diff --git "a/pot_module_training.log" "b/pot_module_training.log" new file mode 100644--- /dev/null +++ "b/pot_module_training.log" @@ -0,0 +1,1596 @@ +2025-05-06 06:31:31,754 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:772] +2025-05-06 06:31:31,754 - INFO - PoT training configuration (Direct Run): - [__main__:777] +2025-05-06 06:31:31,754 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:779] +2025-05-06 06:31:31,754 - INFO - max_seq_length: 768 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - load_in_4bit: False - [__main__:779] +2025-05-06 06:31:31,755 - INFO - load_in_8bit: False - [__main__:779] +2025-05-06 06:31:31,755 - INFO - lora_r: 32 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - lora_alpha: 32 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - lora_dropout: 0.05 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - token: None - [__main__:779] +2025-05-06 06:31:31,755 - INFO - dataset_name: gsm8k - [__main__:779] +2025-05-06 06:31:31,755 - INFO - dataset_config: None - [__main__:779] +2025-05-06 06:31:31,755 - INFO - max_samples: 1000 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - cache_dir: None - [__main__:779] +2025-05-06 06:31:31,755 - INFO - learning_rate: 5e-06 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - warmup_ratio: 0.1 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - weight_decay: 0.1 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - batch_size: 1 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - gradient_accumulation_steps: 4 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - num_generations: 4 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - max_steps: 100 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - output_dir: pot_grpo_outputs - [__main__:779] +2025-05-06 06:31:31,755 - INFO - save_steps: 50 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - logging_steps: 1 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - seed: 3407 - [__main__:779] +2025-05-06 06:31:31,755 - INFO - save_peft: False - [__main__:779] +2025-05-06 06:31:31,755 - INFO - save_merged: False - [__main__:779] +2025-05-06 06:31:31,755 - INFO - reward_config_json: None - [__main__:779] +2025-05-06 06:31:31,756 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:31:31,756 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:564] +2025-05-06 06:31:31,756 - INFO - Using GPU: NVIDIA H200 - [__main__:570] +2025-05-06 06:31:31,756 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:573] +2025-05-06 06:31:31,756 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:579] +2025-05-06 06:31:31,756 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:31:36,487 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:31:36,488 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:31:40,623 - ERROR - Failed to load model/tokenizer: 'NoneType' object has no attribute 'to_dict' - [__main__:585] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 581, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 524, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 531, in from_pretrained + config, kwargs = AutoConfig.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1143, in from_pretrained + return config_class.from_dict(config_dict, **unused_kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 765, in from_dict + logger.info(f"Model config {config}") + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 797, in __repr__ + return f"{self.__class__.__name__} {self.to_json_string()}" + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 931, in to_json_string + config_dict = self.to_diff_dict() + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 811, in to_diff_dict + config_dict = self.to_dict() + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 906, in to_dict + self.quantization_config.to_dict() +AttributeError: 'NoneType' object has no attribute 'to_dict' +2025-05-06 06:31:40,624 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: 'NoneType' object has no attribute 'to_dict' - [__main__:783] +2025-05-06 06:34:14,532 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:779] +2025-05-06 06:34:14,533 - INFO - PoT training configuration (Direct Run): - [__main__:784] +2025-05-06 06:34:14,533 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:786] +2025-05-06 06:34:14,533 - INFO - max_seq_length: 768 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - load_in_4bit: False - [__main__:786] +2025-05-06 06:34:14,533 - INFO - load_in_8bit: False - [__main__:786] +2025-05-06 06:34:14,533 - INFO - lora_r: 32 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - lora_alpha: 32 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - lora_dropout: 0.05 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - token: None - [__main__:786] +2025-05-06 06:34:14,533 - INFO - dataset_name: gsm8k - [__main__:786] +2025-05-06 06:34:14,533 - INFO - dataset_config: None - [__main__:786] +2025-05-06 06:34:14,533 - INFO - max_samples: 1000 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - cache_dir: None - [__main__:786] +2025-05-06 06:34:14,533 - INFO - learning_rate: 5e-06 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - warmup_ratio: 0.1 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - weight_decay: 0.1 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - batch_size: 1 - [__main__:786] +2025-05-06 06:34:14,533 - INFO - gradient_accumulation_steps: 4 - [__main__:786] +2025-05-06 06:34:14,534 - INFO - num_generations: 4 - [__main__:786] +2025-05-06 06:34:14,534 - INFO - max_steps: 100 - [__main__:786] +2025-05-06 06:34:14,534 - INFO - output_dir: pot_grpo_outputs - [__main__:786] +2025-05-06 06:34:14,534 - INFO - save_steps: 50 - [__main__:786] +2025-05-06 06:34:14,534 - INFO - logging_steps: 1 - [__main__:786] +2025-05-06 06:34:14,534 - INFO - seed: 3407 - [__main__:786] +2025-05-06 06:34:14,534 - INFO - save_peft: False - [__main__:786] +2025-05-06 06:34:14,534 - INFO - save_merged: False - [__main__:786] +2025-05-06 06:34:14,534 - INFO - reward_config_json: None - [__main__:786] +2025-05-06 06:34:14,535 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:34:14,535 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:571] +2025-05-06 06:34:14,535 - INFO - Using GPU: NVIDIA H200 - [__main__:577] +2025-05-06 06:34:14,535 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:580] +2025-05-06 06:34:14,535 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:586] +2025-05-06 06:34:14,535 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:34:15,780 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:34:15,780 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:34:56,888 - ERROR - Failed to load model/tokenizer: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:592] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 588, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 549, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained(**model_load_kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained + return model_class.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper + return func(*args, **kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4342, in from_pretrained + model = cls(config, *model_args, **model_kwargs) +TypeError: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' +2025-05-06 06:34:56,889 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:790] +2025-05-06 06:36:12,011 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:777] +2025-05-06 06:36:12,011 - INFO - PoT training configuration (Direct Run): - [__main__:782] +2025-05-06 06:36:12,011 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:784] +2025-05-06 06:36:12,011 - INFO - max_seq_length: 768 - [__main__:784] +2025-05-06 06:36:12,011 - INFO - load_in_4bit: False - [__main__:784] +2025-05-06 06:36:12,011 - INFO - load_in_8bit: False - [__main__:784] +2025-05-06 06:36:12,011 - INFO - lora_r: 32 - [__main__:784] +2025-05-06 06:36:12,011 - INFO - lora_alpha: 32 - [__main__:784] +2025-05-06 06:36:12,011 - INFO - lora_dropout: 0.05 - [__main__:784] +2025-05-06 06:36:12,011 - INFO - token: None - [__main__:784] +2025-05-06 06:36:12,011 - INFO - dataset_name: gsm8k - [__main__:784] +2025-05-06 06:36:12,011 - INFO - dataset_config: None - [__main__:784] +2025-05-06 06:36:12,011 - INFO - max_samples: 1000 - [__main__:784] +2025-05-06 06:36:12,011 - INFO - cache_dir: None - [__main__:784] +2025-05-06 06:36:12,011 - INFO - learning_rate: 5e-06 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - warmup_ratio: 0.1 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - weight_decay: 0.1 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - batch_size: 1 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - gradient_accumulation_steps: 4 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - num_generations: 4 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - max_steps: 100 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - output_dir: pot_grpo_outputs - [__main__:784] +2025-05-06 06:36:12,012 - INFO - save_steps: 50 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - logging_steps: 1 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - seed: 3407 - [__main__:784] +2025-05-06 06:36:12,012 - INFO - save_peft: False - [__main__:784] +2025-05-06 06:36:12,012 - INFO - save_merged: False - [__main__:784] +2025-05-06 06:36:12,012 - INFO - reward_config_json: None - [__main__:784] +2025-05-06 06:36:12,013 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:36:12,013 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:569] +2025-05-06 06:36:12,013 - INFO - Using GPU: NVIDIA H200 - [__main__:575] +2025-05-06 06:36:12,013 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:578] +2025-05-06 06:36:12,013 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:584] +2025-05-06 06:36:12,013 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:36:13,257 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:36:13,258 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:36:17,096 - ERROR - Failed to load model/tokenizer: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'use_rslora' - [__main__:590] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 586, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 547, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained(**model_load_kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained + return model_class.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper + return func(*args, **kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4342, in from_pretrained + model = cls(config, *model_args, **model_kwargs) +TypeError: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'use_rslora' +2025-05-06 06:36:17,096 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'use_rslora' - [__main__:788] +2025-05-06 06:39:12,994 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:780] +2025-05-06 06:39:12,994 - INFO - PoT training configuration (Direct Run): - [__main__:785] +2025-05-06 06:39:12,994 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:787] +2025-05-06 06:39:12,994 - INFO - max_seq_length: 768 - [__main__:787] +2025-05-06 06:39:12,994 - INFO - load_in_4bit: False - [__main__:787] +2025-05-06 06:39:12,994 - INFO - load_in_8bit: False - [__main__:787] +2025-05-06 06:39:12,994 - INFO - lora_r: 32 - [__main__:787] +2025-05-06 06:39:12,994 - INFO - lora_alpha: 32 - [__main__:787] +2025-05-06 06:39:12,994 - INFO - lora_dropout: 0.05 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - token: None - [__main__:787] +2025-05-06 06:39:12,995 - INFO - dataset_name: gsm8k - [__main__:787] +2025-05-06 06:39:12,995 - INFO - dataset_config: None - [__main__:787] +2025-05-06 06:39:12,995 - INFO - max_samples: 1000 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - cache_dir: None - [__main__:787] +2025-05-06 06:39:12,995 - INFO - learning_rate: 5e-06 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - warmup_ratio: 0.1 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - weight_decay: 0.1 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - batch_size: 1 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - gradient_accumulation_steps: 4 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - num_generations: 4 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - max_steps: 100 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - output_dir: pot_grpo_outputs - [__main__:787] +2025-05-06 06:39:12,995 - INFO - save_steps: 50 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - logging_steps: 1 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - seed: 3407 - [__main__:787] +2025-05-06 06:39:12,995 - INFO - save_peft: False - [__main__:787] +2025-05-06 06:39:12,995 - INFO - save_merged: False - [__main__:787] +2025-05-06 06:39:12,995 - INFO - reward_config_json: None - [__main__:787] +2025-05-06 06:39:12,996 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:39:12,996 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:572] +2025-05-06 06:39:12,996 - INFO - Using GPU: NVIDIA H200 - [__main__:578] +2025-05-06 06:39:12,996 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:581] +2025-05-06 06:39:12,996 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:587] +2025-05-06 06:39:12,996 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:39:14,295 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:39:14,295 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:39:18,467 - ERROR - Failed to load model/tokenizer: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:593] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 589, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 550, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained(**unsloth_load_kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained + return model_class.