diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,6100 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 13.829673930853678, + "eval_steps": 1000000, + "global_step": 506415, + "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": 10.3308, + "step": 500 + }, + { + "epoch": 0.03, + "learning_rate": 1.0000000000000002e-06, + "loss": 10.2468, + "step": 1000 + }, + { + "epoch": 0.04, + "learning_rate": 1.5e-06, + "loss": 10.1174, + "step": 1500 + }, + { + "epoch": 0.05, + "learning_rate": 2.0000000000000003e-06, + "loss": 9.9735, + "step": 2000 + }, + { + "epoch": 0.07, + "learning_rate": 2.5e-06, + "loss": 9.8081, + "step": 2500 + }, + { + "epoch": 0.08, + "learning_rate": 3e-06, + "loss": 9.6184, + "step": 3000 + }, + { + "epoch": 0.1, + "learning_rate": 3.5e-06, + "loss": 9.4049, + "step": 3500 + }, + { + "epoch": 0.11, + "learning_rate": 4.000000000000001e-06, + "loss": 9.1719, + "step": 4000 + }, + { + "epoch": 0.12, + "learning_rate": 4.5e-06, + "loss": 8.9239, + "step": 4500 + }, + { + "epoch": 0.14, + "learning_rate": 5e-06, + "loss": 8.6709, + "step": 5000 + }, + { + "epoch": 0.15, + "learning_rate": 5.500000000000001e-06, + "loss": 8.4179, + "step": 5500 + }, + { + "epoch": 0.16, + "learning_rate": 6e-06, + "loss": 8.1713, + "step": 6000 + }, + { + "epoch": 0.18, + "learning_rate": 6.5000000000000004e-06, + "loss": 7.9377, + "step": 6500 + }, + { + "epoch": 0.19, + "learning_rate": 7e-06, + "loss": 7.7264, + "step": 7000 + }, + { + "epoch": 0.2, + "learning_rate": 7.500000000000001e-06, + "loss": 7.543, + "step": 7500 + }, + { + "epoch": 0.22, + "learning_rate": 8.000000000000001e-06, + "loss": 7.3973, + "step": 8000 + }, + { + "epoch": 0.23, + "learning_rate": 8.5e-06, + "loss": 7.2861, + "step": 8500 + }, + { + "epoch": 0.25, + "learning_rate": 9e-06, + "loss": 7.2079, + "step": 9000 + }, + { + "epoch": 0.26, + "learning_rate": 9.5e-06, + "loss": 7.1453, + "step": 9500 + }, + { + "epoch": 0.27, + "learning_rate": 1e-05, + "loss": 7.0956, + "step": 10000 + }, + { + "epoch": 0.29, + "learning_rate": 9.998630812202202e-06, + "loss": 7.0474, + "step": 10500 + }, + { + "epoch": 0.3, + "learning_rate": 9.997261624404405e-06, + "loss": 7.0121, + "step": 11000 + }, + { + "epoch": 0.31, + "learning_rate": 9.995892436606606e-06, + "loss": 6.9804, + "step": 11500 + }, + { + "epoch": 0.33, + "learning_rate": 9.994523248808807e-06, + "loss": 6.95, + "step": 12000 + }, + { + "epoch": 0.34, + "learning_rate": 9.99315406101101e-06, + "loss": 6.926, + "step": 12500 + }, + { + "epoch": 0.36, + "learning_rate": 9.99178487321321e-06, + "loss": 6.9014, + "step": 13000 + }, + { + "epoch": 0.37, + "learning_rate": 9.990415685415411e-06, + "loss": 6.8773, + "step": 13500 + }, + { + "epoch": 0.38, + "learning_rate": 9.989046497617614e-06, + "loss": 6.851, + "step": 14000 + }, + { + "epoch": 0.4, + "learning_rate": 9.987677309819815e-06, + "loss": 6.8385, + "step": 14500 + }, + { + "epoch": 0.41, + "learning_rate": 9.986308122022018e-06, + "loss": 6.8165, + "step": 15000 + }, + { + "epoch": 0.42, + "learning_rate": 9.984938934224219e-06, + "loss": 6.7988, + "step": 15500 + }, + { + "epoch": 0.44, + "learning_rate": 9.98356974642642e-06, + "loss": 6.7783, + "step": 16000 + }, + { + "epoch": 0.45, + "learning_rate": 9.982200558628623e-06, + "loss": 6.7633, + "step": 16500 + }, + { + "epoch": 0.46, + "learning_rate": 9.980831370830824e-06, + "loss": 6.751, + "step": 17000 + }, + { + "epoch": 0.48, + "learning_rate": 9.979462183033025e-06, + "loss": 6.7342, + "step": 17500 + }, + { + "epoch": 0.49, + "learning_rate": 9.978092995235227e-06, + "loss": 6.7283, + "step": 18000 + }, + { + "epoch": 0.51, + "learning_rate": 9.976723807437428e-06, + "loss": 6.7134, + "step": 18500 + }, + { + "epoch": 0.52, + "learning_rate": 9.97535461963963e-06, + "loss": 6.7024, + "step": 19000 + }, + { + "epoch": 0.53, + "learning_rate": 9.973985431841832e-06, + "loss": 6.6863, + "step": 19500 + }, + { + "epoch": 0.55, + "learning_rate": 9.972616244044035e-06, + "loss": 6.6861, + "step": 20000 + }, + { + "epoch": 0.56, + "learning_rate": 9.971247056246236e-06, + "loss": 6.6668, + "step": 20500 + }, + { + "epoch": 0.57, + "learning_rate": 9.969877868448437e-06, + "loss": 6.6587, + "step": 21000 + }, + { + "epoch": 0.59, + "learning_rate": 9.96850868065064e-06, + "loss": 6.6528, + "step": 21500 + }, + { + "epoch": 0.6, + "learning_rate": 9.96713949285284e-06, + "loss": 6.6447, + "step": 22000 + }, + { + "epoch": 0.61, + "learning_rate": 9.965770305055043e-06, + "loss": 6.634, + "step": 22500 + }, + { + "epoch": 0.63, + "learning_rate": 9.964401117257244e-06, + "loss": 6.6248, + "step": 23000 + }, + { + "epoch": 0.64, + "learning_rate": 9.963031929459445e-06, + "loss": 6.6168, + "step": 23500 + }, + { + "epoch": 0.66, + "learning_rate": 9.961662741661648e-06, + "loss": 6.6132, + "step": 24000 + }, + { + "epoch": 0.67, + "learning_rate": 9.960293553863849e-06, + "loss": 6.601, + "step": 24500 + }, + { + "epoch": 0.68, + "learning_rate": 9.95892436606605e-06, + "loss": 6.5959, + "step": 25000 + }, + { + "epoch": 0.7, + "learning_rate": 9.957555178268253e-06, + "loss": 6.5834, + "step": 25500 + }, + { + "epoch": 0.71, + "learning_rate": 9.956185990470454e-06, + "loss": 6.5773, + "step": 26000 + }, + { + "epoch": 0.72, + "learning_rate": 9.954816802672655e-06, + "loss": 6.5728, + "step": 26500 + }, + { + "epoch": 0.74, + "learning_rate": 9.953447614874858e-06, + "loss": 6.5663, + "step": 27000 + }, + { + "epoch": 0.75, + "learning_rate": 9.952078427077059e-06, + "loss": 6.5606, + "step": 27500 + }, + { + "epoch": 0.76, + "learning_rate": 9.95070923927926e-06, + "loss": 6.5534, + "step": 28000 + }, + { + "epoch": 0.78, + "learning_rate": 9.949340051481462e-06, + "loss": 6.5456, + "step": 28500 + }, + { + "epoch": 0.79, + "learning_rate": 9.947970863683663e-06, + "loss": 6.5405, + "step": 29000 + }, + { + "epoch": 0.81, + "learning_rate": 9.946601675885866e-06, + "loss": 6.534, + "step": 29500 + }, + { + "epoch": 0.82, + "learning_rate": 9.945232488088067e-06, + "loss": 6.5306, + "step": 30000 + }, + { + "epoch": 0.83, + "learning_rate": 9.943863300290268e-06, + "loss": 6.5216, + "step": 30500 + }, + { + "epoch": 0.85, + "learning_rate": 9.94249411249247e-06, + "loss": 6.519, + "step": 31000 + }, + { + "epoch": 0.86, + "learning_rate": 9.941124924694672e-06, + "loss": 6.514, + "step": 31500 + }, + { + "epoch": 0.87, + "learning_rate": 9.939755736896873e-06, + "loss": 6.5081, + "step": 32000 + }, + { + "epoch": 0.89, + "learning_rate": 9.938386549099076e-06, + "loss": 6.5064, + "step": 32500 + }, + { + "epoch": 0.9, + "learning_rate": 9.937017361301277e-06, + "loss": 6.4997, + "step": 33000 + }, + { + "epoch": 0.91, + "learning_rate": 9.935648173503478e-06, + "loss": 6.4959, + "step": 33500 + }, + { + "epoch": 0.93, + "learning_rate": 9.93427898570568e-06, + "loss": 6.495, + "step": 34000 + }, + { + "epoch": 0.94, + "learning_rate": 9.932909797907881e-06, + "loss": 6.4894, + "step": 34500 + }, + { + "epoch": 0.96, + "learning_rate": 9.931540610110082e-06, + "loss": 6.4867, + "step": 35000 + }, + { + "epoch": 0.97, + "learning_rate": 9.930171422312285e-06, + "loss": 6.4781, + "step": 35500 + }, + { + "epoch": 0.98, + "learning_rate": 9.928802234514486e-06, + "loss": 6.4766, + "step": 36000 + }, + { + "epoch": 1.0, + "learning_rate": 9.927433046716687e-06, + "loss": 6.4698, + "step": 36500 + }, + { + "epoch": 1.01, + "learning_rate": 9.92606385891889e-06, + "loss": 6.4646, + "step": 37000 + }, + { + "epoch": 1.02, + "learning_rate": 9.924694671121093e-06, + "loss": 6.4636, + "step": 37500 + }, + { + "epoch": 1.04, + "learning_rate": 9.923325483323294e-06, + "loss": 6.4587, + "step": 38000 + }, + { + "epoch": 1.05, + "learning_rate": 9.921956295525496e-06, + "loss": 6.4486, + "step": 38500 + }, + { + "epoch": 1.07, + "learning_rate": 9.920587107727697e-06, + "loss": 6.4511, + "step": 39000 + }, + { + "epoch": 1.08, + "learning_rate": 9.919217919929898e-06, + "loss": 6.4479, + "step": 39500 + }, + { + "epoch": 1.09, + "learning_rate": 9.917848732132101e-06, + "loss": 6.4433, + "step": 40000 + }, + { + "epoch": 1.11, + "learning_rate": 9.916479544334302e-06, + "loss": 6.4364, + "step": 40500 + }, + { + "epoch": 1.12, + "learning_rate": 9.915110356536503e-06, + "loss": 6.4348, + "step": 41000 + }, + { + "epoch": 1.13, + "learning_rate": 9.913741168738706e-06, + "loss": 6.4298, + "step": 41500 + }, + { + "epoch": 1.15, + "learning_rate": 9.912371980940907e-06, + "loss": 6.432, + "step": 42000 + }, + { + "epoch": 1.16, + "learning_rate": 9.911002793143108e-06, + "loss": 6.4239, + "step": 42500 + }, + { + "epoch": 1.17, + "learning_rate": 9.90963360534531e-06, + "loss": 6.4205, + "step": 43000 + }, + { + "epoch": 1.19, + "learning_rate": 9.908264417547512e-06, + "loss": 6.4152, + "step": 43500 + }, + { + "epoch": 1.2, + "learning_rate": 9.906895229749713e-06, + "loss": 6.4114, + "step": 44000 + }, + { + "epoch": 1.22, + "learning_rate": 9.905526041951915e-06, + "loss": 6.4073, + "step": 44500 + }, + { + "epoch": 1.23, + "learning_rate": 9.904156854154116e-06, + "loss": 6.4059, + "step": 45000 + }, + { + "epoch": 1.24, + "learning_rate": 9.902787666356319e-06, + "loss": 6.4027, + "step": 45500 + }, + { + "epoch": 1.26, + "learning_rate": 9.90141847855852e-06, + "loss": 6.399, + "step": 46000 + }, + { + "epoch": 1.27, + "learning_rate": 9.900049290760721e-06, + "loss": 6.4022, + "step": 46500 + }, + { + "epoch": 1.28, + "learning_rate": 9.898680102962924e-06, + "loss": 6.3971, + "step": 47000 + }, + { + "epoch": 1.3, + "learning_rate": 9.897310915165125e-06, + "loss": 6.3949, + "step": 47500 + }, + { + "epoch": 1.31, + "learning_rate": 9.895941727367326e-06, + "loss": 6.3918, + "step": 48000 + }, + { + "epoch": 1.32, + "learning_rate": 9.894572539569529e-06, + "loss": 6.3864, + "step": 48500 + }, + { + "epoch": 1.34, + "learning_rate": 9.89320335177173e-06, + "loss": 6.3829, + "step": 49000 + }, + { + "epoch": 1.35, + "learning_rate": 9.89183416397393e-06, + "loss": 6.3804, + "step": 49500 + }, + { + "epoch": 1.37, + "learning_rate": 9.890464976176133e-06, + "loss": 6.3751, + "step": 50000 + }, + { + "epoch": 1.38, + "learning_rate": 9.889095788378334e-06, + "loss": 6.3749, + "step": 50500 + }, + { + "epoch": 1.39, + "learning_rate": 9.887726600580535e-06, + "loss": 6.3716, + "step": 51000 + }, + { + "epoch": 1.41, + "learning_rate": 9.886357412782738e-06, + "loss": 6.3732, + "step": 51500 + }, + { + "epoch": 1.42, + "learning_rate": 9.884988224984939e-06, + "loss": 6.3658, + "step": 52000 + }, + { + "epoch": 1.43, + "learning_rate": 9.883619037187142e-06, + "loss": 6.3639, + "step": 52500 + }, + { + "epoch": 1.45, + "learning_rate": 9.882249849389343e-06, + "loss": 6.3654, + "step": 53000 + }, + { + "epoch": 1.46, + "learning_rate": 9.880880661591544e-06, + "loss": 6.3605, + "step": 53500 + }, + { + "epoch": 1.47, + "learning_rate": 9.879511473793747e-06, + "loss": 6.3569, + "step": 54000 + }, + { + "epoch": 1.49, + "learning_rate": 9.878142285995948e-06, + "loss": 6.3557, + "step": 54500 + }, + { + "epoch": 1.5, + "learning_rate": 9.876773098198149e-06, + "loss": 6.348, + "step": 55000 + }, + { + "epoch": 1.52, + "learning_rate": 9.875403910400351e-06, + "loss": 6.3483, + "step": 55500 + }, + { + "epoch": 1.53, + "learning_rate": 9.874034722602554e-06, + "loss": 6.3458, + "step": 56000 + }, + { + "epoch": 1.54, + "learning_rate": 9.872665534804755e-06, + "loss": 6.3488, + "step": 56500 + }, + { + "epoch": 1.56, + "learning_rate": 9.871296347006956e-06, + "loss": 6.3471, + "step": 57000 + }, + { + "epoch": 1.57, + "learning_rate": 9.869927159209159e-06, + "loss": 6.3386, + "step": 57500 + }, + { + "epoch": 1.58, + "learning_rate": 9.86855797141136e-06, + "loss": 6.3395, + "step": 58000 + }, + { + "epoch": 1.6, + "learning_rate": 9.86718878361356e-06, + "loss": 6.343, + "step": 58500 + }, + { + "epoch": 1.61, + "learning_rate": 9.865819595815764e-06, + "loss": 6.3363, + "step": 59000 + }, + { + "epoch": 1.62, + "learning_rate": 9.864450408017965e-06, + "loss": 6.3342, + "step": 59500 + }, + { + "epoch": 1.64, + "learning_rate": 9.863081220220167e-06, + "loss": 6.333, + "step": 60000 + }, + { + "epoch": 1.65, + "learning_rate": 9.861712032422368e-06, + "loss": 6.3309, + "step": 60500 + }, + { + "epoch": 1.67, + "learning_rate": 9.86034284462457e-06, + "loss": 6.3287, + "step": 61000 + }, + { + "epoch": 1.68, + "learning_rate": 9.858973656826772e-06, + "loss": 6.3258, + "step": 61500 + }, + { + "epoch": 1.69, + "learning_rate": 9.857604469028973e-06, + "loss": 6.3227, + "step": 62000 + }, + { + "epoch": 1.71, + "learning_rate": 9.856235281231174e-06, + "loss": 6.3229, + "step": 62500 + }, + { + "epoch": 1.72, + "learning_rate": 9.854866093433377e-06, + "loss": 6.321, + "step": 63000 + }, + { + "epoch": 1.73, + "learning_rate": 9.853496905635578e-06, + "loss": 6.3197, + "step": 63500 + }, + { + "epoch": 1.75, + "learning_rate": 9.852127717837779e-06, + "loss": 6.3159, + "step": 64000 + }, + { + "epoch": 1.76, + "learning_rate": 9.850758530039982e-06, + "loss": 6.3126, + "step": 64500 + }, + { + "epoch": 1.78, + "learning_rate": 9.849389342242183e-06, + "loss": 6.3137, + "step": 65000 + }, + { + "epoch": 1.79, + "learning_rate": 9.848020154444384e-06, + "loss": 6.3083, + "step": 65500 + }, + { + "epoch": 1.8, + "learning_rate": 9.846650966646586e-06, + "loss": 6.3048, + "step": 66000 + }, + { + "epoch": 1.82, + "learning_rate": 9.845281778848787e-06, + "loss": 6.3111, + "step": 66500 + }, + { + "epoch": 1.83, + "learning_rate": 9.843912591050988e-06, + "loss": 6.3045, + "step": 67000 + }, + { + "epoch": 1.84, + "learning_rate": 9.842543403253191e-06, + "loss": 6.3045, + "step": 67500 + }, + { + "epoch": 1.86, + "learning_rate": 9.841174215455392e-06, + "loss": 6.3005, + "step": 68000 + }, + { + "epoch": 1.87, + "learning_rate": 9.839805027657595e-06, + "loss": 6.3065, + "step": 68500 + }, + { + "epoch": 1.88, + "learning_rate": 9.838435839859796e-06, + "loss": 6.3017, + "step": 69000 + }, + { + "epoch": 1.9, + "learning_rate": 9.837066652061997e-06, + "loss": 6.2972, + "step": 69500 + }, + { + "epoch": 1.91, + "learning_rate": 9.8356974642642e-06, + "loss": 6.2941, + "step": 70000 + }, + { + "epoch": 1.93, + "learning_rate": 9.8343282764664e-06, + "loss": 6.2912, + "step": 70500 + }, + { + "epoch": 1.94, + "learning_rate": 9.832959088668602e-06, + "loss": 6.2934, + "step": 71000 + }, + { + "epoch": 1.95, + "learning_rate": 9.831589900870804e-06, + "loss": 6.2911, + "step": 71500 + }, + { + "epoch": 1.97, + "learning_rate": 9.830220713073005e-06, + "loss": 6.2889, + "step": 72000 + }, + { + "epoch": 1.98, + "learning_rate": 9.828851525275206e-06, + "loss": 6.2885, + "step": 72500 + }, + { + "epoch": 1.99, + "learning_rate": 9.827482337477409e-06, + "loss": 6.285, + "step": 73000 + }, + { + "epoch": 2.01, + "learning_rate": 9.826113149679612e-06, + "loss": 6.2858, + "step": 73500 + }, + { + "epoch": 2.02, + "learning_rate": 9.824743961881813e-06, + "loss": 6.2816, + "step": 74000 + }, + { + "epoch": 2.03, + "learning_rate": 9.823374774084014e-06, + "loss": 6.2823, + "step": 74500 + }, + { + "epoch": 2.05, + "learning_rate": 9.822005586286217e-06, + "loss": 6.2814, + "step": 75000 + }, + { + "epoch": 2.06, + "learning_rate": 9.820636398488418e-06, + "loss": 6.2758, + "step": 75500 + }, + { + "epoch": 2.08, + "learning_rate": 9.81926721069062e-06, + "loss": 6.2789, + "step": 76000 + }, + { + "epoch": 2.09, + "learning_rate": 9.817898022892821e-06, + "loss": 6.2787, + "step": 76500 + }, + { + "epoch": 2.1, + "learning_rate": 9.816528835095022e-06, + "loss": 6.2748, + "step": 77000 + }, + { + "epoch": 2.12, + "learning_rate": 9.815159647297225e-06, + "loss": 6.2755, + "step": 77500 + }, + { + "epoch": 2.13, + "learning_rate": 9.813790459499426e-06, + "loss": 6.2698, + "step": 78000 + }, + { + "epoch": 2.14, + "learning_rate": 9.812421271701627e-06, + "loss": 6.2702, + "step": 78500 + }, + { + "epoch": 2.16, + "learning_rate": 9.81105208390383e-06, + "loss": 6.2684, + "step": 79000 + }, + { + "epoch": 2.17, + "learning_rate": 9.80968289610603e-06, + "loss": 6.2721, + "step": 79500 + }, + { + "epoch": 2.18, + "learning_rate": 9.808313708308232e-06, + "loss": 6.2685, + "step": 80000 + }, + { + "epoch": 2.2, + "learning_rate": 9.806944520510435e-06, + "loss": 6.2686, + "step": 80500 + }, + { + "epoch": 2.21, + "learning_rate": 9.805575332712636e-06, + "loss": 6.2657, + "step": 81000 + }, + { + "epoch": 2.23, + "learning_rate": 9.804206144914837e-06, + "loss": 6.2655, + "step": 81500 + }, + { + "epoch": 2.24, + "learning_rate": 9.80283695711704e-06, + "loss": 6.2645, + "step": 82000 + }, + { + "epoch": 2.25, + "learning_rate": 9.80146776931924e-06, + "loss": 6.2569, + "step": 82500 + }, + { + "epoch": 2.27, + "learning_rate": 9.800098581521443e-06, + "loss": 6.2592, + "step": 83000 + }, + { + "epoch": 2.28, + "learning_rate": 9.798729393723644e-06, + "loss": 6.2607, + "step": 83500 + }, + { + "epoch": 2.29, + "learning_rate": 9.797360205925845e-06, + "loss": 6.2576, + "step": 84000 + }, + { + "epoch": 2.31, + "learning_rate": 9.795991018128048e-06, + "loss": 6.2586, + "step": 84500 + }, + { + "epoch": 2.32, + "learning_rate": 9.794621830330249e-06, + "loss": 6.2562, + "step": 85000 + }, + { + "epoch": 2.33, + "learning_rate": 9.79325264253245e-06, + "loss": 6.2542, + "step": 85500 + }, + { + "epoch": 2.35, + "learning_rate": 9.791883454734653e-06, + "loss": 6.2586, + "step": 86000 + }, + { + "epoch": 2.36, + "learning_rate": 9.790514266936854e-06, + "loss": 6.2499, + "step": 86500 + }, + { + "epoch": 2.38, + "learning_rate": 9.789145079139055e-06, + "loss": 6.2509, + "step": 87000 + }, + { + "epoch": 2.39, + "learning_rate": 9.787775891341257e-06, + "loss": 6.2495, + "step": 87500 + }, + { + "epoch": 2.4, + "learning_rate": 9.786406703543458e-06, + "loss": 6.2479, + "step": 88000 + }, + { + "epoch": 2.42, + "learning_rate": 9.78503751574566e-06, + "loss": 6.2496, + "step": 88500 + }, + { + "epoch": 2.43, + "learning_rate": 9.783668327947862e-06, + "loss": 6.2444, + "step": 89000 + }, + { + "epoch": 2.44, + "learning_rate": 9.782299140150063e-06, + "loss": 6.245, + "step": 89500 + }, + { + "epoch": 2.46, + "learning_rate": 9.780929952352264e-06, + "loss": 6.2455, + "step": 90000 + }, + { + "epoch": 2.47, + "learning_rate": 9.779560764554467e-06, + "loss": 6.241, + "step": 90500 + }, + { + "epoch": 2.49, + "learning_rate": 9.778191576756668e-06, + "loss": 6.2447, + "step": 91000 + }, + { + "epoch": 2.5, + "learning_rate": 9.77682238895887e-06, + "loss": 6.2416, + "step": 91500 + }, + { + "epoch": 2.51, + "learning_rate": 9.775453201161073e-06, + "loss": 6.2415, + "step": 92000 + }, + { + "epoch": 2.53, + "learning_rate": 9.774084013363274e-06, + "loss": 6.2354, + "step": 92500 + }, + { + "epoch": 2.54, + "learning_rate": 9.772714825565475e-06, + "loss": 6.2402, + "step": 93000 + }, + { + "epoch": 2.55, + "learning_rate": 9.771345637767678e-06, + "loss": 6.2338, + "step": 93500 + }, + { + "epoch": 2.57, + "learning_rate": 9.769976449969879e-06, + "loss": 6.2352, + "step": 94000 + }, + { + "epoch": 2.58, + "learning_rate": 9.76860726217208e-06, + "loss": 6.2351, + "step": 94500 + }, + { + "epoch": 2.59, + "learning_rate": 9.767238074374283e-06, + "loss": 6.2364, + "step": 95000 + }, + { + "epoch": 2.61, + "learning_rate": 9.765868886576484e-06, + "loss": 6.2344, + "step": 95500 + }, + { + "epoch": 2.62, + "learning_rate": 9.764499698778685e-06, + "loss": 6.23, + "step": 96000 + }, + { + "epoch": 2.64, + "learning_rate": 9.763130510980888e-06, + "loss": 6.2338, + "step": 96500 + }, + { + "epoch": 2.65, + "learning_rate": 9.761761323183089e-06, + "loss": 6.2255, + "step": 97000 + }, + { + "epoch": 2.66, + "learning_rate": 9.76039213538529e-06, + "loss": 6.2244, + "step": 97500 + }, + { + "epoch": 2.68, + "learning_rate": 9.759022947587492e-06, + "loss": 6.2281, + "step": 98000 + }, + { + "epoch": 2.69, + "learning_rate": 9.757653759789693e-06, + "loss": 6.2288, + "step": 98500 + }, + { + "epoch": 2.7, + "learning_rate": 9.756284571991896e-06, + "loss": 6.2279, + "step": 99000 + }, + { + "epoch": 2.72, + "learning_rate": 9.754915384194097e-06, + "loss": 6.222, + "step": 99500 + }, + { + "epoch": 2.73, + "learning_rate": 9.753546196396298e-06, + "loss": 6.2289, + "step": 100000 + }, + { + "epoch": 2.74, + "learning_rate": 9.7521770085985e-06, + "loss": 6.2233, + "step": 100500 + }, + { + "epoch": 2.76, + "learning_rate": 9.750807820800702e-06, + "loss": 6.2253, + "step": 101000 + }, + { + "epoch": 2.77, + "learning_rate": 9.749438633002903e-06, + "loss": 6.2179, + "step": 101500 + }, + { + "epoch": 2.79, + "learning_rate": 9.748069445205106e-06, + "loss": 6.2218, + "step": 102000 + }, + { + "epoch": 2.8, + "learning_rate": 9.746700257407307e-06, + "loss": 6.2184, + "step": 102500 + }, + { + "epoch": 2.81, + "learning_rate": 9.745331069609508e-06, + "loss": 6.2207, + "step": 103000 + }, + { + "epoch": 2.83, + "learning_rate": 9.74396188181171e-06, + "loss": 6.2225, + "step": 103500 + }, + { + "epoch": 2.84, + "learning_rate": 9.742592694013911e-06, + "loss": 6.2186, + "step": 104000 + }, + { + "epoch": 2.85, + "learning_rate": 9.741223506216112e-06, + "loss": 6.2158, + "step": 104500 + }, + { + "epoch": 2.87, + "learning_rate": 9.739854318418315e-06, + "loss": 6.2158, + "step": 105000 + }, + { + "epoch": 2.88, + "learning_rate": 9.738485130620516e-06, + "loss": 6.2126, + "step": 105500 + }, + { + "epoch": 2.89, + "learning_rate": 9.737115942822719e-06, + "loss": 6.2137, + "step": 106000 + }, + { + "epoch": 2.91, + "learning_rate": 9.73574675502492e-06, + "loss": 6.2155, + "step": 106500 + }, + { + "epoch": 2.92, + "learning_rate": 9.73437756722712e-06, + "loss": 6.2104, + "step": 107000 + }, + { + "epoch": 2.94, + "learning_rate": 9.733008379429324e-06, + "loss": 6.2136, + "step": 107500 + }, + { + "epoch": 2.95, + "learning_rate": 9.731639191631525e-06, + "loss": 6.2129, + "step": 108000 + }, + { + "epoch": 2.96, + "learning_rate": 9.730270003833726e-06, + "loss": 6.2077, + "step": 108500 + }, + { + "epoch": 2.98, + "learning_rate": 9.728900816035928e-06, + "loss": 6.2094, + "step": 109000 + }, + { + "epoch": 2.99, + "learning_rate": 9.727531628238131e-06, + "loss": 6.2105, + "step": 109500 + }, + { + "epoch": 3.0, + "learning_rate": 9.726162440440332e-06, + "loss": 6.2061, + "step": 110000 + }, + { + "epoch": 3.02, + "learning_rate": 9.724793252642533e-06, + "loss": 6.2071, + "step": 110500 + }, + { + "epoch": 3.03, + "learning_rate": 9.723424064844736e-06, + "loss": 6.2076, + "step": 111000 + }, + { + "epoch": 3.04, + "learning_rate": 9.722054877046937e-06, + "loss": 6.2077, + "step": 111500 + }, + { + "epoch": 3.06, + "learning_rate": 9.720685689249138e-06, + "loss": 6.2047, + "step": 112000 + }, + { + "epoch": 3.07, + "learning_rate": 9.71931650145134e-06, + "loss": 6.2048, + "step": 112500 + }, + { + "epoch": 3.09, + "learning_rate": 9.717947313653542e-06, + "loss": 6.2059, + "step": 113000 + }, + { + "epoch": 3.1, + "learning_rate": 9.716578125855744e-06, + "loss": 6.2018, + "step": 113500 + }, + { + "epoch": 3.11, + "learning_rate": 9.715208938057945e-06, + "loss": 6.2034, + "step": 114000 + }, + { + "epoch": 3.13, + "learning_rate": 9.713839750260146e-06, + "loss": 6.2021, + "step": 114500 + }, + { + "epoch": 3.14, + "learning_rate": 9.712470562462349e-06, + "loss": 6.1983, + "step": 115000 + }, + { + "epoch": 3.15, + "learning_rate": 9.71110137466455e-06, + "loss": 6.1971, + "step": 115500 + }, + { + "epoch": 3.17, + "learning_rate": 9.709732186866751e-06, + "loss": 6.2034, + "step": 116000 + }, + { + "epoch": 3.18, + "learning_rate": 9.708362999068954e-06, + "loss": 6.1995, + "step": 116500 + }, + { + "epoch": 3.2, + "learning_rate": 9.706993811271155e-06, + "loss": 6.1998, + "step": 117000 + }, + { + "epoch": 3.21, + "learning_rate": 9.705624623473356e-06, + "loss": 6.198, + "step": 117500 + }, + { + "epoch": 3.22, + "learning_rate": 9.704255435675559e-06, + "loss": 6.1952, + "step": 118000 + }, + { + "epoch": 3.24, + "learning_rate": 9.70288624787776e-06, + "loss": 6.194, + "step": 118500 + }, + { + "epoch": 3.25, + "learning_rate": 9.70151706007996e-06, + "loss": 6.1976, + "step": 119000 + }, + { + "epoch": 3.26, + "learning_rate": 9.700147872282163e-06, + "loss": 6.1946, + "step": 119500 + }, + { + "epoch": 3.28, + "learning_rate": 9.698778684484364e-06, + "loss": 6.1926, + "step": 120000 + }, + { + "epoch": 3.29, + "learning_rate": 9.697409496686565e-06, + "loss": 6.1937, + "step": 120500 + }, + { + "epoch": 3.3, + "learning_rate": 9.696040308888768e-06, + "loss": 6.193, + "step": 121000 + }, + { + "epoch": 3.32, + "learning_rate": 9.694671121090969e-06, + "loss": 6.193, + "step": 121500 + }, + { + "epoch": 3.33, + "learning_rate": 9.693301933293172e-06, + "loss": 6.1914, + "step": 122000 + }, + { + "epoch": 3.35, + "learning_rate": 9.691932745495373e-06, + "loss": 6.1919, + "step": 122500 + }, + { + "epoch": 3.36, + "learning_rate": 9.690563557697574e-06, + "loss": 6.1897, + "step": 123000 + }, + { + "epoch": 3.37, + "learning_rate": 9.689194369899777e-06, + "loss": 6.1878, + "step": 123500 + }, + { + "epoch": 3.39, + "learning_rate": 9.687825182101978e-06, + "loss": 6.186, + "step": 124000 + }, + { + "epoch": 3.4, + "learning_rate": 9.686455994304179e-06, + "loss": 6.1918, + "step": 124500 + }, + { + "epoch": 3.41, + "learning_rate": 9.685086806506381e-06, + "loss": 6.1868, + "step": 125000 + }, + { + "epoch": 3.43, + "learning_rate": 9.683717618708582e-06, + "loss": 6.1848, + "step": 125500 + }, + { + "epoch": 3.44, + "learning_rate": 9.682348430910783e-06, + "loss": 6.1886, + "step": 126000 + }, + { + "epoch": 3.45, + "learning_rate": 9.680979243112986e-06, + "loss": 6.1866, + "step": 126500 + }, + { + "epoch": 3.47, + "learning_rate": 9.679610055315187e-06, + "loss": 6.1841, + "step": 127000 + }, + { + "epoch": 3.48, + "learning_rate": 9.67824086751739e-06, + "loss": 6.1842, + "step": 127500 + }, + { + "epoch": 3.5, + "learning_rate": 9.67687167971959e-06, + "loss": 6.1831, + "step": 128000 + }, + { + "epoch": 3.51, + "learning_rate": 