fix tokenizer settings for step 2038000

config.json

@@ -2,9 +2,9 @@
   "architectures": [
     "UMT5ForConditionalGeneration"
   ],
-  "d_ff": 2048,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -15,9 +15,9 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "umt5",
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,