- Open “Training process” stage notebook
- Execute 25th cell with the following input:
bigger_finetuned_model = BasicModelRunner(model_name_to_id["bigger_model_name"])
bigger_finetuned_output = bigger_finetuned_model(test_question)
print("Bigger (2.8B) finetuned model (test): ", bigger_finetuned_output)
Cell execution failed with the following output:
LAMINI CONFIGURATION
{}
LAMINI CONFIGURATION
{}
LAMINI CONFIGURATION
{}
status code: 500
---------------------------------------------------------------------------
HTTPError Traceback (most recent call last)
File /usr/local/lib/python3.9/site-packages/lamini/api/rest_requests.py:25, in make_web_request(key, url, http_method, json)
24 try:
---> 25 resp.raise_for_status()
26 except requests.exceptions.HTTPError as e:
File /usr/local/lib/python3.9/site-packages/requests/models.py:1021, in Response.raise_for_status(self)
1020 if http_error_msg:
-> 1021 raise HTTPError(http_error_msg, response=self)
HTTPError: 500 Server Error: Internal Server Error for url: http://jupyter-api-proxy.internal.dlai/rev-proxy/lamini/v1/completions
During handling of the above exception, another exception occurred:
APIError Traceback (most recent call last)
Cell In[25], line 2
1 bigger_finetuned_model = BasicModelRunner(model_name_to_id["bigger_model_name"])
----> 2 bigger_finetuned_output = bigger_finetuned_model(test_question)
3 print("Bigger (2.8B) finetuned model (test): ", bigger_finetuned_output)
File /usr/local/lib/python3.9/site-packages/lamini/runners/base_runner.py:28, in BaseRunner.__call__(self, prompt, system_prompt, output_type, max_tokens)
21 def __call__(
22 self,
23 prompt: Union[str, List[str]],
(...)
26 max_tokens: Optional[int] = None,
27 ):
---> 28 return self.call(prompt, system_prompt, output_type, max_tokens)
File /usr/local/lib/python3.9/site-packages/lamini/runners/base_runner.py:39, in BaseRunner.call(self, prompt, system_prompt, output_type, max_tokens)
30 def call(
31 self,
32 prompt: Union[str, List[str]],
(...)
35 max_tokens: Optional[int] = None,
36 ):
37 input_objects = self.create_final_prompts(prompt, system_prompt)
---> 39 return self.lamini_api.generate(
40 prompt=input_objects,
41 model_name=self.model_name,
42 max_tokens=max_tokens,
43 output_type=output_type,
44 )
File /usr/local/lib/python3.9/site-packages/lamini/api/lamini.py:46, in Lamini.generate(self, prompt, model_name, output_type, max_tokens, stop_tokens)
31 def generate(
32 self,
33 prompt: Union[str, List[str]],
(...)
37 stop_tokens: Optional[List[str]] = None,
38 ):
39 req_data = self.make_llm_req_map(
40 prompt=prompt,
41 model_name=model_name or self.model_name,
(...)
44 stop_tokens=stop_tokens,
45 )
---> 46 result = self.inference_queue.submit(req_data)
47 if isinstance(prompt, str) and len(result) == 1:
48 if output_type is None:
File /usr/local/lib/python3.9/site-packages/lamini/api/inference_queue.py:41, in InferenceQueue.submit(self, request)
39 # Wait for all the results to come back
40 for result in results:
---> 41 result.result()
43 # Combine the results and return them
44 return self.combine_results(results)
File /usr/local/lib/python3.9/concurrent/futures/_base.py:446, in Future.result(self, timeout)
444 raise CancelledError()
445 elif self._state == FINISHED:
--> 446 return self.__get_result()
447 else:
448 raise TimeoutError()
File /usr/local/lib/python3.9/concurrent/futures/_base.py:391, in Future.__get_result(self)
389 if self._exception:
390 try:
--> 391 raise self._exception
392 finally:
393 # Break a reference cycle with the exception in self._exception
394 self = None
File /usr/local/lib/python3.9/concurrent/futures/thread.py:58, in _WorkItem.run(self)
55 return
57 try:
---> 58 result = self.fn(*self.args, **self.kwargs)
59 except BaseException as exc:
60 self.future.set_exception(exc)
File /usr/local/lib/python3.9/site-packages/lamini/api/inference_queue.py:103, in process_batch(key, api_prefix, batch)
101 def process_batch(key, api_prefix, batch):
102 url = api_prefix + "completions"
--> 103 result = make_web_request(key, url, "post", batch)
104 return result
File /usr/local/lib/python3.9/site-packages/lamini/api/rest_requests.py:76, in make_web_request(key, url, http_method, json)
74 if description == {"detail": ""}:
75 raise APIError("500 Internal Server Error")
---> 76 raise APIError(f"API error {description}")
78 return resp.json()
APIError: API error {'code': 500, 'error_id': '143093073380044201231992061503924942078', 'detail': "[Errno 2] No such file or directory: '/home/slurmuser/jobs/2320/checkpoints'"}