9.675502491921794e-06, + "loss": 6.1837, + "step": 128500 + }, + { + "epoch": 3.52, + "learning_rate": 9.674133304123995e-06, + "loss": 6.1826, + "step": 129000 + }, + { + "epoch": 3.54, + "learning_rate": 9.672764116326197e-06, + "loss": 6.1803, + "step": 129500 + }, + { + "epoch": 3.55, + "learning_rate": 9.671394928528398e-06, + "loss": 6.1798, + "step": 130000 + }, + { + "epoch": 3.56, + "learning_rate": 9.6700257407306e-06, + "loss": 6.1842, + "step": 130500 + }, + { + "epoch": 3.58, + "learning_rate": 9.668656552932802e-06, + "loss": 6.1796, + "step": 131000 + }, + { + "epoch": 3.59, + "learning_rate": 9.667287365135003e-06, + "loss": 6.176, + "step": 131500 + }, + { + "epoch": 3.6, + "learning_rate": 9.665918177337204e-06, + "loss": 6.1781, + "step": 132000 + }, + { + "epoch": 3.62, + "learning_rate": 9.664548989539407e-06, + "loss": 6.1774, + "step": 132500 + }, + { + "epoch": 3.63, + "learning_rate": 9.663179801741608e-06, + "loss": 6.1802, + "step": 133000 + }, + { + "epoch": 3.65, + "learning_rate": 9.661810613943809e-06, + "loss": 6.1771, + "step": 133500 + }, + { + "epoch": 3.66, + "learning_rate": 9.660441426146012e-06, + "loss": 6.1767, + "step": 134000 + }, + { + "epoch": 3.67, + "learning_rate": 9.659072238348213e-06, + "loss": 6.1744, + "step": 134500 + }, + { + "epoch": 3.69, + "learning_rate": 9.657703050550414e-06, + "loss": 6.1741, + "step": 135000 + }, + { + "epoch": 3.7, + "learning_rate": 9.656333862752616e-06, + "loss": 6.1741, + "step": 135500 + }, + { + "epoch": 3.71, + "learning_rate": 9.654964674954817e-06, + "loss": 6.1717, + "step": 136000 + }, + { + "epoch": 3.73, + "learning_rate": 9.65359548715702e-06, + "loss": 6.1723, + "step": 136500 + }, + { + "epoch": 3.74, + "learning_rate": 9.652226299359221e-06, + "loss": 6.1737, + "step": 137000 + }, + { + "epoch": 3.75, + "learning_rate": 9.650857111561422e-06, + "loss": 6.1725, + "step": 137500 + }, + { + "epoch": 3.77, + "learning_rate": 9.649487923763625e-06, + "loss": 6.1703, + "step": 138000 + }, + { + "epoch": 3.78, + "learning_rate": 9.648118735965826e-06, + "loss": 6.1696, + "step": 138500 + }, + { + "epoch": 3.8, + "learning_rate": 9.646749548168027e-06, + "loss": 6.1717, + "step": 139000 + }, + { + "epoch": 3.81, + "learning_rate": 9.64538036037023e-06, + "loss": 6.1721, + "step": 139500 + }, + { + "epoch": 3.82, + "learning_rate": 9.64401117257243e-06, + "loss": 6.1696, + "step": 140000 + }, + { + "epoch": 3.84, + "learning_rate": 9.642641984774632e-06, + "loss": 6.1655, + "step": 140500 + }, + { + "epoch": 3.85, + "learning_rate": 9.641272796976834e-06, + "loss": 6.1701, + "step": 141000 + }, + { + "epoch": 3.86, + "learning_rate": 9.639903609179035e-06, + "loss": 6.1704, + "step": 141500 + }, + { + "epoch": 3.88, + "learning_rate": 9.638534421381236e-06, + "loss": 6.17, + "step": 142000 + }, + { + "epoch": 3.89, + "learning_rate": 9.637165233583439e-06, + "loss": 6.166, + "step": 142500 + }, + { + "epoch": 3.91, + "learning_rate": 9.63579604578564e-06, + "loss": 6.1635, + "step": 143000 + }, + { + "epoch": 3.92, + "learning_rate": 9.634426857987841e-06, + "loss": 6.164, + "step": 143500 + }, + { + "epoch": 3.93, + "learning_rate": 9.633057670190044e-06, + "loss": 6.1661, + "step": 144000 + }, + { + "epoch": 3.95, + "learning_rate": 9.631688482392245e-06, + "loss": 6.1627, + "step": 144500 + }, + { + "epoch": 3.96, + "learning_rate": 9.630319294594448e-06, + "loss": 6.1668, + "step": 145000 + }, + { + "epoch": 3.97, + "learning_rate": 9.62895010679665e-06, + "loss": 6.1639, + "step": 145500 + }, + { + "epoch": 3.99, + "learning_rate": 9.627580918998851e-06, + "loss": 6.1643, + "step": 146000 + }, + { + "epoch": 4.0, + "learning_rate": 9.626211731201052e-06, + "loss": 6.1615, + "step": 146500 + }, + { + "epoch": 4.01, + "learning_rate": 9.624842543403255e-06, + "loss": 6.1633, + "step": 147000 + }, + { + "epoch": 4.03, + "learning_rate": 9.623473355605456e-06, + "loss": 6.1625, + "step": 147500 + }, + { + "epoch": 4.04, + "learning_rate": 9.622104167807657e-06, + "loss": 6.1652, + "step": 148000 + }, + { + "epoch": 4.06, + "learning_rate": 9.62073498000986e-06, + "loss": 6.159, + "step": 148500 + }, + { + "epoch": 4.07, + "learning_rate": 9.61936579221206e-06, + "loss": 6.1578, + "step": 149000 + }, + { + "epoch": 4.08, + "learning_rate": 9.617996604414262e-06, + "loss": 6.1631, + "step": 149500 + }, + { + "epoch": 4.1, + "learning_rate": 9.616627416616465e-06, + "loss": 6.1595, + "step": 150000 + }, + { + "epoch": 4.11, + "learning_rate": 9.615258228818666e-06, + "loss": 6.1611, + "step": 150500 + }, + { + "epoch": 4.12, + "learning_rate": 9.613889041020867e-06, + "loss": 6.1561, + "step": 151000 + }, + { + "epoch": 4.14, + "learning_rate": 9.61251985322307e-06, + "loss": 6.1571, + "step": 151500 + }, + { + "epoch": 4.15, + "learning_rate": 9.61115066542527e-06, + "loss": 6.1575, + "step": 152000 + }, + { + "epoch": 4.16, + "learning_rate": 9.609781477627473e-06, + "loss": 6.1587, + "step": 152500 + }, + { + "epoch": 4.18, + "learning_rate": 9.608412289829674e-06, + "loss": 6.1556, + "step": 153000 + }, + { + "epoch": 4.19, + "learning_rate": 9.607043102031875e-06, + "loss": 6.1537, + "step": 153500 + }, + { + "epoch": 4.21, + "learning_rate": 9.605673914234078e-06, + "loss": 6.1549, + "step": 154000 + }, + { + "epoch": 4.22, + "learning_rate": 9.604304726436279e-06, + "loss": 6.1556, + "step": 154500 + }, + { + "epoch": 4.23, + "learning_rate": 9.60293553863848e-06, + "loss": 6.155, + "step": 155000 + }, + { + "epoch": 4.25, + "learning_rate": 9.601566350840683e-06, + "loss": 6.1547, + "step": 155500 + }, + { + "epoch": 4.26, + "learning_rate": 9.600197163042884e-06, + "loss": 6.1534, + "step": 156000 + }, + { + "epoch": 4.27, + "learning_rate": 9.598827975245085e-06, + "loss": 6.1511, + "step": 156500 + }, + { + "epoch": 4.29, + "learning_rate": 9.597458787447287e-06, + "loss": 6.1532, + "step": 157000 + }, + { + "epoch": 4.3, + "learning_rate": 9.596089599649488e-06, + "loss": 6.1532, + "step": 157500 + }, + { + "epoch": 4.31, + "learning_rate": 9.59472041185169e-06, + "loss": 6.155, + "step": 158000 + }, + { + "epoch": 4.33, + "learning_rate": 9.593351224053892e-06, + "loss": 6.1532, + "step": 158500 + }, + { + "epoch": 4.34, + "learning_rate": 9.591982036256093e-06, + "loss": 6.1491, + "step": 159000 + }, + { + "epoch": 4.36, + "learning_rate": 9.590612848458296e-06, + "loss": 6.1511, + "step": 159500 + }, + { + "epoch": 4.37, + "learning_rate": 9.589243660660497e-06, + "loss": 6.1513, + "step": 160000 + }, + { + "epoch": 4.38, + "learning_rate": 9.587874472862698e-06, + "loss": 6.1497, + "step": 160500 + }, + { + "epoch": 4.4, + "learning_rate": 9.5865052850649e-06, + "loss": 6.1464, + "step": 161000 + }, + { + "epoch": 4.41, + "learning_rate": 9.585136097267102e-06, + "loss": 6.1478, + "step": 161500 + }, + { + "epoch": 4.42, + "learning_rate": 9.583766909469303e-06, + "loss": 6.154, + "step": 162000 + }, + { + "epoch": 4.44, + "learning_rate": 9.582397721671505e-06, + "loss": 6.149, + "step": 162500 + }, + { + "epoch": 4.45, + "learning_rate": 9.581028533873706e-06, + "loss": 6.1477, + "step": 163000 + }, + { + "epoch": 4.47, + "learning_rate": 9.579659346075909e-06, + "loss": 6.1475, + "step": 163500 + }, + { + "epoch": 4.48, + "learning_rate": 9.57829015827811e-06, + "loss": 6.152, + "step": 164000 + }, + { + "epoch": 4.49, + "learning_rate": 9.576920970480313e-06, + "loss": 6.1459, + "step": 164500 + }, + { + "epoch": 4.51, + "learning_rate": 9.575551782682514e-06, + "loss": 6.1526, + "step": 165000 + }, + { + "epoch": 4.52, + "learning_rate": 9.574182594884715e-06, + "loss": 6.142, + "step": 165500 + }, + { + "epoch": 4.53, + "learning_rate": 9.572813407086918e-06, + "loss": 6.1456, + "step": 166000 + }, + { + "epoch": 4.55, + "learning_rate": 9.571444219289119e-06, + "loss": 6.1452, + "step": 166500 + }, + { + "epoch": 4.56, + "learning_rate": 9.570075031491321e-06, + "loss": 6.1406, + "step": 167000 + }, + { + "epoch": 4.57, + "learning_rate": 9.568705843693522e-06, + "loss": 6.1417, + "step": 167500 + }, + { + "epoch": 4.59, + "learning_rate": 9.567336655895723e-06, + "loss": 6.1458, + "step": 168000 + }, + { + "epoch": 4.6, + "learning_rate": 9.565967468097926e-06, + "loss": 6.1481, + "step": 168500 + }, + { + "epoch": 4.62, + "learning_rate": 9.564598280300127e-06, + "loss": 6.1422, + "step": 169000 + }, + { + "epoch": 4.63, + "learning_rate": 9.563229092502328e-06, + "loss": 6.1406, + "step": 169500 + }, + { + "epoch": 4.64, + "learning_rate": 9.56185990470453e-06, + "loss": 6.1441, + "step": 170000 + }, + { + "epoch": 4.66, + "learning_rate": 9.560490716906732e-06, + "loss": 6.1444, + "step": 170500 + }, + { + "epoch": 4.67, + "learning_rate": 9.559121529108933e-06, + "loss": 6.1412, + "step": 171000 + }, + { + "epoch": 4.68, + "learning_rate": 9.557752341311136e-06, + "loss": 6.1391, + "step": 171500 + }, + { + "epoch": 4.7, + "learning_rate": 9.556383153513337e-06, + "loss": 6.1343, + "step": 172000 + }, + { + "epoch": 4.71, + "learning_rate": 9.555013965715538e-06, + "loss": 6.1436, + "step": 172500 + }, + { + "epoch": 4.72, + "learning_rate": 9.55364477791774e-06, + "loss": 6.1398, + "step": 173000 + }, + { + "epoch": 4.74, + "learning_rate": 9.552275590119941e-06, + "loss": 6.1381, + "step": 173500 + }, + { + "epoch": 4.75, + "learning_rate": 9.550906402322142e-06, + "loss": 6.1381, + "step": 174000 + }, + { + "epoch": 4.77, + "learning_rate": 9.549537214524345e-06, + "loss": 6.1409, + "step": 174500 + }, + { + "epoch": 4.78, + "learning_rate": 9.548168026726546e-06, + "loss": 6.1408, + "step": 175000 + }, + { + "epoch": 4.79, + "learning_rate": 9.546798838928749e-06, + "loss": 6.1393, + "step": 175500 + }, + { + "epoch": 4.81, + "learning_rate": 9.54542965113095e-06, + "loss": 6.137, + "step": 176000 + }, + { + "epoch": 4.82, + "learning_rate": 9.54406046333315e-06, + "loss": 6.1387, + "step": 176500 + }, + { + "epoch": 4.83, + "learning_rate": 9.542691275535354e-06, + "loss": 6.1371, + "step": 177000 + }, + { + "epoch": 4.85, + "learning_rate": 9.541322087737555e-06, + "loss": 6.1385, + "step": 177500 + }, + { + "epoch": 4.86, + "learning_rate": 9.539952899939756e-06, + "loss": 6.1368, + "step": 178000 + }, + { + "epoch": 4.87, + "learning_rate": 9.538583712141958e-06, + "loss": 6.1332, + "step": 178500 + }, + { + "epoch": 4.89, + "learning_rate": 9.53721452434416e-06, + "loss": 6.1317, + "step": 179000 + }, + { + "epoch": 4.9, + "learning_rate": 9.53584533654636e-06, + "loss": 6.1383, + "step": 179500 + }, + { + "epoch": 4.92, + "learning_rate": 9.534476148748563e-06, + "loss": 6.1317, + "step": 180000 + }, + { + "epoch": 4.93, + "learning_rate": 9.533106960950764e-06, + "loss": 6.1297, + "step": 180500 + }, + { + "epoch": 4.94, + "learning_rate": 9.531737773152965e-06, + "loss": 6.134, + "step": 181000 + }, + { + "epoch": 4.96, + "learning_rate": 9.530368585355168e-06, + "loss": 6.1347, + "step": 181500 + }, + { + "epoch": 4.97, + "learning_rate": 9.52899939755737e-06, + "loss": 6.1344, + "step": 182000 + }, + { + "epoch": 4.98, + "learning_rate": 9.527630209759572e-06, + "loss": 6.1331, + "step": 182500 + }, + { + "epoch": 5.0, + "learning_rate": 9.526261021961774e-06, + "loss": 6.1361, + "step": 183000 + }, + { + "epoch": 5.01, + "learning_rate": 9.524891834163975e-06, + "loss": 6.1294, + "step": 183500 + }, + { + "epoch": 5.02, + "learning_rate": 9.523522646366176e-06, + "loss": 6.1311, + "step": 184000 + }, + { + "epoch": 5.04, + "learning_rate": 9.522153458568379e-06, + "loss": 6.1319, + "step": 184500 + }, + { + "epoch": 5.05, + "learning_rate": 9.52078427077058e-06, + "loss": 6.1302, + "step": 185000 + }, + { + "epoch": 5.07, + "learning_rate": 9.519415082972781e-06, + "loss": 6.1344, + "step": 185500 + }, + { + "epoch": 5.08, + "learning_rate": 9.518045895174984e-06, + "loss": 6.1277, + "step": 186000 + }, + { + "epoch": 5.09, + "learning_rate": 9.516676707377185e-06, + "loss": 6.1295, + "step": 186500 + }, + { + "epoch": 5.11, + "learning_rate": 9.515307519579386e-06, + "loss": 6.1275, + "step": 187000 + }, + { + "epoch": 5.12, + "learning_rate": 9.513938331781589e-06, + "loss": 6.128, + "step": 187500 + }, + { + "epoch": 5.13, + "learning_rate": 9.51256914398379e-06, + "loss": 6.1296, + "step": 188000 + }, + { + "epoch": 5.15, + "learning_rate": 9.51119995618599e-06, + "loss": 6.1299, + "step": 188500 + }, + { + "epoch": 5.16, + "learning_rate": 9.509830768388193e-06, + "loss": 6.1314, + "step": 189000 + }, + { + "epoch": 5.18, + "learning_rate": 9.508461580590394e-06, + "loss": 6.1279, + "step": 189500 + }, + { + "epoch": 5.19, + "learning_rate": 9.507092392792597e-06, + "loss": 6.1258, + "step": 190000 + }, + { + "epoch": 5.2, + "learning_rate": 9.505723204994798e-06, + "loss": 6.1299, + "step": 190500 + }, + { + "epoch": 5.22, + "learning_rate": 9.504354017196999e-06, + "loss": 6.1276, + "step": 191000 + }, + { + "epoch": 5.23, + "learning_rate": 9.502984829399202e-06, + "loss": 6.1248, + "step": 191500 + }, + { + "epoch": 5.24, + "learning_rate": 