{ "best_metric": null, "best_model_checkpoint": null, "epoch": 6.672036348616274, "eval_steps": 1000000, "global_step": 355366, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 5.000000000000001e-07, "loss": 10.2724, "step": 500 }, { "epoch": 0.02, "learning_rate": 1.0000000000000002e-06, "loss": 9.4865, "step": 1000 }, { "epoch": 0.03, "learning_rate": 1.5e-06, "loss": 8.8277, "step": 1500 }, { "epoch": 0.04, "learning_rate": 2.0000000000000003e-06, "loss": 8.2605, "step": 2000 }, { "epoch": 0.05, "learning_rate": 2.5e-06, "loss": 7.7582, "step": 2500 }, { "epoch": 0.06, "learning_rate": 3e-06, "loss": 7.3929, "step": 3000 }, { "epoch": 0.07, "learning_rate": 3.5e-06, "loss": 7.1731, "step": 3500 }, { "epoch": 0.08, "learning_rate": 4.000000000000001e-06, "loss": 7.0389, "step": 4000 }, { "epoch": 0.08, "learning_rate": 4.5e-06, "loss": 6.9427, "step": 4500 }, { "epoch": 0.09, "learning_rate": 5e-06, "loss": 6.8532, "step": 5000 }, { "epoch": 0.1, "learning_rate": 5.500000000000001e-06, "loss": 6.7878, "step": 5500 }, { "epoch": 0.11, "learning_rate": 6e-06, "loss": 6.7304, "step": 6000 }, { "epoch": 0.12, "learning_rate": 6.5000000000000004e-06, "loss": 6.6774, "step": 6500 }, { "epoch": 0.13, "learning_rate": 7e-06, "loss": 6.6394, "step": 7000 }, { "epoch": 0.14, "learning_rate": 7.500000000000001e-06, "loss": 6.5956, "step": 7500 }, { "epoch": 0.15, "learning_rate": 8.000000000000001e-06, "loss": 6.5611, "step": 8000 }, { "epoch": 0.16, "learning_rate": 8.5e-06, "loss": 6.5254, "step": 8500 }, { "epoch": 0.17, "learning_rate": 9e-06, "loss": 6.492, "step": 9000 }, { "epoch": 0.18, "learning_rate": 9.5e-06, "loss": 6.464, "step": 9500 }, { "epoch": 0.19, "learning_rate": 1e-05, "loss": 6.4429, "step": 10000 }, { "epoch": 0.2, "learning_rate": 9.999059478574923e-06, "loss": 6.4178, "step": 10500 }, { "epoch": 0.21, "learning_rate": 9.998118957149845e-06, "loss": 6.398, "step": 11000 }, { "epoch": 0.22, "learning_rate": 9.997178435724768e-06, "loss": 6.3899, "step": 11500 }, { "epoch": 0.23, "learning_rate": 9.99623791429969e-06, "loss": 6.3666, "step": 12000 }, { "epoch": 0.23, "learning_rate": 9.99529739287461e-06, "loss": 6.3563, "step": 12500 }, { "epoch": 0.24, "learning_rate": 9.994356871449533e-06, "loss": 6.3455, "step": 13000 }, { "epoch": 0.25, "learning_rate": 9.993416350024455e-06, "loss": 6.3307, "step": 13500 }, { "epoch": 0.26, "learning_rate": 9.992475828599375e-06, "loss": 6.3228, "step": 14000 }, { "epoch": 0.27, "learning_rate": 9.991535307174298e-06, "loss": 6.3095, "step": 14500 }, { "epoch": 0.28, "learning_rate": 9.99059478574922e-06, "loss": 6.3019, "step": 15000 }, { "epoch": 0.29, "learning_rate": 9.989654264324142e-06, "loss": 6.295, "step": 15500 }, { "epoch": 0.3, "learning_rate": 9.988713742899064e-06, "loss": 6.2841, "step": 16000 }, { "epoch": 0.31, "learning_rate": 9.987773221473987e-06, "loss": 6.2803, "step": 16500 }, { "epoch": 0.32, "learning_rate": 9.986832700048909e-06, "loss": 6.277, "step": 17000 }, { "epoch": 0.33, "learning_rate": 9.98589217862383e-06, "loss": 6.2662, "step": 17500 }, { "epoch": 0.34, "learning_rate": 9.984951657198752e-06, "loss": 6.2626, "step": 18000 }, { "epoch": 0.35, "learning_rate": 9.984011135773674e-06, "loss": 6.2531, "step": 18500 }, { "epoch": 0.36, "learning_rate": 9.983070614348596e-06, "loss": 6.2506, "step": 19000 }, { "epoch": 0.37, "learning_rate": 9.982130092923518e-06, "loss": 6.2441, "step": 19500 }, { "epoch": 0.38, "learning_rate": 9.981189571498439e-06, "loss": 6.2355, "step": 20000 }, { "epoch": 0.38, "learning_rate": 9.980249050073361e-06, "loss": 6.2275, "step": 20500 }, { "epoch": 0.39, "learning_rate": 9.979308528648283e-06, "loss": 6.2268, "step": 21000 }, { "epoch": 0.4, "learning_rate": 9.978368007223206e-06, "loss": 6.2214, "step": 21500 }, { "epoch": 0.41, "learning_rate": 9.977427485798126e-06, "loss": 6.2162, "step": 22000 }, { "epoch": 0.42, "learning_rate": 9.976486964373048e-06, "loss": 6.2105, "step": 22500 }, { "epoch": 0.43, "learning_rate": 9.97554644294797e-06, "loss": 6.2039, "step": 23000 }, { "epoch": 0.44, "learning_rate": 9.974605921522893e-06, "loss": 6.2009, "step": 23500 }, { "epoch": 0.45, "learning_rate": 9.973665400097815e-06, "loss": 6.1966, "step": 24000 }, { "epoch": 0.46, "learning_rate": 9.972724878672737e-06, "loss": 6.1927, "step": 24500 }, { "epoch": 0.47, "learning_rate": 9.97178435724766e-06, "loss": 6.1936, "step": 25000 }, { "epoch": 0.48, "learning_rate": 9.970843835822582e-06, "loss": 6.1807, "step": 25500 }, { "epoch": 0.49, "learning_rate": 9.969903314397504e-06, "loss": 6.1792, "step": 26000 }, { "epoch": 0.5, "learning_rate": 9.968962792972425e-06, "loss": 6.1783, "step": 26500 }, { "epoch": 0.51, "learning_rate": 9.968022271547347e-06, "loss": 6.1717, "step": 27000 }, { "epoch": 0.52, "learning_rate": 9.967081750122269e-06, "loss": 6.1654, "step": 27500 }, { "epoch": 0.53, "learning_rate": 9.96614122869719e-06, "loss": 6.1616, "step": 28000 }, { "epoch": 0.54, "learning_rate": 9.965200707272112e-06, "loss": 6.1554, "step": 28500 }, { "epoch": 0.54, "learning_rate": 9.964260185847034e-06, "loss": 6.1502, "step": 29000 }, { "epoch": 0.55, "learning_rate": 9.963319664421956e-06, "loss": 6.1438, "step": 29500 }, { "epoch": 0.56, "learning_rate": 9.962379142996879e-06, "loss": 6.13, "step": 30000 }, { "epoch": 0.57, "learning_rate": 9.961438621571801e-06, "loss": 6.1228, "step": 30500 }, { "epoch": 0.58, "learning_rate": 9.960498100146723e-06, "loss": 6.1182, "step": 31000 }, { "epoch": 0.59, "learning_rate": 9.959557578721644e-06, "loss": 6.1069, "step": 31500 }, { "epoch": 0.6, "learning_rate": 9.958617057296566e-06, "loss": 6.1002, "step": 32000 }, { "epoch": 0.61, "learning_rate": 9.957676535871488e-06, "loss": 6.0928, "step": 32500 }, { "epoch": 0.62, "learning_rate": 9.95673601444641e-06, "loss": 6.0805, "step": 33000 }, { "epoch": 0.63, "learning_rate": 9.955795493021333e-06, "loss": 6.0777, "step": 33500 }, { "epoch": 0.64, "learning_rate": 9.954854971596253e-06, "loss": 6.0675, "step": 34000 }, { "epoch": 0.65, "learning_rate": 9.953914450171175e-06, "loss": 6.065, "step": 34500 }, { "epoch": 0.66, "learning_rate": 9.952973928746098e-06, "loss": 6.0588, "step": 35000 }, { "epoch": 0.67, "learning_rate": 9.95203340732102e-06, "loss": 6.052, "step": 35500 }, { "epoch": 0.68, "learning_rate": 9.95109288589594e-06, "loss": 6.0446, "step": 36000 }, { "epoch": 0.69, "learning_rate": 9.950152364470863e-06, "loss": 6.0383, "step": 36500 }, { "epoch": 0.69, "learning_rate": 9.949211843045785e-06, "loss": 6.0339, "step": 37000 }, { "epoch": 0.7, "learning_rate": 9.948271321620707e-06, "loss": 6.0246, "step": 37500 }, { "epoch": 0.71, "learning_rate": 9.94733080019563e-06, "loss": 6.0157, "step": 38000 }, { "epoch": 0.72, "learning_rate": 9.946390278770552e-06, "loss": 6.0127, "step": 38500 }, { "epoch": 0.73, "learning_rate": 9.945449757345474e-06, "loss": 6.0073, "step": 39000 }, { "epoch": 0.74, "learning_rate": 9.944509235920396e-06, "loss": 6.0027, "step": 39500 }, { "epoch": 0.75, "learning_rate": 9.943568714495317e-06, "loss": 5.9946, "step": 40000 }, { "epoch": 0.76, "learning_rate": 9.942628193070239e-06, "loss": 5.9919, "step": 40500 }, { "epoch": 0.77, "learning_rate": 9.941687671645161e-06, "loss": 5.9878, "step": 41000 }, { "epoch": 0.78, "learning_rate": 9.940747150220082e-06, "loss": 5.9784, "step": 41500 }, { "epoch": 0.79, "learning_rate": 9.939806628795004e-06, "loss": 5.9727, "step": 42000 }, { "epoch": 0.8, "learning_rate": 9.938866107369926e-06, "loss": 5.9712, "step": 42500 }, { "epoch": 0.81, "learning_rate": 9.937925585944848e-06, "loss": 5.9628, "step": 43000 }, { "epoch": 0.82, "learning_rate": 9.93698506451977e-06, "loss": 5.9606, "step": 43500 }, { "epoch": 0.83, "learning_rate": 9.936044543094693e-06, "loss": 5.952, "step": 44000 }, { "epoch": 0.84, "learning_rate": 9.935104021669615e-06, "loss": 5.9452, "step": 44500 }, { "epoch": 0.84, "learning_rate": 9.934163500244537e-06, "loss": 5.9442, "step": 45000 }, { "epoch": 0.85, "learning_rate": 