diff --git a/examples/experiments/onto-ner.cfg b/examples/experiments/onto-ner.cfg
index 48fe25a67..8970bb3c0 100644
--- a/examples/experiments/onto-ner.cfg
+++ b/examples/experiments/onto-ner.cfg
@@ -9,12 +9,12 @@ max_length = 5000
 limit = 0
 # Data augmentation
 orth_variant_level = 0.0
-dropout = 0.2
+dropout = 0.1
 # Controls early-stopping. 0 or -1 mean unlimited.
-patience = 1600
+patience = 100000
 max_epochs = 0
-max_steps = 20000
-eval_frequency = 500
+max_steps = 100000
+eval_frequency = 2000
 # Other settings
 seed = 0
 accumulate_gradient = 1
@@ -30,25 +30,25 @@ omit_extra_lookups = false
 [training.batch_size]
 @schedules = "compounding.v1"
 start = 100
-stop = 1000
+stop = 2000
 compound = 1.001
 
 [training.optimizer]
 @optimizers = "Adam.v1"
 beta1 = 0.9
 beta2 = 0.999
-L2_is_weight_decay = false
-L2 = 1e-6
+L2_is_weight_decay = true
+L2 = 0.0
 grad_clip = 1.0
 use_averages = true
 eps = 1e-8
 learn_rate = 0.001
 
-#[optimizer.learn_rate]
+#[training.optimizer.learn_rate]
 #@schedules = "warmup_linear.v1"
-#warmup_steps = 250
-#total_steps = 20000
-#initial_rate = 0.001
+#warmup_steps = 1000
+#total_steps = 50000
+#initial_rate = 0.003
 
 [nlp]
 lang = "en"
@@ -58,23 +58,21 @@ vectors = null
 factory = "ner"
 learn_tokens = false
 min_action_freq = 1
-beam_width = 1
-beam_update_prob = 1.0
 
 [nlp.pipeline.ner.model]
 @architectures = "spacy.TransitionBasedParser.v1"
 nr_feature_tokens = 3
 hidden_width = 64
 maxout_pieces = 2
-use_upper = true
+use_upper = false
 
 [nlp.pipeline.ner.model.tok2vec]
 @architectures = "spacy.HashEmbedCNN.v1"
 pretrained_vectors = ${nlp:vectors}
-width = 96
+width = 300
 depth = 4
 window_size = 1
-embed_size = 2000
-maxout_pieces = 3
+embed_size = 7000
+maxout_pieces = 1
 subword_features = true
 dropout = ${training:dropout}