diff --git a/config_cluster.json b/config_cluster.json
index ae28c765..d810a6a3 100644
--- a/config_cluster.json
+++ b/config_cluster.json
@@ -30,7 +30,7 @@
     },
 
     "model": "Tacotron2",   // one of the model in models/    
-    "grad_clip": 0.05,      // upper limit for gradients for clipping.
+    "grad_clip": 1,      // upper limit for gradients for clipping.
     "epochs": 1000,         // total number of epochs to train.
     "lr": 0.0001,            // Initial learning rate. If Noam decay is active, maximum learning rate.
     "lr_decay": false,      // if true, Noam learning rate decaying is applied through training.
@@ -41,21 +41,21 @@
     "batch_size": 16,       // Batch size for training. Lower values than 32 might cause hard to learn attention.
     "eval_batch_size":16,   
     "r": 1,                 // Number of frames to predict for step.
-    "wd": 0.000002,         // Weight decay weight.
+    "wd": 0.000001,         // Weight decay weight.
     "checkpoint": true,     // If true, it saves checkpoints per "save_step"
     "save_step": 1000,      // Number of training steps expected to save traning stats and checkpoints.
     "print_step": 10,       // Number of steps to log traning on console.
-    "tb_model_param_stats": false,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. 
-    "batch_group_size": 4,  //Number of batches to shuffle after bucketing.
+    "tb_model_param_stats": true,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. 
+    "batch_group_size": 8,  //Number of batches to shuffle after bucketing.
 
     "run_eval": true,
-    "test_delay_epochs": 100,  //Until attention is aligned, testing only wastes computation time.
+    "test_delay_epochs": 10,  //Until attention is aligned, testing only wastes computation time.
     "data_path": "/media/erogol/data_ssd/Data/LJSpeech-1.1",  // DATASET-RELATED: can overwritten from command argument
     "meta_file_train": "prompts_train.data",      // DATASET-RELATED: metafile for training dataloader.
     "meta_file_val": "prompts_val.data",    // DATASET-RELATED: metafile for evaluation dataloader.
     "dataset": "nancy",      // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py
     "min_seq_len": 0,       // DATASET-RELATED: minimum text length to use in training
-    "max_seq_len": 50,     // DATASET-RELATED: maximum text length
+    "max_seq_len": 120,     // DATASET-RELATED: maximum text length
     "output_path": "../keep/",      // DATASET-RELATED: output path for all training outputs.
     "num_loader_workers": 8,        // number of training data loader processes. Don't set it too big. 4-8 are good values.
     "num_val_loader_workers": 4,    // number of evaluation data loader processes.