9.933222978819458e-06, "loss": 5.9357, "step": 45500 }, { "epoch": 0.86, "learning_rate": 9.93228245739438e-06, "loss": 5.9295, "step": 46000 }, { "epoch": 0.87, "learning_rate": 9.931341935969302e-06, "loss": 5.9296, "step": 46500 }, { "epoch": 0.88, "learning_rate": 9.930401414544225e-06, "loss": 5.9268, "step": 47000 }, { "epoch": 0.89, "learning_rate": 9.929460893119145e-06, "loss": 5.9184, "step": 47500 }, { "epoch": 0.9, "learning_rate": 9.928520371694067e-06, "loss": 5.9136, "step": 48000 }, { "epoch": 0.91, "learning_rate": 9.92757985026899e-06, "loss": 5.9095, "step": 48500 }, { "epoch": 0.92, "learning_rate": 9.926639328843912e-06, "loss": 5.9096, "step": 49000 }, { "epoch": 0.93, "learning_rate": 9.925698807418834e-06, "loss": 5.8971, "step": 49500 }, { "epoch": 0.94, "learning_rate": 9.924758285993755e-06, "loss": 5.895, "step": 50000 }, { "epoch": 0.95, "learning_rate": 9.923817764568677e-06, "loss": 5.892, "step": 50500 }, { "epoch": 0.96, "learning_rate": 9.9228772431436e-06, "loss": 5.8867, "step": 51000 }, { "epoch": 0.97, "learning_rate": 9.921936721718521e-06, "loss": 5.8746, "step": 51500 }, { "epoch": 0.98, "learning_rate": 9.920996200293444e-06, "loss": 5.877, "step": 52000 }, { "epoch": 0.99, "learning_rate": 9.920055678868366e-06, "loss": 5.8677, "step": 52500 }, { "epoch": 1.0, "learning_rate": 9.919115157443288e-06, "loss": 5.8603, "step": 53000 }, { "epoch": 1.0, "learning_rate": 9.91817463601821e-06, "loss": 5.853, "step": 53500 }, { "epoch": 1.01, "learning_rate": 9.917234114593131e-06, "loss": 5.8453, "step": 54000 }, { "epoch": 1.02, "learning_rate": 9.916293593168053e-06, "loss": 5.8363, "step": 54500 }, { "epoch": 1.03, "learning_rate": 9.915353071742975e-06, "loss": 5.827, "step": 55000 }, { "epoch": 1.04, "learning_rate": 9.914412550317896e-06, "loss": 5.8128, "step": 55500 }, { "epoch": 1.05, "learning_rate": 9.913472028892818e-06, "loss": 5.8023, "step": 56000 }, { "epoch": 1.06, "learning_rate": 9.91253150746774e-06, "loss": 5.7881, "step": 56500 }, { "epoch": 1.07, "learning_rate": 9.911590986042663e-06, "loss": 5.7732, "step": 57000 }, { "epoch": 1.08, "learning_rate": 9.910650464617585e-06, "loss": 5.752, "step": 57500 }, { "epoch": 1.09, "learning_rate": 9.909709943192507e-06, "loss": 5.7292, "step": 58000 }, { "epoch": 1.1, "learning_rate": 9.90876942176743e-06, "loss": 5.7008, "step": 58500 }, { "epoch": 1.11, "learning_rate": 9.907828900342352e-06, "loss": 5.6627, "step": 59000 }, { "epoch": 1.12, "learning_rate": 9.906888378917272e-06, "loss": 5.6226, "step": 59500 }, { "epoch": 1.13, "learning_rate": 9.905947857492194e-06, "loss": 5.5761, "step": 60000 }, { "epoch": 1.14, "learning_rate": 9.905007336067117e-06, "loss": 5.5302, "step": 60500 }, { "epoch": 1.15, "learning_rate": 9.904066814642039e-06, "loss": 5.4789, "step": 61000 }, { "epoch": 1.15, "learning_rate": 9.90312629321696e-06, "loss": 5.4259, "step": 61500 }, { "epoch": 1.16, "learning_rate": 9.902185771791882e-06, "loss": 5.3716, "step": 62000 }, { "epoch": 1.17, "learning_rate": 9.901245250366804e-06, "loss": 5.3342, "step": 62500 }, { "epoch": 1.18, "learning_rate": 9.900304728941726e-06, "loss": 5.2825, "step": 63000 }, { "epoch": 1.19, "learning_rate": 9.899364207516648e-06, "loss": 5.2418, "step": 63500 }, { "epoch": 1.2, "learning_rate": 9.898423686091569e-06, "loss": 5.2058, "step": 64000 }, { "epoch": 1.21, "learning_rate": 9.897483164666491e-06, "loss": 5.1644, "step": 64500 }, { "epoch": 1.22, "learning_rate": 9.896542643241414e-06, "loss": 5.1322, "step": 65000 }, { "epoch": 1.23, "learning_rate": 9.895602121816336e-06, "loss": 5.0915, "step": 65500 }, { "epoch": 1.24, "learning_rate": 9.894661600391258e-06, "loss": 5.0501, "step": 66000 }, { "epoch": 1.25, "learning_rate": 9.89372107896618e-06, "loss": 5.003, "step": 66500 }, { "epoch": 1.26, "learning_rate": 9.892780557541102e-06, "loss": 4.9573, "step": 67000 }, { "epoch": 1.27, "learning_rate": 9.891840036116023e-06, "loss": 4.9069, "step": 67500 }, { "epoch": 1.28, "learning_rate": 9.890899514690945e-06, "loss": 4.8441, "step": 68000 }, { "epoch": 1.29, "learning_rate": 9.889958993265868e-06, "loss": 4.7973, "step": 68500 }, { "epoch": 1.3, "learning_rate": 9.889018471840788e-06, "loss": 4.7475, "step": 69000 }, { "epoch": 1.3, "learning_rate": 9.88807795041571e-06, "loss": 4.7013, "step": 69500 }, { "epoch": 1.31, "learning_rate": 9.887137428990633e-06, "loss": 4.6667, "step": 70000 }, { "epoch": 1.32, "learning_rate": 9.886196907565555e-06, "loss": 4.6227, "step": 70500 }, { "epoch": 1.33, "learning_rate": 9.885256386140477e-06, "loss": 4.6007, "step": 71000 }, { "epoch": 1.34, "learning_rate": 9.8843158647154e-06, "loss": 4.5687, "step": 71500 }, { "epoch": 1.35, "learning_rate": 9.883375343290322e-06, "loss": 4.5459, "step": 72000 }, { "epoch": 1.36, "learning_rate": 9.882434821865244e-06, "loss": 4.5196, "step": 72500 }, { "epoch": 1.37, "learning_rate": 9.881494300440166e-06, "loss": 4.4916, "step": 73000 }, { "epoch": 1.38, "learning_rate": 9.880553779015087e-06, "loss": 4.4718, "step": 73500 }, { "epoch": 1.39, "learning_rate": 9.879613257590009e-06, "loss": 4.4506, "step": 74000 }, { "epoch": 1.4, "learning_rate": 9.878672736164931e-06, "loss": 4.4358, "step": 74500 }, { "epoch": 1.41, "learning_rate": 9.877732214739853e-06, "loss": 4.4118, "step": 75000 }, { "epoch": 1.42, "learning_rate": 9.876791693314774e-06, "loss": 4.3956, "step": 75500 }, { "epoch": 1.43, "learning_rate": 9.875851171889696e-06, "loss": 4.3766, "step": 76000 }, { "epoch": 1.44, "learning_rate": 9.874910650464618e-06, "loss": 4.3673, "step": 76500 }, { "epoch": 1.45, "learning_rate": 9.87397012903954e-06, "loss": 4.3504, "step": 77000 }, { "epoch": 1.46, "learning_rate": 9.873029607614463e-06, "loss": 4.3323, "step": 77500 }, { "epoch": 1.46, "learning_rate": 9.872089086189383e-06, "loss": 4.3156, "step": 78000 }, { "epoch": 1.47, "learning_rate": 9.871148564764306e-06, "loss": 4.3006, "step": 78500 }, { "epoch": 1.48, "learning_rate": 9.870208043339228e-06, "loss": 4.2906, "step": 79000 }, { "epoch": 1.49, "learning_rate": 9.86926752191415e-06, "loss": 4.2742, "step": 79500 }, { "epoch": 1.5, "learning_rate": 9.868327000489072e-06, "loss": 4.2575, "step": 80000 }, { "epoch": 1.51, "learning_rate": 9.867386479063995e-06, "loss": 4.2469, "step": 80500 }, { "epoch": 1.52, "learning_rate": 9.866445957638917e-06, "loss": 4.2354, "step": 81000 }, { "epoch": 1.53, "learning_rate": 9.865505436213837e-06, "loss": 4.2268, "step": 81500 }, { "epoch": 1.54, "learning_rate": 9.86456491478876e-06, "loss": 4.2129, "step": 82000 }, { "epoch": 1.55, "learning_rate": 9.863624393363682e-06, "loss": 4.2056, "step": 82500 }, { "epoch": 1.56, "learning_rate": 9.862683871938602e-06, "loss": 4.1995, "step": 83000 }, { "epoch": 1.57, "learning_rate": 9.861743350513525e-06, "loss": 4.1838, "step": 83500 }, { "epoch": 1.58, "learning_rate": 9.860802829088447e-06, "loss": 4.1761, "step": 84000 }, { "epoch": 1.59, "learning_rate": 9.859862307663369e-06, "loss": 4.1656, "step": 84500 }, { "epoch": 1.6, "learning_rate": 9.858921786238291e-06, "loss": 4.1573, "step": 85000 }, { "epoch": 1.61, "learning_rate": 9.857981264813214e-06, "loss": 4.1509, "step": 85500 }, { "epoch": 1.61, "learning_rate": 9.857040743388136e-06, "loss": 4.1413, "step": 86000 }, { "epoch": 1.62, "learning_rate": 9.856100221963058e-06, "loss": 4.1245, "step": 86500 }, { "epoch": 1.63, "learning_rate": 9.85515970053798e-06, "loss": 4.1195, "step": 87000 }, { "epoch": 1.64, "learning_rate": 9.854219179112901e-06, "loss": 4.1106, "step": 87500 }, { "epoch": 1.65, "learning_rate": 9.853278657687823e-06, "loss": 4.0989, "step": 88000 }, { "epoch": 1.66, "learning_rate": 9.852338136262745e-06, "loss": 4.0895, "step": 88500 }, { "epoch": 1.67, "learning_rate": 9.851397614837666e-06, "loss": 4.0832, "step": 89000 }, { "epoch": 1.68, "learning_rate": 9.850457093412588e-06, "loss": 4.0812, "step": 89500 }, { "epoch": 1.69, "learning_rate": 9.84951657198751e-06, "loss": 4.0694, "step": 90000 }, { "epoch": 1.7, "learning_rate": 