{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 136438, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 0.0001, "loss": 4.0519, "step": 500 }, { "epoch": 0.01, "learning_rate": 9.999946825617329e-05, "loss": 3.6979, "step": 1000 }, { "epoch": 0.02, "learning_rate": 9.99978730360032e-05, "loss": 3.5393, "step": 1500 }, { "epoch": 0.03, "learning_rate": 9.999521437341967e-05, "loss": 3.4397, "step": 2000 }, { "epoch": 0.04, "learning_rate": 9.999149232497183e-05, "loss": 3.4883, "step": 2500 }, { "epoch": 0.04, "learning_rate": 9.998670696982668e-05, "loss": 3.5107, "step": 3000 }, { "epoch": 0.05, "learning_rate": 9.998085840976759e-05, "loss": 3.4742, "step": 3500 }, { "epoch": 0.06, "learning_rate": 9.997394676919193e-05, "loss": 3.3594, "step": 4000 }, { "epoch": 0.07, "learning_rate": 9.996597219510866e-05, "loss": 3.3098, "step": 4500 }, { "epoch": 0.07, "learning_rate": 9.995693485713496e-05, "loss": 3.4248, "step": 5000 }, { "epoch": 0.08, "learning_rate": 9.994683494749277e-05, "loss": 3.3875, "step": 5500 }, { "epoch": 0.09, "learning_rate": 9.993567268100469e-05, "loss": 3.3726, "step": 6000 }, { "epoch": 0.1, "learning_rate": 9.992344829508938e-05, "loss": 3.3911, "step": 6500 }, { "epoch": 0.1, "learning_rate": 9.991016204975648e-05, "loss": 3.3826, "step": 7000 }, { "epoch": 0.11, "learning_rate": 9.989581422760117e-05, "loss": 3.3095, "step": 7500 }, { "epoch": 0.12, "learning_rate": 9.988040513379809e-05, "loss": 3.3544, "step": 8000 }, { "epoch": 0.12, "learning_rate": 9.986393509609485e-05, "loss": 3.3007, "step": 8500 }, { "epoch": 0.13, "learning_rate": 9.984640446480509e-05, "loss": 3.289, "step": 9000 }, { "epoch": 0.14, "learning_rate": 9.9827813612801e-05, "loss": 3.2892, "step": 9500 }, { "epoch": 0.15, "learning_rate": 9.98081629355054e-05, "loss": 3.3141, "step": 10000 }, { "epoch": 0.15, "learning_rate": 9.978745285088338e-05, "loss": 3.3381, "step": 10500 }, { "epoch": 0.16, "learning_rate": 9.97656837994333e-05, "loss": 3.2098, "step": 11000 }, { "epoch": 0.17, "learning_rate": 9.974285624417751e-05, "loss": 3.3139, "step": 11500 }, { "epoch": 0.18, "learning_rate": 9.971897067065248e-05, "loss": 3.2457, "step": 12000 }, { "epoch": 0.18, "learning_rate": 9.969402758689845e-05, "loss": 3.1359, "step": 12500 }, { "epoch": 0.19, "learning_rate": 9.966802752344868e-05, "loss": 3.2499, "step": 13000 }, { "epoch": 0.2, "learning_rate": 9.964097103331806e-05, "loss": 3.3144, "step": 13500 }, { "epoch": 0.21, "learning_rate": 9.961285869199149e-05, "loss": 3.3416, "step": 14000 }, { "epoch": 0.21, "learning_rate": 9.95836910974115e-05, "loss": 3.2466, "step": 14500 }, { "epoch": 0.22, "learning_rate": 9.955346886996564e-05, "loss": 3.2055, "step": 15000 }, { "epoch": 0.23, "learning_rate": 9.952219265247323e-05, "loss": 3.1853, "step": 15500 }, { "epoch": 0.23, "learning_rate": 9.948986311017168e-05, "loss": 3.261, "step": 16000 }, { "epoch": 0.24, "learning_rate": 9.945648093070237e-05, "loss": 3.1393, "step": 16500 }, { "epoch": 0.25, "learning_rate": 9.942204682409603e-05, "loss": 3.3337, "step": 17000 }, { "epoch": 0.26, "learning_rate": 9.938656152275759e-05, "loss": 3.1791, "step": 