Add some warnings and fix RLHF (#1890)

Author: tastelikefeet

swift/llm/eval.py

@@ -260,7 +260,6 @@ def vlmeval_runner(args: EvalArguments, dataset: List[str], model_type: str, is_
 
 
 def eval_opencompass(args: EvalArguments) -> List[Dict[str, Any]]:
-    from evalscope.run import run_task
     from swift.utils.torch_utils import _find_free_port
     logger.info(f'args: {args}')
     if args.eval_few_shot:
@@ -297,12 +296,16 @@ def eval_opencompass(args: EvalArguments) -> List[Dict[str, Any]]:
     nlp_datasets = set(OpenCompassBackendManager.list_datasets()) & set(args.eval_dataset)
     mm_datasets = set(VLMEvalKitBackendManager.list_supported_datasets()) & set(args.eval_dataset)
 
+    final_report = []
     for dataset, runner in zip([list(nlp_datasets), list(mm_datasets)], [opencompass_runner, vlmeval_runner]):
         if not dataset:
             continue
 
-        final_report = runner(args, dataset, model_type, is_chat, url)
-        logger.info(f'Final report:{final_report}\n')
+        report = runner(args, dataset, model_type, is_chat, url)
+        logger.info(f'Final report:{report}\n')
+        final_report.extend(report)
+    if not final_report:
+        raise ValueError(f'Cannot load final report, please check your dataset: {args.eval_dataset} and the eval log')
     if process:
         process.kill()
     return final_report

swift/trainers/cpo_trainer.py

@@ -7,7 +7,8 @@
 
 from swift.llm.utils.template import Template
 from swift.utils import get_logger
-from .mixin import PushToMsHubMixin, SwiftMixin
+from .mixin import SwiftMixin
+from .push_to_ms import PushToMsHubMixin
 from .utils import build_tokenized_answer, patch_trl, sort_by_max_length
 
 logger = get_logger()

swift/trainers/dpo_trainer.py

@@ -8,7 +8,8 @@
 
 from swift.llm.utils.template import Template
 from swift.utils import get_logger
-from .mixin import PushToMsHubMixin, SwiftMixin
+from .mixin import SwiftMixin
+from .push_to_ms import PushToMsHubMixin
 from .utils import build_tokenized_answer, patch_trl, sort_by_max_length
 
 logger = get_logger()

swift/trainers/kto_trainer.py

@@ -10,7 +10,8 @@
 from swift.llm.utils.template import Context, History, Template
 from swift.utils import get_logger
 from .callback import DefaultFlowCallbackNew, PrinterCallbackNew, ProgressCallbackNew
-from .mixin import PushToMsHubMixin, SwiftMixin
+from .mixin import SwiftMixin
+from .push_to_ms import PushToMsHubMixin
 
 logger = get_logger()
 

swift/trainers/orpo_trainer.py

@@ -7,7 +7,8 @@
 
 from swift.llm.utils.template import Template
 from swift.utils import get_logger
-from .mixin import PushToMsHubMixin, SwiftMixin
+from .mixin import SwiftMixin
+from .push_to_ms import PushToMsHubMixin
 from .utils import build_tokenized_answer, patch_trl, sort_by_max_length
 
 logger = get_logger()

swift/ui/llm_train/runtime.py

@@ -440,6 +440,8 @@ def parse_info_from_cmdline(task):
             args = task.split('swift sft')[1]
         elif 'swift rlhf' in task:
             args = task.split('swift rlhf')[1]
+        else:
+            raise ValueError(f'Cannot parse cmd line: {task}')
         args = [arg.strip() for arg in args.split('--') if arg.strip()]
         all_args = {}
         for i in range(len(args)):