9.501615641601403e-06, + "loss": 6.1204, + "step": 192000 + }, + { + "epoch": 5.26, + "learning_rate": 9.500246453803604e-06, + "loss": 6.1241, + "step": 192500 + }, + { + "epoch": 5.27, + "learning_rate": 9.498877266005807e-06, + "loss": 6.1253, + "step": 193000 + }, + { + "epoch": 5.28, + "learning_rate": 9.497508078208008e-06, + "loss": 6.1286, + "step": 193500 + }, + { + "epoch": 5.3, + "learning_rate": 9.496138890410209e-06, + "loss": 6.1254, + "step": 194000 + }, + { + "epoch": 5.31, + "learning_rate": 9.494769702612411e-06, + "loss": 6.1224, + "step": 194500 + }, + { + "epoch": 5.33, + "learning_rate": 9.493400514814612e-06, + "loss": 6.1261, + "step": 195000 + }, + { + "epoch": 5.34, + "learning_rate": 9.492031327016813e-06, + "loss": 6.1263, + "step": 195500 + }, + { + "epoch": 5.35, + "learning_rate": 9.490662139219016e-06, + "loss": 6.1243, + "step": 196000 + }, + { + "epoch": 5.37, + "learning_rate": 9.489292951421217e-06, + "loss": 6.1214, + "step": 196500 + }, + { + "epoch": 5.38, + "learning_rate": 9.487923763623418e-06, + "loss": 6.1199, + "step": 197000 + }, + { + "epoch": 5.39, + "learning_rate": 9.48655457582562e-06, + "loss": 6.1218, + "step": 197500 + }, + { + "epoch": 5.41, + "learning_rate": 9.485185388027822e-06, + "loss": 6.126, + "step": 198000 + }, + { + "epoch": 5.42, + "learning_rate": 9.483816200230025e-06, + "loss": 6.1188, + "step": 198500 + }, + { + "epoch": 5.43, + "learning_rate": 9.482447012432226e-06, + "loss": 6.1201, + "step": 199000 + }, + { + "epoch": 5.45, + "learning_rate": 9.481077824634428e-06, + "loss": 6.1183, + "step": 199500 + }, + { + "epoch": 5.46, + "learning_rate": 9.47970863683663e-06, + "loss": 6.1163, + "step": 200000 + }, + { + "epoch": 5.48, + "learning_rate": 9.478339449038832e-06, + "loss": 6.122, + "step": 200500 + }, + { + "epoch": 5.49, + "learning_rate": 9.476970261241033e-06, + "loss": 6.1194, + "step": 201000 + }, + { + "epoch": 5.5, + "learning_rate": 9.475601073443234e-06, + "loss": 6.121, + "step": 201500 + }, + { + "epoch": 5.52, + "learning_rate": 9.474231885645437e-06, + "loss": 6.1191, + "step": 202000 + }, + { + "epoch": 5.53, + "learning_rate": 9.472862697847638e-06, + "loss": 6.1193, + "step": 202500 + }, + { + "epoch": 5.54, + "learning_rate": 9.471493510049839e-06, + "loss": 6.1194, + "step": 203000 + }, + { + "epoch": 5.56, + "learning_rate": 9.470124322252042e-06, + "loss": 6.1184, + "step": 203500 + }, + { + "epoch": 5.57, + "learning_rate": 9.468755134454243e-06, + "loss": 6.1202, + "step": 204000 + }, + { + "epoch": 5.58, + "learning_rate": 9.467385946656444e-06, + "loss": 6.1166, + "step": 204500 + }, + { + "epoch": 5.6, + "learning_rate": 9.466016758858646e-06, + "loss": 6.1218, + "step": 205000 + }, + { + "epoch": 5.61, + "learning_rate": 9.464647571060847e-06, + "loss": 6.1157, + "step": 205500 + }, + { + "epoch": 5.63, + "learning_rate": 9.46327838326305e-06, + "loss": 6.1185, + "step": 206000 + }, + { + "epoch": 5.64, + "learning_rate": 9.461909195465251e-06, + "loss": 6.1152, + "step": 206500 + }, + { + "epoch": 5.65, + "learning_rate": 9.460540007667452e-06, + "loss": 6.1158, + "step": 207000 + }, + { + "epoch": 5.67, + "learning_rate": 9.459170819869655e-06, + "loss": 6.1155, + "step": 207500 + }, + { + "epoch": 5.68, + "learning_rate": 9.457801632071856e-06, + "loss": 6.1154, + "step": 208000 + }, + { + "epoch": 5.69, + "learning_rate": 9.456432444274057e-06, + "loss": 6.1103, + "step": 208500 + }, + { + "epoch": 5.71, + "learning_rate": 9.45506325647626e-06, + "loss": 6.1153, + "step": 209000 + }, + { + "epoch": 5.72, + "learning_rate": 9.45369406867846e-06, + "loss": 6.1149, + "step": 209500 + }, + { + "epoch": 5.73, + "learning_rate": 9.452324880880662e-06, + "loss": 6.1126, + "step": 210000 + }, + { + "epoch": 5.75, + "learning_rate": 9.450955693082864e-06, + "loss": 6.1107, + "step": 210500 + }, + { + "epoch": 5.76, + "learning_rate": 9.449586505285065e-06, + "loss": 6.1142, + "step": 211000 + }, + { + "epoch": 5.78, + "learning_rate": 9.448217317487266e-06, + "loss": 6.1159, + "step": 211500 + }, + { + "epoch": 5.79, + "learning_rate": 9.446848129689469e-06, + "loss": 6.1091, + "step": 212000 + }, + { + "epoch": 5.8, + "learning_rate": 9.44547894189167e-06, + "loss": 6.1121, + "step": 212500 + }, + { + "epoch": 5.82, + "learning_rate": 9.444109754093873e-06, + "loss": 6.1117, + "step": 213000 + }, + { + "epoch": 5.83, + "learning_rate": 9.442740566296074e-06, + "loss": 6.1118, + "step": 213500 + }, + { + "epoch": 5.84, + "learning_rate": 9.441371378498275e-06, + "loss": 6.1118, + "step": 214000 + }, + { + "epoch": 5.86, + "learning_rate": 9.440002190700478e-06, + "loss": 6.1112, + "step": 214500 + }, + { + "epoch": 5.87, + "learning_rate": 9.438633002902679e-06, + "loss": 6.1113, + "step": 215000 + }, + { + "epoch": 5.89, + "learning_rate": 9.43726381510488e-06, + "loss": 6.1101, + "step": 215500 + }, + { + "epoch": 5.9, + "learning_rate": 9.435894627307082e-06, + "loss": 6.1106, + "step": 216000 + }, + { + "epoch": 5.91, + "learning_rate": 9.434525439509283e-06, + "loss": 6.1152, + "step": 216500 + }, + { + "epoch": 5.93, + "learning_rate": 9.433156251711484e-06, + "loss": 6.1121, + "step": 217000 + }, + { + "epoch": 5.94, + "learning_rate": 9.431787063913687e-06, + "loss": 6.1086, + "step": 217500 + }, + { + "epoch": 5.95, + "learning_rate": 9.43041787611589e-06, + "loss": 6.1114, + "step": 218000 + }, + { + "epoch": 5.97, + "learning_rate": 9.42904868831809e-06, + "loss": 6.1059, + "step": 218500 + }, + { + "epoch": 5.98, + "learning_rate": 9.427679500520292e-06, + "loss": 6.1113, + "step": 219000 + }, + { + "epoch": 5.99, + "learning_rate": 9.426310312722495e-06, + "loss": 6.1121, + "step": 219500 + }, + { + "epoch": 6.01, + "learning_rate": 9.424941124924696e-06, + "loss": 6.1097, + "step": 220000 + }, + { + "epoch": 6.02, + "learning_rate": 9.423571937126898e-06, + "loss": 6.1046, + "step": 220500 + }, + { + "epoch": 6.04, + "learning_rate": 9.4222027493291e-06, + "loss": 6.1084, + "step": 221000 + }, + { + "epoch": 6.05, + "learning_rate": 9.4208335615313e-06, + "loss": 6.1089, + "step": 221500 + }, + { + "epoch": 6.06, + "learning_rate": 9.419464373733503e-06, + "loss": 6.1095, + "step": 222000 + }, + { + "epoch": 6.08, + "learning_rate": 9.418095185935704e-06, + "loss": 6.1081, + "step": 222500 + }, + { + "epoch": 6.09, + "learning_rate": 9.416725998137905e-06, + "loss": 6.1065, + "step": 223000 + }, + { + "epoch": 6.1, + "learning_rate": 9.415356810340108e-06, + "loss": 6.1053, + "step": 223500 + }, + { + "epoch": 6.12, + "learning_rate": 9.413987622542309e-06, + "loss": 6.1099, + "step": 224000 + }, + { + "epoch": 6.13, + "learning_rate": 9.41261843474451e-06, + "loss": 6.1068, + "step": 224500 + }, + { + "epoch": 6.14, + "learning_rate": 9.411249246946713e-06, + "loss": 6.1048, + "step": 225000 + }, + { + "epoch": 6.16, + "learning_rate": 9.409880059148914e-06, + "loss": 6.1052, + "step": 225500 + }, + { + "epoch": 6.17, + "learning_rate": 9.408510871351115e-06, + "loss": 6.1056, + "step": 226000 + }, + { + "epoch": 6.19, + "learning_rate": 9.407141683553317e-06, + "loss": 6.1058, + "step": 226500 + }, + { + "epoch": 6.2, + "learning_rate": 9.405772495755518e-06, + "loss": 6.1059, + "step": 227000 + }, + { + "epoch": 6.21, + "learning_rate": 9.40440330795772e-06, + "loss": 6.103, + "step": 227500 + }, + { + "epoch": 6.23, + "learning_rate": 9.403034120159922e-06, + "loss": 6.1072, + "step": 228000 + }, + { + "epoch": 6.24, + "learning_rate": 9.401664932362123e-06, + "loss": 6.104, + "step": 228500 + }, + { + "epoch": 6.25, + "learning_rate": 9.400295744564326e-06, + "loss": 6.1054, + "step": 229000 + }, + { + "epoch": 6.27, + "learning_rate": 9.398926556766527e-06, + "loss": 6.1073, + "step": 229500 + }, + { + "epoch": 6.28, + "learning_rate": 9.397557368968728e-06, + "loss": 6.1026, + "step": 230000 + }, + { + "epoch": 6.29, + "learning_rate": 9.39618818117093e-06, + "loss": 6.1042, + "step": 230500 + }, + { + "epoch": 6.31, + "learning_rate": 9.394818993373132e-06, + "loss": 6.1038, + "step": 231000 + }, + { + "epoch": 6.32, + "learning_rate": 9.393449805575333e-06, + "loss": 6.1054, + "step": 231500 + }, + { + "epoch": 6.34, + "learning_rate": 9.392080617777535e-06, + "loss": 6.0994, + "step": 232000 + }, + { + "epoch": 6.35, + "learning_rate": 9.390711429979736e-06, + "loss": 6.1025, + "step": 232500 + }, + { + "epoch": 6.36, + "learning_rate": 9.389342242181937e-06, + "loss": 6.1021, + "step": 233000 + }, + { + "epoch": 6.38, + "learning_rate": 9.38797305438414e-06, + "loss": 6.1016, + "step": 233500 + }, + { + "epoch": 6.39, + "learning_rate": 9.386603866586341e-06, + "loss": 6.1032, + "step": 234000 + }, + { + "epoch": 6.4, + "learning_rate": 9.385234678788542e-06, + "loss": 6.1004, + "step": 234500 + }, + { + "epoch": 6.42, + "learning_rate": 9.383865490990745e-06, + "loss": 6.1005, + "step": 235000 + }, + { + "epoch": 6.43, + "learning_rate": 9.382496303192948e-06, + "loss": 6.098, + "step": 235500 + }, + { + "epoch": 6.44, + "learning_rate": 9.381127115395149e-06, + "loss": 6.1004, + "step": 236000 + }, + { + "epoch": 6.46, + "learning_rate": 9.379757927597351e-06, + "loss": 6.0967, + "step": 236500 + }, + { + "epoch": 6.47, + "learning_rate": 9.378388739799552e-06, + "loss": 6.0983, + "step": 237000 + }, + { + "epoch": 6.49, + "learning_rate": 9.377019552001753e-06, + "loss": 6.0969, + "step": 237500 + }, + { + "epoch": 6.5, + "learning_rate": 9.375650364203956e-06, + "loss": 6.0981, + "step": 238000 + }, + { + "epoch": 6.51, + "learning_rate": 9.374281176406157e-06, + "loss": 6.1036, + "step": 238500 + }, + { + "epoch": 6.53, + "learning_rate": 9.372911988608358e-06, + "loss": 6.096, + "step": 239000 + }, + { + "epoch": 6.54, + "learning_rate": 9.37154280081056e-06, + "loss": 6.0977, + "step": 239500 + }, + { + "epoch": 6.55, + "learning_rate": 9.370173613012762e-06, + "loss": 6.0988, + "step": 240000 + }, + { + "epoch": 6.57, + "learning_rate": 9.368804425214963e-06, + "loss": 6.0993, + "step": 240500 + }, + { + "epoch": 6.58, + "learning_rate": 9.367435237417166e-06, + "loss": 6.0982, + "step": 241000 + }, + { + "epoch": 6.6, + "learning_rate": 9.366066049619367e-06, + "loss": 6.0985, + "step": 241500 + }, + { + "epoch": 6.61, + "learning_rate": 9.364696861821568e-06, + "loss": 6.0962, + "step": 242000 + }, + { + "epoch": 6.62, + "learning_rate": 9.36332767402377e-06, + "loss": 6.0962, + "step": 242500 + }, + { + "epoch": 6.64, + "learning_rate": 9.361958486225971e-06, + "loss": 6.0991, + "step": 243000 + }, + { + "epoch": 6.65, + "learning_rate": 9.360589298428174e-06, + "loss": 6.0963, + "step": 243500 + }, + { + "epoch": 6.66, + "learning_rate": 9.359220110630375e-06, + "loss": 6.0987, + "step": 244000 + }, + { + "epoch": 6.68, + "learning_rate": 9.357850922832576e-06, + "loss": 6.0984, + "step": 244500 + }, + { + "epoch": 6.69, + "learning_rate": 9.356481735034779e-06, + "loss": 6.0956, + "step": 245000 + }, + { + "epoch": 6.7, + "learning_rate": 9.35511254723698e-06, + "loss": 6.0956, + "step": 245500 + }, + { + "epoch": 6.72, + "learning_rate": 9.35374335943918e-06, + "loss": 6.0977, + "step": 246000 + }, + { + "epoch": 6.73, + "learning_rate": 9.352374171641384e-06, + "loss": 6.093, + "step": 246500 + }, + { + "epoch": 6.75, + "learning_rate": 9.351004983843585e-06, + "loss": 6.0929, + "step": 247000 + }, + { + "epoch": 6.76, + "learning_rate": 9.349635796045786e-06, + "loss": 6.0944, + "step": 247500 + }, + { + "epoch": 6.77, + "learning_rate": 9.348266608247988e-06, + "loss": 6.0978, + "step": 248000 + }, + { + "epoch": 6.79, + "learning_rate": 9.34689742045019e-06, + "loss": 6.0937, + "step": 248500 + }, + { + "epoch": 6.8, + "learning_rate": 9.34552823265239e-06, + "loss": 6.0937, + "step": 249000 + }, + { + "epoch": 6.81, + "learning_rate": 9.344159044854593e-06, + "loss": 6.0935, + "step": 249500 + }, + { + "epoch": 6.83, + "learning_rate": 9.342789857056794e-06, + "loss": 6.0936, + "step": 250000 + }, + { + "epoch": 6.84, + "learning_rate": 9.341420669258995e-06, + "loss": 6.0948, + "step": 250500 + }, + { + "epoch": 6.85, + "learning_rate": 9.340051481461198e-06, + "loss": 6.0911, + "step": 251000 + }, + { + "epoch": 6.87, + "learning_rate": 9.338682293663399e-06, + "loss": 6.096, + "step": 251500 + }, + { + "epoch": 6.88, + "learning_rate": 9.337313105865602e-06, + "loss": 6.0946, + "step": 252000 + }, + { + "epoch": 6.9, + "learning_rate": 9.335943918067803e-06, + "loss": 6.0896, + "step": 252500 + }, + { + "epoch": 6.91, + "learning_rate": 9.334574730270004e-06, + "loss": 6.0916, + "step": 253000 + }, + { + "epoch": 6.92, + "learning_rate": 9.333205542472206e-06, + "loss": 6.0946, + "step": 253500 + }, + { + "epoch": 6.94, + "learning_rate": 9.331836354674409e-06, + "loss": 6.0908, + "step": 254000 + }, + { + "epoch": 6.95, + "learning_rate": 9.33046716687661e-06, + "loss": 6.0916, + "step": 254500 + }, + { + "epoch": 6.96, + "learning_rate": 9.329097979078811e-06, + "loss": 6.091, + "step": 255000 + }, + { + "epoch": 6.98, + "learning_rate": 