17500 }, { "epoch": 0.26, "learning_rate": 9.935002578145065e-05, "loss": 3.1644, "step": 18000 }, { "epoch": 0.27, "learning_rate": 9.931244037728141e-05, "loss": 3.2369, "step": 18500 }, { "epoch": 0.28, "learning_rate": 9.927380610968213e-05, "loss": 3.2139, "step": 19000 }, { "epoch": 0.29, "learning_rate": 9.923412380039415e-05, "loss": 3.1762, "step": 19500 }, { "epoch": 0.29, "learning_rate": 9.919339429345039e-05, "loss": 3.2732, "step": 20000 }, { "epoch": 0.3, "learning_rate": 9.915161845515739e-05, "loss": 3.197, "step": 20500 }, { "epoch": 0.31, "learning_rate": 9.910879717407693e-05, "loss": 3.1034, "step": 21000 }, { "epoch": 0.32, "learning_rate": 9.906493136100707e-05, "loss": 3.3108, "step": 21500 }, { "epoch": 0.32, "learning_rate": 9.902002194896285e-05, "loss": 3.1394, "step": 22000 }, { "epoch": 0.33, "learning_rate": 9.897406989315634e-05, "loss": 3.2385, "step": 22500 }, { "epoch": 0.34, "learning_rate": 9.892707617097645e-05, "loss": 3.1855, "step": 23000 }, { "epoch": 0.34, "learning_rate": 9.887904178196804e-05, "loss": 3.2088, "step": 23500 }, { "epoch": 0.35, "learning_rate": 9.882996774781066e-05, "loss": 3.2111, "step": 24000 }, { "epoch": 0.36, "learning_rate": 9.877985511229697e-05, "loss": 3.175, "step": 24500 }, { "epoch": 0.37, "learning_rate": 9.87287049413103e-05, "loss": 3.1891, "step": 25000 }, { "epoch": 0.37, "learning_rate": 9.867651832280217e-05, "loss": 3.182, "step": 25500 }, { "epoch": 0.38, "learning_rate": 9.86232963667691e-05, "loss": 3.3346, "step": 26000 }, { "epoch": 0.39, "learning_rate": 9.85690402052289e-05, "loss": 3.2496, "step": 26500 }, { "epoch": 0.4, "learning_rate": 9.851375099219677e-05, "loss": 3.222, "step": 27000 }, { "epoch": 0.4, "learning_rate": 9.845742990366059e-05, "loss": 3.2083, "step": 27500 }, { "epoch": 0.41, "learning_rate": 9.840007813755603e-05, "loss": 3.233, "step": 28000 }, { "epoch": 0.42, "learning_rate": 9.834169691374098e-05, "loss": 3.1732, "step": 28500 }, { "epoch": 0.43, "learning_rate": 9.828228747396964e-05, "loss": 3.1922, "step": 29000 }, { "epoch": 0.43, "learning_rate": 9.822185108186616e-05, "loss": 3.1923, "step": 29500 }, { "epoch": 0.44, "learning_rate": 9.816038902289763e-05, "loss": 3.2879, "step": 30000 }, { "epoch": 0.45, "learning_rate": 9.809790260434693e-05, "loss": 3.2816, "step": 30500 }, { "epoch": 0.45, "learning_rate": 9.803439315528469e-05, "loss": 3.2343, "step": 31000 }, { "epoch": 0.46, "learning_rate": 9.796986202654124e-05, "loss": 3.1372, "step": 31500 }, { "epoch": 0.47, "learning_rate": 9.790431059067775e-05, "loss": 3.2111, "step": 32000 }, { "epoch": 0.48, "learning_rate": 9.783774024195709e-05, "loss": 3.1488, "step": 32500 }, { "epoch": 0.48, "learning_rate": 9.77701523963141e-05, "loss": 3.1637, "step": 33000 }, { "epoch": 0.49, "learning_rate": 9.77015484913256e-05, "loss": 3.1593, "step": 33500 }, { "epoch": 0.5, "learning_rate": 9.763192998617969e-05, "loss": 3.1399, "step": 34000 }, { "epoch": 0.51, "learning_rate": 9.75612983616448e-05, "loss": 3.0628, "step": 34500 }, { "epoch": 0.51, "learning_rate": 9.748965512003812e-05, "loss": 3.2634, "step": 35000 }, { "epoch": 