Update README.md

README.md

@@ -357,7 +357,7 @@ Model Fairness:
 
 ## Training
 
-Canary-Qwen-2.5B was trained using the NVIDIA NeMo toolkit [6] for a total of 90k steps on 32 NVIDIA A100 80GB GPUs. LLM parameters were kept frozen. Speech encoder, projection, and LoRA parameters were trainable. The encoder's output frame rate is 80ms, or 12.5 tokens per second. The model was trained on approximately 1.3B tokens in total (this number inlcudes the speech encoder output frames, text response tokens, prompt tokens, and chat template tokens). 
+Canary-Qwen-2.5B was trained using the NVIDIA NeMo toolkit [6] for a total of 90k steps on 32 NVIDIA A100 80GB GPUs. LLM parameters were kept frozen. Speech encoder, projection, and LoRA parameters were trainable. The encoder's output frame rate is 80ms, or 12.5 tokens per second. The model was trained on approximately 1.3B tokens in total (this number inlcudes the speech encoder output frames, text response tokens, prompt tokens, and chat template tokens). The model was trained in bfloat16 precision (not using AMP) and bucketing. 
 
 The model can be trained using this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/speechlm2/salm_train.py) and [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/speechlm2/conf/salm.yaml).