9.848576050562433e-06, "loss": 4.058, "step": 90500 }, { "epoch": 1.71, "learning_rate": 9.847635529137355e-06, "loss": 4.0595, "step": 91000 }, { "epoch": 1.72, "learning_rate": 9.846695007712277e-06, "loss": 4.0455, "step": 91500 }, { "epoch": 1.73, "learning_rate": 9.845754486287198e-06, "loss": 4.0401, "step": 92000 }, { "epoch": 1.74, "learning_rate": 9.84481396486212e-06, "loss": 4.0343, "step": 92500 }, { "epoch": 1.75, "learning_rate": 9.843873443437042e-06, "loss": 4.0248, "step": 93000 }, { "epoch": 1.76, "learning_rate": 9.842932922011964e-06, "loss": 4.0172, "step": 93500 }, { "epoch": 1.76, "learning_rate": 9.841992400586887e-06, "loss": 4.0094, "step": 94000 }, { "epoch": 1.77, "learning_rate": 9.841051879161809e-06, "loss": 4.0001, "step": 94500 }, { "epoch": 1.78, "learning_rate": 9.84011135773673e-06, "loss": 3.9925, "step": 95000 }, { "epoch": 1.79, "learning_rate": 9.839170836311652e-06, "loss": 3.9872, "step": 95500 }, { "epoch": 1.8, "learning_rate": 9.838230314886574e-06, "loss": 3.9793, "step": 96000 }, { "epoch": 1.81, "learning_rate": 9.837289793461496e-06, "loss": 3.9775, "step": 96500 }, { "epoch": 1.82, "learning_rate": 9.836349272036417e-06, "loss": 3.9674, "step": 97000 }, { "epoch": 1.83, "learning_rate": 9.835408750611339e-06, "loss": 3.9595, "step": 97500 }, { "epoch": 1.84, "learning_rate": 9.834468229186261e-06, "loss": 3.9563, "step": 98000 }, { "epoch": 1.85, "learning_rate": 9.833527707761183e-06, "loss": 3.9461, "step": 98500 }, { "epoch": 1.86, "learning_rate": 9.832587186336106e-06, "loss": 3.9364, "step": 99000 }, { "epoch": 1.87, "learning_rate": 9.831646664911028e-06, "loss": 3.9316, "step": 99500 }, { "epoch": 1.88, "learning_rate": 9.83070614348595e-06, "loss": 3.9244, "step": 100000 }, { "epoch": 1.89, "learning_rate": 9.829765622060872e-06, "loss": 3.918, "step": 100500 }, { "epoch": 1.9, "learning_rate": 9.828825100635795e-06, "loss": 3.9104, "step": 101000 }, { "epoch": 1.91, "learning_rate": 9.827884579210715e-06, "loss": 3.8983, "step": 101500 }, { "epoch": 1.92, "learning_rate": 9.826944057785637e-06, "loss": 3.8924, "step": 102000 }, { "epoch": 1.92, "learning_rate": 9.82600353636056e-06, "loss": 3.8892, "step": 102500 }, { "epoch": 1.93, "learning_rate": 9.82506301493548e-06, "loss": 3.8831, "step": 103000 }, { "epoch": 1.94, "learning_rate": 9.824122493510402e-06, "loss": 3.8713, "step": 103500 }, { "epoch": 1.95, "learning_rate": 9.823181972085325e-06, "loss": 3.8675, "step": 104000 }, { "epoch": 1.96, "learning_rate": 9.822241450660247e-06, "loss": 3.8587, "step": 104500 }, { "epoch": 1.97, "learning_rate": 9.821300929235169e-06, "loss": 3.8494, "step": 105000 }, { "epoch": 1.98, "learning_rate": 9.820360407810091e-06, "loss": 3.8453, "step": 105500 }, { "epoch": 1.99, "learning_rate": 9.819419886385014e-06, "loss": 3.8371, "step": 106000 }, { "epoch": 2.0, "learning_rate": 9.818479364959934e-06, "loss": 3.8377, "step": 106500 }, { "epoch": 2.01, "learning_rate": 9.817538843534856e-06, "loss": 3.8239, "step": 107000 }, { "epoch": 2.02, "learning_rate": 9.816598322109779e-06, "loss": 3.8215, "step": 107500 }, { "epoch": 2.03, "learning_rate": 9.815657800684701e-06, "loss": 3.8147, "step": 108000 }, { "epoch": 2.04, "learning_rate": 9.814717279259623e-06, "loss": 3.8126, "step": 108500 }, { "epoch": 2.05, "learning_rate": 9.813776757834544e-06, "loss": 3.8007, "step": 109000 }, { "epoch": 2.06, "learning_rate": 9.812836236409466e-06, "loss": 3.7954, "step": 109500 }, { "epoch": 2.07, "learning_rate": 9.811895714984388e-06, "loss": 3.7885, "step": 110000 }, { "epoch": 2.07, "learning_rate": 9.81095519355931e-06, "loss": 3.7891, "step": 110500 }, { "epoch": 2.08, "learning_rate": 9.810014672134231e-06, "loss": 3.7769, "step": 111000 }, { "epoch": 2.09, "learning_rate": 9.809074150709153e-06, "loss": 3.7706, "step": 111500 }, { "epoch": 2.1, "learning_rate": 9.808133629284075e-06, "loss": 3.7729, "step": 112000 }, { "epoch": 2.11, "learning_rate": 9.807193107858998e-06, "loss": 3.7636, "step": 112500 }, { "epoch": 2.12, "learning_rate": 9.80625258643392e-06, "loss": 3.7582, "step": 113000 }, { "epoch": 2.13, "learning_rate": 9.805312065008842e-06, "loss": 3.7533, "step": 113500 }, { "epoch": 2.14, "learning_rate": 9.804371543583764e-06, "loss": 3.7475, "step": 114000 }, { "epoch": 2.15, "learning_rate": 9.803431022158687e-06, "loss": 3.7431, "step": 114500 }, { "epoch": 2.16, "learning_rate": 9.802490500733607e-06, "loss": 3.74, "step": 115000 }, { "epoch": 2.17, "learning_rate": 9.80154997930853e-06, "loss": 3.7378, "step": 115500 }, { "epoch": 2.18, "learning_rate": 9.800609457883452e-06, "loss": 3.7306, "step": 116000 }, { "epoch": 2.19, "learning_rate": 9.799668936458372e-06, "loss": 3.7283, "step": 116500 }, { "epoch": 2.2, "learning_rate": 9.798728415033294e-06, "loss": 3.7236, "step": 117000 }, { "epoch": 2.21, "learning_rate": 9.797787893608217e-06, "loss": 3.7138, "step": 117500 }, { "epoch": 2.22, "learning_rate": 9.796847372183139e-06, "loss": 3.7114, "step": 118000 }, { "epoch": 2.22, "learning_rate": 9.795906850758061e-06, "loss": 3.7117, "step": 118500 }, { "epoch": 2.23, "learning_rate": 9.794966329332983e-06, "loss": 3.6983, "step": 119000 }, { "epoch": 2.24, "learning_rate": 9.794025807907906e-06, "loss": 3.6976, "step": 119500 }, { "epoch": 2.25, "learning_rate": 9.793085286482828e-06, "loss": 3.6921, "step": 120000 }, { "epoch": 2.26, "learning_rate": 9.792144765057748e-06, "loss": 3.6908, "step": 120500 }, { "epoch": 2.27, "learning_rate": 9.79120424363267e-06, "loss": 3.6853, "step": 121000 }, { "epoch": 2.28, "learning_rate": 9.790263722207593e-06, "loss": 3.6876, "step": 121500 }, { "epoch": 2.29, "learning_rate": 9.789323200782515e-06, "loss": 3.6777, "step": 122000 }, { "epoch": 2.3, "learning_rate": 9.788382679357436e-06, "loss": 3.6758, "step": 122500 }, { "epoch": 2.31, "learning_rate": 9.787442157932358e-06, "loss": 3.67, "step": 123000 }, { "epoch": 2.32, "learning_rate": 9.78650163650728e-06, "loss": 3.6653, "step": 123500 }, { "epoch": 2.33, "learning_rate": 9.785561115082202e-06, "loss": 3.6607, "step": 124000 }, { "epoch": 2.34, "learning_rate": 9.784620593657125e-06, "loss": 3.6595, "step": 124500 }, { "epoch": 2.35, "learning_rate": 9.783680072232045e-06, "loss": 3.6552, "step": 125000 }, { "epoch": 2.36, "learning_rate": 9.782739550806967e-06, "loss": 3.6549, "step": 125500 }, { "epoch": 2.37, "learning_rate": 9.78179902938189e-06, "loss": 3.6418, "step": 126000 }, { "epoch": 2.38, "learning_rate": 9.780858507956812e-06, "loss": 3.6442, "step": 126500 }, { "epoch": 2.38, "learning_rate": 9.779917986531734e-06, "loss": 3.6381, "step": 127000 }, { "epoch": 2.39, "learning_rate": 9.778977465106656e-06, "loss": 3.6345, "step": 127500 }, { "epoch": 2.4, "learning_rate": 9.778036943681579e-06, "loss": 3.6337, "step": 128000 }, { "epoch": 2.41, "learning_rate": 9.777096422256501e-06, "loss": 3.6264, "step": 128500 }, { "epoch": 2.42, "learning_rate": 9.776155900831421e-06, "loss": 3.6245, "step": 129000 }, { "epoch": 2.43, "learning_rate": 9.775215379406344e-06, "loss": 3.6189, "step": 129500 }, { "epoch": 2.44, "learning_rate": 9.774274857981266e-06, "loss": 3.6138, "step": 130000 }, { "epoch": 2.45, "learning_rate": 9.773334336556187e-06, "loss": 3.61, "step": 130500 }, { "epoch": 2.46, "learning_rate": 9.772393815131109e-06, "loss": 3.6088, "step": 131000 }, { "epoch": 2.47, "learning_rate": 9.771453293706031e-06, "loss": 3.6054, "step": 131500 }, { "epoch": 2.48, "learning_rate": 9.770512772280953e-06, "loss": 3.6056, "step": 132000 }, { "epoch": 2.49, "learning_rate": 9.769572250855875e-06, "loss": 3.6009, "step": 132500 }, { "epoch": 2.5, "learning_rate": 9.768631729430798e-06, "loss": 3.6011, "step": 133000 }, { "epoch": 2.51, "learning_rate": 9.76769120800572e-06, "loss": 3.5902, "step": 133500 }, { "epoch": 2.52, "learning_rate": 9.766750686580642e-06, "loss": 3.5905, "step": 134000 }, { "epoch": 2.53, "learning_rate": 9.765810165155563e-06, "loss": 3.5834, "step": 134500 }, { "epoch": 2.53, "learning_rate": 