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper + return func(*args, **kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4342, in from_pretrained + model = cls(config, *model_args, **model_kwargs) +TypeError: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' +2025-05-06 06:39:18,468 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:791] +2025-05-06 06:40:43,099 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:780] +2025-05-06 06:40:43,099 - INFO - PoT training configuration (Direct Run): - [__main__:785] +2025-05-06 06:40:43,099 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:787] +2025-05-06 06:40:43,099 - INFO - max_seq_length: 768 - [__main__:787] +2025-05-06 06:40:43,099 - INFO - load_in_4bit: False - [__main__:787] +2025-05-06 06:40:43,099 - INFO - load_in_8bit: False - [__main__:787] +2025-05-06 06:40:43,099 - INFO - lora_r: 32 - [__main__:787] +2025-05-06 06:40:43,099 - INFO - lora_alpha: 32 - [__main__:787] +2025-05-06 06:40:43,099 - INFO - lora_dropout: 0.05 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - token: None - [__main__:787] +2025-05-06 06:40:43,100 - INFO - dataset_name: gsm8k - [__main__:787] +2025-05-06 06:40:43,100 - INFO - dataset_config: None - [__main__:787] +2025-05-06 06:40:43,100 - INFO - max_samples: 1000 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - cache_dir: None - [__main__:787] +2025-05-06 06:40:43,100 - INFO - learning_rate: 5e-06 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - warmup_ratio: 0.1 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - weight_decay: 0.1 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - batch_size: 1 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - gradient_accumulation_steps: 4 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - num_generations: 4 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - max_steps: 100 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - output_dir: pot_grpo_outputs - [__main__:787] +2025-05-06 06:40:43,100 - INFO - save_steps: 50 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - logging_steps: 1 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - seed: 3407 - [__main__:787] +2025-05-06 06:40:43,100 - INFO - save_peft: False - [__main__:787] +2025-05-06 06:40:43,100 - INFO - save_merged: False - [__main__:787] +2025-05-06 06:40:43,100 - INFO - reward_config_json: None - [__main__:787] +2025-05-06 06:40:43,101 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:40:43,101 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:572] +2025-05-06 06:40:43,101 - INFO - Using GPU: NVIDIA H200 - [__main__:578] +2025-05-06 06:40:43,101 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:581] +2025-05-06 06:40:43,101 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:587] +2025-05-06 06:40:43,101 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:40:44,354 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:40:44,354 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:40:48,917 - ERROR - Failed to load model/tokenizer: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:593] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 589, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 550, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained(**unsloth_load_kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained + return model_class.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper + return func(*args, **kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4342, in from_pretrained + model = cls(config, *model_args, **model_kwargs) +TypeError: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' +2025-05-06 06:40:48,917 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:791] +2025-05-06 06:41:20,889 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:778] +2025-05-06 06:41:20,889 - INFO - PoT training configuration (Direct Run): - [__main__:783] +2025-05-06 06:41:20,889 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:785] +2025-05-06 06:41:20,889 - INFO - max_seq_length: 768 - [__main__:785] +2025-05-06 06:41:20,889 - INFO - load_in_4bit: False - [__main__:785] +2025-05-06 06:41:20,889 - INFO - load_in_8bit: False - [__main__:785] +2025-05-06 06:41:20,889 - INFO - lora_r: 32 - [__main__:785] +2025-05-06 06:41:20,889 - INFO - lora_alpha: 32 - [__main__:785] +2025-05-06 06:41:20,889 - INFO - lora_dropout: 0.05 - [__main__:785] +2025-05-06 06:41:20,889 - INFO - token: None - [__main__:785] +2025-05-06 06:41:20,889 - INFO - dataset_name: gsm8k - [__main__:785] +2025-05-06 06:41:20,890 - INFO - dataset_config: None - [__main__:785] +2025-05-06 06:41:20,890 - INFO - max_samples: 1000 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - cache_dir: None - [__main__:785] +2025-05-06 06:41:20,890 - INFO - learning_rate: 5e-06 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - warmup_ratio: 0.1 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - weight_decay: 0.1 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - batch_size: 1 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - gradient_accumulation_steps: 4 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - num_generations: 4 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - max_steps: 100 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - output_dir: pot_grpo_outputs - [__main__:785] +2025-05-06 06:41:20,890 - INFO - save_steps: 50 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - logging_steps: 1 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - seed: 3407 - [__main__:785] +2025-05-06 06:41:20,890 - INFO - save_peft: False - [__main__:785] +2025-05-06 06:41:20,890 - INFO - save_merged: False - [__main__:785] +2025-05-06 06:41:20,890 - INFO - reward_config_json: None - [__main__:785] +2025-05-06 06:41:20,891 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:41:20,891 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:570] +2025-05-06 06:41:20,891 - INFO - Using GPU: NVIDIA H200 - [__main__:576] +2025-05-06 06:41:20,891 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:579] +2025-05-06 06:41:20,891 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:585] +2025-05-06 06:41:20,891 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:41:22,178 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:41:22,178 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:41:26,281 - ERROR - Failed to load model/tokenizer: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:591] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 587, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 530, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained + return model_class.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper + return func(*args, **kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4342, in from_pretrained + model = cls(config, *model_args, **model_kwargs) +TypeError: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' +2025-05-06 06:41:26,282 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:789] +2025-05-06 06:41:56,697 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:773] +2025-05-06 06:41:56,697 - INFO - PoT training configuration (Direct Run): - [__main__:778] +2025-05-06 06:41:56,697 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:780] +2025-05-06 06:41:56,697 - INFO - max_seq_length: 768 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - load_in_4bit: False - [__main__:780] +2025-05-06 06:41:56,697 - INFO - load_in_8bit: False - [__main__:780] +2025-05-06 06:41:56,697 - INFO - lora_r: 32 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - lora_alpha: 32 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - lora_dropout: 0.05 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - token: None - [__main__:780] +2025-05-06 06:41:56,697 - INFO - dataset_name: gsm8k - [__main__:780] +2025-05-06 06:41:56,697 - INFO - dataset_config: None - [__main__:780] +2025-05-06 06:41:56,697 - INFO - max_samples: 1000 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - cache_dir: None - [__main__:780] +2025-05-06 06:41:56,697 - INFO - learning_rate: 5e-06 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - warmup_ratio: 0.1 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - weight_decay: 0.1 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - batch_size: 1 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - gradient_accumulation_steps: 4 - [__main__:780] +2025-05-06 06:41:56,697 - INFO - num_generations: 4 - [__main__:780] +2025-05-06 06:41:56,698 - INFO - max_steps: 100 - [__main__:780] +2025-05-06 06:41:56,698 - INFO - output_dir: pot_grpo_outputs - [__main__:780] +2025-05-06 06:41:56,698 - INFO - save_steps: 50 - [__main__:780] +2025-05-06 06:41:56,698 - INFO - logging_steps: 1 - [__main__:780] +2025-05-06 06:41:56,698 - INFO - seed: 3407 - [__main__:780] +2025-05-06 06:41:56,698 - INFO - save_peft: False - [__main__:780] +2025-05-06 06:41:56,698 - INFO - save_merged: False - [__main__:780] +2025-05-06 06:41:56,698 - INFO - reward_config_json: None - [__main__:780] +2025-05-06 06:41:56,698 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:41:56,698 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:565] +2025-05-06 06:41:56,699 - INFO - Using GPU: NVIDIA H200 - [__main__:571] +2025-05-06 06:41:56,699 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:574] +2025-05-06 06:41:56,699 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:580] +2025-05-06 06:41:56,699 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:41:57,941 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:41:57,942 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:42:01,784 - ERROR - Failed to load model/tokenizer: 'NoneType' object has no attribute 'to_dict' - [__main__:586] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 582, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 525, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 531, in from_pretrained + config, kwargs = AutoConfig.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 1143, in from_pretrained + return config_class.from_dict(config_dict, **unused_kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 765, in from_dict + logger.info(f"Model config {config}") + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 797, in __repr__ + return f"{self.__class__.__name__} {self.to_json_string()}" + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 931, in to_json_string + config_dict = self.to_diff_dict() + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 811, in to_diff_dict + config_dict = self.to_dict() + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/configuration_utils.py", line 906, in to_dict + self.quantization_config.to_dict() +AttributeError: 'NoneType' object has no attribute 'to_dict' +2025-05-06 06:42:01,785 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: 'NoneType' object has no attribute 'to_dict' - [__main__:784] +2025-05-06 06:42:32,109 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:779] +2025-05-06 06:42:32,109 - INFO - PoT training configuration (Direct Run): - [__main__:784] +2025-05-06 06:42:32,109 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:786] +2025-05-06 06:42:32,109 - INFO - max_seq_length: 768 - [__main__:786] +2025-05-06 06:42:32,109 - INFO - load_in_4bit: False - [__main__:786] +2025-05-06 06:42:32,109 - INFO - load_in_8bit: False - [__main__:786] +2025-05-06 06:42:32,109 - INFO - lora_r: 32 - [__main__:786] +2025-05-06 06:42:32,109 - INFO - lora_alpha: 32 - [__main__:786] +2025-05-06 06:42:32,109 - INFO - lora_dropout: 0.05 - [__main__:786] +2025-05-06 06:42:32,109 - INFO - token: None - [__main__:786] +2025-05-06 06:42:32,109 - INFO - dataset_name: gsm8k - [__main__:786] +2025-05-06 06:42:32,110 - INFO - dataset_config: None - [__main__:786] +2025-05-06 06:42:32,110 - INFO - max_samples: 1000 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - cache_dir: None - [__main__:786] +2025-05-06 06:42:32,110 - INFO - learning_rate: 5e-06 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - warmup_ratio: 0.1 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - weight_decay: 0.1 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - batch_size: 1 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - gradient_accumulation_steps: 4 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - num_generations: 4 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - max_steps: 100 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - output_dir: pot_grpo_outputs - [__main__:786] +2025-05-06 06:42:32,110 - INFO - save_steps: 50 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - logging_steps: 1 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - seed: 3407 - [__main__:786] +2025-05-06 06:42:32,110 - INFO - save_peft: False - [__main__:786] +2025-05-06 06:42:32,110 - INFO - save_merged: False - [__main__:786] +2025-05-06 06:42:32,110 - INFO - reward_config_json: None - [__main__:786] +2025-05-06 06:42:32,111 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:42:32,111 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:571] +2025-05-06 06:42:32,111 - INFO - Using GPU: NVIDIA H200 - [__main__:577] +2025-05-06 06:42:32,111 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:580] +2025-05-06 06:42:32,111 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:586] +2025-05-06 06:42:32,111 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:42:33,409 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:42:33,409 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:42:37,506 - ERROR - Failed to load model/tokenizer: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:592] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 588, in run_pot_grpo_training + model, tokenizer = load_model_and_tokenizer(args) + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 530, in load_model_and_tokenizer + model, _ = FastLanguageModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 321, in from_pretrained + return FastModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/loader.py", line 732, in from_pretrained + model, tokenizer = FastBaseModel.