9.327728791281014e-06, + "loss": 6.0929, + "step": 255500 + }, + { + "epoch": 6.99, + "learning_rate": 9.326359603483215e-06, + "loss": 6.093, + "step": 256000 + }, + { + "epoch": 7.0, + "learning_rate": 9.324990415685416e-06, + "loss": 6.0875, + "step": 256500 + }, + { + "epoch": 7.02, + "learning_rate": 9.323621227887619e-06, + "loss": 6.0898, + "step": 257000 + }, + { + "epoch": 7.03, + "learning_rate": 9.32225204008982e-06, + "loss": 6.0889, + "step": 257500 + }, + { + "epoch": 7.05, + "learning_rate": 9.32088285229202e-06, + "loss": 6.0894, + "step": 258000 + }, + { + "epoch": 7.06, + "learning_rate": 9.319513664494223e-06, + "loss": 6.0896, + "step": 258500 + }, + { + "epoch": 7.07, + "learning_rate": 9.318144476696424e-06, + "loss": 6.0955, + "step": 259000 + }, + { + "epoch": 7.09, + "learning_rate": 9.316775288898627e-06, + "loss": 6.0919, + "step": 259500 + }, + { + "epoch": 7.1, + "learning_rate": 9.315406101100828e-06, + "loss": 6.0888, + "step": 260000 + }, + { + "epoch": 7.11, + "learning_rate": 9.314036913303029e-06, + "loss": 6.0859, + "step": 260500 + }, + { + "epoch": 7.13, + "learning_rate": 9.312667725505232e-06, + "loss": 6.0894, + "step": 261000 + }, + { + "epoch": 7.14, + "learning_rate": 9.311298537707433e-06, + "loss": 6.0901, + "step": 261500 + }, + { + "epoch": 7.15, + "learning_rate": 9.309929349909634e-06, + "loss": 6.0885, + "step": 262000 + }, + { + "epoch": 7.17, + "learning_rate": 9.308560162111837e-06, + "loss": 6.0882, + "step": 262500 + }, + { + "epoch": 7.18, + "learning_rate": 9.307190974314038e-06, + "loss": 6.0861, + "step": 263000 + }, + { + "epoch": 7.2, + "learning_rate": 9.305821786516239e-06, + "loss": 6.0899, + "step": 263500 + }, + { + "epoch": 7.21, + "learning_rate": 9.304452598718441e-06, + "loss": 6.084, + "step": 264000 + }, + { + "epoch": 7.22, + "learning_rate": 9.303083410920642e-06, + "loss": 6.0902, + "step": 264500 + }, + { + "epoch": 7.24, + "learning_rate": 9.301714223122843e-06, + "loss": 6.0833, + "step": 265000 + }, + { + "epoch": 7.25, + "learning_rate": 9.300345035325046e-06, + "loss": 6.0852, + "step": 265500 + }, + { + "epoch": 7.26, + "learning_rate": 9.298975847527247e-06, + "loss": 6.088, + "step": 266000 + }, + { + "epoch": 7.28, + "learning_rate": 9.29760665972945e-06, + "loss": 6.0844, + "step": 266500 + }, + { + "epoch": 7.29, + "learning_rate": 9.29623747193165e-06, + "loss": 6.0821, + "step": 267000 + }, + { + "epoch": 7.31, + "learning_rate": 9.294868284133852e-06, + "loss": 6.0884, + "step": 267500 + }, + { + "epoch": 7.32, + "learning_rate": 9.293499096336055e-06, + "loss": 6.0845, + "step": 268000 + }, + { + "epoch": 7.33, + "learning_rate": 9.292129908538256e-06, + "loss": 6.0865, + "step": 268500 + }, + { + "epoch": 7.35, + "learning_rate": 9.290760720740457e-06, + "loss": 6.086, + "step": 269000 + }, + { + "epoch": 7.36, + "learning_rate": 9.28939153294266e-06, + "loss": 6.0862, + "step": 269500 + }, + { + "epoch": 7.37, + "learning_rate": 9.28802234514486e-06, + "loss": 6.0865, + "step": 270000 + }, + { + "epoch": 7.39, + "learning_rate": 9.286653157347061e-06, + "loss": 6.0875, + "step": 270500 + }, + { + "epoch": 7.4, + "learning_rate": 9.285283969549264e-06, + "loss": 6.0836, + "step": 271000 + }, + { + "epoch": 7.41, + "learning_rate": 9.283914781751467e-06, + "loss": 6.0814, + "step": 271500 + }, + { + "epoch": 7.43, + "learning_rate": 9.282545593953668e-06, + "loss": 6.0845, + "step": 272000 + }, + { + "epoch": 7.44, + "learning_rate": 9.281176406155869e-06, + "loss": 6.0856, + "step": 272500 + }, + { + "epoch": 7.46, + "learning_rate": 9.279807218358072e-06, + "loss": 6.0852, + "step": 273000 + }, + { + "epoch": 7.47, + "learning_rate": 9.278438030560273e-06, + "loss": 6.0855, + "step": 273500 + }, + { + "epoch": 7.48, + "learning_rate": 9.277068842762475e-06, + "loss": 6.0875, + "step": 274000 + }, + { + "epoch": 7.5, + "learning_rate": 9.275699654964676e-06, + "loss": 6.0873, + "step": 274500 + }, + { + "epoch": 7.51, + "learning_rate": 9.274330467166877e-06, + "loss": 6.0825, + "step": 275000 + }, + { + "epoch": 7.52, + "learning_rate": 9.27296127936908e-06, + "loss": 6.0851, + "step": 275500 + }, + { + "epoch": 7.54, + "learning_rate": 9.271592091571281e-06, + "loss": 6.0845, + "step": 276000 + }, + { + "epoch": 7.55, + "learning_rate": 9.270222903773482e-06, + "loss": 6.0838, + "step": 276500 + }, + { + "epoch": 7.56, + "learning_rate": 9.268853715975685e-06, + "loss": 6.0865, + "step": 277000 + }, + { + "epoch": 7.58, + "learning_rate": 9.267484528177886e-06, + "loss": 6.0816, + "step": 277500 + }, + { + "epoch": 7.59, + "learning_rate": 9.266115340380087e-06, + "loss": 6.0835, + "step": 278000 + }, + { + "epoch": 7.61, + "learning_rate": 9.26474615258229e-06, + "loss": 6.0811, + "step": 278500 + }, + { + "epoch": 7.62, + "learning_rate": 9.26337696478449e-06, + "loss": 6.0794, + "step": 279000 + }, + { + "epoch": 7.63, + "learning_rate": 9.262007776986692e-06, + "loss": 6.0832, + "step": 279500 + }, + { + "epoch": 7.65, + "learning_rate": 9.260638589188894e-06, + "loss": 6.081, + "step": 280000 + }, + { + "epoch": 7.66, + "learning_rate": 9.259269401391095e-06, + "loss": 6.0789, + "step": 280500 + }, + { + "epoch": 7.67, + "learning_rate": 9.257900213593296e-06, + "loss": 6.0811, + "step": 281000 + }, + { + "epoch": 7.69, + "learning_rate": 9.256531025795499e-06, + "loss": 6.0778, + "step": 281500 + }, + { + "epoch": 7.7, + "learning_rate": 9.2551618379977e-06, + "loss": 6.0806, + "step": 282000 + }, + { + "epoch": 7.71, + "learning_rate": 9.253792650199903e-06, + "loss": 6.0818, + "step": 282500 + }, + { + "epoch": 7.73, + "learning_rate": 9.252423462402104e-06, + "loss": 6.0805, + "step": 283000 + }, + { + "epoch": 7.74, + "learning_rate": 9.251054274604305e-06, + "loss": 6.0773, + "step": 283500 + }, + { + "epoch": 7.76, + "learning_rate": 9.249685086806508e-06, + "loss": 6.0777, + "step": 284000 + }, + { + "epoch": 7.77, + "learning_rate": 9.248315899008709e-06, + "loss": 6.0789, + "step": 284500 + }, + { + "epoch": 7.78, + "learning_rate": 9.24694671121091e-06, + "loss": 6.0803, + "step": 285000 + }, + { + "epoch": 7.8, + "learning_rate": 9.245577523413112e-06, + "loss": 6.0823, + "step": 285500 + }, + { + "epoch": 7.81, + "learning_rate": 9.244208335615313e-06, + "loss": 6.0799, + "step": 286000 + }, + { + "epoch": 7.82, + "learning_rate": 9.242839147817514e-06, + "loss": 6.0789, + "step": 286500 + }, + { + "epoch": 7.84, + "learning_rate": 9.241469960019717e-06, + "loss": 6.0785, + "step": 287000 + }, + { + "epoch": 7.85, + "learning_rate": 9.240100772221918e-06, + "loss": 6.0784, + "step": 287500 + }, + { + "epoch": 7.86, + "learning_rate": 9.238731584424119e-06, + "loss": 6.0766, + "step": 288000 + }, + { + "epoch": 7.88, + "learning_rate": 9.237362396626322e-06, + "loss": 6.0789, + "step": 288500 + }, + { + "epoch": 7.89, + "learning_rate": 9.235993208828523e-06, + "loss": 6.0777, + "step": 289000 + }, + { + "epoch": 7.91, + "learning_rate": 9.234624021030726e-06, + "loss": 6.0783, + "step": 289500 + }, + { + "epoch": 7.92, + "learning_rate": 9.233254833232928e-06, + "loss": 6.078, + "step": 290000 + }, + { + "epoch": 7.93, + "learning_rate": 9.23188564543513e-06, + "loss": 6.0763, + "step": 290500 + }, + { + "epoch": 7.95, + "learning_rate": 9.23051645763733e-06, + "loss": 6.0768, + "step": 291000 + }, + { + "epoch": 7.96, + "learning_rate": 9.229147269839533e-06, + "loss": 6.0749, + "step": 291500 + }, + { + "epoch": 7.97, + "learning_rate": 9.227778082041734e-06, + "loss": 6.0755, + "step": 292000 + }, + { + "epoch": 7.99, + "learning_rate": 9.226408894243935e-06, + "loss": 6.0767, + "step": 292500 + }, + { + "epoch": 8.0, + "learning_rate": 9.225039706446138e-06, + "loss": 6.08, + "step": 293000 + }, + { + "epoch": 8.02, + "learning_rate": 9.223670518648339e-06, + "loss": 6.0729, + "step": 293500 + }, + { + "epoch": 8.03, + "learning_rate": 9.22230133085054e-06, + "loss": 6.077, + "step": 294000 + }, + { + "epoch": 8.04, + "learning_rate": 9.220932143052743e-06, + "loss": 6.073, + "step": 294500 + }, + { + "epoch": 8.06, + "learning_rate": 9.219562955254944e-06, + "loss": 6.0763, + "step": 295000 + }, + { + "epoch": 8.07, + "learning_rate": 9.218193767457145e-06, + "loss": 6.0727, + "step": 295500 + }, + { + "epoch": 8.08, + "learning_rate": 9.216824579659347e-06, + "loss": 6.0739, + "step": 296000 + }, + { + "epoch": 8.1, + "learning_rate": 9.215455391861548e-06, + "loss": 6.0711, + "step": 296500 + }, + { + "epoch": 8.11, + "learning_rate": 9.214086204063751e-06, + "loss": 6.0741, + "step": 297000 + }, + { + "epoch": 8.12, + "learning_rate": 9.212717016265952e-06, + "loss": 6.073, + "step": 297500 + }, + { + "epoch": 8.14, + "learning_rate": 9.211347828468153e-06, + "loss": 6.0707, + "step": 298000 + }, + { + "epoch": 8.15, + "learning_rate": 9.209978640670356e-06, + "loss": 6.0749, + "step": 298500 + }, + { + "epoch": 8.17, + "learning_rate": 9.208609452872557e-06, + "loss": 6.0747, + "step": 299000 + }, + { + "epoch": 8.18, + "learning_rate": 9.207240265074758e-06, + "loss": 6.0751, + "step": 299500 + }, + { + "epoch": 8.19, + "learning_rate": 9.20587107727696e-06, + "loss": 6.0745, + "step": 300000 + }, + { + "epoch": 8.21, + "learning_rate": 9.204501889479162e-06, + "loss": 6.0757, + "step": 300500 + }, + { + "epoch": 8.22, + "learning_rate": 9.203132701681363e-06, + "loss": 6.0738, + "step": 301000 + }, + { + "epoch": 8.23, + "learning_rate": 9.201763513883565e-06, + "loss": 6.0727, + "step": 301500 + }, + { + "epoch": 8.25, + "learning_rate": 9.200394326085766e-06, + "loss": 6.0715, + "step": 302000 + }, + { + "epoch": 8.26, + "learning_rate": 9.199025138287967e-06, + "loss": 6.0762, + "step": 302500 + }, + { + "epoch": 8.27, + "learning_rate": 9.19765595049017e-06, + "loss": 6.0726, + "step": 303000 + }, + { + "epoch": 8.29, + "learning_rate": 9.196286762692371e-06, + "loss": 6.076, + "step": 303500 + }, + { + "epoch": 8.3, + "learning_rate": 9.194917574894572e-06, + "loss": 6.0804, + "step": 304000 + }, + { + "epoch": 8.32, + "learning_rate": 9.193548387096775e-06, + "loss": 6.0756, + "step": 304500 + }, + { + "epoch": 8.33, + "learning_rate": 9.192179199298976e-06, + "loss": 6.0708, + "step": 305000 + }, + { + "epoch": 8.34, + "learning_rate": 9.190810011501179e-06, + "loss": 6.0709, + "step": 305500 + }, + { + "epoch": 8.36, + "learning_rate": 9.18944082370338e-06, + "loss": 6.0728, + "step": 306000 + }, + { + "epoch": 8.37, + "learning_rate": 9.18807163590558e-06, + "loss": 6.0738, + "step": 306500 + }, + { + "epoch": 8.38, + "learning_rate": 9.186702448107783e-06, + "loss": 6.0703, + "step": 307000 + }, + { + "epoch": 8.4, + "learning_rate": 9.185333260309986e-06, + "loss": 6.0734, + "step": 307500 + }, + { + "epoch": 8.41, + "learning_rate": 9.183964072512187e-06, + "loss": 6.0685, + "step": 308000 + }, + { + "epoch": 8.42, + "learning_rate": 9.182594884714388e-06, + "loss": 6.0707, + "step": 308500 + }, + { + "epoch": 8.44, + "learning_rate": 9.18122569691659e-06, + "loss": 6.0663, + "step": 309000 + }, + { + "epoch": 8.45, + "learning_rate": 9.179856509118792e-06, + "loss": 6.0694, + "step": 309500 + }, + { + "epoch": 8.47, + "learning_rate": 9.178487321320993e-06, + "loss": 6.0729, + "step": 310000 + }, + { + "epoch": 8.48, + "learning_rate": 9.177118133523196e-06, + "loss": 6.0712, + "step": 310500 + }, + { + "epoch": 8.49, + "learning_rate": 9.175748945725397e-06, + "loss": 6.0726, + "step": 311000 + }, + { + "epoch": 8.51, + "learning_rate": 9.174379757927598e-06, + "loss": 6.07, + "step": 311500 + }, + { + "epoch": 8.52, + "learning_rate": 9.1730105701298e-06, + "loss": 6.0679, + "step": 312000 + }, + { + "epoch": 8.53, + "learning_rate": 9.171641382332001e-06, + "loss": 6.067, + "step": 312500 + }, + { + "epoch": 8.55, + "learning_rate": 9.170272194534204e-06, + "loss": 6.0697, + "step": 313000 + }, + { + "epoch": 8.56, + "learning_rate": 9.168903006736405e-06, + "loss": 6.0712, + "step": 313500 + }, + { + "epoch": 8.58, + "learning_rate": 9.167533818938606e-06, + "loss": 6.0707, + "step": 314000 + }, + { + "epoch": 8.59, + "learning_rate": 9.166164631140809e-06, + "loss": 6.0682, + "step": 314500 + }, + { + "epoch": 8.6, + "learning_rate": 9.16479544334301e-06, + "loss": 6.0691, + "step": 315000 + }, + { + "epoch": 8.62, + "learning_rate": 9.16342625554521e-06, + "loss": 6.067, + "step": 315500 + }, + { + "epoch": 8.63, + "learning_rate": 9.162057067747414e-06, + "loss": 6.0691, + "step": 316000 + }, + { + "epoch": 8.64, + "learning_rate": 9.160687879949615e-06, + "loss": 6.0678, + "step": 316500 + }, + { + "epoch": 8.66, + "learning_rate": 9.159318692151816e-06, + "loss": 6.07, + "step": 317000 + }, + { + "epoch": 8.67, + "learning_rate": 9.157949504354018e-06, + "loss": 6.0679, + "step": 317500 + }, + { + "epoch": 8.68, + "learning_rate": 9.15658031655622e-06, + "loss": 6.0707, + "step": 318000 + }, + { + "epoch": 8.7, + "learning_rate": 9.15521112875842e-06, + "loss": 6.07, + "step": 318500 + }, + { + "epoch": 8.71, + "learning_rate": 9.153841940960623e-06, + "loss": 