getting stuck on CLIP Text Encode for default LoRA

When I try to run LoRA the GUI shows Total 0% Current node: CLIP Text Encode (Prompt) and the terminal shows

got prompt

model weight dtype torch.float16, manual cast: None

model_type EPS

Using split attention in VAE

Using split attention in VAE

VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16

CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16

Requested to load SD1ClipModel

and rocm-smi shows:

rocm-smi

WARNING: AMD GPU device(s) is/are in a low-power state. Check power control/runtime_status

========================================== ROCm System Management Interface ==========================================

==================================================== Concise Info ====================================================

Device Node IDs Temp Power Partitions SCLK MCLK Fan Perf PwrCap VRAM% GPU%

(DID, GUID) (Edge) (Avg) (Mem, Compute, ID)

======================================================================================================================

0 1 0x7550, 62108 49.0°C 109.0W N/A, N/A, 0 3408Mhz 772Mhz 14.9% auto 317.0W 10% 100%

======================================================================================================================

================================================ End of ROCm SMI Log =================================================