| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Starting merged model save process | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Arguments: {'lambdas_path': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/k-fold/task-wise/asdiv/cross_entropy-ep2-10%dataset-lambda05/llm_adamerge_lambdas.json', 'model_config': '/work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/k-fold/task-wise/asdiv/cross_entropy-ep2-10%dataset-lambda05/model_config.yaml', 'output_dir': '/work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/k-fold/task-wise/asdiv/cross_entropy-ep2-10%dataset/lambda05', 'model_name': 'merged-model', 'push_to_hub': False, 'hub_repo_id': 'lejelly/ds7b-ep2-data10-ood-asdiv-taskwise-lambda05', 'private': False, 'device': 'cuda', 'debug': False} | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Loading lambdas from /work/gj26/b20042/LLM-AdaMerge/outputs/deepseek-7b/k-fold/task-wise/asdiv/cross_entropy-ep2-10%dataset-lambda05/llm_adamerge_lambdas.json | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Auto-detected parameter-wise merge from JSON structure | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Merge type: parameter_wise | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - [Initial] Memory Usage: | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Process: 0.43 GB (0.2%) | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - System: 7.98 GB / 212.49 GB (8.4%) | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Available: 194.70 GB | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB | |
| 2025-11-18 13:26:48 - experiment_save_merged_model - INFO - Loading models | |
| 2025-11-18 13:26:59 - experiment_save_merged_model - INFO - [After loading models] Memory Usage: | |
| 2025-11-18 13:26:59 - experiment_save_merged_model - INFO - Process: 0.69 GB (0.3%) | |
| 2025-11-18 13:26:59 - experiment_save_merged_model - INFO - System: 49.59 GB / 212.49 GB (31.3%) | |
| 2025-11-18 13:26:59 - experiment_save_merged_model - INFO - Available: 146.03 GB | |
| 2025-11-18 13:26:59 - experiment_save_merged_model - INFO - GPU 0: Allocated: 38.61 GB, Reserved: 40.64 GB, Total: 94.50 GB | |
| 2025-11-18 13:26:59 - experiment_save_merged_model - INFO - Initializing parameter_wise AdaMerge | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Loading learned lambdas | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Deleting original models to free memory (task vectors already computed) | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - [Before deleting models] Memory Usage: | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Process: 39.04 GB (18.4%) | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - System: 102.72 GB / 212.49 GB (56.3%) | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Available: 92.91 GB | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - GPU 0: Allocated: 38.61 GB, Reserved: 40.64 GB, Total: 94.50 GB | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Clearing model_loader references | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Deleting model variables | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Running garbage collection | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - [After deleting models and GC] Memory Usage: | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Process: 39.04 GB (18.4%) | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - System: 62.05 GB / 212.49 GB (37.1%) | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Available: 133.58 GB | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - [After loading lambdas] Memory Usage: | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Process: 39.04 GB (18.4%) | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - System: 62.05 GB / 212.49 GB (37.1%) | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Available: 133.58 GB | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Creating merged model with learned lambdas | |
| 2025-11-18 13:31:27 - experiment_save_merged_model - INFO - Using merge_models_for_save() | |
| 2025-11-18 13:33:25 - experiment_save_merged_model - INFO - [After merging models] Memory Usage: | |
| 2025-11-18 13:33:25 - experiment_save_merged_model - INFO - Process: 39.07 GB (18.4%) | |
| 2025-11-18 13:33:25 - experiment_save_merged_model - INFO - System: 101.43 GB / 212.49 GB (55.7%) | |
| 2025-11-18 13:33:25 - experiment_save_merged_model - INFO - Available: 94.20 GB | |
| 2025-11-18 13:33:25 - experiment_save_merged_model - INFO - GPU 0: Allocated: 12.87 GB, Reserved: 53.44 GB, Total: 94.50 GB | |
| 2025-11-18 13:33:25 - experiment_save_merged_model - INFO - Freeing memory from AdaMerge object (task vectors and base params no longer needed) | |
| 2025-11-18 13:33:25 - experiment_save_merged_model - INFO - Deleting task vectors | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - Deleting base params | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - Deleting functional model | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - [After freeing AdaMerge memory] Memory Usage: | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - Process: 0.42 GB (0.2%) | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - System: 21.78 GB / 212.49 GB (18.2%) | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - Available: 173.84 GB | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - GPU 0: Allocated: 12.87 GB, Reserved: 13.05 GB, Total: 94.50 GB | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - Saving merged model to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/k-fold/task-wise/asdiv/cross_entropy-ep2-10%dataset/lambda05 | |
| 2025-11-18 13:33:26 - experiment_save_merged_model - INFO - Moving merged model to CPU for saving | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Successfully saved 3 safetensors files: | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - - model-00003-of-00003.safetensors (3674.14 MB) | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - - model-00002-of-00003.safetensors (4750.20 MB) | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - - model-00001-of-00003.safetensors (4756.17 MB) | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - [After saving model] Memory Usage: | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Process: 13.29 GB (6.3%) | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - System: 21.92 GB / 212.49 GB (18.3%) | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Available: 173.70 GB | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Saving tokenizer | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Copied lambdas file to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/k-fold/task-wise/asdiv/cross_entropy-ep2-10%dataset/lambda05/learned_lambdas.json | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Creating model card | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Cleaning up models | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - [After cleanup] Memory Usage: | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Process: 13.30 GB (6.3%) | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - System: 21.92 GB / 212.49 GB (18.3%) | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Available: 173.70 GB | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - GPU 0: Allocated: 0.00 GB, Reserved: 0.00 GB, Total: 94.50 GB | |
| 2025-11-18 13:34:18 - experiment_save_merged_model - INFO - Model saved successfully to /work/gj26/b20042/LLM-AdaMerge/mergekit/outputs/deepseek-7b/k-fold/task-wise/asdiv/cross_entropy-ep2-10%dataset/lambda05 | |