9.764869643730485e-06, "loss": 3.5864, "step": 135000 }, { "epoch": 2.54, "learning_rate": 9.763929122305407e-06, "loss": 3.5809, "step": 135500 }, { "epoch": 2.55, "learning_rate": 9.76298860088033e-06, "loss": 3.5753, "step": 136000 }, { "epoch": 2.56, "learning_rate": 9.76204807945525e-06, "loss": 3.5742, "step": 136500 }, { "epoch": 2.57, "learning_rate": 9.761107558030172e-06, "loss": 3.5752, "step": 137000 }, { "epoch": 2.58, "learning_rate": 9.760167036605095e-06, "loss": 3.565, "step": 137500 }, { "epoch": 2.59, "learning_rate": 9.759226515180017e-06, "loss": 3.5656, "step": 138000 }, { "epoch": 2.6, "learning_rate": 9.758285993754939e-06, "loss": 3.5602, "step": 138500 }, { "epoch": 2.61, "learning_rate": 9.75734547232986e-06, "loss": 3.5603, "step": 139000 }, { "epoch": 2.62, "learning_rate": 9.756404950904782e-06, "loss": 3.5596, "step": 139500 }, { "epoch": 2.63, "learning_rate": 9.755464429479704e-06, "loss": 3.5574, "step": 140000 }, { "epoch": 2.64, "learning_rate": 9.754523908054626e-06, "loss": 3.5446, "step": 140500 }, { "epoch": 2.65, "learning_rate": 9.753583386629549e-06, "loss": 3.5499, "step": 141000 }, { "epoch": 2.66, "learning_rate": 9.75264286520447e-06, "loss": 3.543, "step": 141500 }, { "epoch": 2.67, "learning_rate": 9.751702343779393e-06, "loss": 3.5408, "step": 142000 }, { "epoch": 2.68, "learning_rate": 9.750761822354314e-06, "loss": 3.5415, "step": 142500 }, { "epoch": 2.68, "learning_rate": 9.749821300929236e-06, "loss": 3.5435, "step": 143000 }, { "epoch": 2.69, "learning_rate": 9.748880779504158e-06, "loss": 3.5357, "step": 143500 }, { "epoch": 2.7, "learning_rate": 9.747940258079079e-06, "loss": 3.5336, "step": 144000 }, { "epoch": 2.71, "learning_rate": 9.746999736654e-06, "loss": 3.5298, "step": 144500 }, { "epoch": 2.72, "learning_rate": 9.746059215228923e-06, "loss": 3.5304, "step": 145000 }, { "epoch": 2.73, "learning_rate": 9.745118693803845e-06, "loss": 3.5217, "step": 145500 }, { "epoch": 2.74, "learning_rate": 9.744178172378768e-06, "loss": 3.5178, "step": 146000 }, { "epoch": 2.75, "learning_rate": 9.74323765095369e-06, "loss": 3.5243, "step": 146500 }, { "epoch": 2.76, "learning_rate": 9.742297129528612e-06, "loss": 3.515, "step": 147000 }, { "epoch": 2.77, "learning_rate": 9.741356608103534e-06, "loss": 3.5105, "step": 147500 }, { "epoch": 2.78, "learning_rate": 9.740416086678457e-06, "loss": 3.5177, "step": 148000 }, { "epoch": 2.79, "learning_rate": 9.739475565253377e-06, "loss": 3.5061, "step": 148500 }, { "epoch": 2.8, "learning_rate": 9.7385350438283e-06, "loss": 3.5092, "step": 149000 }, { "epoch": 2.81, "learning_rate": 9.737594522403222e-06, "loss": 3.5023, "step": 149500 }, { "epoch": 2.82, "learning_rate": 9.736654000978144e-06, "loss": 3.5021, "step": 150000 }, { "epoch": 2.83, "learning_rate": 9.735713479553064e-06, "loss": 3.5011, "step": 150500 }, { "epoch": 2.84, "learning_rate": 9.734772958127987e-06, "loss": 3.5029, "step": 151000 }, { "epoch": 2.84, "learning_rate": 9.733832436702909e-06, "loss": 3.4974, "step": 151500 }, { "epoch": 2.85, "learning_rate": 9.732891915277831e-06, "loss": 3.49, "step": 152000 }, { "epoch": 2.86, "learning_rate": 9.731951393852753e-06, "loss": 3.4927, "step": 152500 }, { "epoch": 2.87, "learning_rate": 9.731010872427674e-06, "loss": 3.4845, "step": 153000 }, { "epoch": 2.88, "learning_rate": 9.730070351002596e-06, "loss": 3.4818, "step": 153500 }, { "epoch": 2.89, "learning_rate": 9.729129829577518e-06, "loss": 3.4846, "step": 154000 }, { "epoch": 2.9, "learning_rate": 9.72818930815244e-06, "loss": 3.4805, "step": 154500 }, { "epoch": 2.91, "learning_rate": 9.727248786727363e-06, "loss": 3.474, "step": 155000 }, { "epoch": 2.92, "learning_rate": 9.726308265302285e-06, "loss": 3.4707, "step": 155500 }, { "epoch": 2.93, "learning_rate": 9.725367743877207e-06, "loss": 3.4756, "step": 156000 }, { "epoch": 2.94, "learning_rate": 9.724427222452128e-06, "loss": 3.4713, "step": 156500 }, { "epoch": 2.95, "learning_rate": 9.72348670102705e-06, "loss": 3.469, "step": 157000 }, { "epoch": 2.96, "learning_rate": 9.722546179601972e-06, "loss": 3.4688, "step": 157500 }, { "epoch": 2.97, "learning_rate": 9.721605658176893e-06, "loss": 3.4686, "step": 158000 }, { "epoch": 2.98, "learning_rate": 9.720665136751815e-06, "loss": 3.4622, "step": 158500 }, { "epoch": 2.99, "learning_rate": 9.719724615326737e-06, "loss": 3.4611, "step": 159000 }, { "epoch": 2.99, "learning_rate": 9.71878409390166e-06, "loss": 3.4609, "step": 159500 }, { "epoch": 3.0, "learning_rate": 9.717843572476582e-06, "loss": 3.4537, "step": 160000 }, { "epoch": 3.01, "learning_rate": 9.716903051051504e-06, "loss": 3.4565, "step": 160500 }, { "epoch": 3.02, "learning_rate": 9.715962529626426e-06, "loss": 3.4539, "step": 161000 }, { "epoch": 3.03, "learning_rate": 9.715022008201349e-06, "loss": 3.4538, "step": 161500 }, { "epoch": 3.04, "learning_rate": 9.71408148677627e-06, "loss": 3.4526, "step": 162000 }, { "epoch": 3.05, "learning_rate": 9.713140965351191e-06, "loss": 3.4438, "step": 162500 }, { "epoch": 3.06, "learning_rate": 9.712200443926114e-06, "loss": 3.448, "step": 163000 }, { "epoch": 3.07, "learning_rate": 9.711259922501036e-06, "loss": 3.4444, "step": 163500 }, { "epoch": 3.08, "learning_rate": 9.710319401075956e-06, "loss": 3.4383, "step": 164000 }, { "epoch": 3.09, "learning_rate": 9.709378879650879e-06, "loss": 3.4349, "step": 164500 }, { "epoch": 3.1, "learning_rate": 9.708438358225801e-06, "loss": 3.4406, "step": 165000 }, { "epoch": 3.11, "learning_rate": 9.707497836800723e-06, "loss": 3.4343, "step": 165500 }, { "epoch": 3.12, "learning_rate": 9.706557315375645e-06, "loss": 3.4363, "step": 166000 }, { "epoch": 3.13, "learning_rate": 9.705616793950568e-06, "loss": 3.4354, "step": 166500 }, { "epoch": 3.14, "learning_rate": 9.704676272525488e-06, "loss": 3.4271, "step": 167000 }, { "epoch": 3.14, "learning_rate": 9.70373575110041e-06, "loss": 3.4258, "step": 167500 }, { "epoch": 3.15, "learning_rate": 9.702795229675333e-06, "loss": 3.4231, "step": 168000 }, { "epoch": 3.16, "learning_rate": 9.701854708250255e-06, "loss": 3.4297, "step": 168500 }, { "epoch": 3.17, "learning_rate": 9.700914186825177e-06, "loss": 3.4217, "step": 169000 }, { "epoch": 3.18, "learning_rate": 9.6999736654001e-06, "loss": 3.4272, "step": 169500 }, { "epoch": 3.19, "learning_rate": 9.69903314397502e-06, "loss": 3.421, "step": 170000 }, { "epoch": 3.2, "learning_rate": 9.698092622549942e-06, "loss": 3.4195, "step": 170500 }, { "epoch": 3.21, "learning_rate": 9.697152101124864e-06, "loss": 3.4192, "step": 171000 }, { "epoch": 3.22, "learning_rate": 9.696211579699787e-06, "loss": 3.4116, "step": 171500 }, { "epoch": 3.23, "learning_rate": 9.695271058274707e-06, "loss": 3.4064, "step": 172000 }, { "epoch": 3.24, "learning_rate": 9.69433053684963e-06, "loss": 3.411, "step": 172500 }, { "epoch": 3.25, "learning_rate": 9.693390015424552e-06, "loss": 3.411, "step": 173000 }, { "epoch": 3.26, "learning_rate": 9.692449493999474e-06, "loss": 3.4057, "step": 173500 }, { "epoch": 3.27, "learning_rate": 9.691508972574396e-06, "loss": 3.4061, "step": 174000 }, { "epoch": 3.28, "learning_rate": 9.690568451149318e-06, "loss": 3.399, "step": 174500 }, { "epoch": 3.29, "learning_rate": 9.68962792972424e-06, "loss": 3.3997, "step": 175000 }, { "epoch": 3.3, "learning_rate": 9.688687408299163e-06, "loss": 3.4021, "step": 175500 }, { "epoch": 3.3, "learning_rate": 9.687746886874085e-06, "loss": 3.3957, "step": 176000 }, { "epoch": 3.31, "learning_rate": 9.686806365449006e-06, "loss": 3.3993, "step": 176500 }, { "epoch": 3.32, "learning_rate": 9.685865844023928e-06, "loss": 3.3944, "step": 177000 }, { "epoch": 3.33, "learning_rate": 9.68492532259885e-06, "loss": 3.3935, "step": 177500 }, { "epoch": 3.34, "learning_rate": 9.68398480117377e-06, "loss": 3.3911, "step": 178000 }, { "epoch": 3.35, "learning_rate": 9.683044279748693e-06, "loss": 3.3885, "step": 178500 }, { "epoch": 3.36, "learning_rate": 9.682103758323615e-06, "loss": 3.387, "step": 179000 }, { "epoch": 3.37, "learning_rate": 9.681163236898537e-06, "loss": 3.3863, "step": 179500 }, { "epoch": 3.38, "learning_rate": 9.68022271547346e-06, "loss": 3.3835, "step": 180000 }, { "epoch": 3.39, "learning_rate": 9.679282194048382e-06, "loss": 3.3831, "step": 180500 }, { "epoch": 3.4, "learning_rate": 9.678341672623302e-06, "loss": 3.3813, "step": 181000 }, { "epoch": 3.41, "learning_rate": 9.677401151198225e-06, "loss": 3.3799, "step": 181500 }, { "epoch": 3.42, "learning_rate": 9.676460629773147e-06, "loss": 3.3781, "step": 182000 }, { "epoch": 3.43, "learning_rate": 9.67552010834807e-06, "loss": 3.3767, "step": 182500 }, { "epoch": 3.44, "learning_rate": 9.674579586922991e-06, "loss": 3.3753, "step": 183000 }, { "epoch": 3.45, "learning_rate": 9.673639065497914e-06, "loss": 3.3714, "step": 183500 }, { "epoch": 3.45, "learning_rate": 9.672698544072834e-06, "loss": 3.373, "step": 184000 }, { "epoch": 3.46, "learning_rate": 9.671758022647756e-06, "loss": 3.369, "step": 184500 }, { "epoch": 3.47, "learning_rate": 9.670817501222679e-06, "loss": 3.3688, "step": 185000 }, { "epoch": 3.48, "learning_rate": 9.669876979797601e-06, "loss": 3.3657, "step": 185500 }, { "epoch": 3.49, "learning_rate": 9.668936458372521e-06, "loss": 3.3663, "step": 186000 }, { "epoch": 3.5, "learning_rate": 9.667995936947444e-06, "loss": 3.3626, "step": 186500 }, { "epoch": 3.51, "learning_rate": 9.667055415522366e-06, "loss": 3.3629, "step": 187000 }, { "epoch": 3.52, "learning_rate": 9.666114894097288e-06, "loss": 3.3648, "step": 187500 }, { "epoch": 3.53, "learning_rate": 9.66517437267221e-06, "loss": 3.3591, "step": 188000 }, { "epoch": 3.54, "learning_rate": 9.664233851247133e-06, "loss": 3.3581, "step": 188500 }, { "epoch": 3.55, "learning_rate": 9.663293329822055e-06, "loss": 3.3571, "step": 189000 }, { "epoch": 3.56, "learning_rate": 9.662352808396977e-06, "loss": 3.3532, "step": 189500 }, { "epoch": 3.57, "learning_rate": 9.661412286971898e-06, "loss": 3.3572, "step": 190000 }, { "epoch": 3.58, "learning_rate": 9.66047176554682e-06, "loss": 3.3511, "step": 190500 }, { "epoch": 3.59, "learning_rate": 9.659531244121742e-06, "loss": 3.3525, "step": 191000 }, { "epoch": 3.6, "learning_rate": 9.658590722696663e-06, "loss": 3.3454, "step": 191500 }, { "epoch": 3.6, "learning_rate": 9.657650201271585e-06, "loss": 3.3543, "step": 192000 }, { "epoch": 3.61, "learning_rate": 9.656709679846507e-06, "loss": 3.3439, "step": 192500 }, { "epoch": 3.62, "learning_rate": 9.65576915842143e-06, "loss": 3.3465, "step": 193000 }, { "epoch": 3.63, "learning_rate": 9.654828636996352e-06, "loss": 3.347, "step": 193500 }, { "epoch": 3.64, "learning_rate": 9.653888115571274e-06, "loss": 3.3441, "step": 194000 }, { "epoch": 3.65, "learning_rate": 9.652947594146196e-06, "loss": 3.3434, "step": 194500 }, { "epoch": 3.66, "learning_rate": 9.652007072721118e-06, "loss": 3.3388, "step": 195000 }, { "epoch": 3.67, "learning_rate": 9.651066551296039e-06, "loss": 3.3415, "step": 195500 }, { "epoch": 3.68, "learning_rate": 9.650126029870961e-06, "loss": 3.3404, "step": 196000 }, { "epoch": 3.69, "learning_rate": 9.649185508445883e-06, "loss": 3.3343, "step": 196500 }, { "epoch": 3.7, "learning_rate": 9.648244987020806e-06, "loss": 3.3338, "step": 197000 }, { "epoch": 3.71, "learning_rate": 9.647304465595726e-06, "loss": 3.3308, "step": 197500 }, { "epoch": 3.72, "learning_rate": 9.646363944170649e-06, "loss": 3.3336, "step": 198000 }, { "epoch": 3.73, "learning_rate": 9.64542342274557e-06, "loss": 3.3341, "step": 198500 }, { "epoch": 3.74, "learning_rate": 9.644482901320493e-06, "loss": 3.3296, "step": 199000 }, { "epoch": 3.75, "learning_rate": 9.643542379895415e-06, "loss": 3.3306, "step": 199500 }, { "epoch": 3.76, "learning_rate": 9.642601858470336e-06, "loss": 3.3278, "step": 200000 }, { "epoch": 3.76, "learning_rate": 9.641661337045258e-06, "loss": 3.3269, "step": 200500 }, { "epoch": 3.77, "learning_rate": 9.64072081562018e-06, "loss": 3.3273, "step": 201000 }, { "epoch": 3.78, "learning_rate": 9.639780294195102e-06, "loss": 3.3272, "step": 201500 }, { "epoch": 3.79, "learning_rate": 9.638839772770025e-06, "loss": 3.3228, "step": 202000 }, { "epoch": 3.8, "learning_rate": 9.637899251344947e-06, "loss": 3.3167, "step": 202500 }, { "epoch": 3.81, "learning_rate": 9.63695872991987e-06, "loss": 3.3188, "step": 203000 }, { "epoch": 3.82, "learning_rate": 9.636018208494791e-06, "loss": 3.3225, "step": 203500 }, { "epoch": 3.83, "learning_rate": 9.635077687069712e-06, "loss": 3.3149, "step": 204000 }, { "epoch": 3.84, "learning_rate": 9.634137165644634e-06, "loss": 3.3164, "step": 204500 }, { "epoch": 3.85, "learning_rate": 9.633196644219556e-06, "loss": 3.3194, "step": 205000 }, { "epoch": 3.86, "learning_rate": 9.632256122794477e-06, "loss": 3.315, "step": 205500 }, { "epoch": 3.87, "learning_rate": 9.6313156013694e-06, "loss": 3.3181, "step": 206000 }, { "epoch": 3.88, "learning_rate": 9.630375079944322e-06, "loss": 3.3123, "step": 206500 }, { "epoch": 3.89, "learning_rate": 9.629434558519244e-06, "loss": 3.3108, "step": 207000 }, { "epoch": 3.9, "learning_rate": 9.628494037094166e-06, "loss": 3.3077, "step": 207500 }, { "epoch": 3.91, "learning_rate": 9.627553515669088e-06, "loss": 3.3048, "step": 208000 }, { "epoch": 3.91, "learning_rate": 9.62661299424401e-06, "loss": 3.3066, "step": 208500 }, { "epoch": 3.92, "learning_rate": 9.625672472818933e-06, "loss": 3.3041, "step": 209000 }, { "epoch": 3.93, "learning_rate": 9.624731951393853e-06, "loss": 3.3116, "step": 209500 }, { "epoch": 3.94, "learning_rate": 9.623791429968776e-06, "loss": 3.3016, "step": 210000 }, { "epoch": 3.95, "learning_rate": 9.622850908543698e-06, "loss": 3.3036, "step": 210500 }, { "epoch": 3.96, "learning_rate": 9.62191038711862e-06, "loss": 3.2989, "step": 211000 }, { "epoch": 3.97, "learning_rate": 9.62096986569354e-06, "loss": 3.3045, "step": 211500 }, { "epoch": 3.98, "learning_rate": 9.620029344268463e-06, "loss": 3.3009, "step": 212000 }, { "epoch": 3.99, "learning_rate": 9.619088822843385e-06, "loss": 3.2993, "step": 212500 }, { "epoch": 4.0, "learning_rate": 9.618148301418307e-06, "loss": 3.2943, "step": 213000 }, { "epoch": 4.01, "learning_rate": 9.61720777999323e-06, "loss": 3.2951, "step": 213500 }, { "epoch": 4.02, "learning_rate": 9.61626725856815e-06, "loss": 3.2938, "step": 214000 }, { "epoch": 4.03, "learning_rate": 9.615326737143072e-06, "loss": 3.2914, "step": 214500 }, { "epoch": 4.04, "learning_rate": 9.614386215717995e-06, "loss": 3.2979, "step": 215000 }, { "epoch": 4.05, "learning_rate": 9.613445694292917e-06, "loss": 3.2873, "step": 215500 }, { "epoch": 4.06, "learning_rate": 9.612505172867839e-06, "loss": 3.2894, "step": 216000 }, { "epoch": 4.06, "learning_rate": 9.611564651442761e-06, "loss": 3.2857, "step": 216500 }, { "epoch": 4.07, "learning_rate": 9.610624130017684e-06, "loss": 3.2869, "step": 217000 }, { "epoch": 4.08, "learning_rate": 9.609683608592604e-06, "loss": 3.2871, "step": 217500 }, { "epoch": 4.09, "learning_rate": 9.608743087167526e-06, "loss": 3.2846, "step": 218000 }, { "epoch": 4.1, "learning_rate": 9.607802565742449e-06, "loss": 3.2851, "step": 218500 }, { "epoch": 4.11, "learning_rate": 9.606862044317369e-06, "loss": 3.2849, "step": 219000 }, { "epoch": 4.12, "learning_rate": 9.605921522892291e-06, "loss": 3.2799, "step": 219500 }, { "epoch": 4.13, "learning_rate": 9.604981001467214e-06, "loss": 3.279, "step": 220000 }, { "epoch": 4.14, "learning_rate": 9.604040480042136e-06, "loss": 3.2794, "step": 220500 }, { "epoch": 4.15, "learning_rate": 9.603099958617058e-06, "loss": 3.2786, "step": 221000 }, { "epoch": 4.16, "learning_rate": 9.60215943719198e-06, "loss": 3.2776, "step": 221500 }, { "epoch": 4.17, "learning_rate": 9.601218915766903e-06, "loss": 3.2732, "step": 222000 }, { "epoch": 4.18, "learning_rate": 9.600278394341825e-06, "loss": 3.2723, "step": 222500 }, { "epoch": 4.19, "learning_rate": 9.599337872916747e-06, "loss": 3.2737, "step": 223000 }, { "epoch": 4.2, "learning_rate": 9.598397351491668e-06, "loss": 3.2736, "step": 223500 }, { "epoch": 4.21, "learning_rate": 