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/unsloth/models/vision.py", line 359, in from_pretrained + model = auto_model.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained + return model_class.from_pretrained( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper + return func(*args, **kwargs) + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4342, in from_pretrained + model = cls(config, *model_args, **model_kwargs) +TypeError: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' +2025-05-06 06:42:37,507 - INFO - Direct script execution finished with status: Model/tokenizer loading failed: Gemma3ForConditionalGeneration.__init__() got an unexpected keyword argument 'r' - [__main__:790] +2025-05-06 06:44:24,570 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:788] +2025-05-06 06:44:24,570 - INFO - PoT training configuration (Direct Run): - [__main__:793] +2025-05-06 06:44:24,571 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:795] +2025-05-06 06:44:24,571 - INFO - max_seq_length: 768 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - load_in_4bit: False - [__main__:795] +2025-05-06 06:44:24,571 - INFO - load_in_8bit: False - [__main__:795] +2025-05-06 06:44:24,571 - INFO - lora_r: 32 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - lora_alpha: 32 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - lora_dropout: 0.05 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - token: None - [__main__:795] +2025-05-06 06:44:24,571 - INFO - dataset_name: gsm8k - [__main__:795] +2025-05-06 06:44:24,571 - INFO - dataset_config: None - [__main__:795] +2025-05-06 06:44:24,571 - INFO - max_samples: 1000 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - cache_dir: None - [__main__:795] +2025-05-06 06:44:24,571 - INFO - learning_rate: 5e-06 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - warmup_ratio: 0.1 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - weight_decay: 0.1 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - batch_size: 1 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - gradient_accumulation_steps: 4 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - num_generations: 4 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - max_steps: 100 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - output_dir: pot_grpo_outputs - [__main__:795] +2025-05-06 06:44:24,571 - INFO - save_steps: 50 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - logging_steps: 1 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - seed: 3407 - [__main__:795] +2025-05-06 06:44:24,571 - INFO - save_peft: False - [__main__:795] +2025-05-06 06:44:24,571 - INFO - save_merged: False - [__main__:795] +2025-05-06 06:44:24,571 - INFO - reward_config_json: None - [__main__:795] +2025-05-06 06:44:24,572 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:44:24,572 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config=None, max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:580] +2025-05-06 06:44:24,572 - INFO - Using GPU: NVIDIA H200 - [__main__:586] +2025-05-06 06:44:24,572 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:589] +2025-05-06 06:44:24,572 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:595] +2025-05-06 06:44:24,572 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:490] +2025-05-06 06:44:25,855 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:501] +2025-05-06 06:44:25,855 - INFO - Using compute dtype: torch.bfloat16 - [__main__:506] +2025-05-06 06:44:42,778 - INFO - Base model loaded. Type: - [__main__:539] +2025-05-06 06:44:42,778 - INFO - Applying LoRA with r=32 - [__main__:543] +2025-05-06 06:44:46,406 - INFO - LoRA applied. Model type now: - [__main__:558] +2025-05-06 06:44:46,415 - INFO - Preparing dataset with PoT system prompting... - [__main__:605] +2025-05-06 06:44:46,415 - INFO - Creating PoT dataset using source: gsm8k - [__main__:341] +2025-05-06 06:44:46,416 - INFO - Loading dataset from Hugging Face Hub: gsm8k - [__main__:350] +2025-05-06 06:44:50,394 - ERROR - Failed to load or prepare dataset: Config name is missing. +Please pick one among the available configs: ['main', 'socratic'] +Example of usage: + `load_dataset('gsm8k', 'main')` - [__main__:410] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 351, in create_pot_dataset + base_dataset = load_dataset( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/datasets/load.py", line 2062, in load_dataset + builder_instance = load_dataset_builder( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/datasets/load.py", line 1819, in load_dataset_builder + builder_instance: DatasetBuilder = builder_cls( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/datasets/builder.py", line 343, in __init__ + self.config, self.config_id = self._create_builder_config( + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/datasets/builder.py", line 555, in _create_builder_config + raise ValueError( +ValueError: Config name is missing. +Please pick one among the available configs: ['main', 'socratic'] +Example of usage: + `load_dataset('gsm8k', 'main')` +2025-05-06 06:44:50,395 - ERROR - Failed to load or prepare dataset 'gsm8k': PoT dataset creation resulted in an empty dataset. - [__main__:619] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 616, in run_pot_grpo_training + raise ValueError("PoT dataset creation resulted in an empty dataset.") +ValueError: PoT dataset creation resulted in an empty dataset. +2025-05-06 06:44:50,395 - INFO - Direct script execution finished with status: Dataset preparation failed: PoT dataset creation resulted in an empty dataset. - [__main__:799] +2025-05-06 06:45:56,625 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:796] +2025-05-06 06:45:56,625 - INFO - PoT training configuration (Direct Run): - [__main__:801] +2025-05-06 06:45:56,625 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:803] +2025-05-06 06:45:56,625 - INFO - max_seq_length: 768 - [__main__:803] +2025-05-06 06:45:56,625 - INFO - load_in_4bit: False - [__main__:803] +2025-05-06 06:45:56,625 - INFO - load_in_8bit: False - [__main__:803] +2025-05-06 06:45:56,625 - INFO - lora_r: 32 - [__main__:803] +2025-05-06 06:45:56,625 - INFO - lora_alpha: 32 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - lora_dropout: 0.05 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - token: None - [__main__:803] +2025-05-06 06:45:56,626 - INFO - dataset_name: gsm8k - [__main__:803] +2025-05-06 06:45:56,626 - INFO - dataset_config: main - [__main__:803] +2025-05-06 06:45:56,626 - INFO - max_samples: 1000 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - cache_dir: None - [__main__:803] +2025-05-06 06:45:56,626 - INFO - learning_rate: 5e-06 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - warmup_ratio: 0.1 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - weight_decay: 0.1 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - batch_size: 1 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - gradient_accumulation_steps: 4 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - num_generations: 4 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - max_steps: 100 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - output_dir: pot_grpo_outputs - [__main__:803] +2025-05-06 06:45:56,626 - INFO - save_steps: 50 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - logging_steps: 1 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - seed: 3407 - [__main__:803] +2025-05-06 06:45:56,626 - INFO - save_peft: False - [__main__:803] +2025-05-06 06:45:56,626 - INFO - save_merged: False - [__main__:803] +2025-05-06 06:45:56,626 - INFO - reward_config_json: None - [__main__:803] +2025-05-06 06:45:56,627 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:45:56,627 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config='main', max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:588] +2025-05-06 06:45:56,627 - INFO - Using GPU: NVIDIA H200 - [__main__:594] +2025-05-06 06:45:56,627 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:597] +2025-05-06 06:45:56,627 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:603] +2025-05-06 06:45:56,627 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:498] +2025-05-06 06:45:57,897 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:509] +2025-05-06 06:45:57,897 - INFO - Using compute dtype: torch.bfloat16 - [__main__:514] +2025-05-06 06:46:12,266 - INFO - Base model loaded. Type: - [__main__:547] +2025-05-06 06:46:12,267 - INFO - Applying LoRA with r=32 - [__main__:551] +2025-05-06 06:46:15,831 - INFO - LoRA applied. Model type now: - [__main__:566] +2025-05-06 06:46:15,840 - INFO - Preparing dataset with PoT system prompting... - [__main__:613] +2025-05-06 06:46:15,840 - INFO - Creating PoT dataset using source: gsm8k - [__main__:341] +2025-05-06 06:46:15,840 - INFO - Loading dataset from Hugging Face Hub: gsm8k - [__main__:350] +2025-05-06 06:46:20,126 - INFO - Selecting 1000 samples from base dataset (size 7473). - [__main__:368] +2025-05-06 06:46:20,130 - INFO - Processing 1000 samples for PoT formatting. - [__main__:371] +2025-05-06 06:46:20,221 - INFO - Created PoT dataset with 1000 samples. Skipped 0 due to missing prompts. - [__main__:405] +2025-05-06 06:46:20,238 - INFO - Successfully prepared training dataset with 1000 samples. - [__main__:625] +2025-05-06 06:46:20,238 - INFO - Configuring GRPO training arguments... - [__main__:651] +2025-05-06 06:46:20,239 - INFO - BFloat16 support: True - [__main__:664] +2025-05-06 06:46:50,117 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:796] +2025-05-06 06:46:50,117 - INFO - PoT training configuration (Direct Run): - [__main__:801] +2025-05-06 06:46:50,117 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:803] +2025-05-06 06:46:50,117 - INFO - max_seq_length: 768 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - load_in_4bit: False - [__main__:803] +2025-05-06 06:46:50,117 - INFO - load_in_8bit: False - [__main__:803] +2025-05-06 06:46:50,117 - INFO - lora_r: 32 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - lora_alpha: 32 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - lora_dropout: 0.05 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - token: None - [__main__:803] +2025-05-06 06:46:50,117 - INFO - dataset_name: gsm8k - [__main__:803] +2025-05-06 06:46:50,117 - INFO - dataset_config: main - [__main__:803] +2025-05-06 06:46:50,117 - INFO - max_samples: 1000 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - cache_dir: None - [__main__:803] +2025-05-06 06:46:50,117 - INFO - learning_rate: 5e-06 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - warmup_ratio: 0.1 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - weight_decay: 0.1 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - batch_size: 1 - [__main__:803] +2025-05-06 06:46:50,117 - INFO - gradient_accumulation_steps: 4 - [__main__:803] +2025-05-06 06:46:50,118 - INFO - num_generations: 4 - [__main__:803] +2025-05-06 06:46:50,118 - INFO - max_steps: 100 - [__main__:803] +2025-05-06 06:46:50,118 - INFO - output_dir: pot_grpo_outputs - [__main__:803] +2025-05-06 06:46:50,118 - INFO - save_steps: 50 - [__main__:803] +2025-05-06 06:46:50,118 - INFO - logging_steps: 1 - [__main__:803] +2025-05-06 06:46:50,118 - INFO - seed: 3407 - [__main__:803] +2025-05-06 06:46:50,118 - INFO - save_peft: False - [__main__:803] +2025-05-06 06:46:50,118 - INFO - save_merged: False - [__main__:803] +2025-05-06 06:46:50,118 - INFO - reward_config_json: None - [__main__:803] +2025-05-06 06:46:50,118 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:46:50,118 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config='main', max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:588] +2025-05-06 06:46:50,119 - INFO - Using GPU: NVIDIA H200 - [__main__:594] +2025-05-06 06:46:50,119 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:597] +2025-05-06 06:46:50,119 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:603] +2025-05-06 06:46:50,119 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:498] +2025-05-06 06:46:51,348 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:509] +2025-05-06 06:46:51,348 - INFO - Using compute dtype: torch.bfloat16 - [__main__:514] +2025-05-06 06:47:05,112 - INFO - Base model loaded. Type: - [__main__:547] +2025-05-06 06:47:05,112 - INFO - Applying LoRA with r=32 - [__main__:551] +2025-05-06 06:47:08,736 - INFO - LoRA applied. Model type now: - [__main__:566] +2025-05-06 06:47:08,746 - INFO - Preparing dataset with PoT system prompting... - [__main__:613] +2025-05-06 06:47:08,746 - INFO - Creating PoT dataset using source: gsm8k - [__main__:341] +2025-05-06 06:47:08,746 - INFO - Loading dataset from Hugging Face Hub: gsm8k - [__main__:350] +2025-05-06 06:47:12,816 - INFO - Selecting 1000 samples from base dataset (size 7473). - [__main__:368] +2025-05-06 06:47:12,818 - INFO - Processing 1000 samples for PoT formatting. - [__main__:371] +2025-05-06 06:47:12,912 - INFO - Created PoT dataset with 1000 samples. Skipped 0 due to missing prompts. - [__main__:405] +2025-05-06 06:47:12,930 - INFO - Successfully prepared training dataset with 1000 samples. - [__main__:625] +2025-05-06 06:47:12,930 - INFO - Configuring GRPO training arguments... - [__main__:651] +2025-05-06 06:47:12,930 - INFO - BFloat16 support: True - [__main__:664] +2025-05-06 06:47:12,948 - INFO - Setting up GRPOTrainer with PoT reward function... - [__main__:699] +2025-05-06 06:51:59,838 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:797] +2025-05-06 06:51:59,838 - INFO - PoT training configuration (Direct Run): - [__main__:802] +2025-05-06 06:51:59,838 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:804] +2025-05-06 06:51:59,838 - INFO - max_seq_length: 768 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - load_in_4bit: False - [__main__:804] +2025-05-06 06:51:59,838 - INFO - load_in_8bit: False - [__main__:804] +2025-05-06 06:51:59,838 - INFO - lora_r: 32 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - lora_alpha: 32 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - lora_dropout: 0.05 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - token: None - [__main__:804] +2025-05-06 06:51:59,838 - INFO - dataset_name: gsm8k - [__main__:804] +2025-05-06 06:51:59,838 - INFO - dataset_config: main - [__main__:804] +2025-05-06 06:51:59,838 - INFO - max_samples: 1000 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - cache_dir: None - [__main__:804] +2025-05-06 06:51:59,838 - INFO - learning_rate: 5e-06 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - warmup_ratio: 0.1 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - weight_decay: 0.1 - [__main__:804] +2025-05-06 06:51:59,838 - INFO - batch_size: 1 - [__main__:804] +2025-05-06 06:51:59,839 - INFO - gradient_accumulation_steps: 4 - [__main__:804] +2025-05-06 06:51:59,839 - INFO - num_generations: 4 - [__main__:804] +2025-05-06 06:51:59,839 - INFO - max_steps: 100 - [__main__:804] +2025-05-06 06:51:59,839 - INFO - output_dir: pot_grpo_outputs - [__main__:804] +2025-05-06 06:51:59,839 - INFO - save_steps: 50 - [__main__:804] +2025-05-06 06:51:59,839 - INFO - logging_steps: 1 - [__main__:804] +2025-05-06 06:51:59,839 - INFO - seed: 3407 - [__main__:804] +2025-05-06 06:51:59,839 - INFO - save_peft: False - [__main__:804] +2025-05-06 06:51:59,839 - INFO - save_merged: False - [__main__:804] +2025-05-06 06:51:59,839 - INFO - reward_config_json: None - [__main__:804] +2025-05-06 06:51:59,840 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:51:59,840 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config='main', max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:588] +2025-05-06 06:51:59,840 - INFO - Using GPU: NVIDIA H200 - [__main__:594] +2025-05-06 06:51:59,840 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:597] +2025-05-06 06:51:59,840 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:603] +2025-05-06 06:51:59,840 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:498] +2025-05-06 06:52:01,021 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:509] +2025-05-06 06:52:01,021 - INFO - Using compute dtype: torch.bfloat16 - [__main__:514] +2025-05-06 06:52:14,512 - INFO - Base model loaded. Type: - [__main__:547] +2025-05-06 06:52:14,512 - INFO - Applying LoRA with r=32 - [__main__:551] +2025-05-06 06:52:18,003 - INFO - LoRA applied. Model type now: - [__main__:566] +2025-05-06 06:52:18,013 - INFO - Preparing dataset with PoT system prompting... - [__main__:613] +2025-05-06 06:52:18,013 - INFO - Creating PoT dataset using source: gsm8k - [__main__:341] +2025-05-06 06:52:18,013 - INFO - Loading dataset from Hugging Face Hub: gsm8k - [__main__:350] +2025-05-06 06:52:22,101 - INFO - Selecting 1000 samples from base dataset (size 7473). - [__main__:368] +2025-05-06 06:52:22,103 - INFO - Processing 1000 samples for PoT formatting. - [__main__:371] +2025-05-06 06:52:22,195 - INFO - Created PoT dataset with 1000 samples. Skipped 0 due to missing prompts. - [__main__:405] +2025-05-06 06:52:22,212 - INFO - Successfully prepared training dataset with 1000 samples. - [__main__:625] +2025-05-06 06:52:22,212 - INFO - Configuring GRPO training arguments... - [__main__:651] +2025-05-06 06:52:22,212 - INFO - BFloat16 support: True - [__main__:664] +2025-05-06 06:52:22,230 - INFO - Setting up GRPOTrainer with PoT reward function... - [__main__:699] +2025-05-06 06:52:53,504 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:797] +2025-05-06 06:52:53,504 - INFO - PoT training configuration (Direct Run): - [__main__:802] +2025-05-06 06:52:53,504 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:804] +2025-05-06 06:52:53,504 - INFO - max_seq_length: 768 - [__main__:804] +2025-05-06 06:52:53,504 - INFO - load_in_4bit: False - [__main__:804] +2025-05-06 06:52:53,504 - INFO - load_in_8bit: False - [__main__:804] +2025-05-06 06:52:53,504 - INFO - lora_r: 32 - [__main__:804] +2025-05-06 06:52:53,504 - INFO - lora_alpha: 32 - [__main__:804] +2025-05-06 06:52:53,504 - INFO - lora_dropout: 0.05 - [__main__:804] +2025-05-06 06:52:53,504 - INFO - token: None - [__main__:804] +2025-05-06 06:52:53,504 - INFO - dataset_name: gsm8k - [__main__:804] +2025-05-06 06:52:53,504 - INFO - dataset_config: main - [__main__:804] +2025-05-06 06:52:53,504 - INFO - max_samples: 1000 - [__main__:804] +2025-05-06 06:52:53,504 - INFO - cache_dir: None - [__main__:804] +2025-05-06 06:52:53,505 - INFO - learning_rate: 5e-06 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - warmup_ratio: 0.1 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - weight_decay: 0.1 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - batch_size: 1 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - gradient_accumulation_steps: 4 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - num_generations: 4 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - max_steps: 100 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - output_dir: pot_grpo_outputs - [__main__:804] +2025-05-06 06:52:53,505 - INFO - save_steps: 50 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - logging_steps: 1 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - seed: 3407 - [__main__:804] +2025-05-06 06:52:53,505 - INFO - save_peft: False - [__main__:804] +2025-05-06 06:52:53,505 - INFO - save_merged: False - [__main__:804] +2025-05-06 06:52:53,505 - INFO - reward_config_json: None - [__main__:804] +2025-05-06 06:52:53,506 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:52:53,506 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config='main', max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:588] +2025-05-06 06:52:53,506 - INFO - Using GPU: NVIDIA H200 - [__main__:594] +2025-05-06 06:52:53,506 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:597] +2025-05-06 06:52:53,506 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:603] +2025-05-06 06:52:53,506 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:498] +2025-05-06 06:52:54,740 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:509] +2025-05-06 06:52:54,740 - INFO - Using compute dtype: torch.bfloat16 - [__main__:514] +2025-05-06 06:53:08,414 - INFO - Base model loaded. Type: - [__main__:547] +2025-05-06 06:53:08,414 - INFO - Applying LoRA with r=32 - [__main__:551] +2025-05-06 06:53:11,941 - INFO - LoRA applied. Model type now: - [__main__:566] +2025-05-06 06:53:11,951 - INFO - Preparing dataset with PoT system prompting... - [__main__:613] +2025-05-06 06:53:11,951 - INFO - Creating PoT dataset using source: gsm8k - [__main__:341] +2025-05-06 06:53:11,951 - INFO - Loading dataset from Hugging Face Hub: gsm8k - [__main__:350] +2025-05-06 06:53:16,407 - INFO - Selecting 1000 samples from base dataset (size 7473). - [__main__:368] +2025-05-06 06:53:16,409 - INFO - Processing 1000 samples for PoT formatting. - [__main__:371] +2025-05-06 06:53:16,500 - INFO - Created PoT dataset with 1000 samples. Skipped 0 due to missing prompts. - [__main__:405] +2025-05-06 06:53:16,518 - INFO - Successfully prepared training dataset with 1000 samples. - [__main__:625] +2025-05-06 06:53:16,518 - INFO - Configuring GRPO training arguments... - [__main__:651] +2025-05-06 06:53:16,518 - INFO - BFloat16 support: True - [__main__:664] +2025-05-06 06:53:16,535 - INFO - Setting up GRPOTrainer with PoT reward function... - [__main__:699] +2025-05-06 06:53:16,574 - INFO - Starting PoT GRPO training... - [__main__:714] +2025-05-06 06:54:53,184 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 06:54:53,184 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 06:54:53,191 - ERROR - Training failed during trainer.train(): 'functools.partial' object has no attribute '__name__' - [__main__:719] +Traceback (most recent call last): + File "/home/ubuntu/grpo/src/core/utopia_os.py", line 716, in run_pot_grpo_training + train_result = trainer.train() + File "/home/ubuntu/grpo/h200_env/lib/python3.10/site-packages/transformers/trainer.py", line 2245, in train + return inner_training_loop( + File "", line 315, in _fast_inner_training_loop + File "", line 25, in _unsloth_training_step + File "/home/ubuntu/grpo/unsloth_compiled_cache/UnslothGRPOTrainer.py", line 1066, in _prepare_inputs + reward_func_name = reward_func.__name__ +AttributeError: 'functools.partial' object has no attribute '__name__' +2025-05-06 06:54:53,192 - INFO - Direct script execution finished with status: Training run failed: 'functools.partial' object has no attribute '__name__' - [__main__:808] +2025-05-06 06:57:05,536 - INFO - Reconfigured logging. Log file: /home/ubuntu/grpo/pot_grpo_outputs/pot_module_training.log - [__main__:803] +2025-05-06 06:57:05,536 - INFO - PoT training configuration (Direct Run): - [__main__:808] +2025-05-06 06:57:05,536 - INFO - model_name: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:810] +2025-05-06 06:57:05,536 - INFO - max_seq_length: 768 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - load_in_4bit: False - [__main__:810] +2025-05-06 06:57:05,536 - INFO - load_in_8bit: False - [__main__:810] +2025-05-06 06:57:05,536 - INFO - lora_r: 32 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - lora_alpha: 32 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - lora_dropout: 0.05 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - token: None - [__main__:810] +2025-05-06 06:57:05,536 - INFO - dataset_name: gsm8k - [__main__:810] +2025-05-06 06:57:05,536 - INFO - dataset_config: main - [__main__:810] +2025-05-06 06:57:05,536 - INFO - max_samples: 1000 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - cache_dir: None - [__main__:810] +2025-05-06 06:57:05,536 - INFO - learning_rate: 5e-06 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - warmup_ratio: 0.1 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - weight_decay: 0.1 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - batch_size: 1 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - gradient_accumulation_steps: 4 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - num_generations: 4 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - max_steps: 100 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - output_dir: pot_grpo_outputs - [__main__:810] +2025-05-06 06:57:05,536 - INFO - save_steps: 50 - [__main__:810] +2025-05-06 06:57:05,536 - INFO - logging_steps: 1 - [__main__:810] +2025-05-06 06:57:05,537 - INFO - seed: 3407 - [__main__:810] +2025-05-06 06:57:05,537 - INFO - save_peft: False - [__main__:810] +2025-05-06 06:57:05,537 - INFO - save_merged: False - [__main__:810] +2025-05-06 06:57:05,537 - INFO - reward_config_json: None - [__main__:810] +2025-05-06 06:57:05,537 - INFO - Random seed set to 3407 - [__main__:85] +2025-05-06 06:57:05,537 - INFO - Starting PoT GRPO training pipeline run with args: Namespace(model_name='unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit', max_seq_length=768, load_in_4bit=False, load_in_8bit=False, lora_r=32, lora_alpha=32, lora_dropout=0.05, token=None, dataset_name='gsm8k', dataset_config='main', max_samples=1000, cache_dir=None, learning_rate=5e-06, warmup_ratio=0.1, weight_decay=0.1, batch_size=1, gradient_accumulation_steps=4, num_generations=4, max_steps=100, output_dir='pot_grpo_outputs', save_steps=50, logging_steps=1, seed=3407, save_peft=False, save_merged=False, reward_config_json=None) - [__main__:588] +2025-05-06 06:57:05,537 - INFO - Using GPU: NVIDIA H200 - [__main__:594] +2025-05-06 06:57:05,537 - INFO - Ensured output directory exists: pot_grpo_outputs - [__main__:597] +2025-05-06 06:57:05,537 - INFO - Loading model and tokenizer: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:603] +2025-05-06 06:57:05,537 - INFO - Loading tokenizer for: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:498] +2025-05-06 06:57:06,765 - INFO - Loading model: unsloth/gemma-3-27b-it-qat-unsloth-bnb-4bit - [__main__:509] +2025-05-06 06:57:06,766 - INFO - Using compute dtype: torch.bfloat16 - [__main__:514] +2025-05-06 06:57:21,067 - INFO - Base model loaded. Type: - [__main__:547] +2025-05-06 06:57:21,067 - INFO - Applying LoRA with r=32 - [__main__:551] +2025-05-06 06:57:24,559 - INFO - LoRA applied. Model type now: - [__main__:566] +2025-05-06 06:57:24,568 - INFO - Preparing dataset with PoT system prompting... - [__main__:613] +2025-05-06 06:57:24,568 - INFO - Creating PoT dataset using source: gsm8k - [__main__:341] +2025-05-06 06:57:24,569 - INFO - Loading dataset from Hugging Face Hub: gsm8k - [__main__:350] +2025-05-06 06:57:28,655 - INFO - Selecting 1000 samples from base dataset (size 7473). - [__main__:368] +2025-05-06 06:57:28,657 - INFO - Processing 1000 samples for PoT formatting. - [__main__:371] +2025-05-06 06:57:28,749 - INFO - Created PoT dataset with 1000 samples. Skipped 0 due to missing prompts. - [__main__:405] +2025-05-06 06:57:28,767 - INFO - Successfully prepared training dataset with 1000 samples. - [__main__:625] +2025-05-06 06:57:28,767 - INFO - Configuring GRPO training arguments... - [__main__:657] +2025-05-06 06:57:28,767 - INFO - BFloat16 support: True - [__main__:670] +2025-05-06 06:57:28,784 - INFO - Setting up GRPOTrainer with PoT reward function... - [__main__:705] +2025-05-06 06:57:28,820 - INFO - Starting PoT GRPO training... - [__main__:720] +2025-05-06 06:58:52,679 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 06:58:52,679 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:00:33,904 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:00:33,904 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:01:55,451 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:01:55,451 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.27', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.09'} - [__main__:308] +2025-05-06 07:03:18,261 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:03:18,261 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:04:39,078 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:04:39,079 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 07:06:00,076 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:06:00,076 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:07:21,285 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:07:21,285 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:08:42,169 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:08:42,170 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:10:02,551 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:10:02,551 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:11:23,337 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:11:23,338 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:12:43,378 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:12:43,379 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:14:04,330 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:14:04,330 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:15:24,887 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:15:24,887 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:16:45,570 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:16:45,571 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:18:06,918 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:18:06,919 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:19:28,653 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:19:28,654 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:20:52,718 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:20:52,718 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:22:16,073 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:22:16,073 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:23:38,847 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:23:38,847 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:25:00,032 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:25:00,032 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:26:21,749 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:26:21,749 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:27:43,527 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:27:43,527 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:29:05,165 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:29:05,165 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:30:26,533 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:30:26,533 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:31:47,143 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:31:47,143 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:33:08,949 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:33:08,949 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:34:29,683 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:34:29,683 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:35:49,682 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:35:49,683 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.15', 'correction': '0.38', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.13'} - [__main__:308] +2025-05-06 07:37:10,202 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:37:10,202 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:38:31,252 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:38:31,253 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:39:52,434 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:39:52,434 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:41:12,223 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:41:12,224 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:42:29,511 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:42:29,511 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:43:50,607 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:43:50,607 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:45:10,540 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:45:10,541 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:46:30,703 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:46:30,704 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:47:51,214 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:47:51,214 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:49:11,855 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:49:11,856 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:50:33,200 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:50:33,200 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:51:54,213 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:51:54,213 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:53:14,830 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:53:14,830 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.21', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.07'} - [__main__:308] +2025-05-06 07:54:36,433 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:54:36,433 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:55:57,953 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:55:57,953 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:57:22,806 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:57:22,806 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:58:46,756 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:58:46,757 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 07:59:59,461 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 07:59:59,461 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:01:22,070 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:01:22,070 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:02:44,184 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:02:44,184 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:04:04,190 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:04:04,190 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:05:25,092 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:05:25,092 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:06:45,829 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:06:45,829 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:08:05,984 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:08:05,984 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:09:25,265 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:09:25,265 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:10:46,887 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:10:46,888 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:12:08,057 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:12:08,057 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:13:28,127 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:13:28,127 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:14:47,464 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:14:47,464 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:16:08,033 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:16:08,033 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:17:28,621 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:17:28,621 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:18:48,925 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:18:48,926 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:20:08,188 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:20:08,188 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.14', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.05'} - [__main__:308] +2025-05-06 08:21:28,657 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:21:28,657 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:22:48,900 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:22:48,900 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:24:09,786 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:24:09,786 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:25:29,339 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:25:29,339 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:26:50,812 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:26:50,812 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:28:11,953 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:28:11,954 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:29:31,933 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:29:31,933 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:30:52,070 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:30:52,070 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:32:12,249 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:32:12,249 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:33:32,348 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:33:32,348 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:34:52,541 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:34:52,541 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:36:11,634 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:36:11,634 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:37:32,677 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:37:32,677 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:38:52,727 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:38:52,727 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:40:13,639 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:40:13,640 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:41:33,282 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:41:33,283 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:42:53,218 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:42:53,218 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:44:14,081 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:44:14,081 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:45:33,849 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:45:33,849 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 08:46:54,773 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:46:54,773 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:48:18,876 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:48:18,876 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:49:40,597 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:49:40,597 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:51:02,283 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:51:02,283 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.22', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.28'} - [__main__:308] +2025-05-06 08:52:24,129 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:52:24,129 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:53:50,648 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:53:50,648 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:55:14,025 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:55:14,025 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:56:34,936 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:56:34,936 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:57:56,629 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:57:56,630 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 08:59:18,364 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 08:59:18,364 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:00:38,955 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:00:38,955 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:01:59,701 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:01:59,702 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:03:19,252 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:03:19,252 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:04:40,203 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:04:40,204 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:06:03,052 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:06:03,052 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:07:24,424 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:07:24,424 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:08:44,385 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:08:44,385 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.24', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.08'} - [__main__:308] +2025-05-06 09:10:06,324 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:10:06,324 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 09:11:26,533 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:11:26,534 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:12:46,806 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:12:46,806 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:14:06,332 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:14:06,332 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:15:26,765 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:15:26,765 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:16:47,273 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:16:47,273 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:18:07,721 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:18:07,721 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:19:27,226 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:19:27,226 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:20:48,791 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:20:48,792 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:22:12,219 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:22:12,219 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:23:33,749 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:23:33,749 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:24:53,923 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:24:53,923 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:26:16,060 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:26:16,060 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:27:43,161 