837928216e-06, "loss": 3.5775, "step": 258500 }, { "epoch": 19.25, "learning_rate": 3.7675559188526417e-06, "loss": 3.5739, "step": 259000 }, { "epoch": 19.28, "learning_rate": 3.5817789997770675e-06, "loss": 3.5585, "step": 259500 }, { "epoch": 19.32, "learning_rate": 3.3960020807014937e-06, "loss": 3.5669, "step": 260000 }, { "epoch": 19.36, "learning_rate": 3.2102251616259195e-06, "loss": 3.5983, "step": 260500 }, { "epoch": 19.4, "learning_rate": 3.0244482425503458e-06, "loss": 3.5677, "step": 261000 }, { "epoch": 19.43, "learning_rate": 2.8386713234747716e-06, "loss": 3.5637, "step": 261500 }, { "epoch": 19.47, "learning_rate": 2.652894404399198e-06, "loss": 3.5537, "step": 262000 }, { "epoch": 19.51, "learning_rate": 2.467117485323623e-06, "loss": 3.5905, "step": 262500 }, { "epoch": 19.54, "learning_rate": 2.2813405662480494e-06, "loss": 3.5472, "step": 263000 }, { "epoch": 19.58, "learning_rate": 2.0955636471724752e-06, "loss": 3.5655, "step": 263500 }, { "epoch": 19.62, "learning_rate": 1.9097867280969015e-06, "loss": 3.5524, "step": 264000 }, { "epoch": 19.66, "learning_rate": 1.7240098090213275e-06, "loss": 3.5676, "step": 264500 }, { "epoch": 19.69, "learning_rate": 1.5382328899457533e-06, "loss": 3.573, "step": 265000 }, { "epoch": 19.73, "learning_rate": 1.352455970870179e-06, "loss": 3.5716, "step": 265500 }, { "epoch": 19.77, "learning_rate": 1.1666790517946051e-06, "loss": 3.5609, "step": 266000 }, { "epoch": 19.8, "learning_rate": 9.809021327190311e-07, "loss": 3.5533, "step": 266500 }, { "epoch": 19.84, "learning_rate": 7.951252136434569e-07, "loss": 3.5868, "step": 267000 }, { "epoch": 19.88, "learning_rate": 6.093482945678829e-07, "loss": 3.5714, "step": 267500 }, { "epoch": 19.92, "learning_rate": 4.235713754923089e-07, "loss": 3.582, "step": 268000 }, { "epoch": 19.95, "learning_rate": 2.377944564167348e-07, "loss": 3.5858, "step": 268500 }, { "epoch": 19.99, "learning_rate": 5.2017537341160735e-08, "loss": 3.5559, "step": 269000 }, { "epoch": 20.0, "step": 269140, "total_flos": 510943470337440.0, "train_loss": 3.981161423732987, "train_runtime": 4340.1096, "train_samples_per_second": 992.136, "train_steps_per_second": 62.012 } ], "max_steps": 269140, "num_train_epochs": 20, "total_flos": 510943470337440.0, "trial_name": null, "trial_params": null }