9.59745683006659e-06, "loss": 3.2702, "step": 224000 }, { "epoch": 4.22, "learning_rate": 9.596516308641512e-06, "loss": 3.2711, "step": 224500 }, { "epoch": 4.22, "learning_rate": 9.595575787216433e-06, "loss": 3.2672, "step": 225000 }, { "epoch": 4.23, "learning_rate": 9.594635265791355e-06, "loss": 3.2708, "step": 225500 }, { "epoch": 4.24, "learning_rate": 9.593694744366277e-06, "loss": 3.2663, "step": 226000 }, { "epoch": 4.25, "learning_rate": 9.5927542229412e-06, "loss": 3.2683, "step": 226500 }, { "epoch": 4.26, "learning_rate": 9.591813701516122e-06, "loss": 3.2671, "step": 227000 }, { "epoch": 4.27, "learning_rate": 9.590873180091044e-06, "loss": 3.2643, "step": 227500 }, { "epoch": 4.28, "learning_rate": 9.589932658665964e-06, "loss": 3.2612, "step": 228000 }, { "epoch": 4.29, "learning_rate": 9.588992137240887e-06, "loss": 3.2643, "step": 228500 }, { "epoch": 4.3, "learning_rate": 9.588051615815809e-06, "loss": 3.2637, "step": 229000 }, { "epoch": 4.31, "learning_rate": 9.587111094390731e-06, "loss": 3.2626, "step": 229500 }, { "epoch": 4.32, "learning_rate": 9.586170572965653e-06, "loss": 3.2596, "step": 230000 }, { "epoch": 4.33, "learning_rate": 9.585230051540576e-06, "loss": 3.2643, "step": 230500 }, { "epoch": 4.34, "learning_rate": 9.584289530115498e-06, "loss": 3.2551, "step": 231000 }, { "epoch": 4.35, "learning_rate": 9.583349008690418e-06, "loss": 3.2567, "step": 231500 }, { "epoch": 4.36, "learning_rate": 9.58240848726534e-06, "loss": 3.2598, "step": 232000 }, { "epoch": 4.37, "learning_rate": 9.581467965840263e-06, "loss": 3.2575, "step": 232500 }, { "epoch": 4.37, "learning_rate": 9.580527444415183e-06, "loss": 3.2552, "step": 233000 }, { "epoch": 4.38, "learning_rate": 9.579586922990106e-06, "loss": 3.2554, "step": 233500 }, { "epoch": 4.39, "learning_rate": 9.578646401565028e-06, "loss": 3.2481, "step": 234000 }, { "epoch": 4.4, "learning_rate": 9.57770588013995e-06, "loss": 3.2531, "step": 234500 }, { "epoch": 4.41, "learning_rate": 9.576765358714872e-06, "loss": 3.2532, "step": 235000 }, { "epoch": 4.42, "learning_rate": 9.575824837289795e-06, "loss": 3.2536, "step": 235500 }, { "epoch": 4.43, "learning_rate": 9.574884315864717e-06, "loss": 3.2481, "step": 236000 }, { "epoch": 4.44, "learning_rate": 9.573943794439639e-06, "loss": 3.2488, "step": 236500 }, { "epoch": 4.45, "learning_rate": 9.573003273014561e-06, "loss": 3.2506, "step": 237000 }, { "epoch": 4.46, "learning_rate": 9.572062751589482e-06, "loss": 3.2416, "step": 237500 }, { "epoch": 4.47, "learning_rate": 9.571122230164404e-06, "loss": 3.2444, "step": 238000 }, { "epoch": 4.48, "learning_rate": 9.570181708739326e-06, "loss": 3.2451, "step": 238500 }, { "epoch": 4.49, "learning_rate": 9.569241187314247e-06, "loss": 3.2465, "step": 239000 }, { "epoch": 4.5, "learning_rate": 9.568300665889169e-06, "loss": 3.2445, "step": 239500 }, { "epoch": 4.51, "learning_rate": 9.567360144464091e-06, "loss": 3.2465, "step": 240000 }, { "epoch": 4.52, "learning_rate": 9.566419623039014e-06, "loss": 3.2395, "step": 240500 }, { "epoch": 4.52, "learning_rate": 9.565479101613936e-06, "loss": 3.2352, "step": 241000 }, { "epoch": 4.53, "learning_rate": 9.564538580188858e-06, "loss": 3.2419, "step": 241500 }, { "epoch": 4.54, "learning_rate": 9.563598058763779e-06, "loss": 3.2401, "step": 242000 }, { "epoch": 4.55, "learning_rate": 9.562657537338701e-06, "loss": 3.2363, "step": 242500 }, { "epoch": 4.56, "learning_rate": 9.561717015913623e-06, "loss": 3.2341, "step": 243000 }, { "epoch": 4.57, "learning_rate": 9.560776494488545e-06, "loss": 3.2357, "step": 243500 }, { "epoch": 4.58, "learning_rate": 9.559835973063468e-06, "loss": 3.2328, "step": 244000 }, { "epoch": 4.59, "learning_rate": 9.55889545163839e-06, "loss": 3.236, "step": 244500 }, { "epoch": 4.6, "learning_rate": 9.55795493021331e-06, "loss": 3.2358, "step": 245000 }, { "epoch": 4.61, "learning_rate": 9.557014408788233e-06, "loss": 3.2338, "step": 245500 }, { "epoch": 4.62, "learning_rate": 9.556073887363155e-06, "loss": 3.2294, "step": 246000 }, { "epoch": 4.63, "learning_rate": 9.555133365938077e-06, "loss": 3.2259, "step": 246500 }, { "epoch": 4.64, "learning_rate": 9.554192844512998e-06, "loss": 3.2322, "step": 247000 }, { "epoch": 4.65, "learning_rate": 9.55325232308792e-06, "loss": 3.2303, "step": 247500 }, { "epoch": 4.66, "learning_rate": 9.552311801662842e-06, "loss": 3.2297, "step": 248000 }, { "epoch": 4.67, "learning_rate": 9.551371280237764e-06, "loss": 3.2273, "step": 248500 }, { "epoch": 4.68, "learning_rate": 9.550430758812687e-06, "loss": 3.227, "step": 249000 }, { "epoch": 4.68, "learning_rate": 9.549490237387609e-06, "loss": 3.2182, "step": 249500 }, { "epoch": 4.69, "learning_rate": 9.548549715962531e-06, "loss": 3.2207, "step": 250000 }, { "epoch": 4.7, "learning_rate": 9.547609194537453e-06, "loss": 3.226, "step": 250500 }, { "epoch": 4.71, "learning_rate": 9.546668673112374e-06, "loss": 3.2236, "step": 251000 }, { "epoch": 4.72, "learning_rate": 9.545728151687296e-06, "loss": 3.2222, "step": 251500 }, { "epoch": 4.73, "learning_rate": 9.544787630262218e-06, "loss": 3.2174, "step": 252000 }, { "epoch": 4.74, "learning_rate": 9.54384710883714e-06, "loss": 3.2201, "step": 252500 }, { "epoch": 4.75, "learning_rate": 9.542906587412061e-06, "loss": 3.2201, "step": 253000 }, { "epoch": 4.76, "learning_rate": 9.541966065986983e-06, "loss": 3.216, "step": 253500 }, { "epoch": 4.77, "learning_rate": 9.541025544561906e-06, "loss": 3.2191, "step": 254000 }, { "epoch": 4.78, "learning_rate": 9.540085023136828e-06, "loss": 3.2166, "step": 254500 }, { "epoch": 4.79, "learning_rate": 9.53914450171175e-06, "loss": 3.2138, "step": 255000 }, { "epoch": 4.8, "learning_rate": 9.538203980286672e-06, "loss": 3.2174, "step": 255500 }, { "epoch": 4.81, "learning_rate": 9.537263458861593e-06, "loss": 3.2113, "step": 256000 }, { "epoch": 4.82, "learning_rate": 9.536322937436515e-06, "loss": 3.2152, "step": 256500 }, { "epoch": 4.83, "learning_rate": 9.535382416011437e-06, "loss": 3.2092, "step": 257000 }, { "epoch": 4.83, "learning_rate": 9.53444189458636e-06, "loss": 3.2136, "step": 257500 }, { "epoch": 4.84, "learning_rate": 9.533501373161282e-06, "loss": 3.2109, "step": 258000 }, { "epoch": 4.85, "learning_rate": 9.532560851736204e-06, "loss": 3.2153, "step": 258500 }, { "epoch": 4.86, "learning_rate": 9.531620330311125e-06, "loss": 3.2059, "step": 259000 }, { "epoch": 4.87, "learning_rate": 9.530679808886047e-06, "loss": 3.2083, "step": 259500 }, { "epoch": 4.88, "learning_rate": 9.52973928746097e-06, "loss": 3.2042, "step": 260000 }, { "epoch": 4.89, "learning_rate": 9.528798766035891e-06, "loss": 3.2051, "step": 260500 }, { "epoch": 4.9, "learning_rate": 9.527858244610812e-06, "loss": 3.2083, "step": 261000 }, { "epoch": 4.91, "learning_rate": 9.526917723185734e-06, "loss": 3.2014, "step": 261500 }, { "epoch": 4.92, "learning_rate": 9.525977201760656e-06, "loss": 3.2055, "step": 262000 }, { "epoch": 4.93, "learning_rate": 9.525036680335579e-06, "loss": 3.1989, "step": 262500 }, { "epoch": 4.94, "learning_rate": 9.524096158910501e-06, "loss": 3.2012, "step": 263000 }, { "epoch": 4.95, "learning_rate": 9.523155637485423e-06, "loss": 3.2018, "step": 263500 }, { "epoch": 4.96, "learning_rate": 9.522215116060345e-06, "loss": 3.203, "step": 264000 }, { "epoch": 4.97, "learning_rate": 9.521274594635268e-06, "loss": 3.2038, "step": 264500 }, { "epoch": 4.98, "learning_rate": 9.520334073210188e-06, "loss": 3.1983, "step": 265000 }, { "epoch": 4.98, "learning_rate": 9.51939355178511e-06, "loss": 3.2026, "step": 265500 }, { "epoch": 4.99, "learning_rate": 9.518453030360033e-06, "loss": 3.2042, "step": 266000 }, { "epoch": 5.0, "learning_rate": 9.517512508934953e-06, "loss": 3.1924, "step": 266500 }, { "epoch": 5.01, "learning_rate": 9.516571987509876e-06, "loss": 3.1968, "step": 267000 }, { "epoch": 5.02, "learning_rate": 9.515631466084798e-06, "loss": 3.1933, "step": 267500 }, { "epoch": 5.03, "learning_rate": 9.51469094465972e-06, "loss": 3.1923, "step": 268000 }, { "epoch": 5.04, "learning_rate": 