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:27:43,162 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:29:07,224 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:29:07,225 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:30:26,865 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:30:26,865 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:31:49,132 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:31:49,133 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:33:11,830 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:33:11,831 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:34:33,381 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:34:33,382 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:35:53,319 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:35:53,319 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:37:13,720 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:37:13,721 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:38:34,136 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:38:34,137 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:39:54,352 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:39:54,352 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:41:14,471 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:41:14,472 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:42:33,759 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:42:33,759 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:43:54,024 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:43:54,024 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:45:14,393 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:45:14,393 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:46:35,139 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:46:35,140 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:47:55,630 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:47:55,630 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:49:17,022 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:49:17,022 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:50:37,193 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:50:37,194 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:51:56,826 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:51:56,826 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:53:16,977 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:53:16,977 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:54:38,261 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:54:38,261 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:55:58,333 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:55:58,333 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:57:18,690 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:57:18,690 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 09:58:39,494 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:58:39,494 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 09:59:59,802 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 09:59:59,802 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 10:01:23,567 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:01:23,567 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:02:47,462 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:02:47,463 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:04:09,993 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:04:09,993 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.29', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 10:05:32,484 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:05:32,485 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:06:53,936 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:06:53,936 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:08:14,398 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:08:14,398 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:09:35,552 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:09:35,552 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:10:56,084 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:10:56,084 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:12:16,698 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:12:16,698 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:13:36,542 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:13:36,543 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:14:57,029 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:14:57,029 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:16:17,958 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:16:17,958 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:17:38,657 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:17:38,657 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:18:58,824 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:18:58,824 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:20:19,009 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:20:19,009 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:21:38,881 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:21:38,881 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:23:00,125 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:23:00,125 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:24:19,862 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:24:19,862 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:25:40,184 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:25:40,184 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:27:01,045 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:27:01,046 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.83', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.29'} - [__main__:308] +2025-05-06 10:28:22,581 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:28:22,581 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:29:43,196 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:29:43,196 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:31:04,698 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:31:04,698 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:32:26,234 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:32:26,234 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.16', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.06'} - [__main__:308] +2025-05-06 10:33:47,479 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:33:47,479 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:35:08,181 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:35:08,181 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:36:31,789 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:36:31,789 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:37:59,934 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:37:59,934 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:39:22,907 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:39:22,907 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:40:43,865 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:40:43,865 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:42:06,101 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:42:06,101 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:43:28,605 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:43:28,605 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:44:50,261 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:44:50,261 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:46:10,292 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:46:10,293 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:47:30,472 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:47:30,473 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:48:51,560 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:48:51,561 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:50:13,053 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:50:13,053 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:51:33,232 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:51:33,232 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.16'} - [__main__:308] +2025-05-06 10:52:54,556 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:52:54,557 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:54:15,402 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:54:15,402 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:55:35,899 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:55:35,899 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 10:56:55,897 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:56:55,898 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:58:17,780 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:58:17,780 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 10:59:39,196 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 10:59:39,196 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:01:00,606 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:01:00,606 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:02:21,148 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:02:21,148 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:03:41,729 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:03:41,729 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:05:03,760 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:05:03,760 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:06:24,318 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:06:24,318 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:07:44,555 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:07:44,555 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:09:05,249 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:09:05,249 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:10:25,822 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:10:25,823 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:11:48,129 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:11:48,130 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:13:14,421 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:13:14,421 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:14:39,740 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:14:39,740 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:15:59,926 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:15:59,926 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.16'} - [__main__:308] +2025-05-06 11:17:21,662 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:17:21,663 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:18:42,274 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:18:42,275 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:20:03,977 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:20:03,977 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:21:24,832 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:21:24,833 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 11:22:45,011 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:22:45,011 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:24:04,451 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:24:04,451 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:25:22,844 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:25:22,845 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 11:26:41,346 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:26:41,346 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:28:00,590 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:28:00,591 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 11:29:24,193 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:29:24,193 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:30:43,706 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:30:43,706 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:32:03,591 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:32:03,592 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:33:24,216 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:33:24,217 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:34:43,149 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:34:43,149 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:36:02,321 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:36:02,322 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:37:21,681 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:37:21,681 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:38:42,098 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:38:42,098 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:40:01,159 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:40:01,159 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:41:20,987 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:41:20,987 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:42:30,826 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:42:30,826 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:43:52,006 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:43:52,006 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:45:12,730 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:45:12,730 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:46:32,586 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:46:32,586 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:47:52,268 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:47:52,268 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:49:12,890 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:49:12,890 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:50:34,167 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:50:34,167 