6.0662, + "step": 319000 + }, + { + "epoch": 8.73, + "learning_rate": 9.152472753162824e-06, + "loss": 6.0627, + "step": 319500 + }, + { + "epoch": 8.74, + "learning_rate": 9.151103565365027e-06, + "loss": 6.0685, + "step": 320000 + }, + { + "epoch": 8.75, + "learning_rate": 9.149734377567228e-06, + "loss": 6.0708, + "step": 320500 + }, + { + "epoch": 8.77, + "learning_rate": 9.148365189769429e-06, + "loss": 6.0659, + "step": 321000 + }, + { + "epoch": 8.78, + "learning_rate": 9.146996001971632e-06, + "loss": 6.068, + "step": 321500 + }, + { + "epoch": 8.79, + "learning_rate": 9.145626814173833e-06, + "loss": 6.0655, + "step": 322000 + }, + { + "epoch": 8.81, + "learning_rate": 9.144257626376034e-06, + "loss": 6.0696, + "step": 322500 + }, + { + "epoch": 8.82, + "learning_rate": 9.142888438578236e-06, + "loss": 6.0673, + "step": 323000 + }, + { + "epoch": 8.83, + "learning_rate": 9.141519250780437e-06, + "loss": 6.0658, + "step": 323500 + }, + { + "epoch": 8.85, + "learning_rate": 9.140150062982638e-06, + "loss": 6.0671, + "step": 324000 + }, + { + "epoch": 8.86, + "learning_rate": 9.138780875184841e-06, + "loss": 6.0665, + "step": 324500 + }, + { + "epoch": 8.88, + "learning_rate": 9.137411687387042e-06, + "loss": 6.063, + "step": 325000 + }, + { + "epoch": 8.89, + "learning_rate": 9.136042499589245e-06, + "loss": 6.0632, + "step": 325500 + }, + { + "epoch": 8.9, + "learning_rate": 9.134673311791446e-06, + "loss": 6.0676, + "step": 326000 + }, + { + "epoch": 8.92, + "learning_rate": 9.133304123993649e-06, + "loss": 6.0636, + "step": 326500 + }, + { + "epoch": 8.93, + "learning_rate": 9.13193493619585e-06, + "loss": 6.0673, + "step": 327000 + }, + { + "epoch": 8.94, + "learning_rate": 9.130565748398052e-06, + "loss": 6.0628, + "step": 327500 + }, + { + "epoch": 8.96, + "learning_rate": 9.129196560600253e-06, + "loss": 6.0656, + "step": 328000 + }, + { + "epoch": 8.97, + "learning_rate": 9.127827372802454e-06, + "loss": 6.064, + "step": 328500 + }, + { + "epoch": 8.98, + "learning_rate": 9.126458185004657e-06, + "loss": 6.0658, + "step": 329000 + }, + { + "epoch": 9.0, + "learning_rate": 9.125088997206858e-06, + "loss": 6.0635, + "step": 329500 + }, + { + "epoch": 9.01, + "learning_rate": 9.123719809409059e-06, + "loss": 6.0656, + "step": 330000 + }, + { + "epoch": 9.03, + "learning_rate": 9.122350621611262e-06, + "loss": 6.0619, + "step": 330500 + }, + { + "epoch": 9.04, + "learning_rate": 9.120981433813463e-06, + "loss": 6.0607, + "step": 331000 + }, + { + "epoch": 9.05, + "learning_rate": 9.119612246015664e-06, + "loss": 6.07, + "step": 331500 + }, + { + "epoch": 9.07, + "learning_rate": 9.118243058217867e-06, + "loss": 6.0646, + "step": 332000 + }, + { + "epoch": 9.08, + "learning_rate": 9.116873870420068e-06, + "loss": 6.0623, + "step": 332500 + }, + { + "epoch": 9.09, + "learning_rate": 9.115504682622269e-06, + "loss": 6.0651, + "step": 333000 + }, + { + "epoch": 9.11, + "learning_rate": 9.114135494824471e-06, + "loss": 6.0643, + "step": 333500 + }, + { + "epoch": 9.12, + "learning_rate": 9.112766307026672e-06, + "loss": 6.0617, + "step": 334000 + }, + { + "epoch": 9.13, + "learning_rate": 9.111397119228873e-06, + "loss": 6.0618, + "step": 334500 + }, + { + "epoch": 9.15, + "learning_rate": 9.110027931431076e-06, + "loss": 6.065, + "step": 335000 + }, + { + "epoch": 9.16, + "learning_rate": 9.108658743633277e-06, + "loss": 6.0656, + "step": 335500 + }, + { + "epoch": 9.18, + "learning_rate": 9.10728955583548e-06, + "loss": 6.0626, + "step": 336000 + }, + { + "epoch": 9.19, + "learning_rate": 9.10592036803768e-06, + "loss": 6.0623, + "step": 336500 + }, + { + "epoch": 9.2, + "learning_rate": 9.104551180239882e-06, + "loss": 6.0619, + "step": 337000 + }, + { + "epoch": 9.22, + "learning_rate": 9.103181992442085e-06, + "loss": 6.06, + "step": 337500 + }, + { + "epoch": 9.23, + "learning_rate": 9.101812804644286e-06, + "loss": 6.0643, + "step": 338000 + }, + { + "epoch": 9.24, + "learning_rate": 9.100443616846487e-06, + "loss": 6.0631, + "step": 338500 + }, + { + "epoch": 9.26, + "learning_rate": 9.09907442904869e-06, + "loss": 6.0613, + "step": 339000 + }, + { + "epoch": 9.27, + "learning_rate": 9.09770524125089e-06, + "loss": 6.0598, + "step": 339500 + }, + { + "epoch": 9.29, + "learning_rate": 9.096336053453091e-06, + "loss": 6.0634, + "step": 340000 + }, + { + "epoch": 9.3, + "learning_rate": 9.094966865655294e-06, + "loss": 6.0626, + "step": 340500 + }, + { + "epoch": 9.31, + "learning_rate": 9.093597677857495e-06, + "loss": 6.0625, + "step": 341000 + }, + { + "epoch": 9.33, + "learning_rate": 9.092228490059696e-06, + "loss": 6.0597, + "step": 341500 + }, + { + "epoch": 9.34, + "learning_rate": 9.090859302261899e-06, + "loss": 6.0621, + "step": 342000 + }, + { + "epoch": 9.35, + "learning_rate": 9.0894901144641e-06, + "loss": 6.063, + "step": 342500 + }, + { + "epoch": 9.37, + "learning_rate": 9.088120926666303e-06, + "loss": 6.057, + "step": 343000 + }, + { + "epoch": 9.38, + "learning_rate": 9.086751738868505e-06, + "loss": 6.0615, + "step": 343500 + }, + { + "epoch": 9.39, + "learning_rate": 9.085382551070706e-06, + "loss": 6.058, + "step": 344000 + }, + { + "epoch": 9.41, + "learning_rate": 9.084013363272907e-06, + "loss": 6.0598, + "step": 344500 + }, + { + "epoch": 9.42, + "learning_rate": 9.08264417547511e-06, + "loss": 6.0599, + "step": 345000 + }, + { + "epoch": 9.44, + "learning_rate": 9.081274987677311e-06, + "loss": 6.0631, + "step": 345500 + }, + { + "epoch": 9.45, + "learning_rate": 9.079905799879512e-06, + "loss": 6.0653, + "step": 346000 + }, + { + "epoch": 9.46, + "learning_rate": 9.078536612081715e-06, + "loss": 6.0606, + "step": 346500 + }, + { + "epoch": 9.48, + "learning_rate": 9.077167424283916e-06, + "loss": 6.0572, + "step": 347000 + }, + { + "epoch": 9.49, + "learning_rate": 9.075798236486117e-06, + "loss": 6.0604, + "step": 347500 + }, + { + "epoch": 9.5, + "learning_rate": 9.07442904868832e-06, + "loss": 6.0635, + "step": 348000 + }, + { + "epoch": 9.52, + "learning_rate": 9.07305986089052e-06, + "loss": 6.0581, + "step": 348500 + }, + { + "epoch": 9.53, + "learning_rate": 9.071690673092722e-06, + "loss": 6.0592, + "step": 349000 + }, + { + "epoch": 9.54, + "learning_rate": 9.070321485294924e-06, + "loss": 6.0596, + "step": 349500 + }, + { + "epoch": 9.56, + "learning_rate": 9.068952297497125e-06, + "loss": 6.0633, + "step": 350000 + }, + { + "epoch": 9.57, + "learning_rate": 9.067583109699328e-06, + "loss": 6.0562, + "step": 350500 + }, + { + "epoch": 9.59, + "learning_rate": 9.066213921901529e-06, + "loss": 6.0571, + "step": 351000 + }, + { + "epoch": 9.6, + "learning_rate": 9.06484473410373e-06, + "loss": 6.0602, + "step": 351500 + }, + { + "epoch": 9.61, + "learning_rate": 9.063475546305933e-06, + "loss": 6.057, + "step": 352000 + }, + { + "epoch": 9.63, + "learning_rate": 9.062106358508134e-06, + "loss": 6.0562, + "step": 352500 + }, + { + "epoch": 9.64, + "learning_rate": 9.060737170710335e-06, + "loss": 6.0565, + "step": 353000 + }, + { + "epoch": 9.65, + "learning_rate": 9.059367982912538e-06, + "loss": 6.0602, + "step": 353500 + }, + { + "epoch": 9.67, + "learning_rate": 9.057998795114739e-06, + "loss": 6.0576, + "step": 354000 + }, + { + "epoch": 9.68, + "learning_rate": 9.05662960731694e-06, + "loss": 6.0583, + "step": 354500 + }, + { + "epoch": 9.69, + "learning_rate": 9.055260419519142e-06, + "loss": 6.0586, + "step": 355000 + }, + { + "epoch": 9.71, + "learning_rate": 9.053891231721343e-06, + "loss": 6.0598, + "step": 355500 + }, + { + "epoch": 9.72, + "learning_rate": 9.052522043923544e-06, + "loss": 6.058, + "step": 356000 + }, + { + "epoch": 9.74, + "learning_rate": 9.051152856125747e-06, + "loss": 6.0576, + "step": 356500 + }, + { + "epoch": 9.75, + "learning_rate": 9.049783668327948e-06, + "loss": 6.0587, + "step": 357000 + }, + { + "epoch": 9.76, + "learning_rate": 9.048414480530149e-06, + "loss": 6.0598, + "step": 357500 + }, + { + "epoch": 9.78, + "learning_rate": 9.047045292732352e-06, + "loss": 6.0527, + "step": 358000 + }, + { + "epoch": 9.79, + "learning_rate": 9.045676104934553e-06, + "loss": 6.0546, + "step": 358500 + }, + { + "epoch": 9.8, + "learning_rate": 9.044306917136756e-06, + "loss": 6.0594, + "step": 359000 + }, + { + "epoch": 9.82, + "learning_rate": 9.042937729338957e-06, + "loss": 6.0563, + "step": 359500 + }, + { + "epoch": 9.83, + "learning_rate": 9.041568541541158e-06, + "loss": 6.0595, + "step": 360000 + }, + { + "epoch": 9.84, + "learning_rate": 9.04019935374336e-06, + "loss": 6.0514, + "step": 360500 + }, + { + "epoch": 9.86, + "learning_rate": 9.038830165945561e-06, + "loss": 6.0583, + "step": 361000 + }, + { + "epoch": 9.87, + "learning_rate": 9.037460978147764e-06, + "loss": 6.0572, + "step": 361500 + }, + { + "epoch": 9.89, + "learning_rate": 9.036091790349965e-06, + "loss": 6.0542, + "step": 362000 + }, + { + "epoch": 9.9, + "learning_rate": 9.034722602552168e-06, + "loss": 6.0557, + "step": 362500 + }, + { + "epoch": 9.91, + "learning_rate": 9.033353414754369e-06, + "loss": 6.0544, + "step": 363000 + }, + { + "epoch": 9.93, + "learning_rate": 9.03198422695657e-06, + "loss": 6.0528, + "step": 363500 + }, + { + "epoch": 9.94, + "learning_rate": 9.030615039158773e-06, + "loss": 6.0564, + "step": 364000 + }, + { + "epoch": 9.95, + "learning_rate": 9.029245851360974e-06, + "loss": 6.0532, + "step": 364500 + }, + { + "epoch": 9.97, + "learning_rate": 9.027876663563175e-06, + "loss": 6.0586, + "step": 365000 + }, + { + "epoch": 9.98, + "learning_rate": 9.026507475765377e-06, + "loss": 6.0498, + "step": 365500 + }, + { + "epoch": 10.0, + "learning_rate": 9.025138287967578e-06, + "loss": 6.0514, + "step": 366000 + }, + { + "epoch": 10.01, + "learning_rate": 9.023769100169781e-06, + "loss": 6.055, + "step": 366500 + }, + { + "epoch": 10.02, + "learning_rate": 9.022399912371982e-06, + "loss": 6.0567, + "step": 367000 + }, + { + "epoch": 10.04, + "learning_rate": 9.021030724574183e-06, + "loss": 6.0514, + "step": 367500 + }, + { + "epoch": 10.05, + "learning_rate": 9.019661536776386e-06, + "loss": 6.0566, + "step": 368000 + }, + { + "epoch": 10.06, + "learning_rate": 9.018292348978587e-06, + "loss": 6.0541, + "step": 368500 + }, + { + "epoch": 10.08, + "learning_rate": 9.016923161180788e-06, + "loss": 6.0518, + "step": 369000 + }, + { + "epoch": 10.09, + "learning_rate": 9.01555397338299e-06, + "loss": 6.0537, + "step": 369500 + }, + { + "epoch": 10.1, + "learning_rate": 9.014184785585192e-06, + "loss": 6.0526, + "step": 370000 + }, + { + "epoch": 10.12, + "learning_rate": 9.012815597787393e-06, + "loss": 6.0559, + "step": 370500 + }, + { + "epoch": 10.13, + "learning_rate": 9.011446409989595e-06, + "loss": 6.0543, + "step": 371000 + }, + { + "epoch": 10.15, + "learning_rate": 9.010077222191796e-06, + "loss": 6.053, + "step": 371500 + }, + { + "epoch": 10.16, + "learning_rate": 9.008708034393997e-06, + "loss": 6.0512, + "step": 372000 + }, + { + "epoch": 10.17, + "learning_rate": 9.0073388465962e-06, + "loss": 6.0512, + "step": 372500 + }, + { + "epoch": 10.19, + "learning_rate": 9.005969658798401e-06, + "loss": 6.054, + "step": 373000 + }, + { + "epoch": 10.2, + "learning_rate": 9.004600471000604e-06, + "loss": 6.0528, + "step": 373500 + }, + { + "epoch": 10.21, + "learning_rate": 9.003231283202805e-06, + "loss": 6.0489, + "step": 374000 + }, + { + "epoch": 10.23, + "learning_rate": 9.001862095405006e-06, + "loss": 6.0529, + "step": 374500 + }, + { + "epoch": 10.24, + "learning_rate": 9.000492907607209e-06, + "loss": 6.0511, + "step": 375000 + }, + { + "epoch": 10.25, + "learning_rate": 8.99912371980941e-06, + "loss": 6.0532, + "step": 375500 + }, + { + "epoch": 10.27, + "learning_rate": 8.99775453201161e-06, + "loss": 6.0484, + "step": 376000 + }, + { + "epoch": 10.28, + "learning_rate": 8.996385344213813e-06, + "loss": 6.0569, + "step": 376500 + }, + { + "epoch": 10.3, + "learning_rate": 8.995016156416014e-06, + "loss": 6.0532, + "step": 377000 + }, + { + "epoch": 10.31, + "learning_rate": 8.993646968618215e-06, + "loss": 6.0518, + "step": 377500 + }, + { + "epoch": 10.32, + "learning_rate": 8.992277780820418e-06, + "loss": 6.0494, + "step": 378000 + }, + { + "epoch": 10.34, + "learning_rate": 8.990908593022619e-06, + "loss": 6.0522, + "step": 378500 + }, + { + "epoch": 10.35, + "learning_rate": 8.98953940522482e-06, + "loss": 6.051, + "step": 379000 + }, + { + "epoch": 10.36, + "learning_rate": 8.988170217427023e-06, + "loss": 6.0513, + "step": 379500 + }, + { + "epoch": 10.38, + "learning_rate": 8.986801029629226e-06, + "loss": 6.0533, + "step": 380000 + }, + { + "epoch": 10.39, + "learning_rate": 8.985431841831427e-06, + "loss": 6.0485, + "step": 380500 + }, + { + "epoch": 10.4, + "learning_rate": 8.98406265403363e-06, + "loss": 6.0511, + "step": 381000 + }, + { + "epoch": 10.42, + "learning_rate": 8.98269346623583e-06, + "loss": 6.0529, + "step": 381500 + }, + { + "epoch": 10.43, + "learning_rate": 8.981324278438031e-06, + "loss": 6.0486, + "step": 382000 + }, + { + "epoch": 10.45, + "learning_rate": 