0.52, "learning_rate": 9.741700178519374e-05, "loss": 3.1562, "step": 35500 }, { "epoch": 0.53, "learning_rate": 9.734333990243012e-05, "loss": 3.2411, "step": 36000 }, { "epoch": 0.54, "learning_rate": 9.726867103851735e-05, "loss": 3.1336, "step": 36500 }, { "epoch": 0.54, "learning_rate": 9.719299678164369e-05, "loss": 3.1557, "step": 37000 }, { "epoch": 0.55, "learning_rate": 9.711631874138192e-05, "loss": 3.1368, "step": 37500 }, { "epoch": 0.56, "learning_rate": 9.703863854865502e-05, "loss": 3.1296, "step": 38000 }, { "epoch": 0.56, "learning_rate": 9.69599578557015e-05, "loss": 3.1308, "step": 38500 }, { "epoch": 0.57, "learning_rate": 9.688027833604027e-05, "loss": 3.1526, "step": 39000 }, { "epoch": 0.58, "learning_rate": 9.679960168443507e-05, "loss": 3.2699, "step": 39500 }, { "epoch": 0.59, "learning_rate": 9.671792961685831e-05, "loss": 3.0819, "step": 40000 }, { "epoch": 0.59, "learning_rate": 9.663526387045473e-05, "loss": 3.0947, "step": 40500 }, { "epoch": 0.6, "learning_rate": 9.655160620350434e-05, "loss": 3.1903, "step": 41000 }, { "epoch": 0.61, "learning_rate": 9.646695839538503e-05, "loss": 3.0587, "step": 41500 }, { "epoch": 0.62, "learning_rate": 9.638132224653482e-05, "loss": 3.1778, "step": 42000 }, { "epoch": 0.62, "learning_rate": 9.629469957841341e-05, "loss": 3.0616, "step": 42500 }, { "epoch": 0.63, "learning_rate": 9.62070922334636e-05, "loss": 3.1816, "step": 43000 }, { "epoch": 0.64, "learning_rate": 9.611850207507196e-05, "loss": 3.1625, "step": 43500 }, { "epoch": 0.64, "learning_rate": 9.602893098752929e-05, "loss": 3.2755, "step": 44000 }, { "epoch": 0.65, "learning_rate": 9.59383808759905e-05, "loss": 3.1046, "step": 44500 }, { "epoch": 0.66, "learning_rate": 9.584685366643411e-05, "loss": 3.176, "step": 45000 }, { "epoch": 0.67, "learning_rate": 9.575435130562125e-05, "loss": 3.1618, "step": 45500 }, { "epoch": 0.67, "learning_rate": 9.566087576105431e-05, "loss": 3.2012, "step": 46000 }, { "epoch": 0.68, "learning_rate": 9.556642902093503e-05, "loss": 3.2124, "step": 46500 }, { "epoch": 0.69, "learning_rate": 9.547101309412226e-05, "loss": 3.1282, "step": 47000 }, { "epoch": 0.7, "learning_rate": 9.53746300100892e-05, "loss": 3.1725, "step": 47500 }, { "epoch": 0.7, "learning_rate": 9.527728181888023e-05, "loss": 3.1428, "step": 48000 }, { "epoch": 0.71, "learning_rate": 9.517897059106737e-05, "loss": 3.1074, "step": 48500 }, { "epoch": 0.72, "learning_rate": 9.507969841770614e-05, "loss": 3.2534, "step": 49000 }, { "epoch": 0.73, "learning_rate": 9.497946741029116e-05, "loss": 3.1394, "step": 49500 }, { "epoch": 0.73, "learning_rate": 9.48782797007112e-05, "loss": 3.1688, "step": 50000 }, { "epoch": 0.74, "learning_rate": 9.477613744120386e-05, "loss": 3.2439, "step": 50500 }, { "epoch": 0.75, "learning_rate": 9.467304280430977e-05, "loss": 3.0768, "step": 51000 }, { "epoch": 0.75, "learning_rate": 9.456899798282642e-05, "loss": 3.082, "step": 51500 }, { "epoch": 0.76, "learning_rate": 9.446400518976144e-05, "loss": 3.1203, "step": 52000 }, { "epoch": 0.77, "learning_rate": 9.435806665828566e-05, "loss": 3.1243, "step": 52500 }, { "epoch": 0.78, "learning_rate": 9.425118464168545e-05, "loss": 