#6390:L1 loss pcc issue

[umadevimcw]

To fix the low PCC issue

• l1 loss returns only a single value in torch whereas in TT single value output will be in 32x32 tensor hence while comparing the results we need to fetch the data at the 0th index
• Since it involves bfloat16 computation there will be difference between the values hence compall_close is used for comparison instead of comp_pcc