8.979955090640234e-06, + "loss": 6.0513, + "step": 382500 + }, + { + "epoch": 10.46, + "learning_rate": 8.978585902842435e-06, + "loss": 6.0528, + "step": 383000 + }, + { + "epoch": 10.47, + "learning_rate": 8.977216715044636e-06, + "loss": 6.0513, + "step": 383500 + }, + { + "epoch": 10.49, + "learning_rate": 8.975847527246839e-06, + "loss": 6.0511, + "step": 384000 + }, + { + "epoch": 10.5, + "learning_rate": 8.97447833944904e-06, + "loss": 6.0497, + "step": 384500 + }, + { + "epoch": 10.51, + "learning_rate": 8.97310915165124e-06, + "loss": 6.0509, + "step": 385000 + }, + { + "epoch": 10.53, + "learning_rate": 8.971739963853444e-06, + "loss": 6.0497, + "step": 385500 + }, + { + "epoch": 10.54, + "learning_rate": 8.970370776055645e-06, + "loss": 6.0509, + "step": 386000 + }, + { + "epoch": 10.55, + "learning_rate": 8.969001588257846e-06, + "loss": 6.0501, + "step": 386500 + }, + { + "epoch": 10.57, + "learning_rate": 8.967632400460048e-06, + "loss": 6.0482, + "step": 387000 + }, + { + "epoch": 10.58, + "learning_rate": 8.96626321266225e-06, + "loss": 6.0502, + "step": 387500 + }, + { + "epoch": 10.6, + "learning_rate": 8.96489402486445e-06, + "loss": 6.0486, + "step": 388000 + }, + { + "epoch": 10.61, + "learning_rate": 8.963524837066653e-06, + "loss": 6.0546, + "step": 388500 + }, + { + "epoch": 10.62, + "learning_rate": 8.962155649268854e-06, + "loss": 6.0488, + "step": 389000 + }, + { + "epoch": 10.64, + "learning_rate": 8.960786461471057e-06, + "loss": 6.0476, + "step": 389500 + }, + { + "epoch": 10.65, + "learning_rate": 8.959417273673258e-06, + "loss": 6.0503, + "step": 390000 + }, + { + "epoch": 10.66, + "learning_rate": 8.958048085875459e-06, + "loss": 6.0499, + "step": 390500 + }, + { + "epoch": 10.68, + "learning_rate": 8.956678898077662e-06, + "loss": 6.0487, + "step": 391000 + }, + { + "epoch": 10.69, + "learning_rate": 8.955309710279863e-06, + "loss": 6.0525, + "step": 391500 + }, + { + "epoch": 10.71, + "learning_rate": 8.953940522482064e-06, + "loss": 6.0478, + "step": 392000 + }, + { + "epoch": 10.72, + "learning_rate": 8.952571334684266e-06, + "loss": 6.0457, + "step": 392500 + }, + { + "epoch": 10.73, + "learning_rate": 8.951202146886467e-06, + "loss": 6.0497, + "step": 393000 + }, + { + "epoch": 10.75, + "learning_rate": 8.949832959088668e-06, + "loss": 6.0443, + "step": 393500 + }, + { + "epoch": 10.76, + "learning_rate": 8.948463771290871e-06, + "loss": 6.0462, + "step": 394000 + }, + { + "epoch": 10.77, + "learning_rate": 8.947094583493072e-06, + "loss": 6.0487, + "step": 394500 + }, + { + "epoch": 10.79, + "learning_rate": 8.945725395695273e-06, + "loss": 6.047, + "step": 395000 + }, + { + "epoch": 10.8, + "learning_rate": 8.944356207897476e-06, + "loss": 6.0471, + "step": 395500 + }, + { + "epoch": 10.81, + "learning_rate": 8.942987020099677e-06, + "loss": 6.0464, + "step": 396000 + }, + { + "epoch": 10.83, + "learning_rate": 8.94161783230188e-06, + "loss": 6.0501, + "step": 396500 + }, + { + "epoch": 10.84, + "learning_rate": 8.94024864450408e-06, + "loss": 6.0485, + "step": 397000 + }, + { + "epoch": 10.86, + "learning_rate": 8.938879456706283e-06, + "loss": 6.0468, + "step": 397500 + }, + { + "epoch": 10.87, + "learning_rate": 8.937510268908484e-06, + "loss": 6.0441, + "step": 398000 + }, + { + "epoch": 10.88, + "learning_rate": 8.936141081110687e-06, + "loss": 6.0464, + "step": 398500 + }, + { + "epoch": 10.9, + "learning_rate": 8.934771893312888e-06, + "loss": 6.0473, + "step": 399000 + }, + { + "epoch": 10.91, + "learning_rate": 8.933402705515089e-06, + "loss": 6.0441, + "step": 399500 + }, + { + "epoch": 10.92, + "learning_rate": 8.932033517717292e-06, + "loss": 6.0457, + "step": 400000 + }, + { + "epoch": 10.94, + "learning_rate": 8.930664329919493e-06, + "loss": 6.0446, + "step": 400500 + }, + { + "epoch": 10.95, + "learning_rate": 8.929295142121694e-06, + "loss": 6.0478, + "step": 401000 + }, + { + "epoch": 10.96, + "learning_rate": 8.927925954323897e-06, + "loss": 6.0465, + "step": 401500 + }, + { + "epoch": 10.98, + "learning_rate": 8.926556766526098e-06, + "loss": 6.0435, + "step": 402000 + }, + { + "epoch": 10.99, + "learning_rate": 8.925187578728299e-06, + "loss": 6.0434, + "step": 402500 + }, + { + "epoch": 11.01, + "learning_rate": 8.923818390930501e-06, + "loss": 6.0475, + "step": 403000 + }, + { + "epoch": 11.02, + "learning_rate": 8.922449203132702e-06, + "loss": 6.0473, + "step": 403500 + }, + { + "epoch": 11.03, + "learning_rate": 8.921080015334905e-06, + "loss": 6.0487, + "step": 404000 + }, + { + "epoch": 11.05, + "learning_rate": 8.919710827537106e-06, + "loss": 6.042, + "step": 404500 + }, + { + "epoch": 11.06, + "learning_rate": 8.918341639739307e-06, + "loss": 6.0404, + "step": 405000 + }, + { + "epoch": 11.07, + "learning_rate": 8.91697245194151e-06, + "loss": 6.0454, + "step": 405500 + }, + { + "epoch": 11.09, + "learning_rate": 8.91560326414371e-06, + "loss": 6.0472, + "step": 406000 + }, + { + "epoch": 11.1, + "learning_rate": 8.914234076345912e-06, + "loss": 6.0468, + "step": 406500 + }, + { + "epoch": 11.11, + "learning_rate": 8.912864888548115e-06, + "loss": 6.0423, + "step": 407000 + }, + { + "epoch": 11.13, + "learning_rate": 8.911495700750316e-06, + "loss": 6.0425, + "step": 407500 + }, + { + "epoch": 11.14, + "learning_rate": 8.910126512952517e-06, + "loss": 6.0427, + "step": 408000 + }, + { + "epoch": 11.16, + "learning_rate": 8.90875732515472e-06, + "loss": 6.0417, + "step": 408500 + }, + { + "epoch": 11.17, + "learning_rate": 8.90738813735692e-06, + "loss": 6.0479, + "step": 409000 + }, + { + "epoch": 11.18, + "learning_rate": 8.906018949559121e-06, + "loss": 6.0465, + "step": 409500 + }, + { + "epoch": 11.2, + "learning_rate": 8.904649761761324e-06, + "loss": 6.0452, + "step": 410000 + }, + { + "epoch": 11.21, + "learning_rate": 8.903280573963525e-06, + "loss": 6.0462, + "step": 410500 + }, + { + "epoch": 11.22, + "learning_rate": 8.901911386165726e-06, + "loss": 6.0425, + "step": 411000 + }, + { + "epoch": 11.24, + "learning_rate": 8.900542198367929e-06, + "loss": 6.042, + "step": 411500 + }, + { + "epoch": 11.25, + "learning_rate": 8.89917301057013e-06, + "loss": 6.0424, + "step": 412000 + }, + { + "epoch": 11.26, + "learning_rate": 8.897803822772333e-06, + "loss": 6.0488, + "step": 412500 + }, + { + "epoch": 11.28, + "learning_rate": 8.896434634974534e-06, + "loss": 6.0441, + "step": 413000 + }, + { + "epoch": 11.29, + "learning_rate": 8.895065447176735e-06, + "loss": 6.0458, + "step": 413500 + }, + { + "epoch": 11.31, + "learning_rate": 8.893696259378937e-06, + "loss": 6.0401, + "step": 414000 + }, + { + "epoch": 11.32, + "learning_rate": 8.892327071581138e-06, + "loss": 6.0463, + "step": 414500 + }, + { + "epoch": 11.33, + "learning_rate": 8.89095788378334e-06, + "loss": 6.044, + "step": 415000 + }, + { + "epoch": 11.35, + "learning_rate": 8.889588695985542e-06, + "loss": 6.0458, + "step": 415500 + }, + { + "epoch": 11.36, + "learning_rate": 8.888219508187745e-06, + "loss": 6.0448, + "step": 416000 + }, + { + "epoch": 11.37, + "learning_rate": 8.886850320389946e-06, + "loss": 6.0406, + "step": 416500 + }, + { + "epoch": 11.39, + "learning_rate": 8.885481132592147e-06, + "loss": 6.0425, + "step": 417000 + }, + { + "epoch": 11.4, + "learning_rate": 8.88411194479435e-06, + "loss": 6.043, + "step": 417500 + }, + { + "epoch": 11.42, + "learning_rate": 8.88274275699655e-06, + "loss": 6.0398, + "step": 418000 + }, + { + "epoch": 11.43, + "learning_rate": 8.881373569198752e-06, + "loss": 6.047, + "step": 418500 + }, + { + "epoch": 11.44, + "learning_rate": 8.880004381400954e-06, + "loss": 6.0421, + "step": 419000 + }, + { + "epoch": 11.46, + "learning_rate": 8.878635193603155e-06, + "loss": 6.0403, + "step": 419500 + }, + { + "epoch": 11.47, + "learning_rate": 8.877266005805358e-06, + "loss": 6.0415, + "step": 420000 + }, + { + "epoch": 11.48, + "learning_rate": 8.875896818007559e-06, + "loss": 6.0418, + "step": 420500 + }, + { + "epoch": 11.5, + "learning_rate": 8.87452763020976e-06, + "loss": 6.0432, + "step": 421000 + }, + { + "epoch": 11.51, + "learning_rate": 8.873158442411963e-06, + "loss": 6.0433, + "step": 421500 + }, + { + "epoch": 11.52, + "learning_rate": 8.871789254614164e-06, + "loss": 6.0421, + "step": 422000 + }, + { + "epoch": 11.54, + "learning_rate": 8.870420066816365e-06, + "loss": 6.0446, + "step": 422500 + }, + { + "epoch": 11.55, + "learning_rate": 8.869050879018568e-06, + "loss": 6.0427, + "step": 423000 + }, + { + "epoch": 11.57, + "learning_rate": 8.867681691220769e-06, + "loss": 6.0424, + "step": 423500 + }, + { + "epoch": 11.58, + "learning_rate": 8.86631250342297e-06, + "loss": 6.0475, + "step": 424000 + }, + { + "epoch": 11.59, + "learning_rate": 8.864943315625172e-06, + "loss": 6.0363, + "step": 424500 + }, + { + "epoch": 11.61, + "learning_rate": 8.863574127827373e-06, + "loss": 6.0423, + "step": 425000 + }, + { + "epoch": 11.62, + "learning_rate": 8.862204940029574e-06, + "loss": 6.0435, + "step": 425500 + }, + { + "epoch": 11.63, + "learning_rate": 8.860835752231777e-06, + "loss": 6.0415, + "step": 426000 + }, + { + "epoch": 11.65, + "learning_rate": 8.859466564433978e-06, + "loss": 6.0367, + "step": 426500 + }, + { + "epoch": 11.66, + "learning_rate": 8.85809737663618e-06, + "loss": 6.0409, + "step": 427000 + }, + { + "epoch": 11.67, + "learning_rate": 8.856728188838382e-06, + "loss": 6.0418, + "step": 427500 + }, + { + "epoch": 11.69, + "learning_rate": 8.855359001040583e-06, + "loss": 6.0401, + "step": 428000 + }, + { + "epoch": 11.7, + "learning_rate": 8.853989813242786e-06, + "loss": 6.0417, + "step": 428500 + }, + { + "epoch": 11.72, + "learning_rate": 8.852620625444987e-06, + "loss": 6.0384, + "step": 429000 + }, + { + "epoch": 11.73, + "learning_rate": 8.851251437647188e-06, + "loss": 6.042, + "step": 429500 + }, + { + "epoch": 11.74, + "learning_rate": 8.84988224984939e-06, + "loss": 6.0397, + "step": 430000 + }, + { + "epoch": 11.76, + "learning_rate": 8.848513062051591e-06, + "loss": 6.041, + "step": 430500 + }, + { + "epoch": 11.77, + "learning_rate": 8.847143874253792e-06, + "loss": 6.0429, + "step": 431000 + }, + { + "epoch": 11.78, + "learning_rate": 8.845774686455995e-06, + "loss": 6.0418, + "step": 431500 + }, + { + "epoch": 11.8, + "learning_rate": 8.844405498658196e-06, + "loss": 6.0435, + "step": 432000 + }, + { + "epoch": 11.81, + "learning_rate": 8.843036310860397e-06, + "loss": 6.0379, + "step": 432500 + }, + { + "epoch": 11.82, + "learning_rate": 8.8416671230626e-06, + "loss": 6.0401, + "step": 433000 + }, + { + "epoch": 11.84, + "learning_rate": 8.840297935264803e-06, + "loss": 6.0429, + "step": 433500 + }, + { + "epoch": 11.85, + "learning_rate": 8.838928747467004e-06, + "loss": 6.0401, + "step": 434000 + }, + { + "epoch": 11.87, + "learning_rate": 8.837559559669206e-06, + "loss": 6.042, + "step": 434500 + }, + { + "epoch": 11.88, + "learning_rate": 8.836190371871407e-06, + "loss": 6.0396, + "step": 435000 + }, + { + "epoch": 11.89, + "learning_rate": 8.834821184073608e-06, + "loss": 6.0374, + "step": 435500 + }, + { + "epoch": 11.91, + "learning_rate": 8.833451996275811e-06, + "loss": 6.0383, + "step": 436000 + }, + { + "epoch": 11.92, + "learning_rate": 8.832082808478012e-06, + "loss": 6.0345, + "step": 436500 + }, + { + "epoch": 11.93, + "learning_rate": 8.830713620680213e-06, + "loss": 6.0369, + "step": 437000 + }, + { + "epoch": 11.95, + "learning_rate": 8.829344432882416e-06, + "loss": 6.038, + "step": 437500 + }, + { + "epoch": 11.96, + "learning_rate": 8.827975245084617e-06, + "loss": 6.0376, + "step": 438000 + }, + { + "epoch": 11.97, + "learning_rate": 8.826606057286818e-06, + "loss": 6.0361, + "step": 438500 + }, + { + "epoch": 11.99, + "learning_rate": 8.82523686948902e-06, + "loss": 6.0419, + "step": 439000 + }, + { + "epoch": 12.0, + "learning_rate": 8.823867681691222e-06, + "loss": 6.0366, + "step": 439500 + }, + { + "epoch": 12.02, + "learning_rate": 8.822498493893423e-06, + "loss": 6.0399, + "step": 440000 + }, + { + "epoch": 12.03, + "learning_rate": 8.821129306095625e-06, + "loss": 6.0383, + "step": 440500 + }, + { + "epoch": 12.04, + "learning_rate": 8.819760118297826e-06, + "loss": 6.0357, + "step": 441000 + }, + { + "epoch": 12.06, + "learning_rate": 8.818390930500027e-06, + "loss": 6.0374, + "step": 441500 + }, + { + "epoch": 12.07, + "learning_rate": 8.81702174270223e-06, + "loss": 6.0413, + "step": 442000 + }, + { + "epoch": 12.08, + "learning_rate": 8.815652554904431e-06, + "loss": 6.0396, + "step": 442500 + }, + { + "epoch": 12.1, + "learning_rate": 8.814283367106634e-06, + "loss": 6.0355, + "step": 443000 + }, + { + "epoch": 12.11, + "learning_rate": 8.812914179308835e-06, + "loss": 6.0368, + "step": 443500 + }, + { + "epoch": 12.13, + "learning_rate": 8.811544991511036e-06, + "loss": 6.0396, + "step": 444000 + }, + { + "epoch": 12.14, + "learning_rate": 8.810175803713239e-06, + "loss": 6.04, + "step": 444500 + }, + { + "epoch": 12.15, + "learning_rate": 8.80880661591544e-06, + "loss": 6.0389, + "step": 445000 + }, + { + "epoch": 