9.513750423234642e-06, "loss": 3.1933, "step": 268500 }, { "epoch": 5.05, "learning_rate": 9.512809901809564e-06, "loss": 3.1904, "step": 269000 }, { "epoch": 5.06, "learning_rate": 9.511869380384487e-06, "loss": 3.192, "step": 269500 }, { "epoch": 5.07, "learning_rate": 9.510928858959409e-06, "loss": 3.1919, "step": 270000 }, { "epoch": 5.08, "learning_rate": 9.50998833753433e-06, "loss": 3.1874, "step": 270500 }, { "epoch": 5.09, "learning_rate": 9.509047816109252e-06, "loss": 3.1894, "step": 271000 }, { "epoch": 5.1, "learning_rate": 9.508107294684174e-06, "loss": 3.1927, "step": 271500 }, { "epoch": 5.11, "learning_rate": 9.507166773259096e-06, "loss": 3.1849, "step": 272000 }, { "epoch": 5.12, "learning_rate": 9.506226251834017e-06, "loss": 3.1924, "step": 272500 }, { "epoch": 5.13, "learning_rate": 9.505285730408939e-06, "loss": 3.1847, "step": 273000 }, { "epoch": 5.13, "learning_rate": 9.504345208983861e-06, "loss": 3.187, "step": 273500 }, { "epoch": 5.14, "learning_rate": 9.503404687558783e-06, "loss": 3.1864, "step": 274000 }, { "epoch": 5.15, "learning_rate": 9.502464166133706e-06, "loss": 3.1879, "step": 274500 }, { "epoch": 5.16, "learning_rate": 9.501523644708626e-06, "loss": 3.1865, "step": 275000 }, { "epoch": 5.17, "learning_rate": 9.500583123283549e-06, "loss": 3.1814, "step": 275500 }, { "epoch": 5.18, "learning_rate": 9.49964260185847e-06, "loss": 3.1839, "step": 276000 }, { "epoch": 5.19, "learning_rate": 9.498702080433393e-06, "loss": 3.182, "step": 276500 }, { "epoch": 5.2, "learning_rate": 9.497761559008315e-06, "loss": 3.1831, "step": 277000 }, { "epoch": 5.21, "learning_rate": 9.496821037583237e-06, "loss": 3.1814, "step": 277500 }, { "epoch": 5.22, "learning_rate": 9.49588051615816e-06, "loss": 3.181, "step": 278000 }, { "epoch": 5.23, "learning_rate": 9.494939994733082e-06, "loss": 3.177, "step": 278500 }, { "epoch": 5.24, "learning_rate": 9.493999473308003e-06, "loss": 3.1805, "step": 279000 }, { "epoch": 5.25, "learning_rate": 9.493058951882925e-06, "loss": 3.1783, "step": 279500 }, { "epoch": 5.26, "learning_rate": 9.492118430457847e-06, "loss": 3.1753, "step": 280000 }, { "epoch": 5.27, "learning_rate": 9.491177909032768e-06, "loss": 3.1759, "step": 280500 }, { "epoch": 5.28, "learning_rate": 9.49023738760769e-06, "loss": 3.1735, "step": 281000 }, { "epoch": 5.29, "learning_rate": 9.489296866182612e-06, "loss": 3.1805, "step": 281500 }, { "epoch": 5.29, "learning_rate": 9.488356344757534e-06, "loss": 3.1797, "step": 282000 }, { "epoch": 5.3, "learning_rate": 9.487415823332457e-06, "loss": 3.1728, "step": 282500 }, { "epoch": 5.31, "learning_rate": 9.486475301907379e-06, "loss": 3.172, "step": 283000 }, { "epoch": 5.32, "learning_rate": 9.485534780482301e-06, "loss": 3.1762, "step": 283500 }, { "epoch": 5.33, "learning_rate": 9.484594259057223e-06, "loss": 3.1736, "step": 284000 }, { "epoch": 5.34, "learning_rate": 9.483653737632144e-06, "loss": 3.1728, "step": 284500 }, { "epoch": 5.35, "learning_rate": 9.482713216207066e-06, "loss": 3.1717, "step": 285000 }, { "epoch": 5.36, "learning_rate": 9.481772694781988e-06, "loss": 3.1712, "step": 285500 }, { "epoch": 5.37, "learning_rate": 9.48083217335691e-06, "loss": 3.1661, "step": 286000 }, { "epoch": 5.38, "learning_rate": 9.479891651931831e-06, "loss": 3.1689, "step": 286500 }, { "epoch": 5.39, "learning_rate": 9.478951130506753e-06, "loss": 3.166, "step": 287000 }, { "epoch": 5.4, "learning_rate": 9.478010609081676e-06, "loss": 3.1663, "step": 287500 }, { "epoch": 5.41, "learning_rate": 9.477070087656598e-06, "loss": 3.1665, "step": 288000 }, { "epoch": 5.42, "learning_rate": 9.47612956623152e-06, "loss": 3.1623, "step": 288500 }, { "epoch": 5.43, "learning_rate": 9.47518904480644e-06, "loss": 3.1656, "step": 289000 }, { "epoch": 5.44, "learning_rate": 9.474248523381363e-06, "loss": 3.1601, "step": 289500 }, { "epoch": 5.44, "learning_rate": 9.473308001956285e-06, "loss": 3.1616, "step": 290000 }, { "epoch": 5.45, "learning_rate": 9.472367480531207e-06, "loss": 3.1612, "step": 290500 }, { "epoch": 5.46, "learning_rate": 9.47142695910613e-06, "loss": 3.1615, "step": 291000 }, { "epoch": 5.47, "learning_rate": 9.470486437681052e-06, "loss": 3.1637, "step": 291500 }, { "epoch": 5.48, "learning_rate": 9.469545916255974e-06, "loss": 3.165, "step": 292000 }, { "epoch": 5.49, "learning_rate": 9.468605394830895e-06, "loss": 3.1612, "step": 292500 }, { "epoch": 5.5, "learning_rate": 9.467664873405817e-06, "loss": 3.1596, "step": 293000 }, { "epoch": 5.51, "learning_rate": 9.466724351980739e-06, "loss": 3.1606, "step": 293500 }, { "epoch": 5.52, "learning_rate": 9.46578383055566e-06, "loss": 3.159, "step": 294000 }, { "epoch": 5.53, "learning_rate": 9.464843309130582e-06, "loss": 3.1596, "step": 294500 }, { "epoch": 5.54, "learning_rate": 9.463902787705504e-06, "loss": 3.1551, "step": 295000 }, { "epoch": 5.55, "learning_rate": 9.462962266280426e-06, "loss": 3.1576, "step": 295500 }, { "epoch": 5.56, "learning_rate": 9.462021744855349e-06, "loss": 3.1563, "step": 296000 }, { "epoch": 5.57, "learning_rate": 9.46108122343027e-06, "loss": 3.1529, "step": 296500 }, { "epoch": 5.58, "learning_rate": 9.460140702005193e-06, "loss": 3.1558, "step": 297000 }, { "epoch": 5.59, "learning_rate": 9.459200180580115e-06, "loss": 3.1524, "step": 297500 }, { "epoch": 5.59, "learning_rate": 9.458259659155038e-06, "loss": 3.1578, "step": 298000 }, { "epoch": 5.6, "learning_rate": 9.457319137729958e-06, "loss": 3.152, "step": 298500 }, { "epoch": 5.61, "learning_rate": 9.45637861630488e-06, "loss": 3.1529, "step": 299000 }, { "epoch": 5.62, "learning_rate": 9.455438094879803e-06, "loss": 3.1566, "step": 299500 }, { "epoch": 5.63, "learning_rate": 9.454497573454723e-06, "loss": 3.1445, "step": 300000 }, { "epoch": 5.64, "learning_rate": 9.453557052029645e-06, "loss": 3.1482, "step": 300500 }, { "epoch": 5.65, "learning_rate": 9.452616530604568e-06, "loss": 3.1499, "step": 301000 }, { "epoch": 5.66, "learning_rate": 9.45167600917949e-06, "loss": 3.1499, "step": 301500 }, { "epoch": 5.67, "learning_rate": 9.450735487754412e-06, "loss": 3.1459, "step": 302000 }, { "epoch": 5.68, "learning_rate": 9.449794966329334e-06, "loss": 3.1453, "step": 302500 }, { "epoch": 5.69, "learning_rate": 9.448854444904255e-06, "loss": 3.1468, "step": 303000 }, { "epoch": 5.7, "learning_rate": 9.447913923479177e-06, "loss": 3.1457, "step": 303500 }, { "epoch": 5.71, "learning_rate": 9.4469734020541e-06, "loss": 3.1472, "step": 304000 }, { "epoch": 5.72, "learning_rate": 9.446032880629022e-06, "loss": 3.1484, "step": 304500 }, { "epoch": 5.73, "learning_rate": 9.445092359203944e-06, "loss": 3.1458, "step": 305000 }, { "epoch": 5.74, "learning_rate": 9.444151837778866e-06, "loss": 3.1395, "step": 305500 }, { "epoch": 5.75, "learning_rate": 9.443211316353788e-06, "loss": 3.1423, "step": 306000 }, { "epoch": 5.75, "learning_rate": 9.442270794928709e-06, "loss": 3.1449, "step": 306500 }, { "epoch": 5.76, "learning_rate": 9.441330273503631e-06, "loss": 3.1478, "step": 307000 }, { "epoch": 5.77, "learning_rate": 9.440389752078553e-06, "loss": 3.1429, "step": 307500 }, { "epoch": 5.78, "learning_rate": 9.439449230653474e-06, "loss": 3.1392, "step": 308000 }, { "epoch": 5.79, "learning_rate": 9.438508709228396e-06, "loss": 3.1366, "step": 308500 }, { "epoch": 5.8, "learning_rate": 9.437568187803318e-06, "loss": 3.1386, "step": 309000 }, { "epoch": 5.81, "learning_rate": 9.43662766637824e-06, "loss": 3.1382, "step": 309500 }, { "epoch": 5.82, "learning_rate": 9.435687144953163e-06, "loss": 3.1363, "step": 310000 }, { "epoch": 5.83, "learning_rate": 9.434746623528085e-06, "loss": 3.1394, "step": 310500 }, { "epoch": 5.84, "learning_rate": 9.433806102103007e-06, "loss": 3.1376, "step": 311000 }, { "epoch": 5.85, "learning_rate": 9.43286558067793e-06, "loss": 3.1359, "step": 311500 }, { "epoch": 5.86, "learning_rate": 9.431925059252852e-06, "loss": 3.1327, "step": 312000 }, { "epoch": 5.87, "learning_rate": 9.430984537827772e-06, "loss": 3.1366, "step": 312500 }, { "epoch": 