3.1732, "step": 53000 }, { "epoch": 0.78, "learning_rate": 9.414336141331491e-05, "loss": 3.118, "step": 53500 }, { "epoch": 0.79, "learning_rate": 9.403459926654748e-05, "loss": 3.1597, "step": 54000 }, { "epoch": 0.8, "learning_rate": 9.392490051472718e-05, "loss": 3.1854, "step": 54500 }, { "epoch": 0.81, "learning_rate": 9.381426749111936e-05, "loss": 3.1857, "step": 55000 }, { "epoch": 0.81, "learning_rate": 9.370270254886115e-05, "loss": 3.1094, "step": 55500 }, { "epoch": 0.82, "learning_rate": 9.359020806091126e-05, "loss": 3.1459, "step": 56000 }, { "epoch": 0.83, "learning_rate": 9.347678641999973e-05, "loss": 3.063, "step": 56500 }, { "epoch": 0.84, "learning_rate": 9.336244003857682e-05, "loss": 3.0853, "step": 57000 }, { "epoch": 0.84, "learning_rate": 9.324717134876182e-05, "loss": 3.1004, "step": 57500 }, { "epoch": 0.85, "learning_rate": 9.313098280229133e-05, "loss": 3.0624, "step": 58000 }, { "epoch": 0.86, "learning_rate": 9.301387687046704e-05, "loss": 3.1182, "step": 58500 }, { "epoch": 0.86, "learning_rate": 9.289585604410317e-05, "loss": 3.0812, "step": 59000 }, { "epoch": 0.87, "learning_rate": 9.277692283347357e-05, "loss": 3.1594, "step": 59500 }, { "epoch": 0.88, "learning_rate": 9.265707976825829e-05, "loss": 3.0691, "step": 60000 }, { "epoch": 0.89, "learning_rate": 9.253632939748968e-05, "loss": 3.0989, "step": 60500 }, { "epoch": 0.89, "learning_rate": 9.241467428949837e-05, "loss": 3.1739, "step": 61000 }, { "epoch": 0.9, "learning_rate": 9.229211703185842e-05, "loss": 3.0593, "step": 61500 }, { "epoch": 0.91, "learning_rate": 9.216866023133246e-05, "loss": 3.0508, "step": 62000 }, { "epoch": 0.92, "learning_rate": 9.204430651381613e-05, "loss": 3.1162, "step": 62500 }, { "epoch": 0.92, "learning_rate": 9.191905852428232e-05, "loss": 3.1316, "step": 63000 }, { "epoch": 0.93, "learning_rate": 9.179291892672484e-05, "loss": 3.0565, "step": 63500 }, { "epoch": 0.94, "learning_rate": 9.166589040410175e-05, "loss": 3.1502, "step": 64000 }, { "epoch": 0.95, "learning_rate": 9.153797565827839e-05, "loss": 3.1613, "step": 64500 }, { "epoch": 0.95, "learning_rate": 9.140917740996979e-05, "loss": 2.9902, "step": 65000 }, { "epoch": 0.96, "learning_rate": 9.127949839868292e-05, "loss": 3.0026, "step": 65500 }, { "epoch": 0.97, "learning_rate": 9.114894138265832e-05, "loss": 3.1636, "step": 66000 }, { "epoch": 0.97, "learning_rate": 9.101750913881147e-05, "loss": 3.1233, "step": 66500 }, { "epoch": 0.98, "learning_rate": 9.088520446267374e-05, "loss": 3.0781, "step": 67000 }, { "epoch": 0.99, "learning_rate": 9.075203016833295e-05, "loss": 3.0872, "step": 67500 }, { "epoch": 1.0, "learning_rate": 9.061798908837341e-05, "loss": 3.1095, "step": 68000 }, { "epoch": 1.0, "eval_bleu": 1.0, "eval_brevity_penalty": 1.0, "eval_length_ratio": 1.0, "eval_loss": 2.9751689434051514, "eval_precisions": [ 1.0, 1.0, 1.0, 1.0 ], "eval_reference_length": 7761920, "eval_runtime": 15377.8782, "eval_samples_per_second": 0.986, "eval_steps_per_second": 0.493, "eval_translation_length": 7761920, "step": 68219 }, { "epoch": 1.0, "learning_rate": 9.048308407381583e-05, "loss": 2.9246, "step": 68500 }, { "epoch": 1.01, "learning_rate": 9.034731799405654e-05, "loss": 2.8047, "step": 69000 }, { "epoch": 1.02, "learning_rate": 9.021069373680653e-05, "loss": 2.8717, "step": 69500 }, { "epoch": 1.03, "learning_rate": 9.007321420803e-05, "loss": 2.8453, "step": 70000 }, { "epoch": 1.03, "learning_rate": 8.993488233188263e-05, "loss": 2.8545, "step": 70500 }, { "epoch": 1.04, "learning_rate": 8.979570105064923e-05, "loss": 2.7871, "step": 71000 }, { "epoch": 1.05, "learning_rate": 8.965567332468128e-05, "loss": 2.772, "step": 71500 }, { "epoch": 1.06, "learning_rate": 8.951480213233397e-05, "loss": 2.915, "step": 72000 }, { "epoch": 1.06, "learning_rate": 8.937309046990271e-05, "loss": 2.8076, "step": 72500 }, { "epoch": 1.07, "learning_rate": 8.923054135155963e-05, "loss": 2.693, "step": 73000 }, { "epoch": 1.08, "learning_rate": 8.908715780928925e-05, "loss": 2.8504, "step": 73500 }, { "epoch": 1.08, "learning_rate": 8.89429428928241e-05, "loss": 2.7593, "step": 74000 }, { "epoch": 1.09, "learning_rate": 8.879789966957988e-05, "loss": 2.7953, "step": 74500 }, { "epoch": 1.1, "learning_rate": 8.865203122459008e-05, "loss": 2.7169, "step": 75000 }, { "epoch": 1.11, "learning_rate": 8.850534066044054e-05, "loss": 2.6889, "step": 75500 }, { "epoch": 1.11, "learning_rate": 8.835783109720333e-05, "loss": 2.8703, "step": 76000 }, { "epoch": 1.12, "learning_rate": 8.820950567237043e-05, "loss": 2.8989, "step": 76500 }, { "epoch": 1.13, "learning_rate": 8.806036754078701e-05, "loss": 2.7834, "step": 77000 }, { "epoch": 1.14, "learning_rate": 8.791041987458431e-05, "loss": 2.84, "step": 77500 }, { "epoch": 1.14, "learning_rate": 8.775966586311212e-05, "loss": 2.6913, "step": 78000 }, { "epoch": 1.15, "learning_rate": 8.760810871287108e-05, "loss": 2.7712, "step": 78500 }, { "epoch": 1.16, "learning_rate": 8.745575164744435e-05, "loss": 2.8229, "step": 79000 }, { "epoch": 1.17, "learning_rate": 8.730259790742906e-05, "loss": 2.8877, "step": 79500 }, { "epoch": 1.17, "learning_rate": 8.714865075036746e-05, "loss": 2.7965, "step": 80000 }, { "epoch": 1.18, "learning_rate": 8.699391345067759e-05, "loss": 2.9252, "step": 80500 }, { "epoch": 1.19, "learning_rate": 8.683838929958356e-05, "loss": 2.8585, "step": 81000 }, { "epoch": 1.19, "learning_rate": 8.66820816050457e-05, "loss": 2.7542, "step": 81500 }, { "epoch": 1.2, "learning_rate": 8.652499369169005e-05, "loss": 2.8124, "step": 82000 }, { "epoch": 1.21, "learning_rate": 8.636712890073772e-05, "loss": 2.8251, "step": 82500 }, { "epoch": 1.22, "learning_rate": 8.62084905899339e-05, "loss": 2.7148, "step": 83000 }, { "epoch": 1.22, "learning_rate": 8.604908213347622e-05, "loss": 2.8276, "step": 83500 }, { "epoch": 1.23, "learning_rate": 8.58889069219432e-05, "loss": 2.8799, "step": 84000 }, { "epoch": 1.24, "learning_rate": 8.572796836222206e-05, "loss": 2.7959, "step": 84500 }, { "epoch": 1.25, "learning_rate": 8.556626987743621e-05, "loss": 2.756, "step": 85000 }, { "epoch": 1.25, "learning_rate": 8.54038149068725e-05, "loss": 2.8956, "step": 85500 }, { "epoch": 1.26, "learning_rate": 8.524060690590803e-05, "loss": 2.8619, "step": 86000 }, { "epoch": 1.27, "learning_rate": 