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:51:54,285 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:51:54,286 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:53:14,784 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:53:14,784 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:54:35,552 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:54:35,552 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:55:56,013 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:55:56,013 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 11:57:16,678 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:57:16,678 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 11:58:37,335 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:58:37,335 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.89', 'correction': '0.38', 'mapping': '0.62', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.59'} - [__main__:308] +2025-05-06 11:59:58,034 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 11:59:58,034 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:01:17,792 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:01:17,792 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:02:37,615 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:02:37,615 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:03:57,253 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:03:57,253 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:05:17,279 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:05:17,279 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:06:36,309 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:06:36,310 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:07:56,713 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:07:56,713 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:09:16,898 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:09:16,898 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:10:36,856 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:10:36,856 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:11:57,652 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:11:57,653 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.69', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.24'} - [__main__:308] +2025-05-06 12:13:17,185 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:13:17,186 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.21', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.07'} - [__main__:308] +2025-05-06 12:14:36,600 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:14:36,600 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.24', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.08'} - [__main__:308] +2025-05-06 12:15:56,719 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:15:56,720 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:17:15,463 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:17:15,463 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 12:18:34,898 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:18:34,898 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:19:54,528 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:19:54,529 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:21:15,341 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:21:15,341 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.35', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.12'} - [__main__:308] +2025-05-06 12:22:39,122 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:22:39,122 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:24:03,217 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:24:03,217 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:25:23,941 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:25:23,941 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:26:44,698 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:26:44,698 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.16'} - [__main__:308] +2025-05-06 12:28:04,141 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:28:04,141 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:29:24,921 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:29:24,921 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:30:45,928 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:30:45,929 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 12:32:07,126 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:32:07,127 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:33:28,184 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:33:28,184 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:34:48,970 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:34:48,970 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.16', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.06'} - [__main__:308] +2025-05-06 12:36:09,753 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:36:09,753 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:37:30,300 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:37:30,300 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:38:49,856 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:38:49,857 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:40:10,586 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:40:10,586 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:41:30,284 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:41:30,284 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:42:51,545 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:42:51,545 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:44:12,431 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:44:12,431 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.45', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.16'} - [__main__:308] +2025-05-06 12:45:32,985 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:45:32,985 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 12:46:52,844 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:46:52,844 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:48:12,726 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:48:12,726 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:49:31,982 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:49:31,982 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:50:52,350 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:50:52,350 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:52:13,254 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:52:13,254 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 12:53:32,472 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:53:32,472 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 12:54:52,242 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:54:52,243 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 12:56:11,528 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:56:11,528 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.25', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.09'} - [__main__:308] +2025-05-06 12:57:30,220 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:57:30,220 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 12:58:49,226 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 12:58:49,226 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 13:00:07,340 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:00:07,340 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:01:25,813 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:01:25,813 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:02:46,990 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:02:46,990 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:04:07,691 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:04:07,691 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:05:27,115 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:05:27,115 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:06:47,725 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:06:47,725 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:08:08,316 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:08:08,316 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:09:28,754 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:09:28,754 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.33'} - [__main__:308] +2025-05-06 13:10:48,518 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:10:48,518 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.70', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.43'} - [__main__:308] +2025-05-06 13:12:08,853 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:12:08,853 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 13:13:31,479 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:13:31,479 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:14:53,508 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:14:53,508 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:16:15,547 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:16:15,548 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.22', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.08'} - [__main__:308] +2025-05-06 13:17:36,739 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:17:36,739 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:18:59,801 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:18:59,801 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:20:22,264 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:20:22,264 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.27', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.09'} - [__main__:308] +2025-05-06 13:21:44,354 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:21:44,354 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.20', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.07'} - [__main__:308] +2025-05-06 13:23:06,755 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:23:06,755 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:24:29,613 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:24:29,613 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:25:50,838 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:25:50,839 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 13:27:11,048 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:27:11,049 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:28:32,973 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:28:32,973 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:29:55,795 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:29:55,795 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:31:16,545 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:31:16,545 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:32:37,958 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:32:37,958 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:33:58,469 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:33:58,469 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 13:35:20,089 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:35:20,089 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:36:41,385 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:36:41,385 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:38:01,496 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:38:01,496 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 13:39:23,138 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:39:23,138 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:40:44,522 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:40:44,523 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:42:05,780 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:42:05,780 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:43:26,642 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:43:26,642 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 13:44:48,042 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:44:48,043 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:46:09,368 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:46:09,368 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 13:47:30,937 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:47:30,937 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:48:51,734 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:48:51,734 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.33'} - [__main__:308] +2025-05-06 13:50:13,969 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:50:13,969 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 13:51:36,521 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:51:36,521 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:52:58,855 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:52:58,855 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:54:19,766 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:54:19,766 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:55:41,523 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:55:41,523 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.25', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.09'} - [__main__:308] +2025-05-06 13:57:04,037 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:57:04,037 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:58:26,521 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:58:26,522 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 13:59:47,711 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 13:59:47,711 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:01:08,929 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:01:08,929 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:02:30,280 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:02:30,280 