5.88, "learning_rate": 9.430044016402695e-06, "loss": 3.1385, "step": 313000 }, { "epoch": 5.89, "learning_rate": 9.429103494977617e-06, "loss": 3.1311, "step": 313500 }, { "epoch": 5.9, "learning_rate": 9.428162973552537e-06, "loss": 3.1327, "step": 314000 }, { "epoch": 5.9, "learning_rate": 9.42722245212746e-06, "loss": 3.1328, "step": 314500 }, { "epoch": 5.91, "learning_rate": 9.426281930702382e-06, "loss": 3.13, "step": 315000 }, { "epoch": 5.92, "learning_rate": 9.425341409277304e-06, "loss": 3.1345, "step": 315500 }, { "epoch": 5.93, "learning_rate": 9.424400887852226e-06, "loss": 3.1304, "step": 316000 }, { "epoch": 5.94, "learning_rate": 9.423460366427149e-06, "loss": 3.1279, "step": 316500 }, { "epoch": 5.95, "learning_rate": 9.42251984500207e-06, "loss": 3.1299, "step": 317000 }, { "epoch": 5.96, "learning_rate": 9.421579323576991e-06, "loss": 3.1245, "step": 317500 }, { "epoch": 5.97, "learning_rate": 9.420638802151914e-06, "loss": 3.1271, "step": 318000 }, { "epoch": 5.98, "learning_rate": 9.419698280726836e-06, "loss": 3.1286, "step": 318500 }, { "epoch": 5.99, "learning_rate": 9.418757759301758e-06, "loss": 3.1285, "step": 319000 }, { "epoch": 6.0, "learning_rate": 9.41781723787668e-06, "loss": 3.1324, "step": 319500 }, { "epoch": 6.01, "learning_rate": 9.416876716451601e-06, "loss": 3.1284, "step": 320000 }, { "epoch": 6.02, "learning_rate": 9.415936195026523e-06, "loss": 3.1235, "step": 320500 }, { "epoch": 6.03, "learning_rate": 9.414995673601445e-06, "loss": 3.1227, "step": 321000 }, { "epoch": 6.04, "learning_rate": 9.414055152176368e-06, "loss": 3.1212, "step": 321500 }, { "epoch": 6.05, "learning_rate": 9.413114630751288e-06, "loss": 3.1225, "step": 322000 }, { "epoch": 6.05, "learning_rate": 9.41217410932621e-06, "loss": 3.1238, "step": 322500 }, { "epoch": 6.06, "learning_rate": 9.411233587901133e-06, "loss": 3.1268, "step": 323000 }, { "epoch": 6.07, "learning_rate": 9.410293066476055e-06, "loss": 3.1222, "step": 323500 }, { "epoch": 6.08, "learning_rate": 9.409352545050977e-06, "loss": 3.121, "step": 324000 }, { "epoch": 6.09, "learning_rate": 9.4084120236259e-06, "loss": 3.1224, "step": 324500 }, { "epoch": 6.1, "learning_rate": 9.407471502200822e-06, "loss": 3.1165, "step": 325000 }, { "epoch": 6.11, "learning_rate": 9.406530980775744e-06, "loss": 3.1223, "step": 325500 }, { "epoch": 6.12, "learning_rate": 9.405590459350664e-06, "loss": 3.1173, "step": 326000 }, { "epoch": 6.13, "learning_rate": 9.404649937925587e-06, "loss": 3.1261, "step": 326500 }, { "epoch": 6.14, "learning_rate": 9.403709416500509e-06, "loss": 3.1186, "step": 327000 }, { "epoch": 6.15, "learning_rate": 9.402768895075431e-06, "loss": 3.1124, "step": 327500 }, { "epoch": 6.16, "learning_rate": 9.401828373650352e-06, "loss": 3.12, "step": 328000 }, { "epoch": 6.17, "learning_rate": 9.400887852225274e-06, "loss": 3.1154, "step": 328500 }, { "epoch": 6.18, "learning_rate": 9.399947330800196e-06, "loss": 3.1146, "step": 329000 }, { "epoch": 6.19, "learning_rate": 9.399006809375118e-06, "loss": 3.114, "step": 329500 }, { "epoch": 6.2, "learning_rate": 9.39806628795004e-06, "loss": 3.118, "step": 330000 }, { "epoch": 6.21, "learning_rate": 9.397125766524963e-06, "loss": 3.1128, "step": 330500 }, { "epoch": 6.21, "learning_rate": 9.396185245099883e-06, "loss": 3.116, "step": 331000 }, { "epoch": 6.22, "learning_rate": 9.395244723674806e-06, "loss": 3.1169, "step": 331500 }, { "epoch": 6.23, "learning_rate": 9.394304202249728e-06, "loss": 3.1145, "step": 332000 }, { "epoch": 6.24, "learning_rate": 9.39336368082465e-06, "loss": 3.1116, "step": 332500 }, { "epoch": 6.25, "learning_rate": 9.392423159399572e-06, "loss": 3.11, "step": 333000 }, { "epoch": 6.26, "learning_rate": 9.391482637974495e-06, "loss": 3.1114, "step": 333500 }, { "epoch": 6.27, "learning_rate": 9.390542116549415e-06, "loss": 3.1125, "step": 334000 }, { "epoch": 6.28, "learning_rate": 9.389601595124337e-06, "loss": 3.1127, "step": 334500 }, { "epoch": 6.29, "learning_rate": 9.38866107369926e-06, "loss": 3.1155, "step": 335000 }, { "epoch": 6.3, "learning_rate": 9.387720552274182e-06, "loss": 3.1078, "step": 335500 }, { "epoch": 6.31, "learning_rate": 9.386780030849103e-06, "loss": 3.1044, "step": 336000 }, { "epoch": 6.32, "learning_rate": 9.385839509424025e-06, "loss": 3.1095, "step": 336500 }, { "epoch": 6.33, "learning_rate": 9.384898987998947e-06, "loss": 3.105, "step": 337000 }, { "epoch": 6.34, "learning_rate": 9.38395846657387e-06, "loss": 3.1054, "step": 337500 }, { "epoch": 6.35, "learning_rate": 9.383017945148791e-06, "loss": 3.1093, "step": 338000 }, { "epoch": 6.36, "learning_rate": 9.382077423723714e-06, "loss": 3.1037, "step": 338500 }, { "epoch": 6.36, "learning_rate": 9.381136902298636e-06, "loss": 3.1056, "step": 339000 }, { "epoch": 6.37, "learning_rate": 9.380196380873558e-06, "loss": 3.1065, "step": 339500 }, { "epoch": 6.38, "learning_rate": 9.379255859448479e-06, "loss": 3.1037, "step": 340000 }, { "epoch": 6.39, "learning_rate": 9.378315338023401e-06, "loss": 3.0987, "step": 340500 }, { "epoch": 6.4, "learning_rate": 9.377374816598323e-06, "loss": 3.1032, "step": 341000 }, { "epoch": 6.41, "learning_rate": 9.376434295173244e-06, "loss": 3.0989, "step": 341500 }, { "epoch": 6.42, "learning_rate": 9.375493773748166e-06, "loss": 3.1025, "step": 342000 }, { "epoch": 6.43, "learning_rate": 9.374553252323088e-06, "loss": 3.0981, "step": 342500 }, { "epoch": 6.44, "learning_rate": 9.37361273089801e-06, "loss": 3.1033, "step": 343000 }, { "epoch": 6.45, "learning_rate": 9.372672209472933e-06, "loss": 3.0979, "step": 343500 }, { "epoch": 6.46, "learning_rate": 9.371731688047855e-06, "loss": 3.0975, "step": 344000 }, { "epoch": 6.47, "learning_rate": 9.370791166622777e-06, "loss": 3.0977, "step": 344500 }, { "epoch": 6.48, "learning_rate": 9.369850645197698e-06, "loss": 3.0953, "step": 345000 }, { "epoch": 6.49, "learning_rate": 9.36891012377262e-06, "loss": 3.0966, "step": 345500 }, { "epoch": 6.5, "learning_rate": 9.367969602347542e-06, "loss": 3.1, "step": 346000 }, { "epoch": 6.51, "learning_rate": 9.367029080922464e-06, "loss": 3.0972, "step": 346500 }, { "epoch": 6.51, "learning_rate": 9.366088559497387e-06, "loss": 3.0976, "step": 347000 }, { "epoch": 6.52, "learning_rate": 9.365148038072307e-06, "loss": 3.0926, "step": 347500 }, { "epoch": 6.53, "learning_rate": 9.36420751664723e-06, "loss": 3.0921, "step": 348000 }, { "epoch": 6.54, "learning_rate": 9.363266995222152e-06, "loss": 3.0901, "step": 348500 }, { "epoch": 6.55, "learning_rate": 9.362326473797074e-06, "loss": 3.0927, "step": 349000 }, { "epoch": 6.56, "learning_rate": 9.361385952371996e-06, "loss": 3.0941, "step": 349500 }, { "epoch": 6.57, "learning_rate": 9.360445430946917e-06, "loss": 3.0926, "step": 350000 }, { "epoch": 6.58, "learning_rate": 9.359504909521839e-06, "loss": 3.0934, "step": 350500 }, { "epoch": 6.59, "learning_rate": 9.358564388096761e-06, "loss": 3.0935, "step": 351000 }, { "epoch": 6.6, "learning_rate": 9.357623866671684e-06, "loss": 3.087, "step": 351500 }, { "epoch": 6.61, "learning_rate": 9.356683345246606e-06, "loss": 3.0902, "step": 352000 }, { "epoch": 6.62, "learning_rate": 9.355742823821528e-06, "loss": 3.0903, "step": 352500 }, { "epoch": 6.63, "learning_rate": 9.35480230239645e-06, "loss": 3.0913, "step": 353000 }, { "epoch": 6.64, "learning_rate": 9.353861780971372e-06, "loss": 3.0956, "step": 353500 }, { "epoch": 6.65, "learning_rate": 9.352921259546293e-06, "loss": 3.0843, "step": 354000 }, { "epoch": 6.66, "learning_rate": 9.351980738121215e-06, "loss": 3.0869, "step": 354500 }, { "epoch": 6.67, "learning_rate": 9.351040216696138e-06, "loss": 3.0947, "step": 355000 }, { "epoch": 6.67, "step": 355366, "total_flos": 1.1417198304669204e+18, "train_loss": 3.9441763886343586, "train_runtime": 197998.8709, "train_samples_per_second": 2958.986, "train_steps_per_second": 26.9 } ], "logging_steps": 500, "max_steps": 5326200, "num_train_epochs": 100, "save_steps": 1000000, "total_flos": 1.1417198304669204e+18, "trial_name": null, "trial_params": null }