8.507664934593668e-05, "loss": 2.8005, "step": 86500 }, { "epoch": 1.28, "learning_rate": 8.491194571429526e-05, "loss": 2.8213, "step": 87000 }, { "epoch": 1.28, "learning_rate": 8.474649951418936e-05, "loss": 2.8356, "step": 87500 }, { "epoch": 1.29, "learning_rate": 8.458031426461878e-05, "loss": 2.877, "step": 88000 }, { "epoch": 1.3, "learning_rate": 8.441339350030278e-05, "loss": 2.9189, "step": 88500 }, { "epoch": 1.3, "learning_rate": 8.424574077160476e-05, "loss": 2.8497, "step": 89000 }, { "epoch": 1.31, "learning_rate": 8.407735964445689e-05, "loss": 2.807, "step": 89500 }, { "epoch": 1.32, "learning_rate": 8.390825370028414e-05, "loss": 2.8745, "step": 90000 }, { "epoch": 1.33, "learning_rate": 8.373842653592818e-05, "loss": 2.8054, "step": 90500 }, { "epoch": 1.33, "learning_rate": 8.35678817635709e-05, "loss": 2.7019, "step": 91000 }, { "epoch": 1.34, "learning_rate": 8.339662301065747e-05, "loss": 2.8497, "step": 91500 }, { "epoch": 1.35, "learning_rate": 8.322465391981927e-05, "loss": 2.8442, "step": 92000 }, { "epoch": 1.36, "learning_rate": 8.30519781487964e-05, "loss": 2.7681, "step": 92500 }, { "epoch": 1.36, "learning_rate": 8.287859937035989e-05, "loss": 2.8219, "step": 93000 }, { "epoch": 1.37, "learning_rate": 8.270452127223352e-05, "loss": 2.8409, "step": 93500 }, { "epoch": 1.38, "learning_rate": 8.252974755701546e-05, "loss": 2.7358, "step": 94000 }, { "epoch": 1.39, "learning_rate": 8.235428194209947e-05, "loss": 2.6975, "step": 94500 }, { "epoch": 1.39, "learning_rate": 8.217812815959588e-05, "loss": 2.7972, "step": 95000 }, { "epoch": 1.4, "learning_rate": 8.200128995625211e-05, "loss": 2.8172, "step": 95500 }, { "epoch": 1.41, "learning_rate": 8.182377109337309e-05, "loss": 2.8309, "step": 96000 }, { "epoch": 1.41, "learning_rate": 8.164557534674122e-05, "loss": 2.9371, "step": 96500 }, { "epoch": 1.42, "learning_rate": 8.1466706506536e-05, "loss": 2.738, "step": 97000 }, { "epoch": 1.43, "learning_rate": 8.12871683772535e-05, "loss": 2.8989, "step": 97500 }, { "epoch": 1.44, "learning_rate": 8.110696477762538e-05, "loss": 2.7852, "step": 98000 }, { "epoch": 1.44, "learning_rate": 8.092609954053776e-05, "loss": 2.862, "step": 98500 }, { "epoch": 1.45, "learning_rate": 8.07445765129495e-05, "loss": 2.8234, "step": 99000 }, { "epoch": 1.46, "learning_rate": 8.056239955581064e-05, "loss": 2.844, "step": 99500 }, { "epoch": 1.47, "learning_rate": 8.037957254398004e-05, "loss": 2.7922, "step": 100000 }, { "epoch": 1.47, "learning_rate": 8.01960993661431e-05, "loss": 2.817, "step": 100500 }, { "epoch": 1.48, "learning_rate": 8.0011983924729e-05, "loss": 2.8955, "step": 101000 }, { "epoch": 1.49, "learning_rate": 7.982723013582772e-05, "loss": 2.8279, "step": 101500 }, { "epoch": 1.5, "learning_rate": 7.964184192910672e-05, "loss": 2.8259, "step": 102000 }, { "epoch": 1.5, "learning_rate": 7.94558232477274e-05, "loss": 2.9235, "step": 102500 }, { "epoch": 1.51, "learning_rate": 7.926917804826117e-05, "loss": 2.8261, "step": 103000 }, { "epoch": 1.52, "learning_rate": 7.908191030060532e-05, "loss": 2.7384, "step": 103500 }, { "epoch": 1.52, "learning_rate": 7.889402398789863e-05, "loss": 