DEBUG

src/backend/run_eval_suite_harness.py

@@ -55,11 +55,25 @@ def run_evaluation(eval_request: EvalRequest, task_names: list, num_fewshot: int
 
     logger.info(f"Selected Tasks: {task_names}")
 
+    print("Here are the deets we are putting in:")
+    print("model args:")
+    model_args = eval_request.get_model_args()
+    print(model_args)
+    print("Tasks")
+    print(task_names)
+    print("Num fewshot")
+    print(num_fewshot)
+    print("Batch size")
+    print(batch_size)
+    print("Device")
+    print(device)
+    print("Limit")
+    print(limit)
     # no_cache=no_cache,
     # output_base_path="logs"
     results = evaluator.simple_evaluate(
         model="hf-auto", #= "hf-causal-experimental", # "hf-causal"
-        model_args=eval_request.get_model_args(),
+        model_args=model_args,
         tasks=task_names,
         num_fewshot=num_fewshot,
         batch_size=batch_size,