12.17, + "learning_rate": 8.80743742811764e-06, + "loss": 6.0386, + "step": 445500 + }, + { + "epoch": 12.18, + "learning_rate": 8.806068240319843e-06, + "loss": 6.0405, + "step": 446000 + }, + { + "epoch": 12.19, + "learning_rate": 8.804699052522044e-06, + "loss": 6.0362, + "step": 446500 + }, + { + "epoch": 12.21, + "learning_rate": 8.803329864724245e-06, + "loss": 6.0373, + "step": 447000 + }, + { + "epoch": 12.22, + "learning_rate": 8.801960676926448e-06, + "loss": 6.029, + "step": 447500 + }, + { + "epoch": 12.23, + "learning_rate": 8.800591489128649e-06, + "loss": 6.0384, + "step": 448000 + }, + { + "epoch": 12.25, + "learning_rate": 8.79922230133085e-06, + "loss": 6.0367, + "step": 448500 + }, + { + "epoch": 12.26, + "learning_rate": 8.797853113533053e-06, + "loss": 6.0426, + "step": 449000 + }, + { + "epoch": 12.28, + "learning_rate": 8.796483925735254e-06, + "loss": 6.0356, + "step": 449500 + }, + { + "epoch": 12.29, + "learning_rate": 8.795114737937457e-06, + "loss": 6.0361, + "step": 450000 + }, + { + "epoch": 12.3, + "learning_rate": 8.793745550139658e-06, + "loss": 6.0367, + "step": 450500 + }, + { + "epoch": 12.32, + "learning_rate": 8.792376362341859e-06, + "loss": 6.0335, + "step": 451000 + }, + { + "epoch": 12.33, + "learning_rate": 8.791007174544061e-06, + "loss": 6.0399, + "step": 451500 + }, + { + "epoch": 12.34, + "learning_rate": 8.789637986746264e-06, + "loss": 6.0329, + "step": 452000 + }, + { + "epoch": 12.36, + "learning_rate": 8.788268798948465e-06, + "loss": 6.038, + "step": 452500 + }, + { + "epoch": 12.37, + "learning_rate": 8.786899611150666e-06, + "loss": 6.0355, + "step": 453000 + }, + { + "epoch": 12.38, + "learning_rate": 8.785530423352869e-06, + "loss": 6.0369, + "step": 453500 + }, + { + "epoch": 12.4, + "learning_rate": 8.78416123555507e-06, + "loss": 6.0344, + "step": 454000 + }, + { + "epoch": 12.41, + "learning_rate": 8.78279204775727e-06, + "loss": 6.0346, + "step": 454500 + }, + { + "epoch": 12.43, + "learning_rate": 8.781422859959474e-06, + "loss": 6.0348, + "step": 455000 + }, + { + "epoch": 12.44, + "learning_rate": 8.780053672161675e-06, + "loss": 6.035, + "step": 455500 + }, + { + "epoch": 12.45, + "learning_rate": 8.778684484363876e-06, + "loss": 6.0378, + "step": 456000 + }, + { + "epoch": 12.47, + "learning_rate": 8.777315296566078e-06, + "loss": 6.0338, + "step": 456500 + }, + { + "epoch": 12.48, + "learning_rate": 8.77594610876828e-06, + "loss": 6.0374, + "step": 457000 + }, + { + "epoch": 12.49, + "learning_rate": 8.774576920970482e-06, + "loss": 6.036, + "step": 457500 + }, + { + "epoch": 12.51, + "learning_rate": 8.773207733172683e-06, + "loss": 6.0359, + "step": 458000 + }, + { + "epoch": 12.52, + "learning_rate": 8.771838545374884e-06, + "loss": 6.036, + "step": 458500 + }, + { + "epoch": 12.53, + "learning_rate": 8.770469357577087e-06, + "loss": 6.0358, + "step": 459000 + }, + { + "epoch": 12.55, + "learning_rate": 8.769100169779288e-06, + "loss": 6.0326, + "step": 459500 + }, + { + "epoch": 12.56, + "learning_rate": 8.767730981981489e-06, + "loss": 6.0327, + "step": 460000 + }, + { + "epoch": 12.58, + "learning_rate": 8.766361794183692e-06, + "loss": 6.0337, + "step": 460500 + }, + { + "epoch": 12.59, + "learning_rate": 8.764992606385893e-06, + "loss": 6.0342, + "step": 461000 + }, + { + "epoch": 12.6, + "learning_rate": 8.763623418588094e-06, + "loss": 6.037, + "step": 461500 + }, + { + "epoch": 12.62, + "learning_rate": 8.762254230790296e-06, + "loss": 6.0315, + "step": 462000 + }, + { + "epoch": 12.63, + "learning_rate": 8.760885042992497e-06, + "loss": 6.0333, + "step": 462500 + }, + { + "epoch": 12.64, + "learning_rate": 8.759515855194698e-06, + "loss": 6.0354, + "step": 463000 + }, + { + "epoch": 12.66, + "learning_rate": 8.758146667396901e-06, + "loss": 6.0367, + "step": 463500 + }, + { + "epoch": 12.67, + "learning_rate": 8.756777479599102e-06, + "loss": 6.0346, + "step": 464000 + }, + { + "epoch": 12.69, + "learning_rate": 8.755408291801303e-06, + "loss": 6.028, + "step": 464500 + }, + { + "epoch": 12.7, + "learning_rate": 8.754039104003506e-06, + "loss": 6.0366, + "step": 465000 + }, + { + "epoch": 12.71, + "learning_rate": 8.752669916205707e-06, + "loss": 6.0358, + "step": 465500 + }, + { + "epoch": 12.73, + "learning_rate": 8.75130072840791e-06, + "loss": 6.035, + "step": 466000 + }, + { + "epoch": 12.74, + "learning_rate": 8.74993154061011e-06, + "loss": 6.0334, + "step": 466500 + }, + { + "epoch": 12.75, + "learning_rate": 8.748562352812312e-06, + "loss": 6.0348, + "step": 467000 + }, + { + "epoch": 12.77, + "learning_rate": 8.747193165014514e-06, + "loss": 6.0342, + "step": 467500 + }, + { + "epoch": 12.78, + "learning_rate": 8.745823977216715e-06, + "loss": 6.0346, + "step": 468000 + }, + { + "epoch": 12.79, + "learning_rate": 8.744454789418916e-06, + "loss": 6.0311, + "step": 468500 + }, + { + "epoch": 12.81, + "learning_rate": 8.743085601621119e-06, + "loss": 6.038, + "step": 469000 + }, + { + "epoch": 12.82, + "learning_rate": 8.741716413823322e-06, + "loss": 6.0343, + "step": 469500 + }, + { + "epoch": 12.84, + "learning_rate": 8.740347226025523e-06, + "loss": 6.0341, + "step": 470000 + }, + { + "epoch": 12.85, + "learning_rate": 8.738978038227724e-06, + "loss": 6.0313, + "step": 470500 + }, + { + "epoch": 12.86, + "learning_rate": 8.737608850429927e-06, + "loss": 6.0306, + "step": 471000 + }, + { + "epoch": 12.88, + "learning_rate": 8.736239662632128e-06, + "loss": 6.0343, + "step": 471500 + }, + { + "epoch": 12.89, + "learning_rate": 8.734870474834329e-06, + "loss": 6.035, + "step": 472000 + }, + { + "epoch": 12.9, + "learning_rate": 8.733501287036531e-06, + "loss": 6.0314, + "step": 472500 + }, + { + "epoch": 12.92, + "learning_rate": 8.732132099238732e-06, + "loss": 6.0315, + "step": 473000 + }, + { + "epoch": 12.93, + "learning_rate": 8.730762911440935e-06, + "loss": 6.0299, + "step": 473500 + }, + { + "epoch": 12.94, + "learning_rate": 8.729393723643136e-06, + "loss": 6.0357, + "step": 474000 + }, + { + "epoch": 12.96, + "learning_rate": 8.728024535845337e-06, + "loss": 6.0331, + "step": 474500 + }, + { + "epoch": 12.97, + "learning_rate": 8.72665534804754e-06, + "loss": 6.0336, + "step": 475000 + }, + { + "epoch": 12.99, + "learning_rate": 8.72528616024974e-06, + "loss": 6.0303, + "step": 475500 + }, + { + "epoch": 13.0, + "learning_rate": 8.723916972451942e-06, + "loss": 6.0324, + "step": 476000 + }, + { + "epoch": 13.01, + "learning_rate": 8.722547784654145e-06, + "loss": 6.0318, + "step": 476500 + }, + { + "epoch": 13.03, + "learning_rate": 8.721178596856346e-06, + "loss": 6.0306, + "step": 477000 + }, + { + "epoch": 13.04, + "learning_rate": 8.719809409058547e-06, + "loss": 6.0346, + "step": 477500 + }, + { + "epoch": 13.05, + "learning_rate": 8.71844022126075e-06, + "loss": 6.0306, + "step": 478000 + }, + { + "epoch": 13.07, + "learning_rate": 8.71707103346295e-06, + "loss": 6.0322, + "step": 478500 + }, + { + "epoch": 13.08, + "learning_rate": 8.715701845665151e-06, + "loss": 6.0342, + "step": 479000 + }, + { + "epoch": 13.09, + "learning_rate": 8.714332657867354e-06, + "loss": 6.0291, + "step": 479500 + }, + { + "epoch": 13.11, + "learning_rate": 8.712963470069555e-06, + "loss": 6.0331, + "step": 480000 + }, + { + "epoch": 13.12, + "learning_rate": 8.711594282271758e-06, + "loss": 6.0335, + "step": 480500 + }, + { + "epoch": 13.14, + "learning_rate": 8.710225094473959e-06, + "loss": 6.0308, + "step": 481000 + }, + { + "epoch": 13.15, + "learning_rate": 8.70885590667616e-06, + "loss": 6.0323, + "step": 481500 + }, + { + "epoch": 13.16, + "learning_rate": 8.707486718878363e-06, + "loss": 6.0294, + "step": 482000 + }, + { + "epoch": 13.18, + "learning_rate": 8.706117531080564e-06, + "loss": 6.0313, + "step": 482500 + }, + { + "epoch": 13.19, + "learning_rate": 8.704748343282765e-06, + "loss": 6.0307, + "step": 483000 + }, + { + "epoch": 13.2, + "learning_rate": 8.703379155484967e-06, + "loss": 6.0319, + "step": 483500 + }, + { + "epoch": 13.22, + "learning_rate": 8.702009967687168e-06, + "loss": 6.033, + "step": 484000 + }, + { + "epoch": 13.23, + "learning_rate": 8.70064077988937e-06, + "loss": 6.0333, + "step": 484500 + }, + { + "epoch": 13.24, + "learning_rate": 8.699271592091572e-06, + "loss": 6.0295, + "step": 485000 + }, + { + "epoch": 13.26, + "learning_rate": 8.697902404293773e-06, + "loss": 6.0313, + "step": 485500 + }, + { + "epoch": 13.27, + "learning_rate": 8.696533216495974e-06, + "loss": 6.0281, + "step": 486000 + }, + { + "epoch": 13.29, + "learning_rate": 8.695164028698177e-06, + "loss": 6.0278, + "step": 486500 + }, + { + "epoch": 13.3, + "learning_rate": 8.693794840900378e-06, + "loss": 6.0319, + "step": 487000 + }, + { + "epoch": 13.31, + "learning_rate": 8.69242565310258e-06, + "loss": 6.0286, + "step": 487500 + }, + { + "epoch": 13.33, + "learning_rate": 8.691056465304783e-06, + "loss": 6.0273, + "step": 488000 + }, + { + "epoch": 13.34, + "learning_rate": 8.689687277506984e-06, + "loss": 6.0335, + "step": 488500 + }, + { + "epoch": 13.35, + "learning_rate": 8.688318089709185e-06, + "loss": 6.0316, + "step": 489000 + }, + { + "epoch": 13.37, + "learning_rate": 8.686948901911388e-06, + "loss": 6.0318, + "step": 489500 + }, + { + "epoch": 13.38, + "learning_rate": 8.685579714113589e-06, + "loss": 6.0314, + "step": 490000 + }, + { + "epoch": 13.4, + "learning_rate": 8.68421052631579e-06, + "loss": 6.032, + "step": 490500 + }, + { + "epoch": 13.41, + "learning_rate": 8.682841338517993e-06, + "loss": 6.03, + "step": 491000 + }, + { + "epoch": 13.42, + "learning_rate": 8.681472150720194e-06, + "loss": 6.0288, + "step": 491500 + }, + { + "epoch": 13.44, + "learning_rate": 8.680102962922395e-06, + "loss": 6.0312, + "step": 492000 + }, + { + "epoch": 13.45, + "learning_rate": 8.678733775124598e-06, + "loss": 6.0286, + "step": 492500 + }, + { + "epoch": 13.46, + "learning_rate": 8.677364587326799e-06, + "loss": 6.0346, + "step": 493000 + }, + { + "epoch": 13.48, + "learning_rate": 8.675995399529e-06, + "loss": 6.0283, + "step": 493500 + }, + { + "epoch": 13.49, + "learning_rate": 8.674626211731202e-06, + "loss": 6.0331, + "step": 494000 + }, + { + "epoch": 13.5, + "learning_rate": 8.673257023933403e-06, + "loss": 6.0254, + "step": 494500 + }, + { + "epoch": 13.52, + "learning_rate": 8.671887836135604e-06, + "loss": 6.029, + "step": 495000 + }, + { + "epoch": 13.53, + "learning_rate": 8.670518648337807e-06, + "loss": 6.0309, + "step": 495500 + }, + { + "epoch": 13.55, + "learning_rate": 8.669149460540008e-06, + "loss": 6.0267, + "step": 496000 + }, + { + "epoch": 13.56, + "learning_rate": 8.66778027274221e-06, + "loss": 6.0285, + "step": 496500 + }, + { + "epoch": 13.57, + "learning_rate": 8.666411084944412e-06, + "loss": 6.0301, + "step": 497000 + }, + { + "epoch": 13.59, + "learning_rate": 8.665041897146613e-06, + "loss": 6.0281, + "step": 497500 + }, + { + "epoch": 13.6, + "learning_rate": 8.663672709348816e-06, + "loss": 6.0281, + "step": 498000 + }, + { + "epoch": 13.61, + "learning_rate": 8.662303521551017e-06, + "loss": 6.0255, + "step": 498500 + }, + { + "epoch": 13.63, + "learning_rate": 8.660934333753218e-06, + "loss": 6.0226, + "step": 499000 + }, + { + "epoch": 13.64, + "learning_rate": 8.65956514595542e-06, + "loss": 6.0287, + "step": 499500 + }, + { + "epoch": 13.65, + "learning_rate": 8.658195958157621e-06, + "loss": 6.0301, + "step": 500000 + }, + { + "epoch": 13.67, + "learning_rate": 8.656826770359822e-06, + "loss": 6.0266, + "step": 500500 + }, + { + "epoch": 13.68, + "learning_rate": 8.655457582562025e-06, + "loss": 6.0273, + "step": 501000 + }, + { + "epoch": 13.7, + "learning_rate": 8.654088394764226e-06, + "loss": 6.0267, + "step": 501500 + }, + { + "epoch": 13.71, + "learning_rate": 8.652719206966427e-06, + "loss": 6.0285, + "step": 502000 + }, + { + "epoch": 13.72, + "learning_rate": 8.65135001916863e-06, + "loss": 6.0282, + "step": 502500 + }, + { + "epoch": 13.74, + "learning_rate": 8.64998083137083e-06, + "loss": 6.0279, + "step": 503000 + }, + { + "epoch": 13.75, + "learning_rate": 8.648611643573034e-06, + "loss": 6.0277, + "step": 503500 + }, + { + "epoch": 13.76, + "learning_rate": 8.647242455775235e-06, + "loss": 6.0273, + "step": 504000 + }, + { + "epoch": 13.78, + "learning_rate": 8.645873267977436e-06, + "loss": 6.029, + "step": 504500 + }, + { + "epoch": 13.79, + "learning_rate": 8.644504080179638e-06, + "loss": 6.0287, + "step": 505000 + }, + { + "epoch": 13.8, + "learning_rate": 8.643134892381841e-06, + "loss": 6.0282, + "step": 505500 + }, + { + "epoch": 13.82, + "learning_rate": 8.641765704584042e-06, + "loss": 6.0272, + "step": 506000 + }, + { + "epoch": 13.83, + "step": 506415, + "total_flos": 1.3962705869419315e+17, + "train_loss": 6.195823538107642, + "train_runtime": 197999.5037, + "train_samples_per_second": 2958.976, + "train_steps_per_second": 18.494 + } + ], + "logging_steps": 500, + "max_steps": 3661800, + "num_train_epochs": 100, + "save_steps": 1000000, + "total_flos": 1.3962705869419315e+17, + "trial_name": null, + "trial_params": null +}