2.8064, "step": 104000 }, { "epoch": 1.53, "learning_rate": 7.870552310643656e-05, "loss": 2.8212, "step": 104500 }, { "epoch": 1.54, "learning_rate": 7.851641166558628e-05, "loss": 2.8605, "step": 105000 }, { "epoch": 1.55, "learning_rate": 7.832669368770149e-05, "loss": 2.7907, "step": 105500 }, { "epoch": 1.55, "learning_rate": 7.813637320803671e-05, "loss": 2.7278, "step": 106000 }, { "epoch": 1.56, "learning_rate": 7.794545427466153e-05, "loss": 2.7808, "step": 106500 }, { "epoch": 1.57, "learning_rate": 7.775394094837455e-05, "loss": 2.8643, "step": 107000 }, { "epoch": 1.58, "learning_rate": 7.756183730261694e-05, "loss": 2.738, "step": 107500 }, { "epoch": 1.58, "learning_rate": 7.736914742338577e-05, "loss": 2.7307, "step": 108000 }, { "epoch": 1.59, "learning_rate": 7.71758754091472e-05, "loss": 2.8986, "step": 108500 }, { "epoch": 1.6, "learning_rate": 7.698202537074926e-05, "loss": 2.7493, "step": 109000 }, { "epoch": 1.61, "learning_rate": 7.678760143133436e-05, "loss": 2.8837, "step": 109500 }, { "epoch": 1.61, "learning_rate": 7.659260772625176e-05, "loss": 2.778, "step": 110000 }, { "epoch": 1.62, "learning_rate": 7.639704840296936e-05, "loss": 2.8215, "step": 110500 }, { "epoch": 1.63, "learning_rate": 7.620092762098568e-05, "loss": 2.8389, "step": 111000 }, { "epoch": 1.63, "learning_rate": 7.600424955174132e-05, "loss": 2.8627, "step": 111500 }, { "epoch": 1.64, "learning_rate": 7.580701837853028e-05, "loss": 2.8321, "step": 112000 }, { "epoch": 1.65, "learning_rate": 7.560923829641088e-05, "loss": 2.9496, "step": 112500 }, { "epoch": 1.66, "learning_rate": 7.541091351211666e-05, "loss": 2.8576, "step": 113000 }, { "epoch": 1.66, "learning_rate": 7.521204824396678e-05, "loss": 2.7548, "step": 113500 }, { "epoch": 1.67, "learning_rate": 7.501264672177637e-05, "loss": 2.7738, "step": 114000 }, { "epoch": 1.68, "learning_rate": 7.481271318676662e-05, "loss": 2.8088, "step": 114500 }, { "epoch": 1.69, "learning_rate": 7.46122518914744e-05, "loss": 2.8243, "step": 115000 }, { "epoch": 1.69, "learning_rate": 7.441126709966203e-05, "loss": 2.6794, "step": 115500 }, { "epoch": 1.7, "learning_rate": 7.420976308622632e-05, "loss": 2.8277, "step": 116000 }, { "epoch": 1.71, "learning_rate": 7.400774413710793e-05, "loss": 2.8341, "step": 116500 }, { "epoch": 1.72, "learning_rate": 7.380521454920001e-05, "loss": 2.8003, "step": 117000 }, { "epoch": 1.72, "learning_rate": 7.360217863025687e-05, "loss": 2.724, "step": 117500 }, { "epoch": 1.73, "learning_rate": 7.33986406988024e-05, "loss": 2.829, "step": 118000 }, { "epoch": 1.74, "learning_rate": 7.319460508403811e-05, "loss": 2.812, "step": 118500 }, { "epoch": 1.74, "learning_rate": 7.299007612575117e-05, "loss": 2.8172, "step": 119000 }, { "epoch": 1.75, "learning_rate": 7.278505817422199e-05, "loss": 2.8063, "step": 119500 }, { "epoch": 1.76, "learning_rate": 7.257955559013181e-05, "loss": 2.8775, "step": 120000 }, { "epoch": 1.77, "learning_rate": 7.23735727444698e-05, "loss": 2.7225, "step": 120500 }, { "epoch": 1.77, "learning_rate": 7.216711401844028e-05, "loss": 2.7283, "step": 121000 }, { "epoch": 1.78, "learning_rate": 7.196018380336934e-05, "loss": 2.8786, "step": 121500 }, { "epoch": 1.79, "learning_rate": 7.175278650061156e-05, "loss": 2.7372, "step": 122000 }, { "epoch": 1.8, "learning_rate": 7.154492652145635e-05, "loss": 2.7176, "step": 122500 }, { "epoch": 1.8, "learning_rate": 7.133660828703414e-05, "loss": 2.8233, "step": 123000 }, { "epoch": 1.81, "learning_rate": 7.112783622822235e-05, "loss": 2.8269, "step": 123500 }, { "epoch": 1.82, "learning_rate": 7.091861478555114e-05, "loss": 2.8155, "step": 124000 }, { "epoch": 1.83, "learning_rate": 7.070894840910887e-05, "loss": 2.7793, "step": 124500 }, { "epoch": 1.83, "learning_rate": 7.049884155844762e-05, "loss": 2.8524, "step": 125000 }, { "epoch": 1.84, "learning_rate": 7.028829870248824e-05, "loss": 2.8373, "step": 125500 }, { "epoch": 1.85, "learning_rate": 7.007732431942529e-05, "loss": 2.8219, "step": 126000 }, { "epoch": 1.85, "learning_rate": 6.986592289663177e-05, "loss": 2.6958, "step": 126500 }, { "epoch": 1.86, "learning_rate": 6.965409893056375e-05, "loss": 2.8492, "step": 127000 }, { "epoch": 1.87, "learning_rate": 6.944185692666472e-05, "loss": 2.8947, "step": 127500 }, { "epoch": 1.88, "learning_rate": 6.922920139926964e-05, "loss": 2.8311, "step": 128000 }, { "epoch": 1.88, "learning_rate": 6.90161368715091e-05, "loss": 2.8389, "step": 128500 }, { "epoch": 1.89, "learning_rate": 6.880266787521298e-05, "loss": 2.7657, "step": 129000 }, { "epoch": 1.9, "learning_rate": 6.858879895081412e-05, "loss": 2.8388, "step": 129500 }, { "epoch": 1.91, "learning_rate": 6.837453464725174e-05, "loss": 2.8377, "step": 130000 }, { "epoch": 1.91, "learning_rate": 6.815987952187466e-05, "loss": 2.8376, "step": 130500 }, { "epoch": 1.92, "learning_rate": 6.794483814034439e-05, "loss": 2.7048, "step": 131000 }, { "epoch": 1.93, "learning_rate": 6.772941507653803e-05, "loss": 2.9014, "step": 131500 }, { "epoch": 1.93, "learning_rate": 6.751361491245093e-05, "loss": 2.7394, "step": 132000 }, { "epoch": 1.94, "learning_rate": 6.729744223809929e-05, "loss": 2.7723, "step": 132500 }, { "epoch": 1.95, "learning_rate": 6.708090165142255e-05, "loss": 2.8502, "step": 133000 }, { "epoch": 1.96, "learning_rate": 6.686399775818548e-05, "loss": 2.7521, "step": 133500 }, { "epoch": 1.96, "learning_rate": 6.664673517188036e-05, "loss": 2.8726, "step": 134000 }, { "epoch": 1.97, "learning_rate": 6.642911851362873e-05, "loss": 2.9264, "step": 134500 }, { "epoch": 1.98, "learning_rate": 6.621115241208316e-05, "loss": 2.8401, "step": 135000 }, { "epoch": 1.99, "learning_rate": 6.599284150332885e-05, "loss": 2.8706, "step": 135500 }, { "epoch": 1.99, "learning_rate": 6.57741904307849e-05, "loss": 2.886, "step": 136000 }, { "epoch": 2.0, "eval_bleu": 1.0, "eval_brevity_penalty": 1.0, "eval_length_ratio": 1.0, "eval_loss": 2.8930435180664062, "eval_precisions": [ 1.0, 1.0, 1.0, 1.0 ], "eval_reference_length": 7761920, "eval_runtime": 15438.142, "eval_samples_per_second": 0.982, "eval_steps_per_second": 0.491, "eval_translation_length": 7761920, "step": 136438 } ], "logging_steps": 500, "max_steps": 341095, "num_train_epochs": 5, "save_steps": 500, "total_flos": 6.289158593555988e+17, "trial_name": null, "trial_params": null }