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:03:52,568 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:03:52,568 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:04:47,362 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:04:47,362 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:06:08,487 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:06:08,487 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:07:30,168 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:07:30,168 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:08:51,787 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:08:51,787 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:10:12,845 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:10:12,846 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:11:35,253 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:11:35,253 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:12:57,683 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:12:57,683 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:14:19,241 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:14:19,241 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:15:40,644 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:15:40,644 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.29', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 14:17:02,030 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:17:02,031 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.20', 'correction': '0.38', 'mapping': '0.22', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.23'} - [__main__:308] +2025-05-06 14:18:24,742 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:18:24,743 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:19:47,213 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:19:47,213 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.28', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.30'} - [__main__:308] +2025-05-06 14:21:06,972 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:21:06,972 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.12'} - [__main__:308] +2025-05-06 14:22:29,117 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:22:29,117 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 14:23:50,696 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:23:50,696 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 14:25:12,688 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:25:12,689 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:26:35,146 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:26:35,146 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 14:27:57,867 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:27:57,867 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 14:29:19,531 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:29:19,531 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:30:41,697 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:30:41,697 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 14:32:02,849 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:32:02,849 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 14:33:24,804 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:33:24,804 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:34:47,197 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:34:47,197 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:36:09,530 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:36:09,530 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:37:31,198 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:37:31,199 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:38:53,492 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:38:53,492 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:40:15,790 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:40:15,791 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.35'} - [__main__:308] +2025-05-06 14:41:37,875 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:41:37,876 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:42:59,479 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:42:59,479 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.27', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.28'} - [__main__:308] +2025-05-06 14:44:21,406 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:44:21,406 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:45:42,375 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:45:42,375 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.25', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.09'} - [__main__:308] +2025-05-06 14:47:03,353 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:47:03,353 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:48:24,817 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:48:24,817 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:49:45,142 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:49:45,143 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.35'} - [__main__:308] +2025-05-06 14:51:05,846 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:51:05,847 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.90', 'correction': '0.00', 'mapping': '1.23', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.68'} - [__main__:308] +2025-05-06 14:52:26,793 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:52:26,793 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.14'} - [__main__:308] +2025-05-06 14:53:47,433 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:53:47,434 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.33'} - [__main__:308] +2025-05-06 14:55:08,277 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:55:08,277 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:56:29,540 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:56:29,540 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:57:50,659 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:57:50,659 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 14:59:11,855 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 14:59:11,855 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:00:33,093 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:00:33,093 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:01:53,988 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:01:53,988 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:03:15,333 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:03:15,333 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:04:36,525 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:04:36,525 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:05:58,640 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:05:58,641 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 15:07:18,985 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:07:18,985 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.17', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.06'} - [__main__:308] +2025-05-06 15:08:39,518 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:08:39,518 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:09:58,882 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:09:58,882 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:11:19,425 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:11:19,425 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:12:40,335 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:12:40,335 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.90', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.33'} - [__main__:308] +2025-05-06 15:14:00,016 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:14:00,016 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:15:20,563 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:15:20,563 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:16:41,281 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:16:41,282 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:18:01,761 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:18:01,762 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:19:24,781 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:19:24,781 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.75', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.45'} - [__main__:308] +2025-05-06 15:20:45,062 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:20:45,062 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.40', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.33'} - [__main__:308] +2025-05-06 15:22:06,846 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:22:06,846 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:23:28,060 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:23:28,060 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:24:49,605 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:24:49,605 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.19'} - [__main__:308] +2025-05-06 15:26:10,681 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:26:10,681 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:27:32,360 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:27:32,360 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.70', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.24'} - [__main__:308] +2025-05-06 15:28:53,961 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:28:53,962 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:30:15,553 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:30:15,553 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 15:31:36,031 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:31:36,032 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:32:58,058 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:32:58,058 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.80', 'correction': '0.00', 'mapping': '0.62', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.47'} - [__main__:308] +2025-05-06 15:34:19,040 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:34:19,041 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:35:39,733 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:35:39,734 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:37:00,572 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:37:00,572 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:38:22,250 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:38:22,251 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:39:42,670 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:39:42,670 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:41:03,998 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:41:03,998 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 15:42:24,361 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:42:24,361 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 15:43:45,440 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:43:45,440 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.80', 'correction': '0.00', 'mapping': '1.25', 'interface': '0.12', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.67'} - [__main__:308] +2025-05-06 15:45:06,520 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:45:06,520 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 15:46:28,636 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:46:28,637 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:47:49,282 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:47:49,282 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.30', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.10'} - [__main__:308] +2025-05-06 15:49:10,339 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:49:10,339 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.17'} - [__main__:308] +2025-05-06 15:50:31,181 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:50:31,182 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:51:52,265 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:51:52,265 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.50', 'correction': '0.00', 'mapping': '0.61', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.36'} - [__main__:308] +2025-05-06 15:53:13,468 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:53:13,468 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:54:35,109 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:54:35,109 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.23', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.08'} - [__main__:308] +2025-05-06 15:55:56,616 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:55:56,616 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:57:18,212 - INFO - Step 0 - PoT combined reward weights: {'perception': '0.35', 'correction': '0.20', 'mapping': '0.30', 'interface': '0.15', 'grounding_abstraction': '0.00', 'veridical_coherence': '0.00'} - [__main__:303] +2025-05-06 15:57:18,212 - INFO - Step 0 - Avg PoT Component Scores: {'perception': '0.00', 'correction': '0.00', 'mapping': '0.00', 'interface': '0.00', 'grounding': '0.00', 'coherence': '0.00', 'combined': '0.00'} - [__main__:308] +2025-05-06 15:57:23,426 - INFO - Training completed. Train Result: TrainOutput(global_step=100, training_loss=7.581704841868486e-05, metrics={'train_runtime': 32393.5617, 'train_samples_per_second': 0.049, 'train_steps_per_second': 0.003, 'total_flos': 0.0, 'train_loss': 7.581704841868486e-05}) - [__main__:723] +2025-05-06 15:57:23,426 - INFO - Saving final model adapters to pot_grpo_outputs/final_checkpoint... - [__main__:730] +2025-05-06 15:57:25,395 - INFO - Final adapters saved successfully. - [__main__:735] +2025-05-06 15:57:25,397 - INFO - PoT training pipeline completed successfully in 32419.86 seconds! - [__main__:771] +2025-05-06 15:57:25,398 - INFO - Direct script execution finished with status: Success - [__main__:814]