Update README.md

README.md

@@ -26,7 +26,9 @@ The model is trained on around ~11B tokens (64 size batch, 512 tokens, 350k step
 >>> model = FlaxT5ForConditionalGeneration.from_pretrained("flax-community/bengali-t5-base", config=config)
 ```
 
-The model is trained on `de-noising` objectives followed by the script [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run_t5_mlm_flax.py) and [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run.sh). Currently This model doesn't have any generation capability. If you want this model to have generation capability, please do a finetuning on `prefix-LM` objective mentioned in the [paper](https://arxiv.org/abs/1910.10683).
+The model is trained on `de-noising` objectives followed by the script [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run_t5_mlm_flax.py) and [here](https://huggingface.co/flax-community/bengali-t5-base/blob/main/run.sh). Currently This model doesn't have any generation capability. If you want this model to have generation capability, please do a finetuning on `prefix-LM` objective mentioned in the [paper](https://arxiv.org/abs/1910.10683). 
+
+See the tensorboard log in `Training metrics` tab.
 
 Please note that we haven't finetuned the model in any downstream task.