Fix reduction param validation for flce (#879)

## Summary
<!--- This is a required section; please describe the main purpose of
this proposed code change. --->

This is a fix for Issue #872. @shimizust wants me to submit this fix. 

<!---
## Details
This is an optional section; is there anything specific that reviewers
should be aware of?
--->
@shimizust Could you have a look at the fix?

## Testing Done
<!--- This is a required section; please describe how this change was
tested. --->

<!-- 
Replace BLANK with your device type. For example, A100-80G-PCIe

Complete the following tasks before sending your PR, and replace `[ ]`
with
`[x]` to indicate you have done them. 
-->

- Hardware Type: <BLANK>
- [ ] run `make test` to ensure correctness
- [ ] run `make checkstyle` to ensure code style
- [ ] run `make test-convergence` to ensure convergence

Author: yshenaw

src/liger_kernel/transformers/fused_linear_cross_entropy.py

@@ -25,7 +25,8 @@ def __init__(
         assert reduction in {
             "mean",
             "sum",
-        }, f"reduction must be 'mean' or 'sum'. Got: {reduction}"
+            "none", 
+        }, f"reduction must be 'mean' or 'sum' or 'none'. Got: {reduction}"
         assert softcap is None or softcap > 0, f"softcap must greater than 0.0 or None. Got: {softcap}"
         self.ce_weight = ce_weight
         self.ignore_index = ignore_index