src/open-r1-multimodal/src/open_r1/trainer/grpo_trainer.py [287:306]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.num_generations = args.num_generations  # = G in the GRPO paper
        self.generation_config = GenerationConfig(
            max_new_tokens=self.max_completion_length,
            do_sample=True,  
            temperature=1, # HACK
            num_return_sequences=self.num_generations,
            pad_token_id=pad_token_id,
        )
        self.beta = args.beta

        # The trainer estimates the number of FLOPs (floating-point operations) using the number of elements in the
        # input tensor associated with the key "input_ids". However, in GRPO, the sampled data does not include the
        # "input_ids" key. Instead, the available keys is "prompt". As a result, the trainer issues the warning:
        # "Could not estimate the number of tokens of the input, floating-point operations will not be computed." To
        # suppress this warning, we set the "estimate_tokens" key in the model's "warnings_issued" dictionary to True.
        # This acts as a flag to indicate that the warning has already been issued.
        model.warnings_issued["estimate_tokens"] = True

        # Initialize the metrics
        self._metrics = defaultdict(list)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/open-r1-multimodal/src/open_r1/trainer/vllm_grpo_trainer.py [285:304]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.num_generations = args.num_generations  # = G in the GRPO paper
        self.generation_config = GenerationConfig(
            max_new_tokens=self.max_completion_length,
            do_sample=True,
            temperature=1,  # HACK
            num_return_sequences=self.num_generations,
            pad_token_id=pad_token_id,
        )
        self.beta = args.beta

        # The trainer estimates the number of FLOPs (floating-point operations) using the number of elements in the
        # input tensor associated with the key "input_ids". However, in GRPO, the sampled data does not include the
        # "input_ids" key. Instead, the available keys is "prompt". As a result, the trainer issues the warning:
        # "Could not estimate the number of tokens of the input, floating-point operations will not be computed." To
        # suppress this warning, we set the "estimate_tokens" key in the model's "warnings_issued" dictionary to True.
        # This acts as a flag to indicate that the warning has already been issued.
        model.warnings_issued["estimate_tokens"] = True

        # Initialize the metrics
        self._metrics = defaultdict(list)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -