Story_Generation / logs.log
aiwithi's picture
End of training
28ab977 verified
Raw History Blame Contribute Delete
1.23 kB
INFO 04-21 22:43:28 [__init__.py:239] Automatically detected platform cuda.
INFO 04-21 22:43:38 [config.py:689] This model supports multiple tasks: {'generate', 'score', 'reward', 'embed', 'classify'}. Defaulting to 'generate'.
WARNING 04-21 22:43:38 [config.py:768] bitsandbytes quantization is not fully optimized yet. The speed can be slower than non-quantized models.
INFO 04-21 22:43:38 [config.py:1901] Chunked prefill is enabled with max_num_batched_tokens=16384.
WARNING 04-21 22:43:40 [utils.py:2304] We must use the `spawn` multiprocessing start method. Overriding VLLM_WORKER_MULTIPROC_METHOD to 'spawn'. See https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#python-multiprocessing for more information. Reason: CUDA is initialized
INFO 04-21 22:43:43 [__init__.py:239] Automatically detected platform cuda.
INFO 04-21 22:43:53 [config.py:689] This model supports multiple tasks: {'embed', 'classify', 'reward', 'score', 'generate'}. Defaulting to 'generate'.
WARNING 04-21 22:43:53 [config.py:768] bitsandbytes quantization is not fully optimized yet. The speed can be slower than non-quantized models.
INFO 04-21 22:43:53 [config.py:1901] Chunked prefill is enabled with max_num_batched_tokens=16384.